aboutsummaryrefslogtreecommitdiff
path: root/arch/s390/mm/pgtable.c
diff options
context:
space:
mode:
authorMartin Schwidefsky <schwidefsky@de.ibm.com>2010-10-25 16:10:11 +0200
committerMartin Schwidefsky <sky@mschwide.boeblingen.de.ibm.com>2010-10-25 16:10:15 +0200
commit80217147a3d80c8a4e48f06e2f6e965455f3fe2a (patch)
treeb419ae9ee3ab0e5b92c0ed2a30ff59b76d6a4978 /arch/s390/mm/pgtable.c
parent87799ebab760dd1460f6e4193d4f71ba416d1451 (diff)
[S390] lockless get_user_pages_fast()
Implement get_user_pages_fast without locking in the fastpath on s390. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Diffstat (limited to 'arch/s390/mm/pgtable.c')
-rw-r--r--arch/s390/mm/pgtable.c171
1 files changed, 154 insertions, 17 deletions
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 8d999249d35..19338d228c9 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -15,6 +15,7 @@
#include <linux/spinlock.h>
#include <linux/module.h>
#include <linux/quicklist.h>
+#include <linux/rcupdate.h>
#include <asm/system.h>
#include <asm/pgtable.h>
@@ -23,6 +24,67 @@
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
+struct rcu_table_freelist {
+ struct rcu_head rcu;
+ struct mm_struct *mm;
+ unsigned int pgt_index;
+ unsigned int crst_index;
+ unsigned long *table[0];
+};
+
+#define RCU_FREELIST_SIZE \
+ ((PAGE_SIZE - sizeof(struct rcu_table_freelist)) \
+ / sizeof(unsigned long))
+
+DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
+static DEFINE_PER_CPU(struct rcu_table_freelist *, rcu_table_freelist);
+
+static void __page_table_free(struct mm_struct *mm, unsigned long *table);
+static void __crst_table_free(struct mm_struct *mm, unsigned long *table);
+
+static struct rcu_table_freelist *rcu_table_freelist_get(struct mm_struct *mm)
+{
+ struct rcu_table_freelist **batchp = &__get_cpu_var(rcu_table_freelist);
+ struct rcu_table_freelist *batch = *batchp;
+
+ if (batch)
+ return batch;
+ batch = (struct rcu_table_freelist *) __get_free_page(GFP_ATOMIC);
+ if (batch) {
+ batch->mm = mm;
+ batch->pgt_index = 0;
+ batch->crst_index = RCU_FREELIST_SIZE;
+ *batchp = batch;
+ }
+ return batch;
+}
+
+static void rcu_table_freelist_callback(struct rcu_head *head)
+{
+ struct rcu_table_freelist *batch =
+ container_of(head, struct rcu_table_freelist, rcu);
+
+ while (batch->pgt_index > 0)
+ __page_table_free(batch->mm, batch->table[--batch->pgt_index]);
+ while (batch->crst_index < RCU_FREELIST_SIZE)
+ __crst_table_free(batch->mm, batch->table[batch->crst_index++]);
+ free_page((unsigned long) batch);
+}
+
+void rcu_table_freelist_finish(void)
+{
+ struct rcu_table_freelist *batch = __get_cpu_var(rcu_table_freelist);
+
+ if (!batch)
+ return;
+ call_rcu(&batch->rcu, rcu_table_freelist_callback);
+ __get_cpu_var(rcu_table_freelist) = NULL;
+}
+
+static void smp_sync(void *arg)
+{
+}
+
#ifndef CONFIG_64BIT
#define ALLOC_ORDER 1
#define TABLES_PER_PAGE 4
@@ -78,25 +140,55 @@ unsigned long *crst_table_alloc(struct mm_struct *mm, int noexec)
}
page->index = page_to_phys(shadow);
}
- spin_lock(&mm->context.list_lock);
+ spin_lock_bh(&mm->context.list_lock);
list_add(&page->lru, &mm->context.crst_list);
- spin_unlock(&mm->context.list_lock);
+ spin_unlock_bh(&mm->context.list_lock);
return (unsigned long *) page_to_phys(page);
}
-void crst_table_free(struct mm_struct *mm, unsigned long *table)
+static void __crst_table_free(struct mm_struct *mm, unsigned long *table)
{
unsigned long *shadow = get_shadow_table(table);
- struct page *page = virt_to_page(table);
- spin_lock(&mm->context.list_lock);
- list_del(&page->lru);
- spin_unlock(&mm->context.list_lock);
if (shadow)
free_pages((unsigned long) shadow, ALLOC_ORDER);
free_pages((unsigned long) table, ALLOC_ORDER);
}
+void crst_table_free(struct mm_struct *mm, unsigned long *table)
+{
+ struct page *page = virt_to_page(table);
+
+ spin_lock_bh(&mm->context.list_lock);
+ list_del(&page->lru);
+ spin_unlock_bh(&mm->context.list_lock);
+ __crst_table_free(mm, table);
+}
+
+void crst_table_free_rcu(struct mm_struct *mm, unsigned long *table)
+{
+ struct rcu_table_freelist *batch;
+ struct page *page = virt_to_page(table);
+
+ spin_lock_bh(&mm->context.list_lock);
+ list_del(&page->lru);
+ spin_unlock_bh(&mm->context.list_lock);
+ if (atomic_read(&mm->mm_users) < 2 &&
+ cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) {
+ __crst_table_free(mm, table);
+ return;
+ }
+ batch = rcu_table_freelist_get(mm);
+ if (!batch) {
+ smp_call_function(smp_sync, NULL, 1);
+ __crst_table_free(mm, table);
+ return;
+ }
+ batch->table[--batch->crst_index] = table;
+ if (batch->pgt_index >= batch->crst_index)
+ rcu_table_freelist_finish();
+}
+
#ifdef CONFIG_64BIT
int crst_table_upgrade(struct mm_struct *mm, unsigned long limit)
{
@@ -108,7 +200,7 @@ repeat:
table = crst_table_alloc(mm, mm->context.noexec);
if (!table)
return -ENOMEM;
- spin_lock(&mm->page_table_lock);
+ spin_lock_bh(&mm->page_table_lock);
if (mm->context.asce_limit < limit) {
pgd = (unsigned long *) mm->pgd;
if (mm->context.asce_limit <= (1UL << 31)) {
@@ -130,7 +222,7 @@ repeat:
mm->task_size = mm->context.asce_limit;
table = NULL;
}
- spin_unlock(&mm->page_table_lock);
+ spin_unlock_bh(&mm->page_table_lock);
if (table)
crst_table_free(mm, table);
if (mm->context.asce_limit < limit)
@@ -182,7 +274,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
unsigned long bits;
bits = (mm->context.noexec || mm->context.has_pgste) ? 3UL : 1UL;
- spin_lock(&mm->context.list_lock);
+ spin_lock_bh(&mm->context.list_lock);
page = NULL;
if (!list_empty(&mm->context.pgtable_list)) {
page = list_first_entry(&mm->context.pgtable_list,
@@ -191,7 +283,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
page = NULL;
}
if (!page) {
- spin_unlock(&mm->context.list_lock);
+ spin_unlock_bh(&mm->context.list_lock);
page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
if (!page)
return NULL;
@@ -202,7 +294,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
clear_table_pgstes(table);
else
clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE);
- spin_lock(&mm->context.list_lock);
+ spin_lock_bh(&mm->context.list_lock);
list_add(&page->lru, &mm->context.pgtable_list);
}
table = (unsigned long *) page_to_phys(page);
@@ -213,10 +305,25 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
page->flags |= bits;
if ((page->flags & FRAG_MASK) == ((1UL << TABLES_PER_PAGE) - 1))
list_move_tail(&page->lru, &mm->context.pgtable_list);
- spin_unlock(&mm->context.list_lock);
+ spin_unlock_bh(&mm->context.list_lock);
return table;
}
+static void __page_table_free(struct mm_struct *mm, unsigned long *table)
+{
+ struct page *page;
+ unsigned long bits;
+
+ bits = ((unsigned long) table) & 15;
+ table = (unsigned long *)(((unsigned long) table) ^ bits);
+ page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
+ page->flags ^= bits;
+ if (!(page->flags & FRAG_MASK)) {
+ pgtable_page_dtor(page);
+ __free_page(page);
+ }
+}
+
void page_table_free(struct mm_struct *mm, unsigned long *table)
{
struct page *page;
@@ -225,7 +332,7 @@ void page_table_free(struct mm_struct *mm, unsigned long *table)
bits = (mm->context.noexec || mm->context.has_pgste) ? 3UL : 1UL;
bits <<= (__pa(table) & (PAGE_SIZE - 1)) / 256 / sizeof(unsigned long);
page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
- spin_lock(&mm->context.list_lock);
+ spin_lock_bh(&mm->context.list_lock);
page->flags ^= bits;
if (page->flags & FRAG_MASK) {
/* Page now has some free pgtable fragments. */
@@ -234,18 +341,48 @@ void page_table_free(struct mm_struct *mm, unsigned long *table)
} else
/* All fragments of the 4K page have been freed. */
list_del(&page->lru);
- spin_unlock(&mm->context.list_lock);
+ spin_unlock_bh(&mm->context.list_lock);
if (page) {
pgtable_page_dtor(page);
__free_page(page);
}
}
+void page_table_free_rcu(struct mm_struct *mm, unsigned long *table)
+{
+ struct rcu_table_freelist *batch;
+ struct page *page;
+ unsigned long bits;
+
+ if (atomic_read(&mm->mm_users) < 2 &&
+ cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) {
+ page_table_free(mm, table);
+ return;
+ }
+ batch = rcu_table_freelist_get(mm);
+ if (!batch) {
+ smp_call_function(smp_sync, NULL, 1);
+ page_table_free(mm, table);
+ return;
+ }
+ bits = (mm->context.noexec || mm->context.has_pgste) ? 3UL : 1UL;
+ bits <<= (__pa(table) & (PAGE_SIZE - 1)) / 256 / sizeof(unsigned long);
+ page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
+ spin_lock_bh(&mm->context.list_lock);
+ /* Delayed freeing with rcu prevents reuse of pgtable fragments */
+ list_del_init(&page->lru);
+ spin_unlock_bh(&mm->context.list_lock);
+ table = (unsigned long *)(((unsigned long) table) | bits);
+ batch->table[batch->pgt_index++] = table;
+ if (batch->pgt_index >= batch->crst_index)
+ rcu_table_freelist_finish();
+}
+
void disable_noexec(struct mm_struct *mm, struct task_struct *tsk)
{
struct page *page;
- spin_lock(&mm->context.list_lock);
+ spin_lock_bh(&mm->context.list_lock);
/* Free shadow region and segment tables. */
list_for_each_entry(page, &mm->context.crst_list, lru)
if (page->index) {
@@ -255,7 +392,7 @@ void disable_noexec(struct mm_struct *mm, struct task_struct *tsk)
/* "Free" second halves of page tables. */
list_for_each_entry(page, &mm->context.pgtable_list, lru)
page->flags &= ~SECOND_HALVES;
- spin_unlock(&mm->context.list_lock);
+ spin_unlock_bh(&mm->context.list_lock);
mm->context.noexec = 0;
update_mm(mm, tsk);
}