Merge branch 'akpm' (second patch-bomb from Andrew)

Merge second patchbomb from Andrew Morton:
 - the rest of MM
 - misc fs fixes
 - add execveat() syscall
 - new ratelimit feature for fault-injection
 - decompressor updates
 - ipc/ updates
 - fallocate feature creep
 - fsnotify cleanups
 - a few other misc things

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (99 commits)
  cgroups: Documentation: fix trivial typos and wrong paragraph numberings
  parisc: percpu: update comments referring to __get_cpu_var
  percpu: update local_ops.txt to reflect this_cpu operations
  percpu: remove __get_cpu_var and __raw_get_cpu_var macros
  fsnotify: remove destroy_list from fsnotify_mark
  fsnotify: unify inode and mount marks handling
  fallocate: create FAN_MODIFY and IN_MODIFY events
  mm/cma: make kmemleak ignore CMA regions
  slub: fix cpuset check in get_any_partial
  slab: fix cpuset check in fallback_alloc
  shmdt: use i_size_read() instead of ->i_size
  ipc/shm.c: fix overly aggressive shmdt() when calls span multiple segments
  ipc/msg: increase MSGMNI, remove scaling
  ipc/sem.c: increase SEMMSL, SEMMNI, SEMOPM
  ipc/sem.c: change memory barrier in sem_lock() to smp_rmb()
  lib/decompress.c: consistency of compress formats for kernel image
  decompress_bunzip2: off by one in get_next_block()
  usr/Kconfig: make initrd compression algorithm selection not expert
  fault-inject: add ratelimit option
  ratelimit: add initialization macro
  ...

6 files changed, 138 insertions, 72 deletions

diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 7c5d87191b28..85be040a21c8 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -228,8 +228,8 @@ memory_block_action(unsigned long phys_index, unsigned long action, int online_t
 	struct page *first_page;
 	int ret;
 
-	first_page = pfn_to_page(phys_index << PFN_SECTION_SHIFT);
-	start_pfn = page_to_pfn(first_page);
+	start_pfn = phys_index << PFN_SECTION_SHIFT;
+	first_page = pfn_to_page(start_pfn);
 
 	switch (action) {
 		case MEM_ONLINE:
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 3920ee45aa59..bd8bda386e02 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -44,15 +44,14 @@ static const char *default_compressor = "lzo";
 static unsigned int num_devices = 1;
 
 #define ZRAM_ATTR_RO(name)						\
-static ssize_t zram_attr_##name##_show(struct device *d,		\
+static ssize_t name##_show(struct device *d,		\
 				struct device_attribute *attr, char *b)	\
 {									\
 	struct zram *zram = dev_to_zram(d);				\
 	return scnprintf(b, PAGE_SIZE, "%llu\n",			\
 		(u64)atomic64_read(&zram->stats.name));			\
 }									\
-static struct device_attribute dev_attr_##name =			\
-	__ATTR(name, S_IRUGO, zram_attr_##name##_show, NULL);
+static DEVICE_ATTR_RO(name);
 
 static inline int init_done(struct zram *zram)
 {
@@ -287,19 +286,18 @@ static inline int is_partial_io(struct bio_vec *bvec)
 /*
  * Check if request is within bounds and aligned on zram logical blocks.
  */
-static inline int valid_io_request(struct zram *zram, struct bio *bio)
+static inline int valid_io_request(struct zram *zram,
+		sector_t start, unsigned int size)
 {
-	u64 start, end, bound;
+	u64 end, bound;
 
 	/* unaligned request */
-	if (unlikely(bio->bi_iter.bi_sector &
-		     (ZRAM_SECTOR_PER_LOGICAL_BLOCK - 1)))
+	if (unlikely(start & (ZRAM_SECTOR_PER_LOGICAL_BLOCK - 1)))
 		return 0;
-	if (unlikely(bio->bi_iter.bi_size & (ZRAM_LOGICAL_BLOCK_SIZE - 1)))
+	if (unlikely(size & (ZRAM_LOGICAL_BLOCK_SIZE - 1)))
 		return 0;
 
-	start = bio->bi_iter.bi_sector;
-	end = start + (bio->bi_iter.bi_size >> SECTOR_SHIFT);
+	end = start + (size >> SECTOR_SHIFT);
 	bound = zram->disksize >> SECTOR_SHIFT;
 	/* out of range range */
 	if (unlikely(start >= bound || end > bound || start > end))
@@ -453,7 +451,7 @@ static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
 }
 
 static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
-			  u32 index, int offset, struct bio *bio)
+			  u32 index, int offset)
 {
 	int ret;
 	struct page *page;
@@ -645,14 +643,13 @@ out:
 }
 
 static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
-			int offset, struct bio *bio)
+			int offset, int rw)
 {
 	int ret;
-	int rw = bio_data_dir(bio);
 
 	if (rw == READ) {
 		atomic64_inc(&zram->stats.num_reads);
-		ret = zram_bvec_read(zram, bvec, index, offset, bio);
+		ret = zram_bvec_read(zram, bvec, index, offset);
 	} else {
 		atomic64_inc(&zram->stats.num_writes);
 		ret = zram_bvec_write(zram, bvec, index, offset);
@@ -853,7 +850,7 @@ out:
 
 static void __zram_make_request(struct zram *zram, struct bio *bio)
 {
-	int offset;
+	int offset, rw;
 	u32 index;
 	struct bio_vec bvec;
 	struct bvec_iter iter;
@@ -868,6 +865,7 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 		return;
 	}
 
+	rw = bio_data_dir(bio);
 	bio_for_each_segment(bvec, bio, iter) {
 		int max_transfer_size = PAGE_SIZE - offset;
 
@@ -882,15 +880,15 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 			bv.bv_len = max_transfer_size;
 			bv.bv_offset = bvec.bv_offset;
 
-			if (zram_bvec_rw(zram, &bv, index, offset, bio) < 0)
+			if (zram_bvec_rw(zram, &bv, index, offset, rw) < 0)
 				goto out;
 
 			bv.bv_len = bvec.bv_len - max_transfer_size;
 			bv.bv_offset += max_transfer_size;
-			if (zram_bvec_rw(zram, &bv, index + 1, 0, bio) < 0)
+			if (zram_bvec_rw(zram, &bv, index + 1, 0, rw) < 0)
 				goto out;
 		} else
-			if (zram_bvec_rw(zram, &bvec, index, offset, bio) < 0)
+			if (zram_bvec_rw(zram, &bvec, index, offset, rw) < 0)
 				goto out;
 
 		update_position(&index, &offset, &bvec);
@@ -915,7 +913,8 @@ static void zram_make_request(struct request_queue *queue, struct bio *bio)
 	if (unlikely(!init_done(zram)))
 		goto error;
 
-	if (!valid_io_request(zram, bio)) {
+	if (!valid_io_request(zram, bio->bi_iter.bi_sector,
+					bio->bi_iter.bi_size)) {
 		atomic64_inc(&zram->stats.invalid_io);
 		goto error;
 	}
@@ -945,25 +944,64 @@ static void zram_slot_free_notify(struct block_device *bdev,
 	atomic64_inc(&zram->stats.notify_free);
 }
 
+static int zram_rw_page(struct block_device *bdev, sector_t sector,
+		       struct page *page, int rw)
+{
+	int offset, err;
+	u32 index;
+	struct zram *zram;
+	struct bio_vec bv;
+
+	zram = bdev->bd_disk->private_data;
+	if (!valid_io_request(zram, sector, PAGE_SIZE)) {
+		atomic64_inc(&zram->stats.invalid_io);
+		return -EINVAL;
+	}
+
+	down_read(&zram->init_lock);
+	if (unlikely(!init_done(zram))) {
+		err = -EIO;
+		goto out_unlock;
+	}
+
+	index = sector >> SECTORS_PER_PAGE_SHIFT;
+	offset = sector & (SECTORS_PER_PAGE - 1) << SECTOR_SHIFT;
+
+	bv.bv_page = page;
+	bv.bv_len = PAGE_SIZE;
+	bv.bv_offset = 0;
+
+	err = zram_bvec_rw(zram, &bv, index, offset, rw);
+out_unlock:
+	up_read(&zram->init_lock);
+	/*
+	 * If I/O fails, just return error(ie, non-zero) without
+	 * calling page_endio.
+	 * It causes resubmit the I/O with bio request by upper functions
+	 * of rw_page(e.g., swap_readpage, __swap_writepage) and
+	 * bio->bi_end_io does things to handle the error
+	 * (e.g., SetPageError, set_page_dirty and extra works).
+	 */
+	if (err == 0)
+		page_endio(page, rw, 0);
+	return err;
+}
+
 static const struct block_device_operations zram_devops = {
 	.swap_slot_free_notify = zram_slot_free_notify,
+	.rw_page = zram_rw_page,
 	.owner = THIS_MODULE
 };
 
-static DEVICE_ATTR(disksize, S_IRUGO | S_IWUSR,
-		disksize_show, disksize_store);
-static DEVICE_ATTR(initstate, S_IRUGO, initstate_show, NULL);
-static DEVICE_ATTR(reset, S_IWUSR, NULL, reset_store);
-static DEVICE_ATTR(orig_data_size, S_IRUGO, orig_data_size_show, NULL);
-static DEVICE_ATTR(mem_used_total, S_IRUGO, mem_used_total_show, NULL);
-static DEVICE_ATTR(mem_limit, S_IRUGO | S_IWUSR, mem_limit_show,
-		mem_limit_store);
-static DEVICE_ATTR(mem_used_max, S_IRUGO | S_IWUSR, mem_used_max_show,
-		mem_used_max_store);
-static DEVICE_ATTR(max_comp_streams, S_IRUGO | S_IWUSR,
-		max_comp_streams_show, max_comp_streams_store);
-static DEVICE_ATTR(comp_algorithm, S_IRUGO | S_IWUSR,
-		comp_algorithm_show, comp_algorithm_store);
+static DEVICE_ATTR_RW(disksize);
+static DEVICE_ATTR_RO(initstate);
+static DEVICE_ATTR_WO(reset);
+static DEVICE_ATTR_RO(orig_data_size);
+static DEVICE_ATTR_RO(mem_used_total);
+static DEVICE_ATTR_RW(mem_limit);
+static DEVICE_ATTR_RW(mem_used_max);
+static DEVICE_ATTR_RW(max_comp_streams);
+static DEVICE_ATTR_RW(comp_algorithm);
 
 ZRAM_ATTR_RO(num_reads);
 ZRAM_ATTR_RO(num_writes);
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index c6ee271317f5..b05a816b09ac 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -66,8 +66,8 @@ static const size_t max_zpage_size = PAGE_SIZE / 4 * 3;
 /* Flags for zram pages (table[page_no].value) */
 enum zram_pageflags {
 	/* Page consists entirely of zeros */
-	ZRAM_ZERO = ZRAM_FLAG_SHIFT + 1,
-	ZRAM_ACCESS,	/* page in now accessed */
+	ZRAM_ZERO = ZRAM_FLAG_SHIFT,
+	ZRAM_ACCESS,	/* page is now accessed */
 
 	__NR_ZRAM_PAGEFLAGS,
 };
diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index a2d87a60c27f..bea878f8e7d3 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -509,45 +509,67 @@ static void finish_pri_tag(struct device_state *dev_state,
 	spin_unlock_irqrestore(&pasid_state->lock, flags);
 }
 
+static void handle_fault_error(struct fault *fault)
+{
+	int status;
+
+	if (!fault->dev_state->inv_ppr_cb) {
+		set_pri_tag_status(fault->state, fault->tag, PPR_INVALID);
+		return;
+	}
+
+	status = fault->dev_state->inv_ppr_cb(fault->dev_state->pdev,
+					      fault->pasid,
+					      fault->address,
+					      fault->flags);
+	switch (status) {
+	case AMD_IOMMU_INV_PRI_RSP_SUCCESS:
+		set_pri_tag_status(fault->state, fault->tag, PPR_SUCCESS);
+		break;
+	case AMD_IOMMU_INV_PRI_RSP_INVALID:
+		set_pri_tag_status(fault->state, fault->tag, PPR_INVALID);
+		break;
+	case AMD_IOMMU_INV_PRI_RSP_FAIL:
+		set_pri_tag_status(fault->state, fault->tag, PPR_FAILURE);
+		break;
+	default:
+		BUG();
+	}
+}
+
 static void do_fault(struct work_struct *work)
 {
 	struct fault *fault = container_of(work, struct fault, work);
-	int npages, write;
-	struct page *page;
+	struct mm_struct *mm;
+	struct vm_area_struct *vma;
+	u64 address;
+	int ret, write;
 
 	write = !!(fault->flags & PPR_FAULT_WRITE);
 
-	down_read(&fault->state->mm->mmap_sem);
-	npages = get_user_pages(NULL, fault->state->mm,
-				fault->address, 1, write, 0, &page, NULL);
-	up_read(&fault->state->mm->mmap_sem);
-
-	if (npages == 1) {
-		put_page(page);
-	} else if (fault->dev_state->inv_ppr_cb) {
-		int status;
-
-		status = fault->dev_state->inv_ppr_cb(fault->dev_state->pdev,
-						      fault->pasid,
-						      fault->address,
-						      fault->flags);
-		switch (status) {
-		case AMD_IOMMU_INV_PRI_RSP_SUCCESS:
-			set_pri_tag_status(fault->state, fault->tag, PPR_SUCCESS);
-			break;
-		case AMD_IOMMU_INV_PRI_RSP_INVALID:
-			set_pri_tag_status(fault->state, fault->tag, PPR_INVALID);
-			break;
-		case AMD_IOMMU_INV_PRI_RSP_FAIL:
-			set_pri_tag_status(fault->state, fault->tag, PPR_FAILURE);
-			break;
-		default:
-			BUG();
-		}
-	} else {
-		set_pri_tag_status(fault->state, fault->tag, PPR_INVALID);
+	mm = fault->state->mm;
+	address = fault->address;
+
+	down_read(&mm->mmap_sem);
+	vma = find_extend_vma(mm, address);
+	if (!vma || address < vma->vm_start) {
+		/* failed to get a vma in the right range */
+		up_read(&mm->mmap_sem);
+		handle_fault_error(fault);
+		goto out;
+	}
+
+	ret = handle_mm_fault(mm, vma, address, write);
+	if (ret & VM_FAULT_ERROR) {
+		/* failed to service fault */
+		up_read(&mm->mmap_sem);
+		handle_fault_error(fault);
+		goto out;
 	}
 
+	up_read(&mm->mmap_sem);
+
+out:
 	finish_pri_tag(fault->dev_state, fault->state, fault->tag);
 
 	put_pasid_state(fault->state);
diff --git a/drivers/rtc/rtc-snvs.c b/drivers/rtc/rtc-snvs.c
index 2cd8ffe5c698..942b267c6271 100644
--- a/drivers/rtc/rtc-snvs.c
+++ b/drivers/rtc/rtc-snvs.c
@@ -344,13 +344,20 @@ static int snvs_rtc_resume(struct device *dev)
 
 	return 0;
 }
-#endif
 
 static const struct dev_pm_ops snvs_rtc_pm_ops = {
 	.suspend_noirq = snvs_rtc_suspend,
 	.resume_noirq = snvs_rtc_resume,
 };
 
+#define SNVS_RTC_PM_OPS	(&snvs_rtc_pm_ops)
+
+#else
+
+#define SNVS_RTC_PM_OPS	NULL
+
+#endif
+
 static const struct of_device_id snvs_dt_ids[] = {
 	{ .compatible = "fsl,sec-v4.0-mon-rtc-lp", },
 	{ /* sentinel */ }
@@ -361,7 +368,7 @@ static struct platform_driver snvs_rtc_driver = {
 	.driver = {
 		.name	= "snvs_rtc",
 		.owner	= THIS_MODULE,
-		.pm	= &snvs_rtc_pm_ops,
+		.pm	= SNVS_RTC_PM_OPS,
 		.of_match_table = snvs_dt_ids,
 	},
 	.probe		= snvs_rtc_probe,
diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c
index ad4f5790a76f..46f8ef42559e 100644
--- a/drivers/staging/android/ashmem.c
+++ b/drivers/staging/android/ashmem.c
@@ -418,7 +418,7 @@ out:
 }
 
 /*
- * ashmem_shrink - our cache shrinker, called from mm/vmscan.c :: shrink_slab
+ * ashmem_shrink - our cache shrinker, called from mm/vmscan.c
  *
  * 'nr_to_scan' is the number of objects to scan for freeing.
  *
@@ -785,7 +785,6 @@ static long ashmem_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 				.nr_to_scan = LONG_MAX,
 			};
 			ret = ashmem_shrink_count(&ashmem_shrinker, &sc);
-			nodes_setall(sc.nodes_to_scan);
 			ashmem_shrink_scan(&ashmem_shrinker, &sc);
 		}
 		break;