Merge tag 'mm-stable-2022-12-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - More userfaultfs work from Peter Xu

 - Several convert-to-folios series from Sidhartha Kumar and Huang Ying

 - Some filemap cleanups from Vishal Moola

 - David Hildenbrand added the ability to selftest anon memory COW
   handling

 - Some cpuset simplifications from Liu Shixin

 - Addition of vmalloc tracing support by Uladzislau Rezki

 - Some pagecache folioifications and simplifications from Matthew
   Wilcox

 - A pagemap cleanup from Kefeng Wang: we have VM_ACCESS_FLAGS, so use
   it

 - Miguel Ojeda contributed some cleanups for our use of the
   __no_sanitize_thread__ gcc keyword.

   This series should have been in the non-MM tree, my bad

 - Naoya Horiguchi improved the interaction between memory poisoning and
   memory section removal for huge pages

 - DAMON cleanups and tuneups from SeongJae Park

 - Tony Luck fixed the handling of COW faults against poisoned pages

 - Peter Xu utilized the PTE marker code for handling swapin errors

 - Hugh Dickins reworked compound page mapcount handling, simplifying it
   and making it more efficient

 - Removal of the autonuma savedwrite infrastructure from Nadav Amit and
   David Hildenbrand

 - zram support for multiple compression streams from Sergey Senozhatsky

 - David Hildenbrand reworked the GUP code's R/O long-term pinning so
   that drivers no longer need to use the FOLL_FORCE workaround which
   didn't work very well anyway

 - Mel Gorman altered the page allocator so that local IRQs can remnain
   enabled during per-cpu page allocations

 - Vishal Moola removed the try_to_release_page() wrapper

 - Stefan Roesch added some per-BDI sysfs tunables which are used to
   prevent network block devices from dirtying excessive amounts of
   pagecache

 - David Hildenbrand did some cleanup and repair work on KSM COW
   breaking

 - Nhat Pham and Johannes Weiner have implemented writeback in zswap's
   zsmalloc backend

 - Brian Foster has fixed a longstanding corner-case oddity in
   file[map]_write_and_wait_range()

 - sparse-vmemmap changes for MIPS, LoongArch and NIOS2 from Feiyang
   Chen

 - Shiyang Ruan has done some work on fsdax, to make its reflink mode
   work better under xfstests. Better, but still not perfect

 - Christoph Hellwig has removed the .writepage() method from several
   filesystems. They only need .writepages()

 - Yosry Ahmed wrote a series which fixes the memcg reclaim target
   beancounting

 - David Hildenbrand has fixed some of our MM selftests for 32-bit
   machines

 - Many singleton patches, as usual

* tag 'mm-stable-2022-12-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (313 commits)
  mm/hugetlb: set head flag before setting compound_order in __prep_compound_gigantic_folio
  mm: mmu_gather: allow more than one batch of delayed rmaps
  mm: fix typo in struct pglist_data code comment
  kmsan: fix memcpy tests
  mm: add cond_resched() in swapin_walk_pmd_entry()
  mm: do not show fs mm pc for VM_LOCKONFAULT pages
  selftests/vm: ksm_functional_tests: fixes for 32bit
  selftests/vm: cow: fix compile warning on 32bit
  selftests/vm: madv_populate: fix missing MADV_POPULATE_(READ|WRITE) definitions
  mm/gup_test: fix PIN_LONGTERM_TEST_READ with highmem
  mm,thp,rmap: fix races between updates of subpages_mapcount
  mm: memcg: fix swapcached stat accounting
  mm: add nodes= arg to memory.reclaim
  mm: disable top-tier fallback to reclaim on proactive reclaim
  selftests: cgroup: make sure reclaim target memcg is unprotected
  selftests: cgroup: refactor proactive reclaim code to reclaim_until()
  mm: memcg: fix stale protection of reclaim target memcg
  mm/mmap: properly unaccount memory on mas_preallocate() failure
  omfs: remove ->writepage
  jfs: remove ->writepage
  ...

19 files changed, 640 insertions, 131 deletions

diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index 6cceca64a6bc..605a0c7053be 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -780,11 +780,6 @@ static int hmat_callback(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 
-static struct notifier_block hmat_callback_nb = {
-	.notifier_call = hmat_callback,
-	.priority = 2,
-};
-
 static __init void hmat_free_structures(void)
 {
 	struct memory_target *target, *tnext;
@@ -867,7 +862,7 @@ static __init int hmat_init(void)
 	hmat_register_targets();
 
 	/* Keep the table and structures if the notifier may use them */
-	if (!register_hotmemory_notifier(&hmat_callback_nb))
+	if (!hotplug_memory_notifier(hmat_callback, HMAT_CALLBACK_PRI))
 		return 0;
 out_put:
 	hmat_free_structures();
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 9aa0da991cfb..fe98fb8d94e5 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -175,6 +175,15 @@ int memory_notify(unsigned long val, void *v)
 	return blocking_notifier_call_chain(&memory_chain, val, v);
 }
 
+#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG)
+static unsigned long memblk_nr_poison(struct memory_block *mem);
+#else
+static inline unsigned long memblk_nr_poison(struct memory_block *mem)
+{
+	return 0;
+}
+#endif
+
 static int memory_block_online(struct memory_block *mem)
 {
 	unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
@@ -183,6 +192,9 @@ static int memory_block_online(struct memory_block *mem)
 	struct zone *zone;
 	int ret;
 
+	if (memblk_nr_poison(mem))
+		return -EHWPOISON;
+
 	zone = zone_for_pfn_range(mem->online_type, mem->nid, mem->group,
 				  start_pfn, nr_pages);
 
@@ -864,6 +876,7 @@ void remove_memory_block_devices(unsigned long start, unsigned long size)
 		mem = find_memory_block_by_id(block_id);
 		if (WARN_ON_ONCE(!mem))
 			continue;
+		num_poisoned_pages_sub(-1UL, memblk_nr_poison(mem));
 		unregister_memory_block_under_nodes(mem);
 		remove_memory_block(mem);
 	}
@@ -1164,3 +1177,28 @@ int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func,
 	}
 	return ret;
 }
+
+#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG)
+void memblk_nr_poison_inc(unsigned long pfn)
+{
+	const unsigned long block_id = pfn_to_block_id(pfn);
+	struct memory_block *mem = find_memory_block_by_id(block_id);
+
+	if (mem)
+		atomic_long_inc(&mem->nr_hwpoison);
+}
+
+void memblk_nr_poison_sub(unsigned long pfn, long i)
+{
+	const unsigned long block_id = pfn_to_block_id(pfn);
+	struct memory_block *mem = find_memory_block_by_id(block_id);
+
+	if (mem)
+		atomic_long_sub(i, &mem->nr_hwpoison);
+}
+
+static unsigned long memblk_nr_poison(struct memory_block *mem)
+{
+	return atomic_long_read(&mem->nr_hwpoison);
+}
+#endif
diff --git a/drivers/block/zram/Kconfig b/drivers/block/zram/Kconfig
index d4100b0c083e..0386b7da02aa 100644
--- a/drivers/block/zram/Kconfig
+++ b/drivers/block/zram/Kconfig
@@ -78,3 +78,12 @@ config ZRAM_MEMORY_TRACKING
 	  /sys/kernel/debug/zram/zramX/block_state.
 
 	  See Documentation/admin-guide/blockdev/zram.rst for more information.
+
+config ZRAM_MULTI_COMP
+	bool "Enable multiple compression streams"
+	depends on ZRAM
+	help
+	  This will enable multi-compression streams, so that ZRAM can
+	  re-compress pages using a potentially slower but more effective
+	  compression algorithm. Note, that IDLE page recompression
+	  requires ZRAM_MEMORY_TRACKING.
diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c
index 0916de952e09..55af4efd7983 100644
--- a/drivers/block/zram/zcomp.c
+++ b/drivers/block/zram/zcomp.c
@@ -206,7 +206,7 @@ void zcomp_destroy(struct zcomp *comp)
  * case of allocation error, or any other error potentially
  * returned by zcomp_init().
  */
-struct zcomp *zcomp_create(const char *compress)
+struct zcomp *zcomp_create(const char *alg)
 {
 	struct zcomp *comp;
 	int error;
@@ -216,14 +216,14 @@ struct zcomp *zcomp_create(const char *compress)
 	 * is not loaded yet. We must do it here, otherwise we are about to
 	 * call /sbin/modprobe under CPU hot-plug lock.
 	 */
-	if (!zcomp_available_algorithm(compress))
+	if (!zcomp_available_algorithm(alg))
 		return ERR_PTR(-EINVAL);
 
 	comp = kzalloc(sizeof(struct zcomp), GFP_KERNEL);
 	if (!comp)
 		return ERR_PTR(-ENOMEM);
 
-	comp->name = compress;
+	comp->name = alg;
 	error = zcomp_init(comp);
 	if (error) {
 		kfree(comp);
diff --git a/drivers/block/zram/zcomp.h b/drivers/block/zram/zcomp.h
index 40f6420f4b2e..cdefdef93da8 100644
--- a/drivers/block/zram/zcomp.h
+++ b/drivers/block/zram/zcomp.h
@@ -27,7 +27,7 @@ int zcomp_cpu_dead(unsigned int cpu, struct hlist_node *node);
 ssize_t zcomp_available_show(const char *comp, char *buf);
 bool zcomp_available_algorithm(const char *comp);
 
-struct zcomp *zcomp_create(const char *comp);
+struct zcomp *zcomp_create(const char *alg);
 void zcomp_destroy(struct zcomp *comp);
 
 struct zcomp_strm *zcomp_stream_get(struct zcomp *comp);
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 966aab902d19..e290d6d97047 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -155,6 +155,25 @@ static inline bool is_partial_io(struct bio_vec *bvec)
 }
 #endif
 
+static inline void zram_set_priority(struct zram *zram, u32 index, u32 prio)
+{
+	prio &= ZRAM_COMP_PRIORITY_MASK;
+	/*
+	 * Clear previous priority value first, in case if we recompress
+	 * further an already recompressed page
+	 */
+	zram->table[index].flags &= ~(ZRAM_COMP_PRIORITY_MASK <<
+				      ZRAM_COMP_PRIORITY_BIT1);
+	zram->table[index].flags |= (prio << ZRAM_COMP_PRIORITY_BIT1);
+}
+
+static inline u32 zram_get_priority(struct zram *zram, u32 index)
+{
+	u32 prio = zram->table[index].flags >> ZRAM_COMP_PRIORITY_BIT1;
+
+	return prio & ZRAM_COMP_PRIORITY_MASK;
+}
+
 /*
  * Check if request is within bounds and aligned on zram logical blocks.
  */
@@ -188,16 +207,13 @@ static void update_position(u32 *index, int *offset, struct bio_vec *bvec)
 static inline void update_used_max(struct zram *zram,
 					const unsigned long pages)
 {
-	unsigned long old_max, cur_max;
-
-	old_max = atomic_long_read(&zram->stats.max_used_pages);
+	unsigned long cur_max = atomic_long_read(&zram->stats.max_used_pages);
 
 	do {
-		cur_max = old_max;
-		if (pages > cur_max)
-			old_max = atomic_long_cmpxchg(
-				&zram->stats.max_used_pages, cur_max, pages);
-	} while (old_max != cur_max);
+		if (cur_max >= pages)
+			return;
+	} while (!atomic_long_try_cmpxchg(&zram->stats.max_used_pages,
+					  &cur_max, pages));
 }
 
 static inline void zram_fill_page(void *ptr, unsigned long len,
@@ -629,10 +645,10 @@ static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec,
 
 #define PAGE_WB_SIG "page_index="
 
-#define PAGE_WRITEBACK 0
-#define HUGE_WRITEBACK (1<<0)
-#define IDLE_WRITEBACK (1<<1)
-
+#define PAGE_WRITEBACK			0
+#define HUGE_WRITEBACK			(1<<0)
+#define IDLE_WRITEBACK			(1<<1)
+#define INCOMPRESSIBLE_WRITEBACK	(1<<2)
 
 static ssize_t writeback_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t len)
@@ -653,6 +669,8 @@ static ssize_t writeback_store(struct device *dev,
 		mode = HUGE_WRITEBACK;
 	else if (sysfs_streq(buf, "huge_idle"))
 		mode = IDLE_WRITEBACK | HUGE_WRITEBACK;
+	else if (sysfs_streq(buf, "incompressible"))
+		mode = INCOMPRESSIBLE_WRITEBACK;
 	else {
 		if (strncmp(buf, PAGE_WB_SIG, sizeof(PAGE_WB_SIG) - 1))
 			return -EINVAL;
@@ -715,11 +733,15 @@ static ssize_t writeback_store(struct device *dev,
 			goto next;
 
 		if (mode & IDLE_WRITEBACK &&
-			  !zram_test_flag(zram, index, ZRAM_IDLE))
+		    !zram_test_flag(zram, index, ZRAM_IDLE))
 			goto next;
 		if (mode & HUGE_WRITEBACK &&
-			  !zram_test_flag(zram, index, ZRAM_HUGE))
+		    !zram_test_flag(zram, index, ZRAM_HUGE))
+			goto next;
+		if (mode & INCOMPRESSIBLE_WRITEBACK &&
+		    !zram_test_flag(zram, index, ZRAM_INCOMPRESSIBLE))
 			goto next;
+
 		/*
 		 * Clearing ZRAM_UNDER_WB is duty of caller.
 		 * IOW, zram_free_page never clear it.
@@ -753,8 +775,12 @@ static ssize_t writeback_store(struct device *dev,
 			zram_clear_flag(zram, index, ZRAM_IDLE);
 			zram_slot_unlock(zram, index);
 			/*
-			 * Return last IO error unless every IO were
-			 * not suceeded.
+			 * BIO errors are not fatal, we continue and simply
+			 * attempt to writeback the remaining objects (pages).
+			 * At the same time we need to signal user-space that
+			 * some writes (at least one, but also could be all of
+			 * them) were not successful and we do so by returning
+			 * the most recent BIO error.
 			 */
 			ret = err;
 			continue;
@@ -920,13 +946,16 @@ static ssize_t read_block_state(struct file *file, char __user *buf,
 
 		ts = ktime_to_timespec64(zram->table[index].ac_time);
 		copied = snprintf(kbuf + written, count,
-			"%12zd %12lld.%06lu %c%c%c%c\n",
+			"%12zd %12lld.%06lu %c%c%c%c%c%c\n",
 			index, (s64)ts.tv_sec,
 			ts.tv_nsec / NSEC_PER_USEC,
 			zram_test_flag(zram, index, ZRAM_SAME) ? 's' : '.',
 			zram_test_flag(zram, index, ZRAM_WB) ? 'w' : '.',
 			zram_test_flag(zram, index, ZRAM_HUGE) ? 'h' : '.',
-			zram_test_flag(zram, index, ZRAM_IDLE) ? 'i' : '.');
+			zram_test_flag(zram, index, ZRAM_IDLE) ? 'i' : '.',
+			zram_get_priority(zram, index) ? 'r' : '.',
+			zram_test_flag(zram, index,
+				       ZRAM_INCOMPRESSIBLE) ? 'n' : '.');
 
 		if (count <= copied) {
 			zram_slot_unlock(zram, index);
@@ -1000,46 +1029,143 @@ static ssize_t max_comp_streams_store(struct device *dev,
 	return len;
 }
 
-static ssize_t comp_algorithm_show(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static void comp_algorithm_set(struct zram *zram, u32 prio, const char *alg)
 {
-	size_t sz;
-	struct zram *zram = dev_to_zram(dev);
+	/* Do not free statically defined compression algorithms */
+	if (zram->comp_algs[prio] != default_compressor)
+		kfree(zram->comp_algs[prio]);
+
+	zram->comp_algs[prio] = alg;
+}
+
+static ssize_t __comp_algorithm_show(struct zram *zram, u32 prio, char *buf)
+{
+	ssize_t sz;
 
 	down_read(&zram->init_lock);
-	sz = zcomp_available_show(zram->compressor, buf);
+	sz = zcomp_available_show(zram->comp_algs[prio], buf);
 	up_read(&zram->init_lock);
 
 	return sz;
 }
 
-static ssize_t comp_algorithm_store(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t len)
+static int __comp_algorithm_store(struct zram *zram, u32 prio, const char *buf)
 {
-	struct zram *zram = dev_to_zram(dev);
-	char compressor[ARRAY_SIZE(zram->compressor)];
+	char *compressor;
 	size_t sz;
 
-	strscpy(compressor, buf, sizeof(compressor));
+	sz = strlen(buf);
+	if (sz >= CRYPTO_MAX_ALG_NAME)
+		return -E2BIG;
+
+	compressor = kstrdup(buf, GFP_KERNEL);
+	if (!compressor)
+		return -ENOMEM;
+
 	/* ignore trailing newline */
-	sz = strlen(compressor);
 	if (sz > 0 && compressor[sz - 1] == '\n')
 		compressor[sz - 1] = 0x00;
 
-	if (!zcomp_available_algorithm(compressor))
+	if (!zcomp_available_algorithm(compressor)) {
+		kfree(compressor);
 		return -EINVAL;
+	}
 
 	down_write(&zram->init_lock);
 	if (init_done(zram)) {
 		up_write(&zram->init_lock);
+		kfree(compressor);
 		pr_info("Can't change algorithm for initialized device\n");
 		return -EBUSY;
 	}
 
-	strcpy(zram->compressor, compressor);
+	comp_algorithm_set(zram, prio, compressor);
 	up_write(&zram->init_lock);
-	return len;
+	return 0;
+}
+
+static ssize_t comp_algorithm_show(struct device *dev,
+				   struct device_attribute *attr,
+				   char *buf)
+{
+	struct zram *zram = dev_to_zram(dev);
+
+	return __comp_algorithm_show(zram, ZRAM_PRIMARY_COMP, buf);
+}
+
+static ssize_t comp_algorithm_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf,
+				    size_t len)
+{
+	struct zram *zram = dev_to_zram(dev);
+	int ret;
+
+	ret = __comp_algorithm_store(zram, ZRAM_PRIMARY_COMP, buf);
+	return ret ? ret : len;
+}
+
+#ifdef CONFIG_ZRAM_MULTI_COMP
+static ssize_t recomp_algorithm_show(struct device *dev,
+				     struct device_attribute *attr,
+				     char *buf)
+{
+	struct zram *zram = dev_to_zram(dev);
+	ssize_t sz = 0;
+	u32 prio;
+
+	for (prio = ZRAM_SECONDARY_COMP; prio < ZRAM_MAX_COMPS; prio++) {
+		if (!zram->comp_algs[prio])
+			continue;
+
+		sz += scnprintf(buf + sz, PAGE_SIZE - sz - 2, "#%d: ", prio);
+		sz += __comp_algorithm_show(zram, prio, buf + sz);
+	}
+
+	return sz;
+}
+
+static ssize_t recomp_algorithm_store(struct device *dev,
+				      struct device_attribute *attr,
+				      const char *buf,
+				      size_t len)
+{
+	struct zram *zram = dev_to_zram(dev);
+	int prio = ZRAM_SECONDARY_COMP;
+	char *args, *param, *val;
+	char *alg = NULL;
+	int ret;
+
+	args = skip_spaces(buf);
+	while (*args) {
+		args = next_arg(args, &param, &val);
+
+		if (!*val)
+			return -EINVAL;
+
+		if (!strcmp(param, "algo")) {
+			alg = val;
+			continue;
+		}
+
+		if (!strcmp(param, "priority")) {
+			ret = kstrtoint(val, 10, &prio);
+			if (ret)
+				return ret;
+			continue;
+		}
+	}
+
+	if (!alg)
+		return -EINVAL;
+
+	if (prio < ZRAM_SECONDARY_COMP || prio >= ZRAM_MAX_COMPS)
+		return -EINVAL;
+
+	ret = __comp_algorithm_store(zram, prio, alg);
+	return ret ? ret : len;
 }
+#endif
 
 static ssize_t compact_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t len)
@@ -1210,6 +1336,11 @@ static void zram_free_page(struct zram *zram, size_t index)
 		atomic64_dec(&zram->stats.huge_pages);
 	}
 
+	if (zram_test_flag(zram, index, ZRAM_INCOMPRESSIBLE))
+		zram_clear_flag(zram, index, ZRAM_INCOMPRESSIBLE);
+
+	zram_set_priority(zram, index, 0);
+
 	if (zram_test_flag(zram, index, ZRAM_WB)) {
 		zram_clear_flag(zram, index, ZRAM_WB);
 		free_block_bdev(zram, zram_get_element(zram, index));
@@ -1242,32 +1373,37 @@ out:
 		~(1UL << ZRAM_LOCK | 1UL << ZRAM_UNDER_WB));
 }
 
-static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
-				struct bio *bio, bool partial_io)
+/*
+ * Reads a page from the writeback devices. Corresponding ZRAM slot
+ * should be unlocked.
+ */
+static int zram_bvec_read_from_bdev(struct zram *zram, struct page *page,
+				    u32 index, struct bio *bio, bool partial_io)
+{
+	struct bio_vec bvec = {
+		.bv_page = page,
+		.bv_len = PAGE_SIZE,
+		.bv_offset = 0,
+	};
+
+	return read_from_bdev(zram, &bvec, zram_get_element(zram, index), bio,
+			      partial_io);
+}
+
+/*
+ * Reads (decompresses if needed) a page from zspool (zsmalloc).
+ * Corresponding ZRAM slot should be locked.
+ */
+static int zram_read_from_zspool(struct zram *zram, struct page *page,
+				 u32 index)
 {
 	struct zcomp_strm *zstrm;
 	unsigned long handle;
 	unsigned int size;
 	void *src, *dst;
+	u32 prio;
 	int ret;
 
-	zram_slot_lock(zram, index);
-	if (zram_test_flag(zram, index, ZRAM_WB)) {
-		struct bio_vec bvec;
-
-		zram_slot_unlock(zram, index);
-		/* A null bio means rw_page was used, we must fallback to bio */
-		if (!bio)
-			return -EOPNOTSUPP;
-
-		bvec.bv_page = page;
-		bvec.bv_len = PAGE_SIZE;
-		bvec.bv_offset = 0;
-		return read_from_bdev(zram, &bvec,
-				zram_get_element(zram, index),
-				bio, partial_io);
-	}
-
 	handle = zram_get_handle(zram, index);
 	if (!handle || zram_test_flag(zram, index, ZRAM_SAME)) {
 		unsigned long value;
@@ -1277,14 +1413,15 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
 		mem = kmap_atomic(page);
 		zram_fill_page(mem, PAGE_SIZE, value);
 		kunmap_atomic(mem);
-		zram_slot_unlock(zram, index);
 		return 0;
 	}
 
 	size = zram_get_obj_size(zram, index);
 
-	if (size != PAGE_SIZE)
-		zstrm = zcomp_stream_get(zram->comp);
+	if (size != PAGE_SIZE) {
+		prio = zram_get_priority(zram, index);
+		zstrm = zcomp_stream_get(zram->comps[prio]);
+	}
 
 	src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO);
 	if (size == PAGE_SIZE) {
@@ -1296,20 +1433,43 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
 		dst = kmap_atomic(page);
 		ret = zcomp_decompress(zstrm, src, size, dst);
 		kunmap_atomic(dst);
-		zcomp_stream_put(zram->comp);
+		zcomp_stream_put(zram->comps[prio]);
 	}
 	zs_unmap_object(zram->mem_pool, handle);
-	zram_slot_unlock(zram, index);
+	return ret;
+}
+
+static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
+			    struct bio *bio, bool partial_io)
+{
+	int ret;
+
+	zram_slot_lock(zram, index);
+	if (!zram_test_flag(zram, index, ZRAM_WB)) {
+		/* Slot should be locked through out the function call */
+		ret = zram_read_from_zspool(zram, page, index);
+		zram_slot_unlock(zram, index);
+	} else {
+		/* Slot should be unlocked before the function call */
+		zram_slot_unlock(zram, index);
+
+		/* A null bio means rw_page was used, we must fallback to bio */
+		if (!bio)
+			return -EOPNOTSUPP;
+
+		ret = zram_bvec_read_from_bdev(zram, page, index, bio,
+					       partial_io);
+	}
 
 	/* Should NEVER happen. Return bio error if it does. */
-	if (WARN_ON(ret))
+	if (WARN_ON(ret < 0))
 		pr_err("Decompression failed! err=%d, page=%u\n", ret, index);
 
 	return ret;
 }
 
 static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
-				u32 index, int offset, struct bio *bio)
+			  u32 index, int offset, struct bio *bio)
 {
 	int ret;
 	struct page *page;
@@ -1363,13 +1523,13 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec,
 	kunmap_atomic(mem);
 
 compress_again:
-	zstrm = zcomp_stream_get(zram->comp);
+	zstrm = zcomp_stream_get(zram->comps[ZRAM_PRIMARY_COMP]);
 	src = kmap_atomic(page);
 	ret = zcomp_compress(zstrm, src, &comp_len);
 	kunmap_atomic(src);
 
 	if (unlikely(ret)) {
-		zcomp_stream_put(zram->comp);
+		zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]);
 		pr_err("Compression failed! err=%d\n", ret);
 		zs_free(zram->mem_pool, handle);
 		return ret;
@@ -1390,19 +1550,19 @@ compress_again:
 	 * if we have a 'non-null' handle here then we are coming
 	 * from the slow path and handle has already been allocated.
 	 */
-	if (IS_ERR((void *)handle))
+	if (IS_ERR_VALUE(handle))
 		handle = zs_malloc(zram->mem_pool, comp_len,
 				__GFP_KSWAPD_RECLAIM |
 				__GFP_NOWARN |
 				__GFP_HIGHMEM |
 				__GFP_MOVABLE);
-	if (IS_ERR((void *)handle)) {
-		zcomp_stream_put(zram->comp);
+	if (IS_ERR_VALUE(handle)) {
+		zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]);
 		atomic64_inc(&zram->stats.writestall);
 		handle = zs_malloc(zram->mem_pool, comp_len,
 				GFP_NOIO | __GFP_HIGHMEM |
 				__GFP_MOVABLE);
-		if (IS_ERR((void *)handle))
+		if (IS_ERR_VALUE(handle))
 			return PTR_ERR((void *)handle);
 
 		if (comp_len != PAGE_SIZE)
@@ -1414,14 +1574,14 @@ compress_again:
 		 * zstrm buffer back. It is necessary that the dereferencing
 		 * of the zstrm variable below occurs correctly.
 		 */
-		zstrm = zcomp_stream_get(zram->comp);
+		zstrm = zcomp_stream_get(zram->comps[ZRAM_PRIMARY_COMP]);
 	}
 
 	alloced_pages = zs_get_total_pages(zram->mem_pool);
 	update_used_max(zram, alloced_pages);
 
 	if (zram->limit_pages && alloced_pages > zram->limit_pages) {
-		zcomp_stream_put(zram->comp);
+		zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]);
 		zs_free(zram->mem_pool, handle);
 		return -ENOMEM;
 	}
@@ -1435,7 +1595,7 @@ compress_again:
 	if (comp_len == PAGE_SIZE)
 		kunmap_atomic(src);
 
-	zcomp_stream_put(zram->comp);
+	zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]);
 	zs_unmap_object(zram->mem_pool, handle);
 	atomic64_add(comp_len, &zram->stats.compr_data_size);
 out:
@@ -1504,6 +1664,274 @@ out:
 	return ret;
 }
 
+#ifdef CONFIG_ZRAM_MULTI_COMP
+/*
+ * This function will decompress (unless it's ZRAM_HUGE) the page and then
+ * attempt to compress it using provided compression algorithm priority
+ * (which is potentially more effective).
+ *
+ * Corresponding ZRAM slot should be locked.
+ */
+static int zram_recompress(struct zram *zram, u32 index, struct page *page,
+			   u32 threshold, u32 prio, u32 prio_max)
+{
+	struct zcomp_strm *zstrm = NULL;
+	unsigned long handle_old;
+	unsigned long handle_new;
+	unsigned int comp_len_old;
+	unsigned int comp_len_new;
+	unsigned int class_index_old;
+	unsigned int class_index_new;
+	u32 num_recomps = 0;
+	void *src, *dst;
+	int ret;
+
+	handle_old = zram_get_handle(zram, index);
+	if (!handle_old)
+		return -EINVAL;
+
+	comp_len_old = zram_get_obj_size(zram, index);
+	/*
+	 * Do not recompress objects that are already "small enough".
+	 */
+	if (comp_len_old < threshold)
+		return 0;
+
+	ret = zram_read_from_zspool(zram, page, index);
+	if (ret)
+		return ret;
+
+	class_index_old = zs_lookup_class_index(zram->mem_pool, comp_len_old);
+	/*
+	 * Iterate the secondary comp algorithms list (in order of priority)
+	 * and try to recompress the page.
+	 */
+	for (; prio < prio_max; prio++) {
+		if (!zram->comps[prio])
+			continue;
+
+		/*
+		 * Skip if the object is already re-compressed with a higher
+		 * priority algorithm (or same algorithm).
+		 */
+		if (prio <= zram_get_priority(zram, index))
+			continue;
+
+		num_recomps++;
+		zstrm = zcomp_stream_get(zram->comps[prio]);
+		src = kmap_atomic(page);
+		ret = zcomp_compress(zstrm, src, &comp_len_new);
+		kunmap_atomic(src);
+
+		if (ret) {
+			zcomp_stream_put(zram->comps[prio]);
+			return ret;
+		}
+
+		class_index_new = zs_lookup_class_index(zram->mem_pool,
+							comp_len_new);
+
+		/* Continue until we make progress */
+		if (class_index_new >= class_index_old ||
+		    (threshold && comp_len_new >= threshold)) {
+			zcomp_stream_put(zram->comps[prio]);
+			continue;
+		}
+
+		/* Recompression was successful so break out */
+		break;
+	}
+
+	/*
+	 * We did not try to recompress, e.g. when we have only one
+	 * secondary algorithm and the page is already recompressed
+	 * using that algorithm
+	 */
+	if (!zstrm)
+		return 0;
+
+	if (class_index_new >= class_index_old) {
+		/*
+		 * Secondary algorithms failed to re-compress the page
+		 * in a way that would save memory, mark the object as
+		 * incompressible so that we will not try to compress
+		 * it again.
+		 *
+		 * We need to make sure that all secondary algorithms have
+		 * failed, so we test if the number of recompressions matches
+		 * the number of active secondary algorithms.
+		 */
+		if (num_recomps == zram->num_active_comps - 1)
+			zram_set_flag(zram, index, ZRAM_INCOMPRESSIBLE);
+		return 0;
+	}
+
+	/* Successful recompression but above threshold */
+	if (threshold && comp_len_new >= threshold)
+		return 0;
+
+	/*
+	 * No direct reclaim (slow path) for handle allocation and no
+	 * re-compression attempt (unlike in __zram_bvec_write()) since
+	 * we already have stored that object in zsmalloc. If we cannot
+	 * alloc memory for recompressed object then we bail out and
+	 * simply keep the old (existing) object in zsmalloc.
+	 */
+	handle_new = zs_malloc(zram->mem_pool, comp_len_new,
+			       __GFP_KSWAPD_RECLAIM |
+			       __GFP_NOWARN |
+			       __GFP_HIGHMEM |
+			       __GFP_MOVABLE);
+	if (IS_ERR_VALUE(handle_new)) {
+		zcomp_stream_put(zram->comps[prio]);
+		return PTR_ERR((void *)handle_new);
+	}
+
+	dst = zs_map_object(zram->mem_pool, handle_new, ZS_MM_WO);
+	memcpy(dst, zstrm->buffer, comp_len_new);
+	zcomp_stream_put(zram->comps[prio]);
+
+	zs_unmap_object(zram->mem_pool, handle_new);
+
+	zram_free_page(zram, index);
+	zram_set_handle(zram, index, handle_new);
+	zram_set_obj_size(zram, index, comp_len_new);
+	zram_set_priority(zram, index, prio);
+
+	atomic64_add(comp_len_new, &zram->stats.compr_data_size);
+	atomic64_inc(&zram->stats.pages_stored);
+
+	return 0;
+}
+
+#define RECOMPRESS_IDLE		(1 << 0)
+#define RECOMPRESS_HUGE		(1 << 1)
+
+static ssize_t recompress_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t len)
+{
+	u32 prio = ZRAM_SECONDARY_COMP, prio_max = ZRAM_MAX_COMPS;
+	struct zram *zram = dev_to_zram(dev);
+	unsigned long nr_pages = zram->disksize >> PAGE_SHIFT;
+	char *args, *param, *val, *algo = NULL;
+	u32 mode = 0, threshold = 0;
+	unsigned long index;
+	struct page *page;
+	ssize_t ret;
+
+	args = skip_spaces(buf);
+	while (*args) {
+		args = next_arg(args, &param, &val);
+
+		if (!*val)
+			return -EINVAL;
+
+		if (!strcmp(param, "type")) {
+			if (!strcmp(val, "idle"))
+				mode = RECOMPRESS_IDLE;
+			if (!strcmp(val, "huge"))
+				mode = RECOMPRESS_HUGE;
+			if (!strcmp(val, "huge_idle"))
+				mode = RECOMPRESS_IDLE | RECOMPRESS_HUGE;
+			continue;
+		}
+
+		if (!strcmp(param, "threshold")) {
+			/*
+			 * We will re-compress only idle objects equal or
+			 * greater in size than watermark.
+			 */
+			ret = kstrtouint(val, 10, &threshold);
+			if (ret)
+				return ret;
+			continue;
+		}
+
+		if (!strcmp(param, "algo")) {
+			algo = val;
+			continue;
+		}
+	}
+
+	if (threshold >= PAGE_SIZE)
+		return -EINVAL;
+
+	down_read(&zram->init_lock);
+	if (!init_done(zram)) {
+		ret = -EINVAL;
+		goto release_init_lock;
+	}
+
+	if (algo) {
+		bool found = false;
+
+		for (; prio < ZRAM_MAX_COMPS; prio++) {
+			if (!zram->comp_algs[prio])
+				continue;
+
+			if (!strcmp(zram->comp_algs[prio], algo)) {
+				prio_max = min(prio + 1, ZRAM_MAX_COMPS);
+				found = true;
+				break;
+			}
+		}
+
+		if (!found) {
+			ret = -EINVAL;
+			goto release_init_lock;
+		}
+	}
+
+	page = alloc_page(GFP_KERNEL);
+	if (!page) {
+		ret = -ENOMEM;
+		goto release_init_lock;
+	}
+
+	ret = len;
+	for (index = 0; index < nr_pages; index++) {
+		int err = 0;
+
+		zram_slot_lock(zram, index);
+