From bf0c0259c79b325fd4ea139f363366d319786ea2 Mon Sep 17 00:00:00 2001 From: Thadeu Lima de Souza Cascardo Date: Tue, 2 Aug 2011 14:20:26 -0300 Subject: staging: fix zcache building zcache is only building tmem.c and not building zcache.c. To keep the module name, zcache.c must be renamed if symbols from tmem.c are to remain unexported. Signed-off-by: Thadeu Lima de Souza Cascardo Acked-by: Dan Magenheimer Signed-off-by: Greg Kroah-Hartman --- drivers/staging/zcache/Makefile | 2 +- drivers/staging/zcache/zcache-main.c | 1996 ++++++++++++++++++++++++++++++++++ drivers/staging/zcache/zcache.c | 1996 ---------------------------------- 3 files changed, 1997 insertions(+), 1997 deletions(-) create mode 100644 drivers/staging/zcache/zcache-main.c delete mode 100644 drivers/staging/zcache/zcache.c (limited to 'drivers/staging') diff --git a/drivers/staging/zcache/Makefile b/drivers/staging/zcache/Makefile index f5ec64f94470..60daa272c204 100644 --- a/drivers/staging/zcache/Makefile +++ b/drivers/staging/zcache/Makefile @@ -1,3 +1,3 @@ -zcache-y := tmem.o +zcache-y := zcache-main.o tmem.o obj-$(CONFIG_ZCACHE) += zcache.o diff --git a/drivers/staging/zcache/zcache-main.c b/drivers/staging/zcache/zcache-main.c new file mode 100644 index 000000000000..65a81a0d7c49 --- /dev/null +++ b/drivers/staging/zcache/zcache-main.c @@ -0,0 +1,1996 @@ +/* + * zcache.c + * + * Copyright (c) 2010,2011, Dan Magenheimer, Oracle Corp. + * Copyright (c) 2010,2011, Nitin Gupta + * + * Zcache provides an in-kernel "host implementation" for transcendent memory + * and, thus indirectly, for cleancache and frontswap. Zcache includes two + * page-accessible memory [1] interfaces, both utilizing lzo1x compression: + * 1) "compression buddies" ("zbud") is used for ephemeral pages + * 2) xvmalloc is used for persistent pages. + * Xvmalloc (based on the TLSF allocator) has very low fragmentation + * so maximizes space efficiency, while zbud allows pairs (and potentially, + * in the future, more than a pair of) compressed pages to be closely linked + * so that reclaiming can be done via the kernel's physical-page-oriented + * "shrinker" interface. + * + * [1] For a definition of page-accessible memory (aka PAM), see: + * http://marc.info/?l=linux-mm&m=127811271605009 + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include "tmem.h" + +#include "../zram/xvmalloc.h" /* if built in drivers/staging */ + +#if (!defined(CONFIG_CLEANCACHE) && !defined(CONFIG_FRONTSWAP)) +#error "zcache is useless without CONFIG_CLEANCACHE or CONFIG_FRONTSWAP" +#endif +#ifdef CONFIG_CLEANCACHE +#include +#endif +#ifdef CONFIG_FRONTSWAP +#include +#endif + +#if 0 +/* this is more aggressive but may cause other problems? */ +#define ZCACHE_GFP_MASK (GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN) +#else +#define ZCACHE_GFP_MASK \ + (__GFP_FS | __GFP_NORETRY | __GFP_NOWARN | __GFP_NOMEMALLOC) +#endif + +#define MAX_POOLS_PER_CLIENT 16 + +#define MAX_CLIENTS 16 +#define LOCAL_CLIENT ((uint16_t)-1) +struct zcache_client { + struct tmem_pool *tmem_pools[MAX_POOLS_PER_CLIENT]; + struct xv_pool *xvpool; + bool allocated; + atomic_t refcount; +}; + +static struct zcache_client zcache_host; +static struct zcache_client zcache_clients[MAX_CLIENTS]; + +static inline uint16_t get_client_id_from_client(struct zcache_client *cli) +{ + BUG_ON(cli == NULL); + if (cli == &zcache_host) + return LOCAL_CLIENT; + return cli - &zcache_clients[0]; +} + +static inline bool is_local_client(struct zcache_client *cli) +{ + return cli == &zcache_host; +} + +/********** + * Compression buddies ("zbud") provides for packing two (or, possibly + * in the future, more) compressed ephemeral pages into a single "raw" + * (physical) page and tracking them with data structures so that + * the raw pages can be easily reclaimed. + * + * A zbud page ("zbpg") is an aligned page containing a list_head, + * a lock, and two "zbud headers". The remainder of the physical + * page is divided up into aligned 64-byte "chunks" which contain + * the compressed data for zero, one, or two zbuds. Each zbpg + * resides on: (1) an "unused list" if it has no zbuds; (2) a + * "buddied" list if it is fully populated with two zbuds; or + * (3) one of PAGE_SIZE/64 "unbuddied" lists indexed by how many chunks + * the one unbuddied zbud uses. The data inside a zbpg cannot be + * read or written unless the zbpg's lock is held. + */ + +#define ZBH_SENTINEL 0x43214321 +#define ZBPG_SENTINEL 0xdeadbeef + +#define ZBUD_MAX_BUDS 2 + +struct zbud_hdr { + uint16_t client_id; + uint16_t pool_id; + struct tmem_oid oid; + uint32_t index; + uint16_t size; /* compressed size in bytes, zero means unused */ + DECL_SENTINEL +}; + +struct zbud_page { + struct list_head bud_list; + spinlock_t lock; + struct zbud_hdr buddy[ZBUD_MAX_BUDS]; + DECL_SENTINEL + /* followed by NUM_CHUNK aligned CHUNK_SIZE-byte chunks */ +}; + +#define CHUNK_SHIFT 6 +#define CHUNK_SIZE (1 << CHUNK_SHIFT) +#define CHUNK_MASK (~(CHUNK_SIZE-1)) +#define NCHUNKS (((PAGE_SIZE - sizeof(struct zbud_page)) & \ + CHUNK_MASK) >> CHUNK_SHIFT) +#define MAX_CHUNK (NCHUNKS-1) + +static struct { + struct list_head list; + unsigned count; +} zbud_unbuddied[NCHUNKS]; +/* list N contains pages with N chunks USED and NCHUNKS-N unused */ +/* element 0 is never used but optimizing that isn't worth it */ +static unsigned long zbud_cumul_chunk_counts[NCHUNKS]; + +struct list_head zbud_buddied_list; +static unsigned long zcache_zbud_buddied_count; + +/* protects the buddied list and all unbuddied lists */ +static DEFINE_SPINLOCK(zbud_budlists_spinlock); + +static LIST_HEAD(zbpg_unused_list); +static unsigned long zcache_zbpg_unused_list_count; + +/* protects the unused page list */ +static DEFINE_SPINLOCK(zbpg_unused_list_spinlock); + +static atomic_t zcache_zbud_curr_raw_pages; +static atomic_t zcache_zbud_curr_zpages; +static unsigned long zcache_zbud_curr_zbytes; +static unsigned long zcache_zbud_cumul_zpages; +static unsigned long zcache_zbud_cumul_zbytes; +static unsigned long zcache_compress_poor; +static unsigned long zcache_mean_compress_poor; + +/* forward references */ +static void *zcache_get_free_page(void); +static void zcache_free_page(void *p); + +/* + * zbud helper functions + */ + +static inline unsigned zbud_max_buddy_size(void) +{ + return MAX_CHUNK << CHUNK_SHIFT; +} + +static inline unsigned zbud_size_to_chunks(unsigned size) +{ + BUG_ON(size == 0 || size > zbud_max_buddy_size()); + return (size + CHUNK_SIZE - 1) >> CHUNK_SHIFT; +} + +static inline int zbud_budnum(struct zbud_hdr *zh) +{ + unsigned offset = (unsigned long)zh & (PAGE_SIZE - 1); + struct zbud_page *zbpg = NULL; + unsigned budnum = -1U; + int i; + + for (i = 0; i < ZBUD_MAX_BUDS; i++) + if (offset == offsetof(typeof(*zbpg), buddy[i])) { + budnum = i; + break; + } + BUG_ON(budnum == -1U); + return budnum; +} + +static char *zbud_data(struct zbud_hdr *zh, unsigned size) +{ + struct zbud_page *zbpg; + char *p; + unsigned budnum; + + ASSERT_SENTINEL(zh, ZBH); + budnum = zbud_budnum(zh); + BUG_ON(size == 0 || size > zbud_max_buddy_size()); + zbpg = container_of(zh, struct zbud_page, buddy[budnum]); + ASSERT_SPINLOCK(&zbpg->lock); + p = (char *)zbpg; + if (budnum == 0) + p += ((sizeof(struct zbud_page) + CHUNK_SIZE - 1) & + CHUNK_MASK); + else if (budnum == 1) + p += PAGE_SIZE - ((size + CHUNK_SIZE - 1) & CHUNK_MASK); + return p; +} + +/* + * zbud raw page management + */ + +static struct zbud_page *zbud_alloc_raw_page(void) +{ + struct zbud_page *zbpg = NULL; + struct zbud_hdr *zh0, *zh1; + bool recycled = 0; + + /* if any pages on the zbpg list, use one */ + spin_lock(&zbpg_unused_list_spinlock); + if (!list_empty(&zbpg_unused_list)) { + zbpg = list_first_entry(&zbpg_unused_list, + struct zbud_page, bud_list); + list_del_init(&zbpg->bud_list); + zcache_zbpg_unused_list_count--; + recycled = 1; + } + spin_unlock(&zbpg_unused_list_spinlock); + if (zbpg == NULL) + /* none on zbpg list, try to get a kernel page */ + zbpg = zcache_get_free_page(); + if (likely(zbpg != NULL)) { + INIT_LIST_HEAD(&zbpg->bud_list); + zh0 = &zbpg->buddy[0]; zh1 = &zbpg->buddy[1]; + spin_lock_init(&zbpg->lock); + if (recycled) { + ASSERT_INVERTED_SENTINEL(zbpg, ZBPG); + SET_SENTINEL(zbpg, ZBPG); + BUG_ON(zh0->size != 0 || tmem_oid_valid(&zh0->oid)); + BUG_ON(zh1->size != 0 || tmem_oid_valid(&zh1->oid)); + } else { + atomic_inc(&zcache_zbud_curr_raw_pages); + INIT_LIST_HEAD(&zbpg->bud_list); + SET_SENTINEL(zbpg, ZBPG); + zh0->size = 0; zh1->size = 0; + tmem_oid_set_invalid(&zh0->oid); + tmem_oid_set_invalid(&zh1->oid); + } + } + return zbpg; +} + +static void zbud_free_raw_page(struct zbud_page *zbpg) +{ + struct zbud_hdr *zh0 = &zbpg->buddy[0], *zh1 = &zbpg->buddy[1]; + + ASSERT_SENTINEL(zbpg, ZBPG); + BUG_ON(!list_empty(&zbpg->bud_list)); + ASSERT_SPINLOCK(&zbpg->lock); + BUG_ON(zh0->size != 0 || tmem_oid_valid(&zh0->oid)); + BUG_ON(zh1->size != 0 || tmem_oid_valid(&zh1->oid)); + INVERT_SENTINEL(zbpg, ZBPG); + spin_unlock(&zbpg->lock); + spin_lock(&zbpg_unused_list_spinlock); + list_add(&zbpg->bud_list, &zbpg_unused_list); + zcache_zbpg_unused_list_count++; + spin_unlock(&zbpg_unused_list_spinlock); +} + +/* + * core zbud handling routines + */ + +static unsigned zbud_free(struct zbud_hdr *zh) +{ + unsigned size; + + ASSERT_SENTINEL(zh, ZBH); + BUG_ON(!tmem_oid_valid(&zh->oid)); + size = zh->size; + BUG_ON(zh->size == 0 || zh->size > zbud_max_buddy_size()); + zh->size = 0; + tmem_oid_set_invalid(&zh->oid); + INVERT_SENTINEL(zh, ZBH); + zcache_zbud_curr_zbytes -= size; + atomic_dec(&zcache_zbud_curr_zpages); + return size; +} + +static void zbud_free_and_delist(struct zbud_hdr *zh) +{ + unsigned chunks; + struct zbud_hdr *zh_other; + unsigned budnum = zbud_budnum(zh), size; + struct zbud_page *zbpg = + container_of(zh, struct zbud_page, buddy[budnum]); + + spin_lock(&zbpg->lock); + if (list_empty(&zbpg->bud_list)) { + /* ignore zombie page... see zbud_evict_pages() */ + spin_unlock(&zbpg->lock); + return; + } + size = zbud_free(zh); + ASSERT_SPINLOCK(&zbpg->lock); + zh_other = &zbpg->buddy[(budnum == 0) ? 1 : 0]; + if (zh_other->size == 0) { /* was unbuddied: unlist and free */ + chunks = zbud_size_to_chunks(size) ; + spin_lock(&zbud_budlists_spinlock); + BUG_ON(list_empty(&zbud_unbuddied[chunks].list)); + list_del_init(&zbpg->bud_list); + zbud_unbuddied[chunks].count--; + spin_unlock(&zbud_budlists_spinlock); + zbud_free_raw_page(zbpg); + } else { /* was buddied: move remaining buddy to unbuddied list */ + chunks = zbud_size_to_chunks(zh_other->size) ; + spin_lock(&zbud_budlists_spinlock); + list_del_init(&zbpg->bud_list); + zcache_zbud_buddied_count--; + list_add_tail(&zbpg->bud_list, &zbud_unbuddied[chunks].list); + zbud_unbuddied[chunks].count++; + spin_unlock(&zbud_budlists_spinlock); + spin_unlock(&zbpg->lock); + } +} + +static struct zbud_hdr *zbud_create(uint16_t client_id, uint16_t pool_id, + struct tmem_oid *oid, + uint32_t index, struct page *page, + void *cdata, unsigned size) +{ + struct zbud_hdr *zh0, *zh1, *zh = NULL; + struct zbud_page *zbpg = NULL, *ztmp; + unsigned nchunks; + char *to; + int i, found_good_buddy = 0; + + nchunks = zbud_size_to_chunks(size) ; + for (i = MAX_CHUNK - nchunks + 1; i > 0; i--) { + spin_lock(&zbud_budlists_spinlock); + if (!list_empty(&zbud_unbuddied[i].list)) { + list_for_each_entry_safe(zbpg, ztmp, + &zbud_unbuddied[i].list, bud_list) { + if (spin_trylock(&zbpg->lock)) { + found_good_buddy = i; + goto found_unbuddied; + } + } + } + spin_unlock(&zbud_budlists_spinlock); + } + /* didn't find a good buddy, try allocating a new page */ + zbpg = zbud_alloc_raw_page(); + if (unlikely(zbpg == NULL)) + goto out; + /* ok, have a page, now compress the data before taking locks */ + spin_lock(&zbpg->lock); + spin_lock(&zbud_budlists_spinlock); + list_add_tail(&zbpg->bud_list, &zbud_unbuddied[nchunks].list); + zbud_unbuddied[nchunks].count++; + zh = &zbpg->buddy[0]; + goto init_zh; + +found_unbuddied: + ASSERT_SPINLOCK(&zbpg->lock); + zh0 = &zbpg->buddy[0]; zh1 = &zbpg->buddy[1]; + BUG_ON(!((zh0->size == 0) ^ (zh1->size == 0))); + if (zh0->size != 0) { /* buddy0 in use, buddy1 is vacant */ + ASSERT_SENTINEL(zh0, ZBH); + zh = zh1; + } else if (zh1->size != 0) { /* buddy1 in use, buddy0 is vacant */ + ASSERT_SENTINEL(zh1, ZBH); + zh = zh0; + } else + BUG(); + list_del_init(&zbpg->bud_list); + zbud_unbuddied[found_good_buddy].count--; + list_add_tail(&zbpg->bud_list, &zbud_buddied_list); + zcache_zbud_buddied_count++; + +init_zh: + SET_SENTINEL(zh, ZBH); + zh->size = size; + zh->index = index; + zh->oid = *oid; + zh->pool_id = pool_id; + zh->client_id = client_id; + /* can wait to copy the data until the list locks are dropped */ + spin_unlock(&zbud_budlists_spinlock); + + to = zbud_data(zh, size); + memcpy(to, cdata, size); + spin_unlock(&zbpg->lock); + zbud_cumul_chunk_counts[nchunks]++; + atomic_inc(&zcache_zbud_curr_zpages); + zcache_zbud_cumul_zpages++; + zcache_zbud_curr_zbytes += size; + zcache_zbud_cumul_zbytes += size; +out: + return zh; +} + +static int zbud_decompress(struct page *page, struct zbud_hdr *zh) +{ + struct zbud_page *zbpg; + unsigned budnum = zbud_budnum(zh); + size_t out_len = PAGE_SIZE; + char *to_va, *from_va; + unsigned size; + int ret = 0; + + zbpg = container_of(zh, struct zbud_page, buddy[budnum]); + spin_lock(&zbpg->lock); + if (list_empty(&zbpg->bud_list)) { + /* ignore zombie page... see zbud_evict_pages() */ + ret = -EINVAL; + goto out; + } + ASSERT_SENTINEL(zh, ZBH); + BUG_ON(zh->size == 0 || zh->size > zbud_max_buddy_size()); + to_va = kmap_atomic(page, KM_USER0); + size = zh->size; + from_va = zbud_data(zh, size); + ret = lzo1x_decompress_safe(from_va, size, to_va, &out_len); + BUG_ON(ret != LZO_E_OK); + BUG_ON(out_len != PAGE_SIZE); + kunmap_atomic(to_va, KM_USER0); +out: + spin_unlock(&zbpg->lock); + return ret; +} + +/* + * The following routines handle shrinking of ephemeral pages by evicting + * pages "least valuable" first. + */ + +static unsigned long zcache_evicted_raw_pages; +static unsigned long zcache_evicted_buddied_pages; +static unsigned long zcache_evicted_unbuddied_pages; + +static struct tmem_pool *zcache_get_pool_by_id(uint16_t cli_id, + uint16_t poolid); +static void zcache_put_pool(struct tmem_pool *pool); + +/* + * Flush and free all zbuds in a zbpg, then free the pageframe + */ +static void zbud_evict_zbpg(struct zbud_page *zbpg) +{ + struct zbud_hdr *zh; + int i, j; + uint32_t pool_id[ZBUD_MAX_BUDS], client_id[ZBUD_MAX_BUDS]; + uint32_t index[ZBUD_MAX_BUDS]; + struct tmem_oid oid[ZBUD_MAX_BUDS]; + struct tmem_pool *pool; + + ASSERT_SPINLOCK(&zbpg->lock); + BUG_ON(!list_empty(&zbpg->bud_list)); + for (i = 0, j = 0; i < ZBUD_MAX_BUDS; i++) { + zh = &zbpg->buddy[i]; + if (zh->size) { + client_id[j] = zh->client_id; + pool_id[j] = zh->pool_id; + oid[j] = zh->oid; + index[j] = zh->index; + j++; + zbud_free(zh); + } + } + spin_unlock(&zbpg->lock); + for (i = 0; i < j; i++) { + pool = zcache_get_pool_by_id(client_id[i], pool_id[i]); + if (pool != NULL) { + tmem_flush_page(pool, &oid[i], index[i]); + zcache_put_pool(pool); + } + } + ASSERT_SENTINEL(zbpg, ZBPG); + spin_lock(&zbpg->lock); + zbud_free_raw_page(zbpg); +} + +/* + * Free nr pages. This code is funky because we want to hold the locks + * protecting various lists for as short a time as possible, and in some + * circumstances the list may change asynchronously when the list lock is + * not held. In some cases we also trylock not only to avoid waiting on a + * page in use by another cpu, but also to avoid potential deadlock due to + * lock inversion. + */ +static void zbud_evict_pages(int nr) +{ + struct zbud_page *zbpg; + int i; + + /* first try freeing any pages on unused list */ +retry_unused_list: + spin_lock_bh(&zbpg_unused_list_spinlock); + if (!list_empty(&zbpg_unused_list)) { + /* can't walk list here, since it may change when unlocked */ + zbpg = list_first_entry(&zbpg_unused_list, + struct zbud_page, bud_list); + list_del_init(&zbpg->bud_list); + zcache_zbpg_unused_list_count--; + atomic_dec(&zcache_zbud_curr_raw_pages); + spin_unlock_bh(&zbpg_unused_list_spinlock); + zcache_free_page(zbpg); + zcache_evicted_raw_pages++; + if (--nr <= 0) + goto out; + goto retry_unused_list; + } + spin_unlock_bh(&zbpg_unused_list_spinlock); + + /* now try freeing unbuddied pages, starting with least space avail */ + for (i = 0; i < MAX_CHUNK; i++) { +retry_unbud_list_i: + spin_lock_bh(&zbud_budlists_spinlock); + if (list_empty(&zbud_unbuddied[i].list)) { + spin_unlock_bh(&zbud_budlists_spinlock); + continue; + } + list_for_each_entry(zbpg, &zbud_unbuddied[i].list, bud_list) { + if (unlikely(!spin_trylock(&zbpg->lock))) + continue; + list_del_init(&zbpg->bud_list); + zbud_unbuddied[i].count--; + spin_unlock(&zbud_budlists_spinlock); + zcache_evicted_unbuddied_pages++; + /* want budlists unlocked when doing zbpg eviction */ + zbud_evict_zbpg(zbpg); + local_bh_enable(); + if (--nr <= 0) + goto out; + goto retry_unbud_list_i; + } + spin_unlock_bh(&zbud_budlists_spinlock); + } + + /* as a last resort, free buddied pages */ +retry_bud_list: + spin_lock_bh(&zbud_budlists_spinlock); + if (list_empty(&zbud_buddied_list)) { + spin_unlock_bh(&zbud_budlists_spinlock); + goto out; + } + list_for_each_entry(zbpg, &zbud_buddied_list, bud_list) { + if (unlikely(!spin_trylock(&zbpg->lock))) + continue; + list_del_init(&zbpg->bud_list); + zcache_zbud_buddied_count--; + spin_unlock(&zbud_budlists_spinlock); + zcache_evicted_buddied_pages++; + /* want budlists unlocked when doing zbpg eviction */ + zbud_evict_zbpg(zbpg); + local_bh_enable(); + if (--nr <= 0) + goto out; + goto retry_bud_list; + } + spin_unlock_bh(&zbud_budlists_spinlock); +out: + return; +} + +static void zbud_init(void) +{ + int i; + + INIT_LIST_HEAD(&zbud_buddied_list); + zcache_zbud_buddied_count = 0; + for (i = 0; i < NCHUNKS; i++) { + INIT_LIST_HEAD(&zbud_unbuddied[i].list); + zbud_unbuddied[i].count = 0; + } +} + +#ifdef CONFIG_SYSFS +/* + * These sysfs routines show a nice distribution of how many zbpg's are + * currently (and have ever been placed) in each unbuddied list. It's fun + * to watch but can probably go away before final merge. + */ +static int zbud_show_unbuddied_list_counts(char *buf) +{ + int i; + char *p = buf; + + for (i = 0; i < NCHUNKS; i++) + p += sprintf(p, "%u ", zbud_unbuddied[i].count); + return p - buf; +} + +static int zbud_show_cumul_chunk_counts(char *buf) +{ + unsigned long i, chunks = 0, total_chunks = 0, sum_total_chunks = 0; + unsigned long total_chunks_lte_21 = 0, total_chunks_lte_32 = 0; + unsigned long total_chunks_lte_42 = 0; + char *p = buf; + + for (i = 0; i < NCHUNKS; i++) { + p += sprintf(p, "%lu ", zbud_cumul_chunk_counts[i]); + chunks += zbud_cumul_chunk_counts[i]; + total_chunks += zbud_cumul_chunk_counts[i]; + sum_total_chunks += i * zbud_cumul_chunk_counts[i]; + if (i == 21) + total_chunks_lte_21 = total_chunks; + if (i == 32) + total_chunks_lte_32 = total_chunks; + if (i == 42) + total_chunks_lte_42 = total_chunks; + } + p += sprintf(p, "<=21:%lu <=32:%lu <=42:%lu, mean:%lu\n", + total_chunks_lte_21, total_chunks_lte_32, total_chunks_lte_42, + chunks == 0 ? 0 : sum_total_chunks / chunks); + return p - buf; +} +#endif + +/********** + * This "zv" PAM implementation combines the TLSF-based xvMalloc + * with lzo1x compression to maximize the amount of data that can + * be packed into a physical page. + * + * Zv represents a PAM page with the index and object (plus a "size" value + * necessary for decompression) immediately preceding the compressed data. + */ + +#define ZVH_SENTINEL 0x43214321 + +struct zv_hdr { + uint32_t pool_id; + struct tmem_oid oid; + uint32_t index; + DECL_SENTINEL +}; + +/* rudimentary policy limits */ +/* total number of persistent pages may not exceed this percentage */ +static unsigned int zv_page_count_policy_percent = 75; +/* + * byte count defining poor compression; pages with greater zsize will be + * rejected + */ +static unsigned int zv_max_zsize = (PAGE_SIZE / 8) * 7; +/* + * byte count defining poor *mean* compression; pages with greater zsize + * will be rejected until sufficient better-compressed pages are accepted + * driving the man below this threshold + */ +static unsigned int zv_max_mean_zsize = (PAGE_SIZE / 8) * 5; + +static unsigned long zv_curr_dist_counts[NCHUNKS]; +static unsigned long zv_cumul_dist_counts[NCHUNKS]; + +static struct zv_hdr *zv_create(struct xv_pool *xvpool, uint32_t pool_id, + struct tmem_oid *oid, uint32_t index, + void *cdata, unsigned clen) +{ + struct page *page; + struct zv_hdr *zv = NULL; + uint32_t offset; + int alloc_size = clen + sizeof(struct zv_hdr); + int chunks = (alloc_size + (CHUNK_SIZE - 1)) >> CHUNK_SHIFT; + int ret; + + BUG_ON(!irqs_disabled()); + BUG_ON(chunks >= NCHUNKS); + ret = xv_malloc(xvpool, alloc_size, + &page, &offset, ZCACHE_GFP_MASK); + if (unlikely(ret)) + goto out; + zv_curr_dist_counts[chunks]++; + zv_cumul_dist_counts[chunks]++; + zv = kmap_atomic(page, KM_USER0) + offset; + zv->index = index; + zv->oid = *oid; + zv->pool_id = pool_id; + SET_SENTINEL(zv, ZVH); + memcpy((char *)zv + sizeof(struct zv_hdr), cdata, clen); + kunmap_atomic(zv, KM_USER0); +out: + return zv; +} + +static void zv_free(struct xv_pool *xvpool, struct zv_hdr *zv) +{ + unsigned long flags; + struct page *page; + uint32_t offset; + uint16_t size = xv_get_object_size(zv); + int chunks = (size + (CHUNK_SIZE - 1)) >> CHUNK_SHIFT; + + ASSERT_SENTINEL(zv, ZVH); + BUG_ON(chunks >= NCHUNKS); + zv_curr_dist_counts[chunks]--; + size -= sizeof(*zv); + BUG_ON(size == 0); + INVERT_SENTINEL(zv, ZVH); + page = virt_to_page(zv); + offset = (unsigned long)zv & ~PAGE_MASK; + local_irq_save(flags); + xv_free(xvpool, page, offset); + local_irq_restore(flags); +} + +static void zv_decompress(struct page *page, struct zv_hdr *zv) +{ + size_t clen = PAGE_SIZE; + char *to_va; + unsigned size; + int ret; + + ASSERT_SENTINEL(zv, ZVH); + size = xv_get_object_size(zv) - sizeof(*zv); + BUG_ON(size == 0); + to_va = kmap_atomic(page, KM_USER0); + ret = lzo1x_decompress_safe((char *)zv + sizeof(*zv), + size, to_va, &clen); + kunmap_atomic(to_va, KM_USER0); + BUG_ON(ret != LZO_E_OK); + BUG_ON(clen != PAGE_SIZE); +} + +#ifdef CONFIG_SYSFS +/* + * show a distribution of compression stats for zv pages. + */ + +static int zv_curr_dist_counts_show(char *buf) +{ + unsigned long i, n, chunks = 0, sum_total_chunks = 0; + char *p = buf; + + for (i = 0; i < NCHUNKS; i++) { + n = zv_curr_dist_counts[i]; + p += sprintf(p, "%lu ", n); + chunks += n; + sum_total_chunks += i * n; + } + p += sprintf(p, "mean:%lu\n", + chunks == 0 ? 0 : sum_total_chunks / chunks); + return p - buf; +} + +static int zv_cumul_dist_counts_show(char *buf) +{ + unsigned long i, n, chunks = 0, sum_total_chunks = 0; + char *p = buf; + + for (i = 0; i < NCHUNKS; i++) { + n = zv_cumul_dist_counts[i]; + p += sprintf(p, "%lu ", n); + chunks += n; + sum_total_chunks += i * n; + } + p += sprintf(p, "mean:%lu\n", + chunks == 0 ? 0 : sum_total_chunks / chunks); + return p - buf; +} + +/* + * setting zv_max_zsize via sysfs causes all persistent (e.g. swap) + * pages that don't compress to less than this value (including metadata + * overhead) to be rejected. We don't allow the value to get too close + * to PAGE_SIZE. + */ +static ssize_t zv_max_zsize_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", zv_max_zsize); +} + +static ssize_t zv_max_zsize_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + unsigned long val; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + err = strict_strtoul(buf, 10, &val); + if (err || (val == 0) || (val > (PAGE_SIZE / 8) * 7)) + return -EINVAL; + zv_max_zsize = val; + return count; +} + +/* + * setting zv_max_mean_zsize via sysfs causes all persistent (e.g. swap) + * pages that don't compress to less than this value (including metadata + * overhead) to be rejected UNLESS the mean compression is also smaller + * than this value. In other words, we are load-balancing-by-zsize the + * accepted pages. Again, we don't allow the value to get too close + * to PAGE_SIZE. + */ +static ssize_t zv_max_mean_zsize_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", zv_max_mean_zsize); +} + +static ssize_t zv_max_mean_zsize_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + unsigned long val; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + err = strict_strtoul(buf, 10, &val); + if (err || (val == 0) || (val > (PAGE_SIZE / 8) * 7)) + return -EINVAL; + zv_max_mean_zsize = val; + return count; +} + +/* + * setting zv_page_count_policy_percent via sysfs sets an upper bound of + * persistent (e.g. swap) pages that will be retained according to: + * (zv_page_count_policy_percent * totalram_pages) / 100) + * when that limit is reached, further puts will be rejected (until + * some pages have been flushed). Note that, due to compression, + * this number may exceed 100; it defaults to 75 and we set an + * arbitary limit of 150. A poor choice will almost certainly result + * in OOM's, so this value should only be changed prudently. + */ +static ssize_t zv_page_count_policy_percent_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", zv_page_count_policy_percent); +} + +static ssize_t zv_page_count_policy_percent_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + unsigned long val; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + err = strict_strtoul(buf, 10, &val); + if (err || (val == 0) || (val > 150)) + return -EINVAL; + zv_page_count_policy_percent = val; + return count; +} + +static struct kobj_attribute zcache_zv_max_zsize_attr = { + .attr = { .name = "zv_max_zsize", .mode = 0644 }, + .show = zv_max_zsize_show, + .store = zv_max_zsize_store, +}; + +static struct kobj_attribute zcache_zv_max_mean_zsize_attr = { + .attr = { .name = "zv_max_mean_zsize", .mode = 0644 }, + .show = zv_max_mean_zsize_show, + .store = zv_max_mean_zsize_store, +}; + +static struct kobj_attribute zcache_zv_page_count_policy_percent_attr = { + .attr = { .name = "zv_page_count_policy_percent", + .mode = 0644 }, + .show = zv_page_count_policy_percent_show, + .store = zv_page_count_policy_percent_store, +}; +#endif + +/* + * zcache core code starts here + */ + +/* useful stats not collected by cleancache or frontswap */ +static unsigned long zcache_flush_total; +static unsigned long zcache_flush_found; +static unsigned long zcache_flobj_total; +static unsigned long zcache_flobj_found; +static unsigned long zcache_failed_eph_puts; +static unsigned long zcache_failed_pers_puts; + +/* + * Tmem operations assume the poolid implies the invoking client. + * Zcache only has one client (the kernel itself): LOCAL_CLIENT. + * RAMster has each client numbered by cluster node, and a KVM version + * of zcache would have one client per guest and each client might + * have a poolid==N. + */ +static struct tmem_pool *zcache_get_pool_by_id(uint16_t cli_id, uint16_t poolid) +{ + struct tmem_pool *pool = NULL; + struct zcache_client *cli = NULL; + + if (cli_id == LOCAL_CLIENT) + cli = &zcache_host; + else { + if (cli_id >= MAX_CLIENTS) + goto out; + cli = &zcache_clients[cli_id]; + if (cli == NULL) + goto out; + atomic_inc(&cli->refcount); + } + if (poolid < MAX_POOLS_PER_CLIENT) { + pool = cli->tmem_pools[poolid]; + if (pool != NULL) + atomic_inc(&pool->refcount); + } +out: + return pool; +} + +static void zcache_put_pool(struct tmem_pool *pool) +{ + struct zcache_client *cli = NULL; + + if (pool == NULL) + BUG(); + cli = pool->client; + atomic_dec(&pool->refcount); + atomic_dec(&cli->refcount); +} + +int zcache_new_client(uint16_t cli_id) +{ + struct zcache_client *cli = NULL; + int ret = -1; + + if (cli_id == LOCAL_CLIENT) + cli = &zcache_host; + else if ((unsigned int)cli_id < MAX_CLIENTS) + cli = &zcache_clients[cli_id]; + if (cli == NULL) + goto out; + if (cli->allocated) + goto out; + cli->allocated = 1; +#ifdef CONFIG_FRONTSWAP + cli->xvpool = xv_create_pool(); + if (cli->xvpool == NULL) + goto out; +#endif + ret = 0; +out: + return ret; +} + +/* counters for debugging */ +static unsigned long zcache_failed_get_free_pages; +static unsigned long zcache_failed_alloc; +static unsigned long zcache_put_to_flush; +static unsigned long zcache_aborted_preload; +static unsigned long zcache_aborted_shrink; + +/* + * Ensure that memory allocation requests in zcache don't result + * in direct reclaim requests via the shrinker, which would cause + * an infinite loop. Maybe a GFP flag would be better? + */ +static DEFINE_SPINLOCK(zcache_direct_reclaim_lock); + +/* + * for now, used named slabs so can easily track usage; later can + * either just use kmalloc, or perhaps add a slab-like allocator + * to more carefully manage total memory utilization + */ +static struct kmem_cache *zcache_objnode_cache; +static struct kmem_cache *zcache_obj_cache; +static atomic_t zcache_curr_obj_count = ATOMIC_INIT(0); +static unsigned long zcache_curr_obj_count_max; +static atomic_t zcache_curr_objnode_count = ATOMIC_INIT(0); +static unsigned long zcache_curr_objnode_count_max; + +/* + * to avoid memory allocation recursion (e.g. due to direct reclaim), we + * preload all necessary data structures so the hostops callbacks never + * actually do a malloc + */ +struct zcache_preload { + void *page; + struct tmem_obj *obj; + int nr; + struct tmem_objnode *objnodes[OBJNODE_TREE_MAX_PATH]; +}; +static DEFINE_PER_CPU(struct zcache_preload, zcache_preloads) = { 0, }; + +static int zcache_do_preload(struct tmem_pool *pool) +{ + struct zcache_preload *kp; + struct tmem_objnode *objnode; + struct tmem_obj *obj; + void *page; + int ret = -ENOMEM; + + if (unlikely(zcache_objnode_cache == NULL)) + goto out; + if (unlikely(zcache_obj_cache == NULL)) + goto out; + if (!spin_trylock(&zcache_direct_reclaim_lock)) { + zcache_aborted_preload++; + goto out; + } + preempt_disable(); + kp = &__get_cpu_var(zcache_preloads); + while (kp->nr < ARRAY_SIZE(kp->objnodes)) { + preempt_enable_no_resched(); + objnode = kmem_cache_alloc(zcache_objnode_cache, + ZCACHE_GFP_MASK); + if (unlikely(objnode == NULL)) { + zcache_failed_alloc++; + goto unlock_out; + } + preempt_disable(); + kp = &__get_cpu_var(zcache_preloads); + if (kp->nr < ARRAY_SIZE(kp->objnodes)) + kp->objnodes[kp->nr++] = objnode; + else + kmem_cache_free(zcache_objnode_cache, objnode); + } + preempt_enable_no_resched(); + obj = kmem_cache_alloc(zcache_obj_cache, ZCACHE_GFP_MASK); + if (unlikely(obj == NULL)) { + zcache_failed_alloc++; + goto unlock_out; + } + page = (void *)__get_free_page(ZCACHE_GFP_MASK); + if (unlikely(page == NULL)) { + zcache_failed_get_free_pages++; + kmem_cache_free(zcache_obj_cache, obj); + goto unlock_out; + } + preempt_disable(); + kp = &__get_cpu_var(zcache_preloads); + if (kp->obj == NULL) + kp->obj = obj; + else + kmem_cache_free(zcache_obj_cache, obj); + if (kp->page == NULL) + kp->page = page; + else + free_page((unsigned long)page); + ret = 0; +unlock_out: + spin_unlock(&zcache_direct_reclaim_lock); +out: + return ret; +} + +static void *zcache_get_free_page(void) +{ + struct zcache_preload *kp; + void *page; + + kp = &__get_cpu_var(zcache_preloads); + page = kp->page; + BUG_ON(page == NULL); + kp->page = NULL; + return page; +} + +static void zcache_free_page(void *p) +{ + free_page((unsigned long)p); +} + +/* + * zcache implementation for tmem host ops + */ + +static struct tmem_objnode *zcache_objnode_alloc(struct tmem_pool *pool) +{ + struct tmem_objnode *objnode = NULL; + unsigned long count; + struct zcache_preload *kp; + + kp = &__get_cpu_var(zcache_preloads); + if (kp->nr <= 0) + goto out; + objnode = kp->objnodes[kp->nr - 1]; + BUG_ON(objnode == NULL); + kp->objnodes[kp->nr - 1] = NULL; + kp->nr--; + count = atomic_inc_return(&zcache_curr_objnode_count); + if (count > zcache_curr_objnode_count_max) + zcache_curr_objnode_count_max = count; +out: + return objnode; +} + +static void zcache_objnode_free(struct tmem_objnode *objnode, + struct tmem_pool *pool) +{ + atomic_dec(&zcache_curr_objnode_count); + BUG_ON(atomic_read(&zcache_curr_objnode_count) < 0); + kmem_cache_free(zcache_objnode_cache, objnode); +} + +static struct tmem_obj *zcache_obj_alloc(struct tmem_pool *pool) +{ + struct tmem_obj *obj = NULL; + unsigned long count; + struct zcache_preload *kp; + + kp = &__get_cpu_var(zcache_preloads); + obj = kp->obj; + BUG_ON(obj == NULL); + kp->obj = NULL; + count = atomic_inc_return(&zcache_curr_obj_count); + if (count > zcache_curr_obj_count_max) + zcache_curr_obj_count_max = count; + return obj; +} + +static void zcache_obj_free(struct tmem_obj *obj, struct tmem_pool *pool) +{ + atomic_dec(&zcache_curr_obj_count); + BUG_ON(atomic_read(&zcache_curr_obj_count) < 0); + kmem_cache_free(zcache_obj_cache, obj); +} + +static struct tmem_hostops zcache_hostops = { + .obj_alloc = zcache_obj_alloc, + .obj_free = zcache_obj_free, + .objnode_alloc = zcache_objnode_alloc, + .objnode_free = zcache_objnode_free, +}; + +/* + * zcache implementations for PAM page descriptor ops + */ + +static atomic_t zcache_curr_eph_pampd_count = ATOMIC_INIT(0); +static unsigned long zcache_curr_eph_pampd_count_max; +static atomic_t zcache_curr_pers_pampd_count = ATOMIC_INIT(0); +static unsigned long zcache_curr_pers_pampd_count_max; + +/* forward reference */ +static int zcache_compress(struct page *from, void **out_va, size_t *out_len); + +static void *zcache_pampd_create(char *data, size_t size, bool raw, int eph, + struct tmem_pool *pool, struct tmem_oid *oid, + uint32_t index) +{ + void *pampd = NULL, *cdata; + size_t clen; + int ret; + unsigned long count; + struct page *page = virt_to_page(data); + struct zcache_client *cli = pool->client; + uint16_t client_id = get_client_id_from_client(cli); + unsigned long zv_mean_zsize; + unsigned long curr_pers_pampd_count; + + if (eph) { + ret = zcache_compress(page, &cdata, &clen); + if (ret == 0) + goto out; + if (clen == 0 || clen > zbud_max_buddy_size()) { + zcache_compress_poor++; + goto out; + } + pampd = (void *)zbud_create(client_id, pool->pool_id, oid, + index, page, cdata, clen); + if (pampd != NULL) { + count = atomic_inc_return(&zcache_curr_eph_pampd_count); + if (count > zcache_curr_eph_pampd_count_max) + zcache_curr_eph_pampd_count_max = count; + } + } else { + curr_pers_pampd_count = + atomic_read(&zcache_curr_pers_pampd_count); + if (curr_pers_pampd_count > + (zv_page_count_policy_percent * totalram_pages) / 100) + goto out; + ret = zcache_compress(page, &cdata, &clen); + if (ret == 0) + goto out; + /* reject if compression is too poor */ + if (clen > zv_max_zsize) { + zcache_compress_poor++; + goto out; + } + /* reject if mean compression is too poor */ + if ((clen > zv_max_mean_zsize) && (curr_pers_pampd_count > 0)) { + zv_mean_zsize = xv_get_total_size_bytes(cli->xvpool) / + curr_pers_pampd_count; + if (zv_mean_zsize > zv_max_mean_zsize) { + zcache_mean_compress_poor++; + goto out; + } + } + pampd = (void *)zv_create(cli->xvpool, pool->pool_id, + oid, index, cdata, clen); + if (pampd == NULL) + goto out; + count = atomic_inc_return(&zcache_curr_pers_pampd_count); + if (count > zcache_curr_pers_pampd_count_max) + zcache_curr_pers_pampd_count_max = count; + } +out: + return pampd; +} + +/* + * fill the pageframe corresponding to the struct page with the data + * from the passed pampd + */ +static int zcache_pampd_get_data(char *data, size_t *bufsize, bool raw, + void *pampd, struct tmem_pool *pool, + struct tmem_oid *oid, uint32_t index) +{ + int ret = 0; + + BUG_ON(is_ephemeral(pool)); + zv_decompress(virt_to_page(data), pampd); + return ret; +} + +/* + * fill the pageframe corresponding to the struct page with the data + * from the passed pampd + */ +static int zcache_pampd_get_data_and_free(char *data, size_t *bufsize, bool raw, + void *pampd, struct tmem_pool *pool, + struct tmem_oid *oid, uint32_t index) +{ + int ret = 0; + + BUG_ON(!is_ephemeral(pool)); + zbud_decompress(virt_to_page(data), pampd); + zbud_free_and_delist((struct zbud_hdr *)pampd); + atomic_dec(&zcache_curr_eph_pampd_count); + return ret; +} + +/* + * free the pampd and remove it from any zcache lists + * pampd must no longer be pointed to from any tmem data structures! + */ +static void zcache_pampd_free(void *pampd, struct tmem_pool *pool, + struct tmem_oid *oid, uint32_t index) +{ + struct zcache_client *cli = pool->client; + + if (is_ephemeral(pool)) { + zbud_free_and_delist((struct zbud_hdr *)pampd); + atomic_dec(&zcache_curr_eph_pampd_count); + BUG_ON(atomic_read(&zcache_curr_eph_pampd_count) < 0); + } else { + zv_free(cli->xvpool, (struct zv_hdr *)pampd); + atomic_dec(&zcache_curr_pers_pampd_count); + BUG_ON(atomic_read(&zcache_curr_pers_pampd_count) < 0); + } +} + +static void zcache_pampd_free_obj(struct tmem_pool *pool, struct tmem_obj *obj) +{ +} + +static void zcache_pampd_new_obj(struct tmem_obj *obj) +{ +} + +static int zcache_pampd_replace_in_obj(void *pampd, struct tmem_obj *obj) +{ + return -1; +} + +static bool zcache_pampd_is_remote(void *pampd) +{ + return 0; +} + +static struct tmem_pamops zcache_pamops = { + .create = zcache_pampd_create, + .get_data = zcache_pampd_get_data, + .get_data_and_free = zcache_pampd_get_data_and_free, + .free = zcache_pampd_free, + .free_obj = zcache_pampd_free_obj, + .new_obj = zcache_pampd_new_obj, + .replace_in_obj = zcache_pampd_replace_in_obj, + .is_remote = zcache_pampd_is_remote, +}; + +/* + * zcache compression/decompression and related per-cpu stuff + */ + +#define LZO_WORKMEM_BYTES LZO1X_1_MEM_COMPRESS +#define LZO_DSTMEM_PAGE_ORDER 1 +static DEFINE_PER_CPU(unsigned char *, zcache_workmem); +static DEFINE_PER_CPU(unsigned char *, zcache_dstmem); + +static int zcache_compress(struct page *from, void **out_va, size_t *out_len) +{ + int ret = 0; + unsigned char *dmem = __get_cpu_var(zcache_dstmem); + unsigned char *wmem = __get_cpu_var(zcache_workmem); + char *from_va; + + BUG_ON(!irqs_disabled()); + if (unlikely(dmem == NULL || wmem == NULL)) + goto out; /* no buffer, so can't compress */ + from_va = kmap_atomic(from, KM_USER0); + mb(); + ret = lzo1x_1_compress(from_va, PAGE_SIZE, dmem, out_len, wmem); + BUG_ON(ret != LZO_E_OK); + *out_va = dmem; + kunmap_atomic(from_va, KM_USER0); + ret = 1; +out: + return ret; +} + + +static int zcache_cpu_notifier(struct notifier_block *nb, + unsigned long action, void *pcpu) +{ + int cpu = (long)pcpu; + struct zcache_preload *kp; + + switch (action) { + case CPU_UP_PREPARE: + per_cpu(zcache_dstmem, cpu) = (void *)__get_free_pages( + GFP_KERNEL | __GFP_REPEAT, + LZO_DSTMEM_PAGE_ORDER), + per_cpu(zcache_workmem, cpu) = + kzalloc(LZO1X_MEM_COMPRESS, + GFP_KERNEL | __GFP_REPEAT); + break; + case CPU_DEAD: + case CPU_UP_CANCELED: + free_pages((unsigned long)per_cpu(zcache_dstmem, cpu), + LZO_DSTMEM_PAGE_ORDER); + per_cpu(zcache_dstmem, cpu) = NULL; + kfree(per_cpu(zcache_workmem, cpu)); + per_cpu(zcache_workmem, cpu) = NULL; + kp = &per_cpu(zcache_preloads, cpu); + while (kp->nr) { + kmem_cache_free(zcache_objnode_cache, + kp->objnodes[kp->nr - 1]); + kp->objnodes[kp->nr - 1] = NULL; + kp->nr--; + } + kmem_cache_free(zcache_obj_cache, kp->obj); + free_page((unsigned long)kp->page); + break; + default: + break; + } + return NOTIFY_OK; +} + +static struct notifier_block zcache_cpu_notifier_block = { + .notifier_call = zcache_cpu_notifier +}; + +#ifdef CONFIG_SYSFS +#define ZCACHE_SYSFS_RO(_name) \ + static ssize_t zcache_##_name##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, char *buf) \ + { \ + return sprintf(buf, "%lu\n", zcache_##_name); \ + } \ + static struct kobj_attribute zcache_##_name##_attr = { \ + .attr = { .name = __stringify(_name), .mode = 0444 }, \ + .show = zcache_##_name##_show, \ + } + +#define ZCACHE_SYSFS_RO_ATOMIC(_name) \ + static ssize_t zcache_##_name##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, char *buf) \ + { \ + return sprintf(buf, "%d\n", atomic_read(&zcache_##_name)); \ + } \ + static struct kobj_attribute zcache_##_name##_attr = { \ + .attr = { .name = __stringify(_name), .mode = 0444 }, \ + .show = zcache_##_name##_show, \ + } + +#define ZCACHE_SYSFS_RO_CUSTOM(_name, _func) \ + static ssize_t zcache_##_name##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, char *buf) \ + { \ + return _func(buf); \ + } \ + static struct kobj_attribute zcache_##_name##_attr = { \ + .attr = { .name = __stringify(_name), .mode = 0444 }, \ + .show = zcache_##_name##_show, \ + } + +ZCACHE_SYSFS_RO(curr_obj_count_max); +ZCACHE_SYSFS_RO(curr_objnode_count_max); +ZCACHE_SYSFS_RO(flush_total); +ZCACHE_SYSFS_RO(flush_found); +ZCACHE_SYSFS_RO(flobj_total); +ZCACHE_SYSFS_RO(flobj_found); +ZCACHE_SYSFS_RO(failed_eph_puts); +ZCACHE_SYSFS_RO(failed_pers_puts); +ZCACHE_SYSFS_RO(zbud_curr_zbytes); +ZCACHE_SYSFS_RO(zbud_cumul_zpages); +ZCACHE_SYSFS_RO(zbud_cumul_zbytes); +ZCACHE_SYSFS_RO(zbud_buddied_count); +ZCACHE_SYSFS_RO(zbpg_unused_list_count); +ZCACHE_SYSFS_RO(evicted_raw_pages); +ZCACHE_SYSFS_RO(evicted_unbuddied_pages); +ZCACHE_SYSFS_RO(evicted_buddied_pages); +ZCACHE_SYSFS_RO(failed_get_free_pages); +ZCACHE_SYSFS_RO(failed_alloc); +ZCACHE_SYSFS_RO(put_to_flush); +ZCACHE_SYSFS_RO(aborted_preload); +ZCACHE_SYSFS_RO(aborted_shrink); +ZCACHE_SYSFS_RO(compress_poor); +ZCACHE_SYSFS_RO(mean_compress_poor); +ZCACHE_SYSFS_RO_ATOMIC(zbud_curr_raw_pages); +ZCACHE_SYSFS_RO_ATOMIC(zbud_curr_zpages); +ZCACHE_SYSFS_RO_ATOMIC(curr_obj_count); +ZCACHE_SYSFS_RO_ATOMIC(curr_objnode_count); +ZCACHE_SYSFS_RO_CUSTOM(zbud_unbuddied_list_counts, + zbud_show_unbuddied_list_counts); +ZCACHE_SYSFS_RO_CUSTOM(zbud_cumul_chunk_counts, + zbud_show_cumul_chunk_counts); +ZCACHE_SYSFS_RO_CUSTOM(zv_curr_dist_counts, + zv_curr_dist_counts_show); +ZCACHE_SYSFS_RO_CUSTOM(zv_cumul_dist_counts, + zv_cumul_dist_counts_show); + +static struct attribute *zcache_attrs[] = { + &zcache_curr_obj_count_attr.attr, + &zcache_curr_obj_count_max_attr.attr, + &zcache_curr_objnode_count_attr.attr, + &zcache_curr_objnode_count_max_attr.attr, + &zcache_flush_total_attr.attr, + &zcache_flobj_total_attr.attr, + &zcache_flush_found_attr.attr, + &zcache_flobj_found_attr.attr, + &zcache_failed_eph_puts_attr.attr, + &zcache_failed_pers_puts_attr.attr, + &zcache_compress_poor_attr.attr, + &zcache_mean_compress_poor_attr.attr, + &zcache_zbud_curr_raw_pages_attr.attr, + &zcache_zbud_curr_zpages_attr.attr, + &zcache_zbud_curr_zbytes_attr.attr, + &zcache_zbud_cumul_zpages_attr.attr, + &zcache_zbud_cumul_zbytes_attr.attr, + &zcache_zbud_buddied_count_attr.attr, + &zcache_zbpg_unused_list_count_attr.attr, + &zcache_evicted_raw_pages_attr.attr, + &zcache_evicted_unbuddied_pages_attr.attr, + &zcache_evicted_buddied_pages_attr.attr, + &zcache_failed_get_free_pages_attr.attr, + &zcache_failed_alloc_attr.attr, + &zcache_put_to_flush_attr.attr, + &zcache_aborted_preload_attr.attr, + &zcache_aborted_shrink_attr.attr, + &zcache_zbud_unbuddied_list_counts_attr.attr, + &zcache_zbud_cumul_chunk_counts_attr.attr, + &zcache_zv_curr_dist_counts_attr.attr, + &zcache_zv_cumul_dist_counts_attr.attr, + &zcache_zv_max_zsize_attr.attr, + &zcache_zv_max_mean_zsize_attr.attr, + &zcache_zv_page_count_policy_percent_attr.attr, + NULL, +}; + +static struct attribute_group zcache_attr_group = { + .attrs = zcache_attrs, + .name = "zcache", +}; + +#endif /* CONFIG_SYSFS */ +/* + * When zcache is disabled ("frozen"), pools can be created and destroyed, + * but all puts (and thus all other operations that require memory allocation) + * must fail. If zcache is unfrozen, accepts puts, then frozen again, + * data consistency requires all puts while frozen to be converted into + * flushes. + */ +static bool zcache_freeze; + +/* + * zcache shrinker interface (only useful for ephemeral pages, so zbud only) + */ +static int shrink_zcache_memory(struct shrinker *shrink, + struct shrink_control *sc) +{ + int ret = -1; + int nr = sc->nr_to_scan; + gfp_t gfp_mask = sc->gfp_mask; + + if (nr >= 0) { + if (!(gfp_mask & __GFP_FS)) + /* does this case really need to be skipped? */ + goto out; + if (spin_trylock(&zcache_direct_reclaim_lock)) { + zbud_evict_pages(nr); + spin_unlock(&zcache_direct_reclaim_lock); + } else + zcache_aborted_shrink++; + } + ret = (int)atomic_read(&zcache_zbud_curr_raw_pages); +out: + return ret; +} + +static struct shrinker zcache_shrinker = { + .shrink = shrink_zcache_memory, + .seeks = DEFAULT_SEEKS, +}; + +/* + * zcache shims between cleancache/frontswap ops and tmem + */ + +static int zcache_put_page(int cli_id, int pool_id, struct tmem_oid *oidp, + uint32_t index, struct page *page) +{ + struct tmem_pool *pool; + int ret = -1; + + BUG_ON(!irqs_disabled()); + pool = zcache_get_pool_by_id(cli_id, pool_id); + if (unlikely(pool == NULL)) + goto out; + if (!zcache_freeze && zcache_do_preload(pool) == 0) { + /* preload does preempt_disable on success */ + ret = tmem_put(pool, oidp, index, page_address(page), + PAGE_SIZE, 0, is_ephemeral(pool)); + if (ret < 0) { + if (is_ephemeral(pool)) + zcache_failed_eph_puts++; + else + zcache_failed_pers_puts++; + } + zcache_put_pool(pool); + preempt_enable_no_resched(); + } else { + zcache_put_to_flush++; + if (atomic_read(&pool->obj_count) > 0) + /* the put fails whether the flush succeeds or not */ + (void)tmem_flush_page(pool, oidp, index); + zcache_put_pool(pool); + } +out: + return ret; +} + +static int zcache_get_page(int cli_id, int pool_id, struct tmem_oid *oidp, + uint32_t index, struct page *page) +{ + struct tmem_pool *pool; + int ret = -1; + unsigned long flags; + size_t size = PAGE_SIZE; + + local_irq_save(flags); + pool = zcache_get_pool_by_id(cli_id, pool_id); + if (likely(pool != NULL)) { + if (atomic_read(&pool->obj_count) > 0) + ret = tmem_get(pool, oidp, index, page_address(page), + &size, 0, is_ephemeral(pool)); + zcache_put_pool(pool); + } + local_irq_restore(flags); + return ret; +} + +static int zcache_flush_page(int cli_id, int pool_id, + struct tmem_oid *oidp, uint32_t index) +{ + struct tmem_pool *pool; + int ret = -1; + unsigned long flags; + + local_irq_save(flags); + zcache_flush_total++; + pool = zcache_get_pool_by_id(cli_id, pool_id); + if (likely(pool != NULL)) { + if (atomic_read(&pool->obj_count) > 0) + ret = tmem_flush_page(pool, oidp, index); + zcache_put_pool(pool); + } + if (ret >= 0) + zcache_flush_found++; + local_irq_restore(flags); + return ret; +} + +static int zcache_flush_object(int cli_id, int pool_id, + struct tmem_oid *oidp) +{ + struct tmem_pool *pool; + int ret = -1; + unsigned long flags; + + local_irq_save(flags); + zcache_flobj_total++; + pool = zcache_get_pool_by_id(cli_id, pool_id); + if (likely(pool != NULL)) { + if (atomic_read(&pool->obj_count) > 0) + ret = tmem_flush_object(pool, oidp); + zcache_put_pool(pool); + } + if (ret >= 0) + zcache_flobj_found++; + local_irq_restore(flags); + return ret; +} + +static int zcache_destroy_pool(int cli_id, int pool_id) +{ + struct tmem_pool *pool = NULL; + struct zcache_client *cli = NULL; + int ret = -1; + + if (pool_id < 0) + goto out; + if (cli_id == LOCAL_CLIENT) + cli = &zcache_host; + else if ((unsigned int)cli_id < MAX_CLIENTS) + cli = &zcache_clients[cli_id]; + if (cli == NULL) + goto out; + atomic_inc(&cli->refcount); + pool = cli->tmem_pools[pool_id]; + if (pool == NULL) + goto out; + cli->tmem_pools[pool_id] = NULL; + /* wait for pool activity on other cpus to quiesce */ + while (atomic_read(&pool->refcount) != 0) + ; + atomic_dec(&cli->refcount); + local_bh_disable(); + ret = tmem_destroy_pool(pool); + local_bh_enable(); + kfree(pool); + pr_info("zcache: destroyed pool id=%d, cli_id=%d\n", + pool_id, cli_id); +out: + return ret; +} + +static int zcache_new_pool(uint16_t cli_id, uint32_t flags) +{ + int poolid = -1; + struct tmem_pool *pool; + struct zcache_client *cli = NULL; + + if (cli_id == LOCAL_CLIENT) + cli = &zcache_host; + else if ((unsigned int)cli_id < MAX_CLIENTS) + cli = &zcache_clients[cli_id]; + if (cli == NULL) + goto out; + atomic_inc(&cli->refcount); + pool = kmalloc(sizeof(struct tmem_pool), GFP_KERNEL); + if (pool == NULL) { + pr_info("zcache: pool creation failed: out of memory\n"); + goto out; + } + + for (poolid = 0; poolid < MAX_POOLS_PER_CLIENT; poolid++) + if (cli->tmem_pools[poolid] == NULL) + break; + if (poolid >= MAX_POOLS_PER_CLIENT) { + pr_info("zcache: pool creation failed: max exceeded\n"); + kfree(pool); + poolid = -1; + goto out; + } + atomic_set(&pool->refcount, 0); + pool->client = cli; + pool->pool_id = poolid; + tmem_new_pool(pool, flags); + cli->tmem_pools[poolid] = pool; + pr_info("zcache: created %s tmem pool, id=%d, client=%d\n", + flags & TMEM_POOL_PERSIST ? "persistent" : "ephemeral", + poolid, cli_id); +out: + if (cli != NULL) + atomic_dec(&cli->refcount); + return poolid; +} + +/********** + * Two kernel functionalities currently can be layered on top of tmem. + * These are "cleancache" which is used as a second-chance cache for clean + * page cache pages; and "frontswap" which is used for swap pages + * to avoid writes to disk. A generic "shim" is provided here for each + * to translate in-kernel semantics to zcache semantics. + */ + +#ifdef CONFIG_CLEANCACHE +static void zcache_cleancache_put_page(int pool_id, + struct cleancache_filekey key, + pgoff_t index, struct page *page) +{ + u32 ind = (u32) index; + struct tmem_oid oid = *(struct tmem_oid *)&key; + + if (likely(ind == index)) + (void)zcache_put_page(LOCAL_CLIENT, pool_id, &oid, index, page); +} + +static int zcache_cleancache_get_page(int pool_id, + struct cleancache_filekey key, + pgoff_t index, struct page *page) +{ + u32 ind = (u32) index; + struct tmem_oid oid = *(struct tmem_oid *)&key; + int ret = -1; + + if (likely(ind == index)) + ret = zcache_get_page(LOCAL_CLIENT, pool_id, &oid, index, page); + return ret; +} + +static void zcache_cleancache_flush_page(int pool_id, + struct cleancache_filekey key, + pgoff_t index) +{ + u32 ind = (u32) index; + struct tmem_oid oid = *(struct tmem_oid *)&key; + + if (likely(ind == index)) + (void)zcache_flush_page(LOCAL_CLIENT, pool_id, &oid, ind); +} + +static void zcache_cleancache_flush_inode(int pool_id, + struct cleancache_filekey key) +{ + struct tmem_oid oid = *(struct tmem_oid *)&key; + + (void)zcache_flush_object(LOCAL_CLIENT, pool_id, &oid); +} + +static void zcache_cleancache_flush_fs(int pool_id) +{ + if (pool_id >= 0) + (void)zcache_destroy_pool(LOCAL_CLIENT, pool_id); +} + +static int zcache_cleancache_init_fs(size_t pagesize) +{ + BUG_ON(sizeof(struct cleancache_filekey) != + sizeof(struct tmem_oid)); + BUG_ON(pagesize != PAGE_SIZE); + return zcache_new_pool(LOCAL_CLIENT, 0); +} + +static int zcache_cleancache_init_shared_fs(char *uuid, size_t pagesize) +{ + /* shared pools are unsupported and map to private */ + BUG_ON(sizeof(struct cleancache_filekey) != + sizeof(struct tmem_oid)); + BUG_ON(pagesize != PAGE_SIZE); + return zcache_new_pool(LOCAL_CLIENT, 0); +} + +static struct cleancache_ops zcache_cleancache_ops = { + .put_page = zcache_cleancache_put_page, + .get_page = zcache_cleancache_get_page, + .flush_page = zcache_cleancache_flush_page, + .flush_inode = zcache_cleancache_flush_inode, + .flush_fs = zcache_cleancache_flush_fs, + .init_shared_fs = zcache_cleancache_init_shared_fs, + .init_fs = zcache_cleancache_init_fs +}; + +struct cleancache_ops zcache_cleancache_register_ops(void) +{ + struct cleancache_ops old_ops = + cleancache_register_ops(&zcache_cleancache_ops); + + return old_ops; +} +#endif + +#ifdef CONFIG_FRONTSWAP +/* a single tmem poolid is used for all frontswap "types" (swapfiles) */ +static int zcache_frontswap_poolid = -1; + +/* + * Swizzling increases objects per swaptype, increasing tmem concurrency + * for heavy swaploads. Later, larger nr_cpus -> larger SWIZ_BITS + */ +#define SWIZ_BITS 4 +#define SWIZ_MASK ((1 << SWIZ_BITS) - 1) +#define _oswiz(_type, _ind) ((_type << SWIZ_BITS) | (_ind & SWIZ_MASK)) +#define iswiz(_ind) (_ind >> SWIZ_BITS) + +static inline struct tmem_oid oswiz(unsigned type, u32 ind) +{ + struct tmem_oid oid = { .oid = { 0 } }; + oid.oid[0] = _oswiz(type, ind); + return oid; +} + +static int zcache_frontswap_put_page(unsigned type, pgoff_t offset, + struct page *page) +{ + u64 ind64 = (u64)offset; + u32 ind = (u32)offset; + struct tmem_oid oid = oswiz(type, ind); + int ret = -1; + unsigned long flags; + + BUG_ON(!PageLocked(page)); + if (likely(ind64 == ind)) { + local_irq_save(flags); + ret = zcache_put_page(LOCAL_CLIENT, zcache_frontswap_poolid, + &oid, iswiz(ind), page); + local_irq_restore(flags); + } + return ret; +} + +/* returns 0 if the page was successfully gotten from frontswap, -1 if + * was not present (should never happen!) */ +static int zcache_frontswap_get_page(unsigned type, pgoff_t offset, + struct page *page) +{ + u64 ind64 = (u64)offset; + u32 ind = (u32)offset; + struct tmem_oid oid = oswiz(type, ind); + int ret = -1; + + BUG_ON(!PageLocked(page)); + if (likely(ind64 == ind)) + ret = zcache_get_page(LOCAL_CLIENT, zcache_frontswap_poolid, + &oid, iswiz(ind), page); + return ret; +} + +/* flush a single page from frontswap */ +static void zcache_frontswap_flush_page(unsigned type, pgoff_t offset) +{ + u64 ind64 = (u64)offset; + u32 ind = (u32)offset; + struct tmem_oid oid = oswiz(type, ind); + + if (likely(ind64 == ind)) + (void)zcache_flush_page(LOCAL_CLIENT, zcache_frontswap_poolid, + &oid, iswiz(ind)); +} + +/* flush all pages from the passed swaptype */ +static void zcache_frontswap_flush_area(unsigned type) +{ + struct tmem_oid oid; + int ind; + + for (ind = SWIZ_MASK; ind >= 0; ind--) { + oid = oswiz(type, ind); + (void)zcache_flush_object(LOCAL_CLIENT, + zcache_frontswap_poolid, &oid); + } +} + +static void zcache_frontswap_init(unsigned ignored) +{ + /* a single tmem poolid is used for all frontswap "types" (swapfiles) */ + if (zcache_frontswap_poolid < 0) + zcache_frontswap_poolid = + zcache_new_pool(LOCAL_CLIENT, TMEM_POOL_PERSIST); +} + +static struct frontswap_ops zcache_frontswap_ops = { + .put_page = zcache_frontswap_put_page, + .get_page = zcache_frontswap_get_page, + .flush_page = zcache_frontswap_flush_page, + .flush_area = zcache_frontswap_flush_area, + .init = zcache_frontswap_init +}; + +struct frontswap_ops zcache_frontswap_register_ops(void) +{ + struct frontswap_ops old_ops = + frontswap_register_ops(&zcache_frontswap_ops); + + return old_ops; +} +#endif + +/* + * zcache initialization + * NOTE FOR NOW zcache MUST BE PROVIDED AS A KERNEL BOOT PARAMETER OR + * NOTHING HAPPENS! + */ + +static int zcache_enabled; + +static int __init enable_zcache(char *s) +{ + zcache_enabled = 1; + return 1; +} +__setup("zcache", enable_zcache); + +/* allow independent dynamic disabling of cleancache and frontswap */ + +static int use_cleancache = 1; + +static int __init no_cleancache(char *s) +{ + use_cleancache = 0; + return 1; +} + +__setup("nocleancache", no_cleancache); + +static int use_frontswap = 1; + +static int __init no_frontswap(char *s) +{ + use_frontswap = 0; + return 1; +} + +__setup("nofrontswap", no_frontswap); + +static int __init zcache_init(void) +{ +#ifdef CONFIG_SYSFS + int ret = 0; + + ret = sysfs_create_group(mm_kobj, &zcache_attr_group); + if (ret) { + pr_err("zcache: can't create sysfs\n"); + goto out; + } +#endif /* CONFIG_SYSFS */ +#if defined(CONFIG_CLEANCACHE) || defined(CONFIG_FRONTSWAP) + if (zcache_enabled) { + unsigned int cpu; + + tmem_register_hostops(&zcache_hostops); + tmem_register_pamops(&zcache_pamops); + ret = register_cpu_notifier(&zcache_cpu_notifier_block); + if (ret) { + pr_err("zcache: can't register cpu notifier\n"); + goto out; + } + for_each_online_cpu(cpu) { + void *pcpu = (void *)(long)cpu; + zcache_cpu_notifier(&zcache_cpu_notifier_block, + CPU_UP_PREPARE, pcpu); + } + } + zcache_objnode_cache = kmem_cache_create("zcache_objnode", + sizeof(struct tmem_objnode), 0, 0, NULL); + zcache_obj_cache = kmem_cache_create("zcache_obj", + sizeof(struct tmem_obj), 0, 0, NULL); + ret = zcache_new_client(LOCAL_CLIENT); + if (ret) { + pr_err("zcache: can't create client\n"); + goto out; + } +#endif +#ifdef CONFIG_CLEANCACHE + if (zcache_enabled && use_cleancache) { + struct cleancache_ops old_ops; + + zbud_init(); + register_shrinker(&zcache_shrinker); + old_ops = zcache_cleancache_register_ops(); + pr_info("zcache: cleancache enabled using kernel " + "transcendent memory and compression buddies\n"); + if (old_ops.init_fs != NULL) + pr_warning("zcache: cleancache_ops overridden"); + } +#endif +#ifdef CONFIG_FRONTSWAP + if (zcache_enabled && use_frontswap) { + struct frontswap_ops old_ops; + + old_ops = zcache_frontswap_register_ops(); + pr_info("zcache: frontswap enabled using kernel " + "transcendent memory and xvmalloc\n"); + if (old_ops.init != NULL) + pr_warning("ktmem: frontswap_ops overridden"); + } +#endif +out: + return ret; +} + +module_init(zcache_init) diff --git a/drivers/staging/zcache/zcache.c b/drivers/staging/zcache/zcache.c deleted file mode 100644 index 65a81a0d7c49..000000000000 --- a/drivers/staging/zcache/zcache.c +++ /dev/null @@ -1,1996 +0,0 @@ -/* - * zcache.c - * - * Copyright (c) 2010,2011, Dan Magenheimer, Oracle Corp. - * Copyright (c) 2010,2011, Nitin Gupta - * - * Zcache provides an in-kernel "host implementation" for transcendent memory - * and, thus indirectly, for cleancache and frontswap. Zcache includes two - * page-accessible memory [1] interfaces, both utilizing lzo1x compression: - * 1) "compression buddies" ("zbud") is used for ephemeral pages - * 2) xvmalloc is used for persistent pages. - * Xvmalloc (based on the TLSF allocator) has very low fragmentation - * so maximizes space efficiency, while zbud allows pairs (and potentially, - * in the future, more than a pair of) compressed pages to be closely linked - * so that reclaiming can be done via the kernel's physical-page-oriented - * "shrinker" interface. - * - * [1] For a definition of page-accessible memory (aka PAM), see: - * http://marc.info/?l=linux-mm&m=127811271605009 - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include "tmem.h" - -#include "../zram/xvmalloc.h" /* if built in drivers/staging */ - -#if (!defined(CONFIG_CLEANCACHE) && !defined(CONFIG_FRONTSWAP)) -#error "zcache is useless without CONFIG_CLEANCACHE or CONFIG_FRONTSWAP" -#endif -#ifdef CONFIG_CLEANCACHE -#include -#endif -#ifdef CONFIG_FRONTSWAP -#include -#endif - -#if 0 -/* this is more aggressive but may cause other problems? */ -#define ZCACHE_GFP_MASK (GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN) -#else -#define ZCACHE_GFP_MASK \ - (__GFP_FS | __GFP_NORETRY | __GFP_NOWARN | __GFP_NOMEMALLOC) -#endif - -#define MAX_POOLS_PER_CLIENT 16 - -#define MAX_CLIENTS 16 -#define LOCAL_CLIENT ((uint16_t)-1) -struct zcache_client { - struct tmem_pool *tmem_pools[MAX_POOLS_PER_CLIENT]; - struct xv_pool *xvpool; - bool allocated; - atomic_t refcount; -}; - -static struct zcache_client zcache_host; -static struct zcache_client zcache_clients[MAX_CLIENTS]; - -static inline uint16_t get_client_id_from_client(struct zcache_client *cli) -{ - BUG_ON(cli == NULL); - if (cli == &zcache_host) - return LOCAL_CLIENT; - return cli - &zcache_clients[0]; -} - -static inline bool is_local_client(struct zcache_client *cli) -{ - return cli == &zcache_host; -} - -/********** - * Compression buddies ("zbud") provides for packing two (or, possibly - * in the future, more) compressed ephemeral pages into a single "raw" - * (physical) page and tracking them with data structures so that - * the raw pages can be easily reclaimed. - * - * A zbud page ("zbpg") is an aligned page containing a list_head, - * a lock, and two "zbud headers". The remainder of the physical - * page is divided up into aligned 64-byte "chunks" which contain - * the compressed data for zero, one, or two zbuds. Each zbpg - * resides on: (1) an "unused list" if it has no zbuds; (2) a - * "buddied" list if it is fully populated with two zbuds; or - * (3) one of PAGE_SIZE/64 "unbuddied" lists indexed by how many chunks - * the one unbuddied zbud uses. The data inside a zbpg cannot be - * read or written unless the zbpg's lock is held. - */ - -#define ZBH_SENTINEL 0x43214321 -#define ZBPG_SENTINEL 0xdeadbeef - -#define ZBUD_MAX_BUDS 2 - -struct zbud_hdr { - uint16_t client_id; - uint16_t pool_id; - struct tmem_oid oid; - uint32_t index; - uint16_t size; /* compressed size in bytes, zero means unused */ - DECL_SENTINEL -}; - -struct zbud_page { - struct list_head bud_list; - spinlock_t lock; - struct zbud_hdr buddy[ZBUD_MAX_BUDS]; - DECL_SENTINEL - /* followed by NUM_CHUNK aligned CHUNK_SIZE-byte chunks */ -}; - -#define CHUNK_SHIFT 6 -#define CHUNK_SIZE (1 << CHUNK_SHIFT) -#define CHUNK_MASK (~(CHUNK_SIZE-1)) -#define NCHUNKS (((PAGE_SIZE - sizeof(struct zbud_page)) & \ - CHUNK_MASK) >> CHUNK_SHIFT) -#define MAX_CHUNK (NCHUNKS-1) - -static struct { - struct list_head list; - unsigned count; -} zbud_unbuddied[NCHUNKS]; -/* list N contains pages with N chunks USED and NCHUNKS-N unused */ -/* element 0 is never used but optimizing that isn't worth it */ -static unsigned long zbud_cumul_chunk_counts[NCHUNKS]; - -struct list_head zbud_buddied_list; -static unsigned long zcache_zbud_buddied_count; - -/* protects the buddied list and all unbuddied lists */ -static DEFINE_SPINLOCK(zbud_budlists_spinlock); - -static LIST_HEAD(zbpg_unused_list); -static unsigned long zcache_zbpg_unused_list_count; - -/* protects the unused page list */ -static DEFINE_SPINLOCK(zbpg_unused_list_spinlock); - -static atomic_t zcache_zbud_curr_raw_pages; -static atomic_t zcache_zbud_curr_zpages; -static unsigned long zcache_zbud_curr_zbytes; -static unsigned long zcache_zbud_cumul_zpages; -static unsigned long zcache_zbud_cumul_zbytes; -static unsigned long zcache_compress_poor; -static unsigned long zcache_mean_compress_poor; - -/* forward references */ -static void *zcache_get_free_page(void); -static void zcache_free_page(void *p); - -/* - * zbud helper functions - */ - -static inline unsigned zbud_max_buddy_size(void) -{ - return MAX_CHUNK << CHUNK_SHIFT; -} - -static inline unsigned zbud_size_to_chunks(unsigned size) -{ - BUG_ON(size == 0 || size > zbud_max_buddy_size()); - return (size + CHUNK_SIZE - 1) >> CHUNK_SHIFT; -} - -static inline int zbud_budnum(struct zbud_hdr *zh) -{ - unsigned offset = (unsigned long)zh & (PAGE_SIZE - 1); - struct zbud_page *zbpg = NULL; - unsigned budnum = -1U; - int i; - - for (i = 0; i < ZBUD_MAX_BUDS; i++) - if (offset == offsetof(typeof(*zbpg), buddy[i])) { - budnum = i; - break; - } - BUG_ON(budnum == -1U); - return budnum; -} - -static char *zbud_data(struct zbud_hdr *zh, unsigned size) -{ - struct zbud_page *zbpg; - char *p; - unsigned budnum; - - ASSERT_SENTINEL(zh, ZBH); - budnum = zbud_budnum(zh); - BUG_ON(size == 0 || size > zbud_max_buddy_size()); - zbpg = container_of(zh, struct zbud_page, buddy[budnum]); - ASSERT_SPINLOCK(&zbpg->lock); - p = (char *)zbpg; - if (budnum == 0) - p += ((sizeof(struct zbud_page) + CHUNK_SIZE - 1) & - CHUNK_MASK); - else if (budnum == 1) - p += PAGE_SIZE - ((size + CHUNK_SIZE - 1) & CHUNK_MASK); - return p; -} - -/* - * zbud raw page management - */ - -static struct zbud_page *zbud_alloc_raw_page(void) -{ - struct zbud_page *zbpg = NULL; - struct zbud_hdr *zh0, *zh1; - bool recycled = 0; - - /* if any pages on the zbpg list, use one */ - spin_lock(&zbpg_unused_list_spinlock); - if (!list_empty(&zbpg_unused_list)) { - zbpg = list_first_entry(&zbpg_unused_list, - struct zbud_page, bud_list); - list_del_init(&zbpg->bud_list); - zcache_zbpg_unused_list_count--; - recycled = 1; - } - spin_unlock(&zbpg_unused_list_spinlock); - if (zbpg == NULL) - /* none on zbpg list, try to get a kernel page */ - zbpg = zcache_get_free_page(); - if (likely(zbpg != NULL)) { - INIT_LIST_HEAD(&zbpg->bud_list); - zh0 = &zbpg->buddy[0]; zh1 = &zbpg->buddy[1]; - spin_lock_init(&zbpg->lock); - if (recycled) { - ASSERT_INVERTED_SENTINEL(zbpg, ZBPG); - SET_SENTINEL(zbpg, ZBPG); - BUG_ON(zh0->size != 0 || tmem_oid_valid(&zh0->oid)); - BUG_ON(zh1->size != 0 || tmem_oid_valid(&zh1->oid)); - } else { - atomic_inc(&zcache_zbud_curr_raw_pages); - INIT_LIST_HEAD(&zbpg->bud_list); - SET_SENTINEL(zbpg, ZBPG); - zh0->size = 0; zh1->size = 0; - tmem_oid_set_invalid(&zh0->oid); - tmem_oid_set_invalid(&zh1->oid); - } - } - return zbpg; -} - -static void zbud_free_raw_page(struct zbud_page *zbpg) -{ - struct zbud_hdr *zh0 = &zbpg->buddy[0], *zh1 = &zbpg->buddy[1]; - - ASSERT_SENTINEL(zbpg, ZBPG); - BUG_ON(!list_empty(&zbpg->bud_list)); - ASSERT_SPINLOCK(&zbpg->lock); - BUG_ON(zh0->size != 0 || tmem_oid_valid(&zh0->oid)); - BUG_ON(zh1->size != 0 || tmem_oid_valid(&zh1->oid)); - INVERT_SENTINEL(zbpg, ZBPG); - spin_unlock(&zbpg->lock); - spin_lock(&zbpg_unused_list_spinlock); - list_add(&zbpg->bud_list, &zbpg_unused_list); - zcache_zbpg_unused_list_count++; - spin_unlock(&zbpg_unused_list_spinlock); -} - -/* - * core zbud handling routines - */ - -static unsigned zbud_free(struct zbud_hdr *zh) -{ - unsigned size; - - ASSERT_SENTINEL(zh, ZBH); - BUG_ON(!tmem_oid_valid(&zh->oid)); - size = zh->size; - BUG_ON(zh->size == 0 || zh->size > zbud_max_buddy_size()); - zh->size = 0; - tmem_oid_set_invalid(&zh->oid); - INVERT_SENTINEL(zh, ZBH); - zcache_zbud_curr_zbytes -= size; - atomic_dec(&zcache_zbud_curr_zpages); - return size; -} - -static void zbud_free_and_delist(struct zbud_hdr *zh) -{ - unsigned chunks; - struct zbud_hdr *zh_other; - unsigned budnum = zbud_budnum(zh), size; - struct zbud_page *zbpg = - container_of(zh, struct zbud_page, buddy[budnum]); - - spin_lock(&zbpg->lock); - if (list_empty(&zbpg->bud_list)) { - /* ignore zombie page... see zbud_evict_pages() */ - spin_unlock(&zbpg->lock); - return; - } - size = zbud_free(zh); - ASSERT_SPINLOCK(&zbpg->lock); - zh_other = &zbpg->buddy[(budnum == 0) ? 1 : 0]; - if (zh_other->size == 0) { /* was unbuddied: unlist and free */ - chunks = zbud_size_to_chunks(size) ; - spin_lock(&zbud_budlists_spinlock); - BUG_ON(list_empty(&zbud_unbuddied[chunks].list)); - list_del_init(&zbpg->bud_list); - zbud_unbuddied[chunks].count--; - spin_unlock(&zbud_budlists_spinlock); - zbud_free_raw_page(zbpg); - } else { /* was buddied: move remaining buddy to unbuddied list */ - chunks = zbud_size_to_chunks(zh_other->size) ; - spin_lock(&zbud_budlists_spinlock); - list_del_init(&zbpg->bud_list); - zcache_zbud_buddied_count--; - list_add_tail(&zbpg->bud_list, &zbud_unbuddied[chunks].list); - zbud_unbuddied[chunks].count++; - spin_unlock(&zbud_budlists_spinlock); - spin_unlock(&zbpg->lock); - } -} - -static struct zbud_hdr *zbud_create(uint16_t client_id, uint16_t pool_id, - struct tmem_oid *oid, - uint32_t index, struct page *page, - void *cdata, unsigned size) -{ - struct zbud_hdr *zh0, *zh1, *zh = NULL; - struct zbud_page *zbpg = NULL, *ztmp; - unsigned nchunks; - char *to; - int i, found_good_buddy = 0; - - nchunks = zbud_size_to_chunks(size) ; - for (i = MAX_CHUNK - nchunks + 1; i > 0; i--) { - spin_lock(&zbud_budlists_spinlock); - if (!list_empty(&zbud_unbuddied[i].list)) { - list_for_each_entry_safe(zbpg, ztmp, - &zbud_unbuddied[i].list, bud_list) { - if (spin_trylock(&zbpg->lock)) { - found_good_buddy = i; - goto found_unbuddied; - } - } - } - spin_unlock(&zbud_budlists_spinlock); - } - /* didn't find a good buddy, try allocating a new page */ - zbpg = zbud_alloc_raw_page(); - if (unlikely(zbpg == NULL)) - goto out; - /* ok, have a page, now compress the data before taking locks */ - spin_lock(&zbpg->lock); - spin_lock(&zbud_budlists_spinlock); - list_add_tail(&zbpg->bud_list, &zbud_unbuddied[nchunks].list); - zbud_unbuddied[nchunks].count++; - zh = &zbpg->buddy[0]; - goto init_zh; - -found_unbuddied: - ASSERT_SPINLOCK(&zbpg->lock); - zh0 = &zbpg->buddy[0]; zh1 = &zbpg->buddy[1]; - BUG_ON(!((zh0->size == 0) ^ (zh1->size == 0))); - if (zh0->size != 0) { /* buddy0 in use, buddy1 is vacant */ - ASSERT_SENTINEL(zh0, ZBH); - zh = zh1; - } else if (zh1->size != 0) { /* buddy1 in use, buddy0 is vacant */ - ASSERT_SENTINEL(zh1, ZBH); - zh = zh0; - } else - BUG(); - list_del_init(&zbpg->bud_list); - zbud_unbuddied[found_good_buddy].count--; - list_add_tail(&zbpg->bud_list, &zbud_buddied_list); - zcache_zbud_buddied_count++; - -init_zh: - SET_SENTINEL(zh, ZBH); - zh->size = size; - zh->index = index; - zh->oid = *oid; - zh->pool_id = pool_id; - zh->client_id = client_id; - /* can wait to copy the data until the list locks are dropped */ - spin_unlock(&zbud_budlists_spinlock); - - to = zbud_data(zh, size); - memcpy(to, cdata, size); - spin_unlock(&zbpg->lock); - zbud_cumul_chunk_counts[nchunks]++; - atomic_inc(&zcache_zbud_curr_zpages); - zcache_zbud_cumul_zpages++; - zcache_zbud_curr_zbytes += size; - zcache_zbud_cumul_zbytes += size; -out: - return zh; -} - -static int zbud_decompress(struct page *page, struct zbud_hdr *zh) -{ - struct zbud_page *zbpg; - unsigned budnum = zbud_budnum(zh); - size_t out_len = PAGE_SIZE; - char *to_va, *from_va; - unsigned size; - int ret = 0; - - zbpg = container_of(zh, struct zbud_page, buddy[budnum]); - spin_lock(&zbpg->lock); - if (list_empty(&zbpg->bud_list)) { - /* ignore zombie page... see zbud_evict_pages() */ - ret = -EINVAL; - goto out; - } - ASSERT_SENTINEL(zh, ZBH); - BUG_ON(zh->size == 0 || zh->size > zbud_max_buddy_size()); - to_va = kmap_atomic(page, KM_USER0); - size = zh->size; - from_va = zbud_data(zh, size); - ret = lzo1x_decompress_safe(from_va, size, to_va, &out_len); - BUG_ON(ret != LZO_E_OK); - BUG_ON(out_len != PAGE_SIZE); - kunmap_atomic(to_va, KM_USER0); -out: - spin_unlock(&zbpg->lock); - return ret; -} - -/* - * The following routines handle shrinking of ephemeral pages by evicting - * pages "least valuable" first. - */ - -static unsigned long zcache_evicted_raw_pages; -static unsigned long zcache_evicted_buddied_pages; -static unsigned long zcache_evicted_unbuddied_pages; - -static struct tmem_pool *zcache_get_pool_by_id(uint16_t cli_id, - uint16_t poolid); -static void zcache_put_pool(struct tmem_pool *pool); - -/* - * Flush and free all zbuds in a zbpg, then free the pageframe - */ -static void zbud_evict_zbpg(struct zbud_page *zbpg) -{ - struct zbud_hdr *zh; - int i, j; - uint32_t pool_id[ZBUD_MAX_BUDS], client_id[ZBUD_MAX_BUDS]; - uint32_t index[ZBUD_MAX_BUDS]; - struct tmem_oid oid[ZBUD_MAX_BUDS]; - struct tmem_pool *pool; - - ASSERT_SPINLOCK(&zbpg->lock); - BUG_ON(!list_empty(&zbpg->bud_list)); - for (i = 0, j = 0; i < ZBUD_MAX_BUDS; i++) { - zh = &zbpg->buddy[i]; - if (zh->size) { - client_id[j] = zh->client_id; - pool_id[j] = zh->pool_id; - oid[j] = zh->oid; - index[j] = zh->index; - j++; - zbud_free(zh); - } - } - spin_unlock(&zbpg->lock); - for (i = 0; i < j; i++) { - pool = zcache_get_pool_by_id(client_id[i], pool_id[i]); - if (pool != NULL) { - tmem_flush_page(pool, &oid[i], index[i]); - zcache_put_pool(pool); - } - } - ASSERT_SENTINEL(zbpg, ZBPG); - spin_lock(&zbpg->lock); - zbud_free_raw_page(zbpg); -} - -/* - * Free nr pages. This code is funky because we want to hold the locks - * protecting various lists for as short a time as possible, and in some - * circumstances the list may change asynchronously when the list lock is - * not held. In some cases we also trylock not only to avoid waiting on a - * page in use by another cpu, but also to avoid potential deadlock due to - * lock inversion. - */ -static void zbud_evict_pages(int nr) -{ - struct zbud_page *zbpg; - int i; - - /* first try freeing any pages on unused list */ -retry_unused_list: - spin_lock_bh(&zbpg_unused_list_spinlock); - if (!list_empty(&zbpg_unused_list)) { - /* can't walk list here, since it may change when unlocked */ - zbpg = list_first_entry(&zbpg_unused_list, - struct zbud_page, bud_list); - list_del_init(&zbpg->bud_list); - zcache_zbpg_unused_list_count--; - atomic_dec(&zcache_zbud_curr_raw_pages); - spin_unlock_bh(&zbpg_unused_list_spinlock); - zcache_free_page(zbpg); - zcache_evicted_raw_pages++; - if (--nr <= 0) - goto out; - goto retry_unused_list; - } - spin_unlock_bh(&zbpg_unused_list_spinlock); - - /* now try freeing unbuddied pages, starting with least space avail */ - for (i = 0; i < MAX_CHUNK; i++) { -retry_unbud_list_i: - spin_lock_bh(&zbud_budlists_spinlock); - if (list_empty(&zbud_unbuddied[i].list)) { - spin_unlock_bh(&zbud_budlists_spinlock); - continue; - } - list_for_each_entry(zbpg, &zbud_unbuddied[i].list, bud_list) { - if (unlikely(!spin_trylock(&zbpg->lock))) - continue; - list_del_init(&zbpg->bud_list); - zbud_unbuddied[i].count--; - spin_unlock(&zbud_budlists_spinlock); - zcache_evicted_unbuddied_pages++; - /* want budlists unlocked when doing zbpg eviction */ - zbud_evict_zbpg(zbpg); - local_bh_enable(); - if (--nr <= 0) - goto out; - goto retry_unbud_list_i; - } - spin_unlock_bh(&zbud_budlists_spinlock); - } - - /* as a last resort, free buddied pages */ -retry_bud_list: - spin_lock_bh(&zbud_budlists_spinlock); - if (list_empty(&zbud_buddied_list)) { - spin_unlock_bh(&zbud_budlists_spinlock); - goto out; - } - list_for_each_entry(zbpg, &zbud_buddied_list, bud_list) { - if (unlikely(!spin_trylock(&zbpg->lock))) - continue; - list_del_init(&zbpg->bud_list); - zcache_zbud_buddied_count--; - spin_unlock(&zbud_budlists_spinlock); - zcache_evicted_buddied_pages++; - /* want budlists unlocked when doing zbpg eviction */ - zbud_evict_zbpg(zbpg); - local_bh_enable(); - if (--nr <= 0) - goto out; - goto retry_bud_list; - } - spin_unlock_bh(&zbud_budlists_spinlock); -out: - return; -} - -static void zbud_init(void) -{ - int i; - - INIT_LIST_HEAD(&zbud_buddied_list); - zcache_zbud_buddied_count = 0; - for (i = 0; i < NCHUNKS; i++) { - INIT_LIST_HEAD(&zbud_unbuddied[i].list); - zbud_unbuddied[i].count = 0; - } -} - -#ifdef CONFIG_SYSFS -/* - * These sysfs routines show a nice distribution of how many zbpg's are - * currently (and have ever been placed) in each unbuddied list. It's fun - * to watch but can probably go away before final merge. - */ -static int zbud_show_unbuddied_list_counts(char *buf) -{ - int i; - char *p = buf; - - for (i = 0; i < NCHUNKS; i++) - p += sprintf(p, "%u ", zbud_unbuddied[i].count); - return p - buf; -} - -static int zbud_show_cumul_chunk_counts(char *buf) -{ - unsigned long i, chunks = 0, total_chunks = 0, sum_total_chunks = 0; - unsigned long total_chunks_lte_21 = 0, total_chunks_lte_32 = 0; - unsigned long total_chunks_lte_42 = 0; - char *p = buf; - - for (i = 0; i < NCHUNKS; i++) { - p += sprintf(p, "%lu ", zbud_cumul_chunk_counts[i]); - chunks += zbud_cumul_chunk_counts[i]; - total_chunks += zbud_cumul_chunk_counts[i]; - sum_total_chunks += i * zbud_cumul_chunk_counts[i]; - if (i == 21) - total_chunks_lte_21 = total_chunks; - if (i == 32) - total_chunks_lte_32 = total_chunks; - if (i == 42) - total_chunks_lte_42 = total_chunks; - } - p += sprintf(p, "<=21:%lu <=32:%lu <=42:%lu, mean:%lu\n", - total_chunks_lte_21, total_chunks_lte_32, total_chunks_lte_42, - chunks == 0 ? 0 : sum_total_chunks / chunks); - return p - buf; -} -#endif - -/********** - * This "zv" PAM implementation combines the TLSF-based xvMalloc - * with lzo1x compression to maximize the amount of data that can - * be packed into a physical page. - * - * Zv represents a PAM page with the index and object (plus a "size" value - * necessary for decompression) immediately preceding the compressed data. - */ - -#define ZVH_SENTINEL 0x43214321 - -struct zv_hdr { - uint32_t pool_id; - struct tmem_oid oid; - uint32_t index; - DECL_SENTINEL -}; - -/* rudimentary policy limits */ -/* total number of persistent pages may not exceed this percentage */ -static unsigned int zv_page_count_policy_percent = 75; -/* - * byte count defining poor compression; pages with greater zsize will be - * rejected - */ -static unsigned int zv_max_zsize = (PAGE_SIZE / 8) * 7; -/* - * byte count defining poor *mean* compression; pages with greater zsize - * will be rejected until sufficient better-compressed pages are accepted - * driving the man below this threshold - */ -static unsigned int zv_max_mean_zsize = (PAGE_SIZE / 8) * 5; - -static unsigned long zv_curr_dist_counts[NCHUNKS]; -static unsigned long zv_cumul_dist_counts[NCHUNKS]; - -static struct zv_hdr *zv_create(struct xv_pool *xvpool, uint32_t pool_id, - struct tmem_oid *oid, uint32_t index, - void *cdata, unsigned clen) -{ - struct page *page; - struct zv_hdr *zv = NULL; - uint32_t offset; - int alloc_size = clen + sizeof(struct zv_hdr); - int chunks = (alloc_size + (CHUNK_SIZE - 1)) >> CHUNK_SHIFT; - int ret; - - BUG_ON(!irqs_disabled()); - BUG_ON(chunks >= NCHUNKS); - ret = xv_malloc(xvpool, alloc_size, - &page, &offset, ZCACHE_GFP_MASK); - if (unlikely(ret)) - goto out; - zv_curr_dist_counts[chunks]++; - zv_cumul_dist_counts[chunks]++; - zv = kmap_atomic(page, KM_USER0) + offset; - zv->index = index; - zv->oid = *oid; - zv->pool_id = pool_id; - SET_SENTINEL(zv, ZVH); - memcpy((char *)zv + sizeof(struct zv_hdr), cdata, clen); - kunmap_atomic(zv, KM_USER0); -out: - return zv; -} - -static void zv_free(struct xv_pool *xvpool, struct zv_hdr *zv) -{ - unsigned long flags; - struct page *page; - uint32_t offset; - uint16_t size = xv_get_object_size(zv); - int chunks = (size + (CHUNK_SIZE - 1)) >> CHUNK_SHIFT; - - ASSERT_SENTINEL(zv, ZVH); - BUG_ON(chunks >= NCHUNKS); - zv_curr_dist_counts[chunks]--; - size -= sizeof(*zv); - BUG_ON(size == 0); - INVERT_SENTINEL(zv, ZVH); - page = virt_to_page(zv); - offset = (unsigned long)zv & ~PAGE_MASK; - local_irq_save(flags); - xv_free(xvpool, page, offset); - local_irq_restore(flags); -} - -static void zv_decompress(struct page *page, struct zv_hdr *zv) -{ - size_t clen = PAGE_SIZE; - char *to_va; - unsigned size; - int ret; - - ASSERT_SENTINEL(zv, ZVH); - size = xv_get_object_size(zv) - sizeof(*zv); - BUG_ON(size == 0); - to_va = kmap_atomic(page, KM_USER0); - ret = lzo1x_decompress_safe((char *)zv + sizeof(*zv), - size, to_va, &clen); - kunmap_atomic(to_va, KM_USER0); - BUG_ON(ret != LZO_E_OK); - BUG_ON(clen != PAGE_SIZE); -} - -#ifdef CONFIG_SYSFS -/* - * show a distribution of compression stats for zv pages. - */ - -static int zv_curr_dist_counts_show(char *buf) -{ - unsigned long i, n, chunks = 0, sum_total_chunks = 0; - char *p = buf; - - for (i = 0; i < NCHUNKS; i++) { - n = zv_curr_dist_counts[i]; - p += sprintf(p, "%lu ", n); - chunks += n; - sum_total_chunks += i * n; - } - p += sprintf(p, "mean:%lu\n", - chunks == 0 ? 0 : sum_total_chunks / chunks); - return p - buf; -} - -static int zv_cumul_dist_counts_show(char *buf) -{ - unsigned long i, n, chunks = 0, sum_total_chunks = 0; - char *p = buf; - - for (i = 0; i < NCHUNKS; i++) { - n = zv_cumul_dist_counts[i]; - p += sprintf(p, "%lu ", n); - chunks += n; - sum_total_chunks += i * n; - } - p += sprintf(p, "mean:%lu\n", - chunks == 0 ? 0 : sum_total_chunks / chunks); - return p - buf; -} - -/* - * setting zv_max_zsize via sysfs causes all persistent (e.g. swap) - * pages that don't compress to less than this value (including metadata - * overhead) to be rejected. We don't allow the value to get too close - * to PAGE_SIZE. - */ -static ssize_t zv_max_zsize_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", zv_max_zsize); -} - -static ssize_t zv_max_zsize_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) -{ - unsigned long val; - int err; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - err = strict_strtoul(buf, 10, &val); - if (err || (val == 0) || (val > (PAGE_SIZE / 8) * 7)) - return -EINVAL; - zv_max_zsize = val; - return count; -} - -/* - * setting zv_max_mean_zsize via sysfs causes all persistent (e.g. swap) - * pages that don't compress to less than this value (including metadata - * overhead) to be rejected UNLESS the mean compression is also smaller - * than this value. In other words, we are load-balancing-by-zsize the - * accepted pages. Again, we don't allow the value to get too close - * to PAGE_SIZE. - */ -static ssize_t zv_max_mean_zsize_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", zv_max_mean_zsize); -} - -static ssize_t zv_max_mean_zsize_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) -{ - unsigned long val; - int err; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - err = strict_strtoul(buf, 10, &val); - if (err || (val == 0) || (val > (PAGE_SIZE / 8) * 7)) - return -EINVAL; - zv_max_mean_zsize = val; - return count; -} - -/* - * setting zv_page_count_policy_percent via sysfs sets an upper bound of - * persistent (e.g. swap) pages that will be retained according to: - * (zv_page_count_policy_percent * totalram_pages) / 100) - * when that limit is reached, further puts will be rejected (until - * some pages have been flushed). Note that, due to compression, - * this number may exceed 100; it defaults to 75 and we set an - * arbitary limit of 150. A poor choice will almost certainly result - * in OOM's, so this value should only be changed prudently. - */ -static ssize_t zv_page_count_policy_percent_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", zv_page_count_policy_percent); -} - -static ssize_t zv_page_count_policy_percent_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) -{ - unsigned long val; - int err; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - err = strict_strtoul(buf, 10, &val); - if (err || (val == 0) || (val > 150)) - return -EINVAL; - zv_page_count_policy_percent = val; - return count; -} - -static struct kobj_attribute zcache_zv_max_zsize_attr = { - .attr = { .name = "zv_max_zsize", .mode = 0644 }, - .show = zv_max_zsize_show, - .store = zv_max_zsize_store, -}; - -static struct kobj_attribute zcache_zv_max_mean_zsize_attr = { - .attr = { .name = "zv_max_mean_zsize", .mode = 0644 }, - .show = zv_max_mean_zsize_show, - .store = zv_max_mean_zsize_store, -}; - -static struct kobj_attribute zcache_zv_page_count_policy_percent_attr = { - .attr = { .name = "zv_page_count_policy_percent", - .mode = 0644 }, - .show = zv_page_count_policy_percent_show, - .store = zv_page_count_policy_percent_store, -}; -#endif - -/* - * zcache core code starts here - */ - -/* useful stats not collected by cleancache or frontswap */ -static unsigned long zcache_flush_total; -static unsigned long zcache_flush_found; -static unsigned long zcache_flobj_total; -static unsigned long zcache_flobj_found; -static unsigned long zcache_failed_eph_puts; -static unsigned long zcache_failed_pers_puts; - -/* - * Tmem operations assume the poolid implies the invoking client. - * Zcache only has one client (the kernel itself): LOCAL_CLIENT. - * RAMster has each client numbered by cluster node, and a KVM version - * of zcache would have one client per guest and each client might - * have a poolid==N. - */ -static struct tmem_pool *zcache_get_pool_by_id(uint16_t cli_id, uint16_t poolid) -{ - struct tmem_pool *pool = NULL; - struct zcache_client *cli = NULL; - - if (cli_id == LOCAL_CLIENT) - cli = &zcache_host; - else { - if (cli_id >= MAX_CLIENTS) - goto out; - cli = &zcache_clients[cli_id]; - if (cli == NULL) - goto out; - atomic_inc(&cli->refcount); - } - if (poolid < MAX_POOLS_PER_CLIENT) { - pool = cli->tmem_pools[poolid]; - if (pool != NULL) - atomic_inc(&pool->refcount); - } -out: - return pool; -} - -static void zcache_put_pool(struct tmem_pool *pool) -{ - struct zcache_client *cli = NULL; - - if (pool == NULL) - BUG(); - cli = pool->client; - atomic_dec(&pool->refcount); - atomic_dec(&cli->refcount); -} - -int zcache_new_client(uint16_t cli_id) -{ - struct zcache_client *cli = NULL; - int ret = -1; - - if (cli_id == LOCAL_CLIENT) - cli = &zcache_host; - else if ((unsigned int)cli_id < MAX_CLIENTS) - cli = &zcache_clients[cli_id]; - if (cli == NULL) - goto out; - if (cli->allocated) - goto out; - cli->allocated = 1; -#ifdef CONFIG_FRONTSWAP - cli->xvpool = xv_create_pool(); - if (cli->xvpool == NULL) - goto out; -#endif - ret = 0; -out: - return ret; -} - -/* counters for debugging */ -static unsigned long zcache_failed_get_free_pages; -static unsigned long zcache_failed_alloc; -static unsigned long zcache_put_to_flush; -static unsigned long zcache_aborted_preload; -static unsigned long zcache_aborted_shrink; - -/* - * Ensure that memory allocation requests in zcache don't result - * in direct reclaim requests via the shrinker, which would cause - * an infinite loop. Maybe a GFP flag would be better? - */ -static DEFINE_SPINLOCK(zcache_direct_reclaim_lock); - -/* - * for now, used named slabs so can easily track usage; later can - * either just use kmalloc, or perhaps add a slab-like allocator - * to more carefully manage total memory utilization - */ -static struct kmem_cache *zcache_objnode_cache; -static struct kmem_cache *zcache_obj_cache; -static atomic_t zcache_curr_obj_count = ATOMIC_INIT(0); -static unsigned long zcache_curr_obj_count_max; -static atomic_t zcache_curr_objnode_count = ATOMIC_INIT(0); -static unsigned long zcache_curr_objnode_count_max; - -/* - * to avoid memory allocation recursion (e.g. due to direct reclaim), we - * preload all necessary data structures so the hostops callbacks never - * actually do a malloc - */ -struct zcache_preload { - void *page; - struct tmem_obj *obj; - int nr; - struct tmem_objnode *objnodes[OBJNODE_TREE_MAX_PATH]; -}; -static DEFINE_PER_CPU(struct zcache_preload, zcache_preloads) = { 0, }; - -static int zcache_do_preload(struct tmem_pool *pool) -{ - struct zcache_preload *kp; - struct tmem_objnode *objnode; - struct tmem_obj *obj; - void *page; - int ret = -ENOMEM; - - if (unlikely(zcache_objnode_cache == NULL)) - goto out; - if (unlikely(zcache_obj_cache == NULL)) - goto out; - if (!spin_trylock(&zcache_direct_reclaim_lock)) { - zcache_aborted_preload++; - goto out; - } - preempt_disable(); - kp = &__get_cpu_var(zcache_preloads); - while (kp->nr < ARRAY_SIZE(kp->objnodes)) { - preempt_enable_no_resched(); - objnode = kmem_cache_alloc(zcache_objnode_cache, - ZCACHE_GFP_MASK); - if (unlikely(objnode == NULL)) { - zcache_failed_alloc++; - goto unlock_out; - } - preempt_disable(); - kp = &__get_cpu_var(zcache_preloads); - if (kp->nr < ARRAY_SIZE(kp->objnodes)) - kp->objnodes[kp->nr++] = objnode; - else - kmem_cache_free(zcache_objnode_cache, objnode); - } - preempt_enable_no_resched(); - obj = kmem_cache_alloc(zcache_obj_cache, ZCACHE_GFP_MASK); - if (unlikely(obj == NULL)) { - zcache_failed_alloc++; - goto unlock_out; - } - page = (void *)__get_free_page(ZCACHE_GFP_MASK); - if (unlikely(page == NULL)) { - zcache_failed_get_free_pages++; - kmem_cache_free(zcache_obj_cache, obj); - goto unlock_out; - } - preempt_disable(); - kp = &__get_cpu_var(zcache_preloads); - if (kp->obj == NULL) - kp->obj = obj; - else - kmem_cache_free(zcache_obj_cache, obj); - if (kp->page == NULL) - kp->page = page; - else - free_page((unsigned long)page); - ret = 0; -unlock_out: - spin_unlock(&zcache_direct_reclaim_lock); -out: - return ret; -} - -static void *zcache_get_free_page(void) -{ - struct zcache_preload *kp; - void *page; - - kp = &__get_cpu_var(zcache_preloads); - page = kp->page; - BUG_ON(page == NULL); - kp->page = NULL; - return page; -} - -static void zcache_free_page(void *p) -{ - free_page((unsigned long)p); -} - -/* - * zcache implementation for tmem host ops - */ - -static struct tmem_objnode *zcache_objnode_alloc(struct tmem_pool *pool) -{ - struct tmem_objnode *objnode = NULL; - unsigned long count; - struct zcache_preload *kp; - - kp = &__get_cpu_var(zcache_preloads); - if (kp->nr <= 0) - goto out; - objnode = kp->objnodes[kp->nr - 1]; - BUG_ON(objnode == NULL); - kp->objnodes[kp->nr - 1] = NULL; - kp->nr--; - count = atomic_inc_return(&zcache_curr_objnode_count); - if (count > zcache_curr_objnode_count_max) - zcache_curr_objnode_count_max = count; -out: - return objnode; -} - -static void zcache_objnode_free(struct tmem_objnode *objnode, - struct tmem_pool *pool) -{ - atomic_dec(&zcache_curr_objnode_count); - BUG_ON(atomic_read(&zcache_curr_objnode_count) < 0); - kmem_cache_free(zcache_objnode_cache, objnode); -} - -static struct tmem_obj *zcache_obj_alloc(struct tmem_pool *pool) -{ - struct tmem_obj *obj = NULL; - unsigned long count; - struct zcache_preload *kp; - - kp = &__get_cpu_var(zcache_preloads); - obj = kp->obj; - BUG_ON(obj == NULL); - kp->obj = NULL; - count = atomic_inc_return(&zcache_curr_obj_count); - if (count > zcache_curr_obj_count_max) - zcache_curr_obj_count_max = count; - return obj; -} - -static void zcache_obj_free(struct tmem_obj *obj, struct tmem_pool *pool) -{ - atomic_dec(&zcache_curr_obj_count); - BUG_ON(atomic_read(&zcache_curr_obj_count) < 0); - kmem_cache_free(zcache_obj_cache, obj); -} - -static struct tmem_hostops zcache_hostops = { - .obj_alloc = zcache_obj_alloc, - .obj_free = zcache_obj_free, - .objnode_alloc = zcache_objnode_alloc, - .objnode_free = zcache_objnode_free, -}; - -/* - * zcache implementations for PAM page descriptor ops - */ - -static atomic_t zcache_curr_eph_pampd_count = ATOMIC_INIT(0); -static unsigned long zcache_curr_eph_pampd_count_max; -static atomic_t zcache_curr_pers_pampd_count = ATOMIC_INIT(0); -static unsigned long zcache_curr_pers_pampd_count_max; - -/* forward reference */ -static int zcache_compress(struct page *from, void **out_va, size_t *out_len); - -static void *zcache_pampd_create(char *data, size_t size, bool raw, int eph, - struct tmem_pool *pool, struct tmem_oid *oid, - uint32_t index) -{ - void *pampd = NULL, *cdata; - size_t clen; - int ret; - unsigned long count; - struct page *page = virt_to_page(data); - struct zcache_client *cli = pool->client; - uint16_t client_id = get_client_id_from_client(cli); - unsigned long zv_mean_zsize; - unsigned long curr_pers_pampd_count; - - if (eph) { - ret = zcache_compress(page, &cdata, &clen); - if (ret == 0) - goto out; - if (clen == 0 || clen > zbud_max_buddy_size()) { - zcache_compress_poor++; - goto out; - } - pampd = (void *)zbud_create(client_id, pool->pool_id, oid, - index, page, cdata, clen); - if (pampd != NULL) { - count = atomic_inc_return(&zcache_curr_eph_pampd_count); - if (count > zcache_curr_eph_pampd_count_max) - zcache_curr_eph_pampd_count_max = count; - } - } else { - curr_pers_pampd_count = - atomic_read(&zcache_curr_pers_pampd_count); - if (curr_pers_pampd_count > - (zv_page_count_policy_percent * totalram_pages) / 100) - goto out; - ret = zcache_compress(page, &cdata, &clen); - if (ret == 0) - goto out; - /* reject if compression is too poor */ - if (clen > zv_max_zsize) { - zcache_compress_poor++; - goto out; - } - /* reject if mean compression is too poor */ - if ((clen > zv_max_mean_zsize) && (curr_pers_pampd_count > 0)) { - zv_mean_zsize = xv_get_total_size_bytes(cli->xvpool) / - curr_pers_pampd_count; - if (zv_mean_zsize > zv_max_mean_zsize) { - zcache_mean_compress_poor++; - goto out; - } - } - pampd = (void *)zv_create(cli->xvpool, pool->pool_id, - oid, index, cdata, clen); - if (pampd == NULL) - goto out; - count = atomic_inc_return(&zcache_curr_pers_pampd_count); - if (count > zcache_curr_pers_pampd_count_max) - zcache_curr_pers_pampd_count_max = count; - } -out: - return pampd; -} - -/* - * fill the pageframe corresponding to the struct page with the data - * from the passed pampd - */ -static int zcache_pampd_get_data(char *data, size_t *bufsize, bool raw, - void *pampd, struct tmem_pool *pool, - struct tmem_oid *oid, uint32_t index) -{ - int ret = 0; - - BUG_ON(is_ephemeral(pool)); - zv_decompress(virt_to_page(data), pampd); - return ret; -} - -/* - * fill the pageframe corresponding to the struct page with the data - * from the passed pampd - */ -static int zcache_pampd_get_data_and_free(char *data, size_t *bufsize, bool raw, - void *pampd, struct tmem_pool *pool, - struct tmem_oid *oid, uint32_t index) -{ - int ret = 0; - - BUG_ON(!is_ephemeral(pool)); - zbud_decompress(virt_to_page(data), pampd); - zbud_free_and_delist((struct zbud_hdr *)pampd); - atomic_dec(&zcache_curr_eph_pampd_count); - return ret; -} - -/* - * free the pampd and remove it from any zcache lists - * pampd must no longer be pointed to from any tmem data structures! - */ -static void zcache_pampd_free(void *pampd, struct tmem_pool *pool, - struct tmem_oid *oid, uint32_t index) -{ - struct zcache_client *cli = pool->client; - - if (is_ephemeral(pool)) { - zbud_free_and_delist((struct zbud_hdr *)pampd); - atomic_dec(&zcache_curr_eph_pampd_count); - BUG_ON(atomic_read(&zcache_curr_eph_pampd_count) < 0); - } else { - zv_free(cli->xvpool, (struct zv_hdr *)pampd); - atomic_dec(&zcache_curr_pers_pampd_count); - BUG_ON(atomic_read(&zcache_curr_pers_pampd_count) < 0); - } -} - -static void zcache_pampd_free_obj(struct tmem_pool *pool, struct tmem_obj *obj) -{ -} - -static void zcache_pampd_new_obj(struct tmem_obj *obj) -{ -} - -static int zcache_pampd_replace_in_obj(void *pampd, struct tmem_obj *obj) -{ - return -1; -} - -static bool zcache_pampd_is_remote(void *pampd) -{ - return 0; -} - -static struct tmem_pamops zcache_pamops = { - .create = zcache_pampd_create, - .get_data = zcache_pampd_get_data, - .get_data_and_free = zcache_pampd_get_data_and_free, - .free = zcache_pampd_free, - .free_obj = zcache_pampd_free_obj, - .new_obj = zcache_pampd_new_obj, - .replace_in_obj = zcache_pampd_replace_in_obj, - .is_remote = zcache_pampd_is_remote, -}; - -/* - * zcache compression/decompression and related per-cpu stuff - */ - -#define LZO_WORKMEM_BYTES LZO1X_1_MEM_COMPRESS -#define LZO_DSTMEM_PAGE_ORDER 1 -static DEFINE_PER_CPU(unsigned char *, zcache_workmem); -static DEFINE_PER_CPU(unsigned char *, zcache_dstmem); - -static int zcache_compress(struct page *from, void **out_va, size_t *out_len) -{ - int ret = 0; - unsigned char *dmem = __get_cpu_var(zcache_dstmem); - unsigned char *wmem = __get_cpu_var(zcache_workmem); - char *from_va; - - BUG_ON(!irqs_disabled()); - if (unlikely(dmem == NULL || wmem == NULL)) - goto out; /* no buffer, so can't compress */ - from_va = kmap_atomic(from, KM_USER0); - mb(); - ret = lzo1x_1_compress(from_va, PAGE_SIZE, dmem, out_len, wmem); - BUG_ON(ret != LZO_E_OK); - *out_va = dmem; - kunmap_atomic(from_va, KM_USER0); - ret = 1; -out: - return ret; -} - - -static int zcache_cpu_notifier(struct notifier_block *nb, - unsigned long action, void *pcpu) -{ - int cpu = (long)pcpu; - struct zcache_preload *kp; - - switch (action) { - case CPU_UP_PREPARE: - per_cpu(zcache_dstmem, cpu) = (void *)__get_free_pages( - GFP_KERNEL | __GFP_REPEAT, - LZO_DSTMEM_PAGE_ORDER), - per_cpu(zcache_workmem, cpu) = - kzalloc(LZO1X_MEM_COMPRESS, - GFP_KERNEL | __GFP_REPEAT); - break; - case CPU_DEAD: - case CPU_UP_CANCELED: - free_pages((unsigned long)per_cpu(zcache_dstmem, cpu), - LZO_DSTMEM_PAGE_ORDER); - per_cpu(zcache_dstmem, cpu) = NULL; - kfree(per_cpu(zcache_workmem, cpu)); - per_cpu(zcache_workmem, cpu) = NULL; - kp = &per_cpu(zcache_preloads, cpu); - while (kp->nr) { - kmem_cache_free(zcache_objnode_cache, - kp->objnodes[kp->nr - 1]); - kp->objnodes[kp->nr - 1] = NULL; - kp->nr--; - } - kmem_cache_free(zcache_obj_cache, kp->obj); - free_page((unsigned long)kp->page); - break; - default: - break; - } - return NOTIFY_OK; -} - -static struct notifier_block zcache_cpu_notifier_block = { - .notifier_call = zcache_cpu_notifier -}; - -#ifdef CONFIG_SYSFS -#define ZCACHE_SYSFS_RO(_name) \ - static ssize_t zcache_##_name##_show(struct kobject *kobj, \ - struct kobj_attribute *attr, char *buf) \ - { \ - return sprintf(buf, "%lu\n", zcache_##_name); \ - } \ - static struct kobj_attribute zcache_##_name##_attr = { \ - .attr = { .name = __stringify(_name), .mode = 0444 }, \ - .show = zcache_##_name##_show, \ - } - -#define ZCACHE_SYSFS_RO_ATOMIC(_name) \ - static ssize_t zcache_##_name##_show(struct kobject *kobj, \ - struct kobj_attribute *attr, char *buf) \ - { \ - return sprintf(buf, "%d\n", atomic_read(&zcache_##_name)); \ - } \ - static struct kobj_attribute zcache_##_name##_attr = { \ - .attr = { .name = __stringify(_name), .mode = 0444 }, \ - .show = zcache_##_name##_show, \ - } - -#define ZCACHE_SYSFS_RO_CUSTOM(_name, _func) \ - static ssize_t zcache_##_name##_show(struct kobject *kobj, \ - struct kobj_attribute *attr, char *buf) \ - { \ - return _func(buf); \ - } \ - static struct kobj_attribute zcache_##_name##_attr = { \ - .attr = { .name = __stringify(_name), .mode = 0444 }, \ - .show = zcache_##_name##_show, \ - } - -ZCACHE_SYSFS_RO(curr_obj_count_max); -ZCACHE_SYSFS_RO(curr_objnode_count_max); -ZCACHE_SYSFS_RO(flush_total); -ZCACHE_SYSFS_RO(flush_found); -ZCACHE_SYSFS_RO(flobj_total); -ZCACHE_SYSFS_RO(flobj_found); -ZCACHE_SYSFS_RO(failed_eph_puts); -ZCACHE_SYSFS_RO(failed_pers_puts); -ZCACHE_SYSFS_RO(zbud_curr_zbytes); -ZCACHE_SYSFS_RO(zbud_cumul_zpages); -ZCACHE_SYSFS_RO(zbud_cumul_zbytes); -ZCACHE_SYSFS_RO(zbud_buddied_count); -ZCACHE_SYSFS_RO(zbpg_unused_list_count); -ZCACHE_SYSFS_RO(evicted_raw_pages); -ZCACHE_SYSFS_RO(evicted_unbuddied_pages); -ZCACHE_SYSFS_RO(evicted_buddied_pages); -ZCACHE_SYSFS_RO(failed_get_free_pages); -ZCACHE_SYSFS_RO(failed_alloc); -ZCACHE_SYSFS_RO(put_to_flush); -ZCACHE_SYSFS_RO(aborted_preload); -ZCACHE_SYSFS_RO(aborted_shrink); -ZCACHE_SYSFS_RO(compress_poor); -ZCACHE_SYSFS_RO(mean_compress_poor); -ZCACHE_SYSFS_RO_ATOMIC(zbud_curr_raw_pages); -ZCACHE_SYSFS_RO_ATOMIC(zbud_curr_zpages); -ZCACHE_SYSFS_RO_ATOMIC(curr_obj_count); -ZCACHE_SYSFS_RO_ATOMIC(curr_objnode_count); -ZCACHE_SYSFS_RO_CUSTOM(zbud_unbuddied_list_counts, - zbud_show_unbuddied_list_counts); -ZCACHE_SYSFS_RO_CUSTOM(zbud_cumul_chunk_counts, - zbud_show_cumul_chunk_counts); -ZCACHE_SYSFS_RO_CUSTOM(zv_curr_dist_counts, - zv_curr_dist_counts_show); -ZCACHE_SYSFS_RO_CUSTOM(zv_cumul_dist_counts, - zv_cumul_dist_counts_show); - -static struct attribute *zcache_attrs[] = { - &zcache_curr_obj_count_attr.attr, - &zcache_curr_obj_count_max_attr.attr, - &zcache_curr_objnode_count_attr.attr, - &zcache_curr_objnode_count_max_attr.attr, - &zcache_flush_total_attr.attr, - &zcache_flobj_total_attr.attr, - &zcache_flush_found_attr.attr, - &zcache_flobj_found_attr.attr, - &zcache_failed_eph_puts_attr.attr, - &zcache_failed_pers_puts_attr.attr, - &zcache_compress_poor_attr.attr, - &zcache_mean_compress_poor_attr.attr, - &zcache_zbud_curr_raw_pages_attr.attr, - &zcache_zbud_curr_zpages_attr.attr, - &zcache_zbud_curr_zbytes_attr.attr, - &zcache_zbud_cumul_zpages_attr.attr, - &zcache_zbud_cumul_zbytes_attr.attr, - &zcache_zbud_buddied_count_attr.attr, - &zcache_zbpg_unused_list_count_attr.attr, - &zcache_evicted_raw_pages_attr.attr, - &zcache_evicted_unbuddied_pages_attr.attr, - &zcache_evicted_buddied_pages_attr.attr, - &zcache_failed_get_free_pages_attr.attr, - &zcache_failed_alloc_attr.attr, - &zcache_put_to_flush_attr.attr, - &zcache_aborted_preload_attr.attr, - &zcache_aborted_shrink_attr.attr, - &zcache_zbud_unbuddied_list_counts_attr.attr, - &zcache_zbud_cumul_chunk_counts_attr.attr, - &zcache_zv_curr_dist_counts_attr.attr, - &zcache_zv_cumul_dist_counts_attr.attr, - &zcache_zv_max_zsize_attr.attr, - &zcache_zv_max_mean_zsize_attr.attr, - &zcache_zv_page_count_policy_percent_attr.attr, - NULL, -}; - -static struct attribute_group zcache_attr_group = { - .attrs = zcache_attrs, - .name = "zcache", -}; - -#endif /* CONFIG_SYSFS */ -/* - * When zcache is disabled ("frozen"), pools can be created and destroyed, - * but all puts (and thus all other operations that require memory allocation) - * must fail. If zcache is unfrozen, accepts puts, then frozen again, - * data consistency requires all puts while frozen to be converted into - * flushes. - */ -static bool zcache_freeze; - -/* - * zcache shrinker interface (only useful for ephemeral pages, so zbud only) - */ -static int shrink_zcache_memory(struct shrinker *shrink, - struct shrink_control *sc) -{ - int ret = -1; - int nr = sc->nr_to_scan; - gfp_t gfp_mask = sc->gfp_mask; - - if (nr >= 0) { - if (!(gfp_mask & __GFP_FS)) - /* does this case really need to be skipped? */ - goto out; - if (spin_trylock(&zcache_direct_reclaim_lock)) { - zbud_evict_pages(nr); - spin_unlock(&zcache_direct_reclaim_lock); - } else - zcache_aborted_shrink++; - } - ret = (int)atomic_read(&zcache_zbud_curr_raw_pages); -out: - return ret; -} - -static struct shrinker zcache_shrinker = { - .shrink = shrink_zcache_memory, - .seeks = DEFAULT_SEEKS, -}; - -/* - * zcache shims between cleancache/frontswap ops and tmem - */ - -static int zcache_put_page(int cli_id, int pool_id, struct tmem_oid *oidp, - uint32_t index, struct page *page) -{ - struct tmem_pool *pool; - int ret = -1; - - BUG_ON(!irqs_disabled()); - pool = zcache_get_pool_by_id(cli_id, pool_id); - if (unlikely(pool == NULL)) - goto out; - if (!zcache_freeze && zcache_do_preload(pool) == 0) { - /* preload does preempt_disable on success */ - ret = tmem_put(pool, oidp, index, page_address(page), - PAGE_SIZE, 0, is_ephemeral(pool)); - if (ret < 0) { - if (is_ephemeral(pool)) - zcache_failed_eph_puts++; - else - zcache_failed_pers_puts++; - } - zcache_put_pool(pool); - preempt_enable_no_resched(); - } else { - zcache_put_to_flush++; - if (atomic_read(&pool->obj_count) > 0) - /* the put fails whether the flush succeeds or not */ - (void)tmem_flush_page(pool, oidp, index); - zcache_put_pool(pool); - } -out: - return ret; -} - -static int zcache_get_page(int cli_id, int pool_id, struct tmem_oid *oidp, - uint32_t index, struct page *page) -{ - struct tmem_pool *pool; - int ret = -1; - unsigned long flags; - size_t size = PAGE_SIZE; - - local_irq_save(flags); - pool = zcache_get_pool_by_id(cli_id, pool_id); - if (likely(pool != NULL)) { - if (atomic_read(&pool->obj_count) > 0) - ret = tmem_get(pool, oidp, index, page_address(page), - &size, 0, is_ephemeral(pool)); - zcache_put_pool(pool); - } - local_irq_restore(flags); - return ret; -} - -static int zcache_flush_page(int cli_id, int pool_id, - struct tmem_oid *oidp, uint32_t index) -{ - struct tmem_pool *pool; - int ret = -1; - unsigned long flags; - - local_irq_save(flags); - zcache_flush_total++; - pool = zcache_get_pool_by_id(cli_id, pool_id); - if (likely(pool != NULL)) { - if (atomic_read(&pool->obj_count) > 0) - ret = tmem_flush_page(pool, oidp, index); - zcache_put_pool(pool); - } - if (ret >= 0) - zcache_flush_found++; - local_irq_restore(flags); - return ret; -} - -static int zcache_flush_object(int cli_id, int pool_id, - struct tmem_oid *oidp) -{ - struct tmem_pool *pool; - int ret = -1; - unsigned long flags; - - local_irq_save(flags); - zcache_flobj_total++; - pool = zcache_get_pool_by_id(cli_id, pool_id); - if (likely(pool != NULL)) { - if (atomic_read(&pool->obj_count) > 0) - ret = tmem_flush_object(pool, oidp); - zcache_put_pool(pool); - } - if (ret >= 0) - zcache_flobj_found++; - local_irq_restore(flags); - return ret; -} - -static int zcache_destroy_pool(int cli_id, int pool_id) -{ - struct tmem_pool *pool = NULL; - struct zcache_client *cli = NULL; - int ret = -1; - - if (pool_id < 0) - goto out; - if (cli_id == LOCAL_CLIENT) - cli = &zcache_host; - else if ((unsigned int)cli_id < MAX_CLIENTS) - cli = &zcache_clients[cli_id]; - if (cli == NULL) - goto out; - atomic_inc(&cli->refcount); - pool = cli->tmem_pools[pool_id]; - if (pool == NULL) - goto out; - cli->tmem_pools[pool_id] = NULL; - /* wait for pool activity on other cpus to quiesce */ - while (atomic_read(&pool->refcount) != 0) - ; - atomic_dec(&cli->refcount); - local_bh_disable(); - ret = tmem_destroy_pool(pool); - local_bh_enable(); - kfree(pool); - pr_info("zcache: destroyed pool id=%d, cli_id=%d\n", - pool_id, cli_id); -out: - return ret; -} - -static int zcache_new_pool(uint16_t cli_id, uint32_t flags) -{ - int poolid = -1; - struct tmem_pool *pool; - struct zcache_client *cli = NULL; - - if (cli_id == LOCAL_CLIENT) - cli = &zcache_host; - else if ((unsigned int)cli_id < MAX_CLIENTS) - cli = &zcache_clients[cli_id]; - if (cli == NULL) - goto out; - atomic_inc(&cli->refcount); - pool = kmalloc(sizeof(struct tmem_pool), GFP_KERNEL); - if (pool == NULL) { - pr_info("zcache: pool creation failed: out of memory\n"); - goto out; - } - - for (poolid = 0; poolid < MAX_POOLS_PER_CLIENT; poolid++) - if (cli->tmem_pools[poolid] == NULL) - break; - if (poolid >= MAX_POOLS_PER_CLIENT) { - pr_info("zcache: pool creation failed: max exceeded\n"); - kfree(pool); - poolid = -1; - goto out; - } - atomic_set(&pool->refcount, 0); - pool->client = cli; - pool->pool_id = poolid; - tmem_new_pool(pool, flags); - cli->tmem_pools[poolid] = pool; - pr_info("zcache: created %s tmem pool, id=%d, client=%d\n", - flags & TMEM_POOL_PERSIST ? "persistent" : "ephemeral", - poolid, cli_id); -out: - if (cli != NULL) - atomic_dec(&cli->refcount); - return poolid; -} - -/********** - * Two kernel functionalities currently can be layered on top of tmem. - * These are "cleancache" which is used as a second-chance cache for clean - * page cache pages; and "frontswap" which is used for swap pages - * to avoid writes to disk. A generic "shim" is provided here for each - * to translate in-kernel semantics to zcache semantics. - */ - -#ifdef CONFIG_CLEANCACHE -static void zcache_cleancache_put_page(int pool_id, - struct cleancache_filekey key, - pgoff_t index, struct page *page) -{ - u32 ind = (u32) index; - struct tmem_oid oid = *(struct tmem_oid *)&key; - - if (likely(ind == index)) - (void)zcache_put_page(LOCAL_CLIENT, pool_id, &oid, index, page); -} - -static int zcache_cleancache_get_page(int pool_id, - struct cleancache_filekey key, - pgoff_t index, struct page *page) -{ - u32 ind = (u32) index; - struct tmem_oid oid = *(struct tmem_oid *)&key; - int ret = -1; - - if (likely(ind == index)) - ret = zcache_get_page(LOCAL_CLIENT, pool_id, &oid, index, page); - return ret; -} - -static void zcache_cleancache_flush_page(int pool_id, - struct cleancache_filekey key, - pgoff_t index) -{ - u32 ind = (u32) index; - struct tmem_oid oid = *(struct tmem_oid *)&key; - - if (likely(ind == index)) - (void)zcache_flush_page(LOCAL_CLIENT, pool_id, &oid, ind); -} - -static void zcache_cleancache_flush_inode(int pool_id, - struct cleancache_filekey key) -{ - struct tmem_oid oid = *(struct tmem_oid *)&key; - - (void)zcache_flush_object(LOCAL_CLIENT, pool_id, &oid); -} - -static void zcache_cleancache_flush_fs(int pool_id) -{ - if (pool_id >= 0) - (void)zcache_destroy_pool(LOCAL_CLIENT, pool_id); -} - -static int zcache_cleancache_init_fs(size_t pagesize) -{ - BUG_ON(sizeof(struct cleancache_filekey) != - sizeof(struct tmem_oid)); - BUG_ON(pagesize != PAGE_SIZE); - return zcache_new_pool(LOCAL_CLIENT, 0); -} - -static int zcache_cleancache_init_shared_fs(char *uuid, size_t pagesize) -{ - /* shared pools are unsupported and map to private */ - BUG_ON(sizeof(struct cleancache_filekey) != - sizeof(struct tmem_oid)); - BUG_ON(pagesize != PAGE_SIZE); - return zcache_new_pool(LOCAL_CLIENT, 0); -} - -static struct cleancache_ops zcache_cleancache_ops = { - .put_page = zcache_cleancache_put_page, - .get_page = zcache_cleancache_get_page, - .flush_page = zcache_cleancache_flush_page, - .flush_inode = zcache_cleancache_flush_inode, - .flush_fs = zcache_cleancache_flush_fs, - .init_shared_fs = zcache_cleancache_init_shared_fs, - .init_fs = zcache_cleancache_init_fs -}; - -struct cleancache_ops zcache_cleancache_register_ops(void) -{ - struct cleancache_ops old_ops = - cleancache_register_ops(&zcache_cleancache_ops); - - return old_ops; -} -#endif - -#ifdef CONFIG_FRONTSWAP -/* a single tmem poolid is used for all frontswap "types" (swapfiles) */ -static int zcache_frontswap_poolid = -1; - -/* - * Swizzling increases objects per swaptype, increasing tmem concurrency - * for heavy swaploads. Later, larger nr_cpus -> larger SWIZ_BITS - */ -#define SWIZ_BITS 4 -#define SWIZ_MASK ((1 << SWIZ_BITS) - 1) -#define _oswiz(_type, _ind) ((_type << SWIZ_BITS) | (_ind & SWIZ_MASK)) -#define iswiz(_ind) (_ind >> SWIZ_BITS) - -static inline struct tmem_oid oswiz(unsigned type, u32 ind) -{ - struct tmem_oid oid = { .oid = { 0 } }; - oid.oid[0] = _oswiz(type, ind); - return oid; -} - -static int zcache_frontswap_put_page(unsigned type, pgoff_t offset, - struct page *page) -{ - u64 ind64 = (u64)offset; - u32 ind = (u32)offset; - struct tmem_oid oid = oswiz(type, ind); - int ret = -1; - unsigned long flags; - - BUG_ON(!PageLocked(page)); - if (likely(ind64 == ind)) { - local_irq_save(flags); - ret = zcache_put_page(LOCAL_CLIENT, zcache_frontswap_poolid, - &oid, iswiz(ind), page); - local_irq_restore(flags); - } - return ret; -} - -/* returns 0 if the page was successfully gotten from frontswap, -1 if - * was not present (should never happen!) */ -static int zcache_frontswap_get_page(unsigned type, pgoff_t offset, - struct page *page) -{ - u64 ind64 = (u64)offset; - u32 ind = (u32)offset; - struct tmem_oid oid = oswiz(type, ind); - int ret = -1; - - BUG_ON(!PageLocked(page)); - if (likely(ind64 == ind)) - ret = zcache_get_page(LOCAL_CLIENT, zcache_frontswap_poolid, - &oid, iswiz(ind), page); - return ret; -} - -/* flush a single page from frontswap */ -static void zcache_frontswap_flush_page(unsigned type, pgoff_t offset) -{ - u64 ind64 = (u64)offset; - u32 ind = (u32)offset; - struct tmem_oid oid = oswiz(type, ind); - - if (likely(ind64 == ind)) - (void)zcache_flush_page(LOCAL_CLIENT, zcache_frontswap_poolid, - &oid, iswiz(ind)); -} - -/* flush all pages from the passed swaptype */ -static void zcache_frontswap_flush_area(unsigned type) -{ - struct tmem_oid oid; - int ind; - - for (ind = SWIZ_MASK; ind >= 0; ind--) { - oid = oswiz(type, ind); - (void)zcache_flush_object(LOCAL_CLIENT, - zcache_frontswap_poolid, &oid); - } -} - -static void zcache_frontswap_init(unsigned ignored) -{ - /* a single tmem poolid is used for all frontswap "types" (swapfiles) */ - if (zcache_frontswap_poolid < 0) - zcache_frontswap_poolid = - zcache_new_pool(LOCAL_CLIENT, TMEM_POOL_PERSIST); -} - -static struct frontswap_ops zcache_frontswap_ops = { - .put_page = zcache_frontswap_put_page, - .get_page = zcache_frontswap_get_page, - .flush_page = zcache_frontswap_flush_page, - .flush_area = zcache_frontswap_flush_area, - .init = zcache_frontswap_init -}; - -struct frontswap_ops zcache_frontswap_register_ops(void) -{ - struct frontswap_ops old_ops = - frontswap_register_ops(&zcache_frontswap_ops); - - return old_ops; -} -#endif - -/* - * zcache initialization - * NOTE FOR NOW zcache MUST BE PROVIDED AS A KERNEL BOOT PARAMETER OR - * NOTHING HAPPENS! - */ - -static int zcache_enabled; - -static int __init enable_zcache(char *s) -{ - zcache_enabled = 1; - return 1; -} -__setup("zcache", enable_zcache); - -/* allow independent dynamic disabling of cleancache and frontswap */ - -static int use_cleancache = 1; - -static int __init no_cleancache(char *s) -{ - use_cleancache = 0; - return 1; -} - -__setup("nocleancache", no_cleancache); - -static int use_frontswap = 1; - -static int __init no_frontswap(char *s) -{ - use_frontswap = 0; - return 1; -} - -__setup("nofrontswap", no_frontswap); - -static int __init zcache_init(void) -{ -#ifdef CONFIG_SYSFS - int ret = 0; - - ret = sysfs_create_group(mm_kobj, &zcache_attr_group); - if (ret) { - pr_err("zcache: can't create sysfs\n"); - goto out; - } -#endif /* CONFIG_SYSFS */ -#if defined(CONFIG_CLEANCACHE) || defined(CONFIG_FRONTSWAP) - if (zcache_enabled) { - unsigned int cpu; - - tmem_register_hostops(&zcache_hostops); - tmem_register_pamops(&zcache_pamops); - ret = register_cpu_notifier(&zcache_cpu_notifier_block); - if (ret) { - pr_err("zcache: can't register cpu notifier\n"); - goto out; - } - for_each_online_cpu(cpu) { - void *pcpu = (void *)(long)cpu; - zcache_cpu_notifier(&zcache_cpu_notifier_block, - CPU_UP_PREPARE, pcpu); - } - } - zcache_objnode_cache = kmem_cache_create("zcache_objnode", - sizeof(struct tmem_objnode), 0, 0, NULL); - zcache_obj_cache = kmem_cache_create("zcache_obj", - sizeof(struct tmem_obj), 0, 0, NULL); - ret = zcache_new_client(LOCAL_CLIENT); - if (ret) { - pr_err("zcache: can't create client\n"); - goto out; - } -#endif -#ifdef CONFIG_CLEANCACHE - if (zcache_enabled && use_cleancache) { - struct cleancache_ops old_ops; - - zbud_init(); - register_shrinker(&zcache_shrinker); - old_ops = zcache_cleancache_register_ops(); - pr_info("zcache: cleancache enabled using kernel " - "transcendent memory and compression buddies\n"); - if (old_ops.init_fs != NULL) - pr_warning("zcache: cleancache_ops overridden"); - } -#endif -#ifdef CONFIG_FRONTSWAP - if (zcache_enabled && use_frontswap) { - struct frontswap_ops old_ops; - - old_ops = zcache_frontswap_register_ops(); - pr_info("zcache: frontswap enabled using kernel " - "transcendent memory and xvmalloc\n"); - if (old_ops.init != NULL) - pr_warning("ktmem: frontswap_ops overridden"); - } -#endif -out: - return ret; -} - -module_init(zcache_init) -- cgit v1.2.3 From fd6b68bbac9f100c8728b2cfe4e34f03f3df4e4d Mon Sep 17 00:00:00 2001 From: Thadeu Lima de Souza Cascardo Date: Tue, 2 Aug 2011 14:20:27 -0300 Subject: staging: zcache: module is GPL This avoids tainting the kernel as if a proprietary module was loaded. The kernel will still be tainted because this is a staging driver. Signed-off-by: Thadeu Lima de Souza Cascardo Signed-off-by: Greg Kroah-Hartman --- drivers/staging/zcache/zcache-main.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/staging') diff --git a/drivers/staging/zcache/zcache-main.c b/drivers/staging/zcache/zcache-main.c index 65a81a0d7c49..a58a03f66d73 100644 --- a/drivers/staging/zcache/zcache-main.c +++ b/drivers/staging/zcache/zcache-main.c @@ -53,6 +53,9 @@ #define MAX_CLIENTS 16 #define LOCAL_CLIENT ((uint16_t)-1) + +MODULE_LICENSE("GPL"); + struct zcache_client { struct tmem_pool *tmem_pools[MAX_POOLS_PER_CLIENT]; struct xv_pool *xvpool; -- cgit v1.2.3 From 2f8d92b7779d1f3145cd71552ed8282c8b299772 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Tue, 26 Jul 2011 17:15:50 +0100 Subject: gma500: Fix clashes with DRM updates The private object support has migrated from gma500 into the DRM core, remove our now clashing copy so -next can build. Signed-off-by: Alan Cox Signed-off-by: Greg Kroah-Hartman --- drivers/staging/gma500/gem_glue.c | 23 +---------------------- drivers/staging/gma500/gem_glue.h | 2 -- 2 files changed, 1 insertion(+), 24 deletions(-) (limited to 'drivers/staging') diff --git a/drivers/staging/gma500/gem_glue.c b/drivers/staging/gma500/gem_glue.c index 779ac1a12d24..daac12120653 100644 --- a/drivers/staging/gma500/gem_glue.c +++ b/drivers/staging/gma500/gem_glue.c @@ -20,26 +20,6 @@ #include #include -/** - * Initialize an already allocated GEM object of the specified size with - * no GEM provided backing store. Instead the caller is responsible for - * backing the object and handling it. - */ -int drm_gem_private_object_init(struct drm_device *dev, - struct drm_gem_object *obj, size_t size) -{ - BUG_ON((size & (PAGE_SIZE - 1)) != 0); - - obj->dev = dev; - obj->filp = NULL; - - kref_init(&obj->refcount); - atomic_set(&obj->handle_count, 0); - obj->size = size; - - return 0; -} - void drm_gem_object_release_wrap(struct drm_gem_object *obj) { /* Remove the list map if one is present */ @@ -51,8 +31,7 @@ void drm_gem_object_release_wrap(struct drm_gem_object *obj) kfree(list->map); list->map = NULL; } - if (obj->filp) - drm_gem_object_release(obj); + drm_gem_object_release(obj); } /** diff --git a/drivers/staging/gma500/gem_glue.h b/drivers/staging/gma500/gem_glue.h index a0f2bc4e4ae7..ce5ce30f74db 100644 --- a/drivers/staging/gma500/gem_glue.h +++ b/drivers/staging/gma500/gem_glue.h @@ -1,4 +1,2 @@ extern void drm_gem_object_release_wrap(struct drm_gem_object *obj); -extern int drm_gem_private_object_init(struct drm_device *dev, - struct drm_gem_object *obj, size_t size); extern int gem_create_mmap_offset(struct drm_gem_object *obj); -- cgit v1.2.3 From 589c3ca00b7886bf743998398884cd4f4d354e17 Mon Sep 17 00:00:00 2001 From: Stefan Lippers-Hollmann Date: Tue, 2 Aug 2011 22:17:25 +0200 Subject: staging: rtl8192u: declare MODULE_FIRMWARE declaring MODULE_FIRMWARE has apparently forgotten while removing the embedded firmware arrays in 0a8692b534e18fcec6eac07551bb37a22659f5c7 (rtl8192u_usb: Remove built-in firmware images). Signed-off-by: Stefan Lippers-Hollmann Cc: stable [2.6.39+] Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192u/r819xU_firmware.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'drivers/staging') diff --git a/drivers/staging/rtl8192u/r819xU_firmware.c b/drivers/staging/rtl8192u/r819xU_firmware.c index 6766f468639f..4bb5fffca5b9 100644 --- a/drivers/staging/rtl8192u/r819xU_firmware.c +++ b/drivers/staging/rtl8192u/r819xU_firmware.c @@ -399,10 +399,7 @@ download_firmware_fail: } - - - - - - +MODULE_FIRMWARE("RTL8192U/boot.img"); +MODULE_FIRMWARE("RTL8192U/main.img"); +MODULE_FIRMWARE("RTL8192U/data.img"); -- cgit v1.2.3 From c060ae7db4ebf1e5e08199b2aec12f051189041a Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Sun, 31 Jul 2011 02:44:05 -0400 Subject: staging: ft1000_proc needs asm/io.h for inw/outw on sparc Seen during an allmodconfig build for sparc: CC [M] drivers/staging/ft1000/ft1000-pcmcia/ft1000_proc.o In file included from drivers/staging/ft1000/ft1000-pcmcia/ft1000_proc.c:26: drivers/staging/ft1000/ft1000-pcmcia/ft1000.h: In function 'ft1000_read_reg': drivers/staging/ft1000/ft1000-pcmcia/ft1000.h:80: error: implicit declaration of function 'inw' drivers/staging/ft1000/ft1000-pcmcia/ft1000.h: In function 'ft1000_write_reg': drivers/staging/ft1000/ft1000-pcmcia/ft1000.h:86: error: implicit declaration of function 'outw' Signed-off-by: Paul Gortmaker Signed-off-by: Greg Kroah-Hartman --- drivers/staging/ft1000/ft1000-pcmcia/ft1000_proc.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/staging') diff --git a/drivers/staging/ft1000/ft1000-pcmcia/ft1000_proc.c b/drivers/staging/ft1000/ft1000-pcmcia/ft1000_proc.c index 627a98b4ec30..9e728b3415e3 100644 --- a/drivers/staging/ft1000/ft1000-pcmcia/ft1000_proc.c +++ b/drivers/staging/ft1000/ft1000-pcmcia/ft1000_proc.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include "ft1000.h" -- cgit v1.2.3 From 8f89615528b11eabda68faaf2438d09c9565a125 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Sat, 30 Jul 2011 11:45:09 +0300 Subject: Staging: iio: add some unlocks to raw_read() functions This code was cut and pasted in several places. It's missing some unlocks on error. Signed-off-by: Dan Carpenter Acked-by: Jonathan Cameron Signed-off-by: Greg Kroah-Hartman --- drivers/staging/iio/accel/adis16203_core.c | 8 ++++++-- drivers/staging/iio/accel/adis16204_core.c | 8 ++++++-- drivers/staging/iio/accel/adis16209_core.c | 8 ++++++-- drivers/staging/iio/accel/adis16240_core.c | 8 ++++++-- drivers/staging/iio/gyro/adis16260_core.c | 8 ++++++-- 5 files changed, 30 insertions(+), 10 deletions(-) (limited to 'drivers/staging') diff --git a/drivers/staging/iio/accel/adis16203_core.c b/drivers/staging/iio/accel/adis16203_core.c index bf1988884e93..cf5d15da76ad 100644 --- a/drivers/staging/iio/accel/adis16203_core.c +++ b/drivers/staging/iio/accel/adis16203_core.c @@ -311,13 +311,17 @@ static int adis16203_read_raw(struct iio_dev *indio_dev, mutex_lock(&indio_dev->mlock); addr = adis16203_addresses[chan->address][0]; ret = adis16203_spi_read_reg_16(indio_dev, addr, &val16); - if (ret) + if (ret) { + mutex_unlock(&indio_dev->mlock); return ret; + } if (val16 & ADIS16203_ERROR_ACTIVE) { ret = adis16203_check_status(indio_dev); - if (ret) + if (ret) { + mutex_unlock(&indio_dev->mlock); return ret; + } } val16 = val16 & ((1 << chan->scan_type.realbits) - 1); if (chan->scan_type.sign == 's') diff --git a/drivers/staging/iio/accel/adis16204_core.c b/drivers/staging/iio/accel/adis16204_core.c index cfd09b3b9937..3e2b62654b7d 100644 --- a/drivers/staging/iio/accel/adis16204_core.c +++ b/drivers/staging/iio/accel/adis16204_core.c @@ -341,13 +341,17 @@ static int adis16204_read_raw(struct iio_dev *indio_dev, mutex_lock(&indio_dev->mlock); addr = adis16204_addresses[chan->address][0]; ret = adis16204_spi_read_reg_16(indio_dev, addr, &val16); - if (ret) + if (ret) { + mutex_unlock(&indio_dev->mlock); return ret; + } if (val16 & ADIS16204_ERROR_ACTIVE) { ret = adis16204_check_status(indio_dev); - if (ret) + if (ret) { + mutex_unlock(&indio_dev->mlock); return ret; + } } val16 = val16 & ((1 << chan->scan_type.realbits) - 1); if (chan->scan_type.sign == 's') diff --git a/drivers/staging/iio/accel/adis16209_core.c b/drivers/staging/iio/accel/adis16209_core.c index 55f3a7bcaf0a..bec1fa8de9b9 100644 --- a/drivers/staging/iio/accel/adis16209_core.c +++ b/drivers/staging/iio/accel/adis16209_core.c @@ -337,13 +337,17 @@ static int adis16209_read_raw(struct iio_dev *indio_dev, mutex_lock(&indio_dev->mlock); addr = adis16209_addresses[chan->address][0]; ret = adis16209_spi_read_reg_16(indio_dev, addr, &val16); - if (ret) + if (ret) { + mutex_unlock(&indio_dev->mlock); return ret; + } if (val16 & ADIS16209_ERROR_ACTIVE) { ret = adis16209_check_status(indio_dev); - if (ret) + if (ret) { + mutex_unlock(&indio_dev->mlock); return ret; + } } val16 = val16 & ((1 << chan->scan_type.realbits) - 1); if (chan->scan_type.sign == 's') diff --git a/drivers/staging/iio/accel/adis16240_core.c b/drivers/staging/iio/accel/adis16240_core.c index 4a4eafc58630..aee8b69173c4 100644 --- a/drivers/staging/iio/accel/adis16240_core.c +++ b/drivers/staging/iio/accel/adis16240_core.c @@ -370,13 +370,17 @@ static int adis16240_read_raw(struct iio_dev *indio_dev, mutex_lock(&indio_dev->mlock); addr = adis16240_addresses[chan->address][0]; ret = adis16240_spi_read_reg_16(indio_dev, addr, &val16); - if (ret) + if (ret) { + mutex_unlock(&indio_dev->mlock); return ret; + } if (val16 & ADIS16240_ERROR_ACTIVE) { ret = adis16240_check_status(indio_dev); - if (ret) + if (ret) { + mutex_unlock(&indio_dev->mlock); return ret; + } } val16 = val16 & ((1 << chan->scan_type.realbits) - 1); if (chan->scan_type.sign == 's') diff --git a/drivers/staging/iio/gyro/adis16260_core.c b/drivers/staging/iio/gyro/adis16260_core.c index 05797f404bea..f2d43cfcc493 100644 --- a/drivers/staging/iio/gyro/adis16260_core.c +++ b/drivers/staging/iio/gyro/adis16260_core.c @@ -446,13 +446,17 @@ static int adis16260_read_raw(struct iio_dev *indio_dev, mutex_lock(&indio_dev->mlock); addr = adis16260_addresses[chan->address][0]; ret = adis16260_spi_read_reg_16(indio_dev, addr, &val16); - if (ret) + if (ret) { + mutex_unlock(&indio_dev->mlock); return ret; + } if (val16 & ADIS16260_ERROR_ACTIVE) { ret = adis16260_check_status(indio_dev); - if (ret) + if (ret) { + mutex_unlock(&indio_dev->mlock); return ret; + } } val16 = val16 & ((1 << chan->scan_type.realbits) - 1); if (chan->scan_type.sign == 's') -- cgit v1.2.3 From 09f9390d797ff34020faab866996884fd93a0081 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 28 Jul 2011 13:59:35 -0700 Subject: drivers/staging/speakup/devsynth.c: fix "buffer size is not provably correct" error x86_64 allmodconfig: In file included from arch/x86/include/asm/uaccess.h:572, from include/linux/uaccess.h:5, from drivers/staging/speakup/devsynth.c:4: In function 'copy_from_user', inlined from 'speakup_file_write' at drivers/staging/speakup/devsynth.c:28: arch/x86/include/asm/uaccess_64.h:64: error: call to 'copy_from_user_overflow' declared with attribute error: copy_from_user() buffer size is not provably correct I'm not sure what was unprovable about it, but size_t is the correct type anyway. Also replace needless min_t() with min() Cc: William Hubbs Cc: Arjan van de Ven Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- drivers/staging/speakup/devsynth.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'drivers/staging') diff --git a/drivers/staging/speakup/devsynth.c b/drivers/staging/speakup/devsynth.c index 39dc586fc8bb..940769ef883f 100644 --- a/drivers/staging/speakup/devsynth.c +++ b/drivers/staging/speakup/devsynth.c @@ -18,13 +18,14 @@ static ssize_t speakup_file_write(struct file *fp, const char *buffer, { size_t count = nbytes; const char *ptr = buffer; - int bytes; + size_t bytes; unsigned long flags; u_char buf[256]; + if (synth == NULL) return -ENODEV; while (count > 0) { - bytes = min_t(size_t, count, sizeof(buf)); + bytes = min(count, sizeof(buf)); if (copy_from_user(buf, ptr, bytes)) return -EFAULT; count -= bytes; -- cgit v1.2.3 From dac95cb8cf40db85fa031b1f170e167cbaa9bf3a Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 28 Jul 2011 13:59:36 -0700 Subject: drivers/staging/dt3155v4l/dt3155v4l.c needs slab.h alpha allmodconfig: drivers/staging/dt3155v4l/dt3155v4l.c:434: error: implicit declaration of function 'kzalloc' Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- drivers/staging/dt3155v4l/dt3155v4l.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/staging') diff --git a/drivers/staging/dt3155v4l/dt3155v4l.c b/drivers/staging/dt3155v4l/dt3155v4l.c index fe02d22274b4..05aa41cf875b 100644 --- a/drivers/staging/dt3155v4l/dt3155v4l.c +++ b/drivers/staging/dt3155v4l/dt3155v4l.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From dd010235fd714571df587d0f14c70eebc6823973 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 28 Jul 2011 13:59:37 -0700 Subject: drivers/staging/solo6x10/core.c needs slab.h alpha allmodconfig: drivers/staging/solo6x10/core.c:140: error: implicit declaration of function 'kzalloc' Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- drivers/staging/solo6x10/core.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/staging') diff --git a/drivers/staging/solo6x10/core.c b/drivers/staging/solo6x10/core.c index 76779949f141..f974f6412ad7 100644 --- a/drivers/staging/solo6x10/core.c +++ b/drivers/staging/solo6x10/core.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include "solo6x10.h" #include "tw28.h" -- cgit v1.2.3 From 7b4785f45db2c124a6cbd73114e7e078a9251e0a Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 28 Jul 2011 13:59:37 -0700 Subject: drivers/staging/solo6x10/p2m.c needs slab.h alpha allmodconfig: drivers/staging/solo6x10/p2m.c:52: error: implicit declaration of function 'kzalloc' Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- drivers/staging/solo6x10/p2m.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/staging') diff --git a/drivers/staging/solo6x10/p2m.c b/drivers/staging/solo6x10/p2m.c index 5717eabb04a4..56210f0fc5ec 100644 --- a/drivers/staging/solo6x10/p2m.c +++ b/drivers/staging/solo6x10/p2m.c @@ -18,6 +18,7 @@ */ #include +#include #include #include "solo6x10.h" -- cgit v1.2.3 From e72be3fc567f587b1f70134e7f6538a4f5ae8f95 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 28 Jul 2011 13:59:38 -0700 Subject: staging: more missing slab.h inclusions Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- drivers/staging/solo6x10/enc.c | 1 + drivers/staging/solo6x10/g723.c | 1 + 2 files changed, 2 insertions(+) (limited to 'drivers/staging') diff --git a/drivers/staging/solo6x10/enc.c b/drivers/staging/solo6x10/enc.c index 285f7f350062..de502599bb19 100644 --- a/drivers/staging/solo6x10/enc.c +++ b/drivers/staging/solo6x10/enc.c @@ -18,6 +18,7 @@ */ #include +#include #include "solo6x10.h" #include "osd-font.h" diff --git a/drivers/staging/solo6x10/g723.c b/drivers/staging/solo6x10/g723.c index bd8eb92c94b1..59274bfca95b 100644 --- a/drivers/staging/solo6x10/g723.c +++ b/drivers/staging/solo6x10/g723.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From 193634ce7740e18a012c543fad0843c6af0440d9 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Thu, 28 Jul 2011 14:46:04 +0200 Subject: drivers/staging/ath6kl/miscdrv/ar3kps/ar3kpsparser.c: adjust array index Convert array index from the loop bound to the loop index. A simplified version of the semantic patch that fixes this problem is as follows: (http://coccinelle.lip6.fr/) // @@ expression e1,e2,ar; @@ for(e1 = 0; e1 < e2; e1++) { <... ar[ - e2 + e1 ] ...> } // Signed-off-by: Julia Lawall Signed-off-by: Greg Kroah-Hartman --- drivers/staging/ath6kl/miscdrv/ar3kps/ar3kpsparser.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/staging') diff --git a/drivers/staging/ath6kl/miscdrv/ar3kps/ar3kpsparser.c b/drivers/staging/ath6kl/miscdrv/ar3kps/ar3kpsparser.c index c01c0cb0af4e..b99a11a9dd69 100644 --- a/drivers/staging/ath6kl/miscdrv/ar3kps/ar3kpsparser.c +++ b/drivers/staging/ath6kl/miscdrv/ar3kps/ar3kpsparser.c @@ -812,7 +812,7 @@ int AthCreateCommandList(struct ps_cmd_packet **HciPacketList, u32 *numPackets) for(count = 0; count < Patch_Count; count++) { AR_DEBUG_PRINTF(ATH_DEBUG_ERR,("Freeing Patch Buffer %d \r\n",count)); - kfree(RamPatch[Patch_Count].Data); + kfree(RamPatch[count].Data); } for(count = 0; count < Tag_Count; count++) { -- cgit v1.2.3 From 55dc6ee7def173f0dd3b6d0d0257917112d542e9 Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 1 Aug 2011 11:45:49 +0100 Subject: Staging: Add clk API note to nvec/TODO Add a note about the abuse of the clk API to the nvec/TODO list. Signed-off-by: Russell King Signed-off-by: Greg Kroah-Hartman --- drivers/staging/nvec/TODO | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'drivers/staging') diff --git a/drivers/staging/nvec/TODO b/drivers/staging/nvec/TODO index 77b47f763f22..649d6b70deaa 100644 --- a/drivers/staging/nvec/TODO +++ b/drivers/staging/nvec/TODO @@ -4,5 +4,7 @@ ToDo list (incomplete, unordered) - add compile as module support - move nvec devices to mfd cells? - adjust to kernel style - - + - fix clk usage + should not be using clk_get_sys(), but clk_get(&pdev->dev, conn) + where conn is either NULL if the device only has one clock, or + the device specific name if it has multiple clocks. -- cgit v1.2.3 From fe3e593601752d547bd00d83f0bdedbce1d80f59 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Sat, 9 Jul 2011 21:23:26 +0200 Subject: drivers/staging/hv/blkvsc_drv.c: eliminate NULL pointer dereference In this code, blkvsc_req is allocated in the cache blkdev->request_pool, but freed in the first case to the cache blkvsc_req->dev->request_pool. blkvsc_req->dev is subsequently initialized to blkdev, making these the same at the second call to kmem_cache_free. But at the point of the first call, blkvsc_req->dev is NULL. The second call is changed too, for uniformity. The semantic patch that fixes this problem is as follows: (http://coccinelle.lip6.fr/) // @@ expression x,e,e1,e2,e3; @@ x = \(kmem_cache_alloc\|kmem_cache_zalloc\)(e1,e2) ... when != x = e ( kmem_cache_free(e1,x); | ?-kmem_cache_free(e3,x); +kmem_cache_free(e1,x); ) // Signed-off-by: Julia Lawall Cc: KY Srinivasan Cc: Hank Janssen Cc: Haiyang Zhang Signed-off-by: Greg Kroah-Hartman --- drivers/staging/hv/blkvsc_drv.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/staging') diff --git a/drivers/staging/hv/blkvsc_drv.c b/drivers/staging/hv/blkvsc_drv.c index 3612574ca520..d286b2223181 100644 --- a/drivers/staging/hv/blkvsc_drv.c +++ b/drivers/staging/hv/blkvsc_drv.c @@ -325,7 +325,7 @@ static int blkvsc_do_operation(struct block_device_context *blkdev, page_buf = alloc_page(GFP_KERNEL); if (!page_buf) { - kmem_cache_free(blkvsc_req->dev->request_pool, blkvsc_req); + kmem_cache_free(blkdev->request_pool, blkvsc_req); return -ENOMEM; } @@ -422,7 +422,7 @@ cleanup: __free_page(page_buf); - kmem_cache_free(blkvsc_req->dev->request_pool, blkvsc_req); + kmem_cache_free(blkdev->request_pool, blkvsc_req); return ret; } -- cgit v1.2.3 From 12623f07b9d01bbaf3035284ea6a110787cc1e66 Mon Sep 17 00:00:00 2001 From: Thadeu Lima de Souza Cascardo Date: Wed, 3 Aug 2011 11:00:40 -0300 Subject: staging: zcache: include module.h for MODULE_LICENSE The oncoming cleanup of module.h usage requires the explicit inclusion of module.h when it was otherwise being included indirectly. Otherwise, building zcache will fail. Reported-by: Stephen Rothwell Signed-off-by: Thadeu Lima de Souza Cascardo Signed-off-by: Greg Kroah-Hartman --- drivers/staging/zcache/zcache-main.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/staging') diff --git a/drivers/staging/zcache/zcache-main.c b/drivers/staging/zcache/zcache-main.c index a58a03f66d73..66469acce58e 100644 --- a/drivers/staging/zcache/zcache-main.c +++ b/drivers/staging/zcache/zcache-main.c @@ -19,6 +19,7 @@ * http://marc.info/?l=linux-mm&m=127811271605009 */ +#include #include #include #include -- cgit v1.2.3 From f8d73aa362cec89e3379bdcdae54cc46e0a6b34d Mon Sep 17 00:00:00 2001 From: Wanlong Gao Date: Wed, 3 Aug 2011 17:17:36 +0800 Subject: drivers:staging:solo6x10:add the missed slab.h Add the missed linux/slab.h to solo6x10.h. Signed-off-by: Wanlong Gao Signed-off-by: Greg Kroah-Hartman --- drivers/staging/solo6x10/solo6x10.h | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/staging') diff --git a/drivers/staging/solo6x10/solo6x10.h b/drivers/staging/solo6x10/solo6x10.h index 17c06bd6cc91..abee7213202f 100644 --- a/drivers/staging/solo6x10/solo6x10.h +++ b/drivers/staging/solo6x10/solo6x10.h @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From f704648281831fbb8a4ca1acbe18cb84bc0267c8 Mon Sep 17 00:00:00 2001 From: wwang Date: Wed, 3 Aug 2011 16:00:25 +0800 Subject: staging:rts_pstor: fix thread synchronization flow Using different completion variables to synchronize different kernel threads This patch fix a bug that may cause memory leak when driver disconnected. This is not a very urgent bug. Because with the default setting, driver disconnectting routine won't be called except when Linux is shut down. But if the option auto_delink_en is set, a small number of memory would leak out after memory card unplugged. Signed-off-by: wwang Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rts_pstor/rtsx.c | 109 +++++++++++++++------------------------ drivers/staging/rts_pstor/rtsx.h | 9 +++- 2 files changed, 50 insertions(+), 68 deletions(-) (limited to 'drivers/staging') diff --git a/drivers/staging/rts_pstor/rtsx.c b/drivers/staging/rts_pstor/rtsx.c index 5ff59f27d101..16c73fbff51f 100644 --- a/drivers/staging/rts_pstor/rtsx.c +++ b/drivers/staging/rts_pstor/rtsx.c @@ -66,12 +66,6 @@ static int msi_en; module_param(msi_en, int, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(msi_en, "enable msi"); -/* These are used to make sure the module doesn't unload before all the - * threads have exited. - */ -static atomic_t total_threads = ATOMIC_INIT(0); -static DECLARE_COMPLETION(threads_gone); - static irqreturn_t rtsx_interrupt(int irq, void *dev_id); /*********************************************************************** @@ -192,7 +186,7 @@ static int queuecommand_lck(struct scsi_cmnd *srb, /* enqueue the command and wake up the control thread */ srb->scsi_done = done; chip->srb = srb; - up(&(dev->sema)); + complete(&dev->cmnd_ready); return 0; } @@ -475,7 +469,7 @@ static int rtsx_control_thread(void *__dev) current->flags |= PF_NOFREEZE; for (;;) { - if (down_interruptible(&dev->sema)) + if (wait_for_completion_interruptible(&dev->cmnd_ready)) break; /* lock the device pointers */ @@ -557,8 +551,6 @@ SkipForAbort: mutex_unlock(&dev->dev_mutex); } /* for (;;) */ - scsi_host_put(host); - /* notify the exit routine that we're actually exiting now * * complete()/wait_for_completion() is similar to up()/down(), @@ -573,7 +565,7 @@ SkipForAbort: * This is important in preemption kernels, which transfer the flow * of execution immediately upon a complete(). */ - complete_and_exit(&threads_gone, 0); + complete_and_exit(&dev->control_exit, 0); } @@ -581,7 +573,6 @@ static int rtsx_polling_thread(void *__dev) { struct rtsx_dev *dev = (struct rtsx_dev *)__dev; struct rtsx_chip *chip = dev->chip; - struct Scsi_Host *host = rtsx_to_host(dev); struct sd_info *sd_card = &(chip->sd_card); struct xd_info *xd_card = &(chip->xd_card); struct ms_info *ms_card = &(chip->ms_card); @@ -621,8 +612,7 @@ static int rtsx_polling_thread(void *__dev) mutex_unlock(&dev->dev_mutex); } - scsi_host_put(host); - complete_and_exit(&threads_gone, 0); + complete_and_exit(&dev->polling_exit, 0); } /* @@ -699,29 +689,38 @@ static void rtsx_release_resources(struct rtsx_dev *dev) { printk(KERN_INFO "-- %s\n", __func__); + /* Tell the control thread to exit. The SCSI host must + * already have been removed so it won't try to queue + * any more commands. + */ + printk(KERN_INFO "-- sending exit command to thread\n"); + complete(&dev->cmnd_ready); + if (dev->ctl_thread) + wait_for_completion(&dev->control_exit); + if (dev->polling_thread) + wait_for_completion(&dev->polling_exit); + + wait_timeout(200); + if (dev->rtsx_resv_buf) { - dma_free_coherent(&(dev->pci->dev), HOST_CMDS_BUF_LEN, + dma_free_coherent(&(dev->pci->dev), RTSX_RESV_BUF_LEN, dev->rtsx_resv_buf, dev->rtsx_resv_buf_addr); dev->chip->host_cmds_ptr = NULL; dev->chip->host_sg_tbl_ptr = NULL; } - pci_disable_device(dev->pci); - pci_release_regions(dev->pci); - - if (dev->irq > 0) { + if (dev->irq > 0) free_irq(dev->irq, (void *)dev); - } - if (dev->chip->msi_en) { + if (dev->chip->msi_en) pci_disable_msi(dev->pci); - } + if (dev->remap_addr) + iounmap(dev->remap_addr); - /* Tell the control thread to exit. The SCSI host must - * already have been removed so it won't try to queue - * any more commands. - */ - printk(KERN_INFO "-- sending exit command to thread\n"); - up(&dev->sema); + pci_disable_device(dev->pci); + pci_release_regions(dev->pci); + + rtsx_release_chip(dev->chip); + kfree(dev->chip); } /* First stage of disconnect processing: stop all commands and remove @@ -739,6 +738,7 @@ static void quiesce_and_remove_host(struct rtsx_dev *dev) scsi_unlock(host); mutex_unlock(&dev->dev_mutex); wake_up(&dev->delay_wait); + wait_for_completion(&dev->scanning_done); /* Wait some time to let other threads exist */ wait_timeout(100); @@ -793,8 +793,7 @@ static int rtsx_scan_thread(void *__dev) /* Should we unbind if no devices were detected? */ } - scsi_host_put(rtsx_to_host(dev)); - complete_and_exit(&threads_gone, 0); + complete_and_exit(&dev->scanning_done, 0); } static void rtsx_init_options(struct rtsx_chip *chip) @@ -941,8 +940,11 @@ static int __devinit rtsx_probe(struct pci_dev *pci, const struct pci_device_id spin_lock_init(&dev->reg_lock); mutex_init(&(dev->dev_mutex)); - sema_init(&(dev->sema), 0); + init_completion(&dev->cmnd_ready); + init_completion(&dev->control_exit); + init_completion(&dev->polling_exit); init_completion(&(dev->notify)); + init_completion(&dev->scanning_done); init_waitqueue_head(&dev->delay_wait); dev->pci = pci; @@ -992,28 +994,22 @@ static int __devinit rtsx_probe(struct pci_dev *pci, const struct pci_device_id pci_set_master(pci); synchronize_irq(dev->irq); - err = scsi_add_host(host, &pci->dev); - if (err) { - printk(KERN_ERR "Unable to add the scsi host\n"); - goto errout; - } - rtsx_init_chip(dev->chip); /* Start up our control thread */ - th = kthread_create(rtsx_control_thread, dev, CR_DRIVER_NAME); + th = kthread_run(rtsx_control_thread, dev, CR_DRIVER_NAME); if (IS_ERR(th)) { printk(KERN_ERR "Unable to start control thread\n"); err = PTR_ERR(th); goto errout; } + dev->ctl_thread = th; - /* Take a reference to the host for the control thread and - * count it among all the threads we have launched. Then - * start it up. */ - scsi_host_get(rtsx_to_host(dev)); - atomic_inc(&total_threads); - wake_up_process(th); + err = scsi_add_host(host, &pci->dev); + if (err) { + printk(KERN_ERR "Unable to add the scsi host\n"); + goto errout; + } /* Start up the thread for delayed SCSI-device scanning */ th = kthread_create(rtsx_scan_thread, dev, "rtsx-scan"); @@ -1024,28 +1020,17 @@ static int __devinit rtsx_probe(struct pci_dev *pci, const struct pci_device_id goto errout; } - /* Take a reference to the host for the scanning thread and - * count it among all the threads we have launched. Then - * start it up. */ - scsi_host_get(rtsx_to_host(dev)); - atomic_inc(&total_threads); wake_up_process(th); /* Start up the thread for polling thread */ - th = kthread_create(rtsx_polling_thread, dev, "rtsx-polling"); + th = kthread_run(rtsx_polling_thread, dev, "rtsx-polling"); if (IS_ERR(th)) { printk(KERN_ERR "Unable to start the device-polling thread\n"); quiesce_and_remove_host(dev); err = PTR_ERR(th); goto errout; } - - /* Take a reference to the host for the polling thread and - * count it among all the threads we have launched. Then - * start it up. */ - scsi_host_get(rtsx_to_host(dev)); - atomic_inc(&total_threads); - wake_up_process(th); + dev->polling_thread = th; pci_set_drvdata(pci, dev); @@ -1108,16 +1093,6 @@ static void __exit rtsx_exit(void) pci_unregister_driver(&driver); - /* Don't return until all of our control and scanning threads - * have exited. Since each thread signals threads_gone as its - * last act, we have to call wait_for_completion the right number - * of times. - */ - while (atomic_read(&total_threads) > 0) { - wait_for_completion(&threads_gone); - atomic_dec(&total_threads); - } - printk(KERN_INFO "%s module exit\n", CR_DRIVER_NAME); } diff --git a/drivers/staging/rts_pstor/rtsx.h b/drivers/staging/rts_pstor/rtsx.h index 247615ba1d2a..86e47c2e3e3c 100644 --- a/drivers/staging/rts_pstor/rtsx.h +++ b/drivers/staging/rts_pstor/rtsx.h @@ -112,9 +112,16 @@ struct rtsx_dev { /* locks */ spinlock_t reg_lock; + struct task_struct *ctl_thread; /* the control thread */ + struct task_struct *polling_thread; /* the polling thread */ + /* mutual exclusion and synchronization structures */ - struct semaphore sema; /* to sleep thread on */ + struct completion cmnd_ready; /* to sleep thread on */ + struct completion control_exit; /* control thread exit */ + struct completion polling_exit; /* polling thread exit */ struct completion notify; /* thread begin/end */ + struct completion scanning_done; /* wait for scan thread */ + wait_queue_head_t delay_wait; /* wait during scan, reset */ struct mutex dev_mutex; -- cgit v1.2.3 From 3ca15c4486beb113700cda44e32109cf0d97528b Mon Sep 17 00:00:00 2001 From: Thadeu Lima de Souza Cascardo Date: Thu, 4 Aug 2011 19:00:33 -0300 Subject: zcache: Use div_u64 for 64-bit division xv_get_total_size_bytes returns a u64 value and it's used in a division. This causes build failures in 32-bit architectures, as reported by Randy Dunlap. Reported-by: Randy Dunlap Signed-off-by: Thadeu Lima de Souza Cascardo Cc: Stephen Rothwell Cc: Dan Magenheimer Cc: Nitin Gupta Acked-by: Randy Dunlap Signed-off-by: Greg Kroah-Hartman --- drivers/staging/zcache/zcache-main.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'drivers/staging') diff --git a/drivers/staging/zcache/zcache-main.c b/drivers/staging/zcache/zcache-main.c index 66469acce58e..2c41c4465e14 100644 --- a/drivers/staging/zcache/zcache-main.c +++ b/drivers/staging/zcache/zcache-main.c @@ -28,6 +28,7 @@ #include #include #include +#include #include "tmem.h" #include "../zram/xvmalloc.h" /* if built in drivers/staging */ @@ -1162,6 +1163,7 @@ static void *zcache_pampd_create(char *data, size_t size, bool raw, int eph, uint16_t client_id = get_client_id_from_client(cli); unsigned long zv_mean_zsize; unsigned long curr_pers_pampd_count; + u64 total_zsize; if (eph) { ret = zcache_compress(page, &cdata, &clen); @@ -1194,8 +1196,9 @@ static void *zcache_pampd_create(char *data, size_t size, bool raw, int eph, } /* reject if mean compression is too poor */ if ((clen > zv_max_mean_zsize) && (curr_pers_pampd_count > 0)) { - zv_mean_zsize = xv_get_total_size_bytes(cli->xvpool) / - curr_pers_pampd_count; + total_zsize = xv_get_total_size_bytes(cli->xvpool); + zv_mean_zsize = div_u64(total_zsize, + curr_pers_pampd_count); if (zv_mean_zsize > zv_max_mean_zsize) { zcache_mean_compress_poor++; goto out; -- cgit v1.2.3 From d8c778fdf2bcd42e495ca1ca67bca729639352b7 Mon Sep 17 00:00:00 2001 From: Nitin Gupta Date: Thu, 4 Aug 2011 15:05:24 -0700 Subject: zcache: Fix build error when sysfs is not defined Signed-off-by: Nitin Gupta Signed-off-by: Greg Kroah-Hartman --- drivers/staging/zcache/zcache-main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/staging') diff --git a/drivers/staging/zcache/zcache-main.c b/drivers/staging/zcache/zcache-main.c index 2c41c4465e14..855a5bb56a47 100644 --- a/drivers/staging/zcache/zcache-main.c +++ b/drivers/staging/zcache/zcache-main.c @@ -1936,9 +1936,9 @@ __setup("nofrontswap", no_frontswap); static int __init zcache_init(void) { -#ifdef CONFIG_SYSFS int ret = 0; +#ifdef CONFIG_SYSFS ret = sysfs_create_group(mm_kobj, &zcache_attr_group); if (ret) { pr_err("zcache: can't create sysfs\n"); -- cgit v1.2.3 From c3585aa91a25264234c8bd27a4a6823d4e544c2a Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Tue, 16 Aug 2011 14:18:48 +0100 Subject: gma500: kill MIPI interface types Kirill Shutemov found problems with the non-upstream IMG driver where the use of extra DRM encoder/connector types caused random crashes when the DRM layer tried to display their matching name. This removes the MIPI types matching the changes Pauli Nieminen made to the non upstream driver set. As Pauli points out: " MIPI (or DSI) is protocol specification on top of LVDS serial bus. That makes it resonable to call MIPI connectors and encoders LVDS." (and indeed they may also be HDMI convertors or similar when we want to report a more useful to end user result) Signed-off-by: Alan Cox Signed-off-by: Linus Torvalds --- drivers/staging/gma500/mdfld_dsi_dbi.c | 3 ++- drivers/staging/gma500/mdfld_dsi_dbi.h | 3 --- drivers/staging/gma500/mdfld_dsi_dpi.c | 7 ++++++- drivers/staging/gma500/mdfld_dsi_output.c | 4 +++- drivers/staging/gma500/medfield.h | 2 -- drivers/staging/gma500/psb_drv.h | 1 - 6 files changed, 11 insertions(+), 9 deletions(-) (limited to 'drivers/staging') diff --git a/drivers/staging/gma500/mdfld_dsi_dbi.c b/drivers/staging/gma500/mdfld_dsi_dbi.c index 02e17c9c8637..fd211f3467c4 100644 --- a/drivers/staging/gma500/mdfld_dsi_dbi.c +++ b/drivers/staging/gma500/mdfld_dsi_dbi.c @@ -711,10 +711,11 @@ struct mdfld_dsi_encoder *mdfld_dsi_dbi_init(struct drm_device *dev, /* Create drm encoder object */ connector = &dsi_connector->base.base; encoder = &dbi_output->base.base; + /* Review this if we ever get MIPI-HDMI bridges or similar */ drm_encoder_init(dev, encoder, p_funcs->encoder_funcs, - DRM_MODE_ENCODER_MIPI); + DRM_MODE_ENCODER_LVDS); drm_encoder_helper_add(encoder, p_funcs->encoder_helper_funcs); /* Attach to given connector */ diff --git a/drivers/staging/gma500/mdfld_dsi_dbi.h b/drivers/staging/gma500/mdfld_dsi_dbi.h index dc6242c51d0b..f0fa986fd934 100644 --- a/drivers/staging/gma500/mdfld_dsi_dbi.h +++ b/drivers/staging/gma500/mdfld_dsi_dbi.h @@ -42,9 +42,6 @@ #include "mdfld_dsi_output.h" #include "mdfld_output.h" -#define DRM_MODE_ENCODER_MIPI 5 - - /* * DBI encoder which inherits from mdfld_dsi_encoder */ diff --git a/drivers/staging/gma500/mdfld_dsi_dpi.c b/drivers/staging/gma500/mdfld_dsi_dpi.c index 6e03a91e947e..e685f1217baa 100644 --- a/drivers/staging/gma500/mdfld_dsi_dpi.c +++ b/drivers/staging/gma500/mdfld_dsi_dpi.c @@ -777,10 +777,15 @@ struct mdfld_dsi_encoder *mdfld_dsi_dpi_init(struct drm_device *dev, /* Create drm encoder object */ connector = &dsi_connector->base.base; encoder = &dpi_output->base.base; + /* + * On existing hardware this will be a panel of some form, + * if future devices also have HDMI bridges this will need + * revisiting + */ drm_encoder_init(dev, encoder, p_funcs->encoder_funcs, - DRM_MODE_ENCODER_MIPI); + DRM_MODE_ENCODER_LVDS); drm_encoder_helper_add(encoder, p_funcs->encoder_helper_funcs); diff --git a/drivers/staging/gma500/mdfld_dsi_output.c b/drivers/staging/gma500/mdfld_dsi_output.c index 7536095c30a0..9050c0f78b15 100644 --- a/drivers/staging/gma500/mdfld_dsi_output.c +++ b/drivers/staging/gma500/mdfld_dsi_output.c @@ -955,7 +955,9 @@ void mdfld_dsi_output_init(struct drm_device *dev, psb_output->type = (pipe == 0) ? INTEL_OUTPUT_MIPI : INTEL_OUTPUT_MIPI2; connector = &psb_output->base; - drm_connector_init(dev, connector, &mdfld_dsi_connector_funcs, DRM_MODE_CONNECTOR_MIPI); + /* Revisit type if MIPI/HDMI bridges ever appear on Medfield */ + drm_connector_init(dev, connector, &mdfld_dsi_connector_funcs, + DRM_MODE_CONNECTOR_LVDS); drm_connector_helper_add(connector, &mdfld_dsi_connector_helper_funcs); connector->display_info.subpixel_order = SubPixelHorizontalRGB; diff --git a/drivers/staging/gma500/medfield.h b/drivers/staging/gma500/medfield.h index 38165e8367e5..09e9687431f1 100644 --- a/drivers/staging/gma500/medfield.h +++ b/drivers/staging/gma500/medfield.h @@ -21,8 +21,6 @@ * DEALINGS IN THE SOFTWARE. */ -#define DRM_MODE_ENCODER_MIPI 5 - /* Medfield DSI controller registers */ #define MIPIA_DEVICE_READY_REG 0xb000 diff --git a/drivers/staging/gma500/psb_drv.h b/drivers/staging/gma500/psb_drv.h index 72f487a2a1b7..fd4732dd783a 100644 --- a/drivers/staging/gma500/psb_drv.h +++ b/drivers/staging/gma500/psb_drv.h @@ -35,7 +35,6 @@ /* Append new drm mode definition here, align with libdrm definition */ #define DRM_MODE_SCALE_NO_SCALE 2 -#define DRM_MODE_CONNECTOR_MIPI 15 enum { CHIP_PSB_8108 = 0, /* Poulsbo */ -- cgit v1.2.3 From 9818a4775a3ab18b84a689537088b3d72a742130 Mon Sep 17 00:00:00 2001 From: Arend Van Spriel Date: Mon, 8 Aug 2011 15:57:45 +0200 Subject: staging: brcm80211: fix compile error on non-x86 archs since 3.0 kernel Since the arrival of kernel version 3.0 in the staging tree it turns out compile error occurs for sparc64, powerpc, and arm platforms. This patch fixes that issue. Reviewed-by: Pieter-Paul Giesberts Reviewed-by: Henry Ptasinski Signed-off-by: Arend van Spriel Signed-off-by: Greg Kroah-Hartman --- drivers/staging/brcm80211/brcmsmac/types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/staging') diff --git a/drivers/staging/brcm80211/brcmsmac/types.h b/drivers/staging/brcm80211/brcmsmac/types.h index bbf21897ae0e..823b5e4672e2 100644 --- a/drivers/staging/brcm80211/brcmsmac/types.h +++ b/drivers/staging/brcm80211/brcmsmac/types.h @@ -18,6 +18,7 @@ #define _BRCM_TYPES_H_ #include +#include /* Bus types */ #define SI_BUS 0 /* SOC Interconnect */ -- cgit v1.2.3 From 20cc7995fe66ce6417678bb0db6b3d4955fb1ff6 Mon Sep 17 00:00:00 2001 From: Pieter-Paul Giesberts Date: Mon, 8 Aug 2011 15:59:03 +0200 Subject: staging: brcm80211: SPARC build error fix Due to missing memset function declaration. Reviewed-by: Roland Vossen Signed-off-by: Arend van Spriel Signed-off-by: Greg Kroah-Hartman --- drivers/staging/brcm80211/brcmsmac/otp.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/staging') diff --git a/drivers/staging/brcm80211/brcmsmac/otp.c b/drivers/staging/brcm80211/brcmsmac/otp.c index 34253cf37812..4a70180eba5d 100644 --- a/drivers/staging/brcm80211/brcmsmac/otp.c +++ b/drivers/staging/brcm80211/brcmsmac/otp.c @@ -16,6 +16,7 @@ #include #include +#include #include #include -- cgit v1.2.3 From c5f5c4db393837ebb2ae47bf061d70e498f48f8c Mon Sep 17 00:00:00 2001 From: Seth Jennings Date: Wed, 10 Aug 2011 12:56:49 -0500 Subject: staging: zcache: fix crash on high memory swap zcache_put_page() was modified to pass page_address(page) instead of the actual page structure. In combination with the function signature changes to tmem_put() and zcache_pampd_create(), zcache_pampd_create() tries to (re)derive the page structure from the virtual address. However, if the original page is a high memory page (or any unmapped page), this virt_to_page() fails because the page_address() in zcache_put_page() returned NULL. This patch changes zcache_put_page() and zcache_get_page() to pass the page structure instead of the page's virtual address, which may or may not exist. Signed-off-by: Seth Jennings Acked-by: Dan Magenheimer Signed-off-by: Greg Kroah-Hartman --- drivers/staging/zcache/zcache-main.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'drivers/staging') diff --git a/drivers/staging/zcache/zcache-main.c b/drivers/staging/zcache/zcache-main.c index 855a5bb56a47..a3f5162bfedc 100644 --- a/drivers/staging/zcache/zcache-main.c +++ b/drivers/staging/zcache/zcache-main.c @@ -1158,7 +1158,7 @@ static void *zcache_pampd_create(char *data, size_t size, bool raw, int eph, size_t clen; int ret; unsigned long count; - struct page *page = virt_to_page(data); + struct page *page = (struct page *)(data); struct zcache_client *cli = pool->client; uint16_t client_id = get_client_id_from_client(cli); unsigned long zv_mean_zsize; @@ -1227,7 +1227,7 @@ static int zcache_pampd_get_data(char *data, size_t *bufsize, bool raw, int ret = 0; BUG_ON(is_ephemeral(pool)); - zv_decompress(virt_to_page(data), pampd); + zv_decompress((struct page *)(data), pampd); return ret; } @@ -1539,7 +1539,7 @@ static int zcache_put_page(int cli_id, int pool_id, struct tmem_oid *oidp, goto out; if (!zcache_freeze && zcache_do_preload(pool) == 0) { /* preload does preempt_disable on success */ - ret = tmem_put(pool, oidp, index, page_address(page), + ret = tmem_put(pool, oidp, index, (char *)(page), PAGE_SIZE, 0, is_ephemeral(pool)); if (ret < 0) { if (is_ephemeral(pool)) @@ -1572,7 +1572,7 @@ static int zcache_get_page(int cli_id, int pool_id, struct tmem_oid *oidp, pool = zcache_get_pool_by_id(cli_id, pool_id); if (likely(pool != NULL)) { if (atomic_read(&pool->obj_count) > 0) - ret = tmem_get(pool, oidp, index, page_address(page), + ret = tmem_get(pool, oidp, index, (char *)(page), &size, 0, is_ephemeral(pool)); zcache_put_pool(pool); } -- cgit v1.2.3 From 1dcab0875b113a148b6601d87b4e0e3444440339 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 9 Aug 2011 21:01:33 +0300 Subject: Staging: zcache: signedness bug in tmem_get() "ret" needs to be signed for the error handling to work properly. Signed-off-by: Dan Carpenter Acked-by: Dan Magenheimer Signed-off-by: Greg Kroah-Hartman --- drivers/staging/zcache/tmem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/staging') diff --git a/drivers/staging/zcache/tmem.c b/drivers/staging/zcache/tmem.c index 975e34bcd722..1ca66ea9b281 100644 --- a/drivers/staging/zcache/tmem.c +++ b/drivers/staging/zcache/tmem.c @@ -604,7 +604,7 @@ int tmem_get(struct tmem_pool *pool, struct tmem_oid *oidp, uint32_t index, struct tmem_obj *obj; void *pampd; bool ephemeral = is_ephemeral(pool); - uint32_t ret = -1; + int ret = -1; struct tmem_hashbucket *hb; bool free = (get_and_free == 1) || ((get_and_free == 0) && ephemeral); bool lock_held = false; -- cgit v1.2.3 From 048316be72893455f69ad728fa94c26e2e582ba2 Mon Sep 17 00:00:00 2001 From: David Daney Date: Tue, 16 Aug 2011 10:10:56 -0700 Subject: staging: octeon-ethernet: Add missing #includes. I looks like something used to implicitly include linux/interrupt.h, and no longer does. Fix the resulting build error by explicitly including it. Signed-off-by: David Daney Cc: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/staging/octeon/ethernet-rgmii.c | 1 + drivers/staging/octeon/ethernet-spi.c | 1 + 2 files changed, 2 insertions(+) (limited to 'drivers/staging') diff --git a/drivers/staging/octeon/ethernet-rgmii.c b/drivers/staging/octeon/ethernet-rgmii.c index 9c0d2936e486..c3d73f8431ae 100644 --- a/drivers/staging/octeon/ethernet-rgmii.c +++ b/drivers/staging/octeon/ethernet-rgmii.c @@ -26,6 +26,7 @@ **********************************************************************/ #include #include +#include #include #include #include diff --git a/drivers/staging/octeon/ethernet-spi.c b/drivers/staging/octeon/ethernet-spi.c index 970825421884..d0e2d514968a 100644 --- a/drivers/staging/octeon/ethernet-spi.c +++ b/drivers/staging/octeon/ethernet-spi.c @@ -26,6 +26,7 @@ **********************************************************************/ #include #include +#include #include #include -- cgit v1.2.3 From 1b965f1891eac2d8583b5248ef0bcbc91c201e27 Mon Sep 17 00:00:00 2001 From: Omar Ramirez Luna Date: Wed, 24 Aug 2011 15:07:04 -0500 Subject: staging: tidspbridge: fix compilation on dsp clock functions Seen on v3.1-rc3, patch: omap: mcbsp: Drop in-driver transfer support bafe2721a0fbd1cc1af04384133684f660f3658e Removed code that now cause tidspbridge to break while compiling. Signed-off-by: Omar Ramirez Luna Signed-off-by: Greg Kroah-Hartman --- drivers/staging/tidspbridge/core/dsp-clock.c | 1 - 1 file changed, 1 deletion(-) (limited to 'drivers/staging') diff --git a/drivers/staging/tidspbridge/core/dsp-clock.c b/drivers/staging/tidspbridge/core/dsp-clock.c index 589a0554332e..3d1279c424a8 100644 --- a/drivers/staging/tidspbridge/core/dsp-clock.c +++ b/drivers/staging/tidspbridge/core/dsp-clock.c @@ -209,7 +209,6 @@ int dsp_clk_enable(enum dsp_clk_id clk_id) break; #ifdef CONFIG_OMAP_MCBSP case MCBSP_CLK: - omap_mcbsp_set_io_type(MCBSP_ID(clk_id), OMAP_MCBSP_POLL_IO); omap_mcbsp_request(MCBSP_ID(clk_id)); omap2_mcbsp_set_clks_src(MCBSP_ID(clk_id), MCBSP_CLKS_PAD_SRC); break; -- cgit v1.2.3 From c19cc78efe922e86da7ba694dbfc4be066dd7eb4 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 19 Sep 2011 16:05:10 -0700 Subject: staging: fix comedi build when ISA_DMA_API is enabled but COMEDI_PCI is not enabled Fix build when CONFIG_ISA_DMA_API is enabled but CONFIG_COMEDI_PCI[_DRIVERS] is not enabled. Fixes these build errors: drivers/staging/comedi/drivers/ni_labpc.c: In function 'labpc_ai_cmd': drivers/staging/comedi/drivers/ni_labpc.c:1351: error: implicit declaration of function 'labpc_suggest_transfer_size' drivers/staging/comedi/drivers/ni_labpc.c: At top level: drivers/staging/comedi/drivers/ni_labpc.c:1802: error: conflicting types for 'labpc_suggest_transfer_size' drivers/staging/comedi/drivers/ni_labpc.c:1351: note: previous implicit declaration of 'labpc_suggest_transfer_size' was here Signed-off-by: Randy Dunlap Signed-off-by: Greg Kroah-Hartman Signed-off-by: Linus Torvalds --- drivers/staging/comedi/drivers/ni_labpc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'drivers/staging') diff --git a/drivers/staging/comedi/drivers/ni_labpc.c b/drivers/staging/comedi/drivers/ni_labpc.c index 6859af0778cf..7611def97d06 100644 --- a/drivers/staging/comedi/drivers/ni_labpc.c +++ b/drivers/staging/comedi/drivers/ni_labpc.c @@ -241,8 +241,10 @@ static int labpc_eeprom_write_insn(struct comedi_device *dev, struct comedi_insn *insn, unsigned int *data); static void labpc_adc_timing(struct comedi_device *dev, struct comedi_cmd *cmd); -#ifdef CONFIG_COMEDI_PCI +#ifdef CONFIG_ISA_DMA_API static unsigned int labpc_suggest_transfer_size(struct comedi_cmd cmd); +#endif +#ifdef CONFIG_COMEDI_PCI static int labpc_find_device(struct comedi_device *dev, int bus, int slot); #endif static int labpc_dio_mem_callback(int dir, int port, int data, -- cgit v1.2.3 From 80976804f501303a34a76e925119393722596dca Mon Sep 17 00:00:00 2001 From: Seth Jennings Date: Tue, 20 Sep 2011 13:09:56 -0700 Subject: staging: zcache: fix cleancache crash After commit c5f5c4db3938 ("staging: zcache: fix crash on high memory swap") cleancache crashes on the first successful get. This was caused by a remaining virt_to_page() call in zcache_pampd_get_data_and_free() that only gets run in the cleancache path. The patch converts the virt_to_page() to struct page casting like was done for other instances in c5f5c4db3938. Signed-off-by: Seth Jennings Tested-By: Valdis Kletnieks Acked-by: Dan Magenheimer Signed-off-by: Greg Kroah-Hartman Signed-off-by: Linus Torvalds --- drivers/staging/zcache/zcache-main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/staging') diff --git a/drivers/staging/zcache/zcache-main.c b/drivers/staging/zcache/zcache-main.c index a3f5162bfedc..462fbc20561f 100644 --- a/drivers/staging/zcache/zcache-main.c +++ b/drivers/staging/zcache/zcache-main.c @@ -1242,7 +1242,7 @@ static int zcache_pampd_get_data_and_free(char *data, size_t *bufsize, bool raw, int ret = 0; BUG_ON(!is_ephemeral(pool)); - zbud_decompress(virt_to_page(data), pampd); + zbud_decompress((struct page *)(data), pampd); zbud_free_and_delist((struct zbud_hdr *)pampd); atomic_dec(&zcache_curr_eph_pampd_count); return ret; -- cgit v1.2.3 From a4be637b34a543af5b5421a8ee0ee04d30f5f58e Mon Sep 17 00:00:00 2001 From: "Roy.Li" Date: Mon, 26 Sep 2011 09:08:00 +0800 Subject: staging/octeon: Software should check the checksum of no tcp/udp packets Icmp packets with wrong checksum are never dropped since skb->ip_summed is set to CHECKSUM_UNNECESSARY. When icmp packets with wrong checksum pass through the octeon net driver, the not_IP, IP_exc, L4_error hardware indicators show no error. so the driver sets CHECKSUM_UNNECESSARY on skb->ip_summed. L4_error only works for TCP/UDP, not for ICMP. Signed-off-by: Roy.Li To: linux-mips@linux-mips.org Cc: netdev@vger.kernel.org Cc: ralf@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/2798/ Acked-by: David Daney Cc: Greg KH --- drivers/staging/octeon/ethernet-rx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/staging') diff --git a/drivers/staging/octeon/ethernet-rx.c b/drivers/staging/octeon/ethernet-rx.c index 1a7c19ae766f..8b307b428791 100644 --- a/drivers/staging/octeon/ethernet-rx.c +++ b/drivers/staging/octeon/ethernet-rx.c @@ -411,7 +411,8 @@ static int cvm_oct_napi_poll(struct napi_struct *napi, int budget) skb->protocol = eth_type_trans(skb, dev); skb->dev = dev; - if (unlikely(work->word2.s.not_IP || work->word2.s.IP_exc || work->word2.s.L4_error)) + if (unlikely(work->word2.s.not_IP || work->word2.s.IP_exc || + work->word2.s.L4_error || !work->word2.s.tcp_or_udp)) skb->ip_summed = CHECKSUM_NONE; else skb->ip_summed = CHECKSUM_UNNECESSARY; -- cgit v1.2.3