Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751648Ab2F0ERv (ORCPT ); Wed, 27 Jun 2012 00:17:51 -0400 Received: from e1.ny.us.ibm.com ([32.97.182.141]:38371 "EHLO e1.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750714Ab2F0ERr (ORCPT ); Wed, 27 Jun 2012 00:17:47 -0400 From: John Stultz To: LKML Cc: John Stultz , Andrew Morton , Android Kernel Team , Robert Love , Mel Gorman , Hugh Dickins , Dave Hansen , Rik van Riel , Dmitry Adamushko , Dave Chinner , Neil Brown , Andrea Righi , "Aneesh Kumar K.V" , Taras Glek , Mike Hommey , Jan Kara , KOSAKI Motohiro , Michel Lespinasse , Minchan Kim , "linux-mm@kvack.org" Subject: [PATCH 3/5] [RFC] ashmem: Convert ashmem to use volatile ranges Date: Wed, 27 Jun 2012 00:17:13 -0400 Message-Id: <1340770635-9909-4-git-send-email-john.stultz@linaro.org> X-Mailer: git-send-email 1.7.9.5 In-Reply-To: <1340770635-9909-1-git-send-email-john.stultz@linaro.org> References: <1340770635-9909-1-git-send-email-john.stultz@linaro.org> X-Content-Scanned: Fidelis XPS MAILER x-cbid: 12062704-6078-0000-0000-00000C9344B6 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 13973 Lines: 470 Rework of my first pass attempt at getting ashmem to utilize the volatile range code, now using the fallocate interface. In this implementaiton GET_PIN_STATUS is unimplemented, due to the fact that adding a ISVOLATILE check wasn't considered terribly useful in earlier reviews. It would be trivial to re-add that functionality, but I wanted to check w/ the Android developers to see how often GET_PIN_STATUS is actually used? Similarly the ashmem PURGE_ALL_CACHES ioctl does not function, as the volatile range purging is no longer directly under its control. CC: Andrew Morton CC: Android Kernel Team CC: Robert Love CC: Mel Gorman CC: Hugh Dickins CC: Dave Hansen CC: Rik van Riel CC: Dmitry Adamushko CC: Dave Chinner CC: Neil Brown CC: Andrea Righi CC: Aneesh Kumar K.V CC: Taras Glek CC: Mike Hommey CC: Jan Kara CC: KOSAKI Motohiro CC: Michel Lespinasse CC: Minchan Kim CC: linux-mm@kvack.org Signed-off-by: John Stultz --- drivers/staging/android/ashmem.c | 331 ++------------------------------------ 1 file changed, 9 insertions(+), 322 deletions(-) diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c index e84dbec..9e8fe37 100644 --- a/drivers/staging/android/ashmem.c +++ b/drivers/staging/android/ashmem.c @@ -50,26 +50,6 @@ struct ashmem_area { }; /* - * ashmem_range - represents an interval of unpinned (evictable) pages - * Lifecycle: From unpin to pin - * Locking: Protected by `ashmem_mutex' - */ -struct ashmem_range { - struct list_head lru; /* entry in LRU list */ - struct list_head unpinned; /* entry in its area's unpinned list */ - struct ashmem_area *asma; /* associated area */ - size_t pgstart; /* starting page, inclusive */ - size_t pgend; /* ending page, inclusive */ - unsigned int purged; /* ASHMEM_NOT or ASHMEM_WAS_PURGED */ -}; - -/* LRU list of unpinned pages, protected by ashmem_mutex */ -static LIST_HEAD(ashmem_lru_list); - -/* Count of pages on our LRU list, protected by ashmem_mutex */ -static unsigned long lru_count; - -/* * ashmem_mutex - protects the list of and each individual ashmem_area * * Lock Ordering: ashmex_mutex -> i_mutex -> i_alloc_sem @@ -77,102 +57,9 @@ static unsigned long lru_count; static DEFINE_MUTEX(ashmem_mutex); static struct kmem_cache *ashmem_area_cachep __read_mostly; -static struct kmem_cache *ashmem_range_cachep __read_mostly; - -#define range_size(range) \ - ((range)->pgend - (range)->pgstart + 1) - -#define range_on_lru(range) \ - ((range)->purged == ASHMEM_NOT_PURGED) - -#define page_range_subsumes_range(range, start, end) \ - (((range)->pgstart >= (start)) && ((range)->pgend <= (end))) - -#define page_range_subsumed_by_range(range, start, end) \ - (((range)->pgstart <= (start)) && ((range)->pgend >= (end))) - -#define page_in_range(range, page) \ - (((range)->pgstart <= (page)) && ((range)->pgend >= (page))) - -#define page_range_in_range(range, start, end) \ - (page_in_range(range, start) || page_in_range(range, end) || \ - page_range_subsumes_range(range, start, end)) - -#define range_before_page(range, page) \ - ((range)->pgend < (page)) #define PROT_MASK (PROT_EXEC | PROT_READ | PROT_WRITE) -static inline void lru_add(struct ashmem_range *range) -{ - list_add_tail(&range->lru, &ashmem_lru_list); - lru_count += range_size(range); -} - -static inline void lru_del(struct ashmem_range *range) -{ - list_del(&range->lru); - lru_count -= range_size(range); -} - -/* - * range_alloc - allocate and initialize a new ashmem_range structure - * - * 'asma' - associated ashmem_area - * 'prev_range' - the previous ashmem_range in the sorted asma->unpinned list - * 'purged' - initial purge value (ASMEM_NOT_PURGED or ASHMEM_WAS_PURGED) - * 'start' - starting page, inclusive - * 'end' - ending page, inclusive - * - * Caller must hold ashmem_mutex. - */ -static int range_alloc(struct ashmem_area *asma, - struct ashmem_range *prev_range, unsigned int purged, - size_t start, size_t end) -{ - struct ashmem_range *range; - - range = kmem_cache_zalloc(ashmem_range_cachep, GFP_KERNEL); - if (unlikely(!range)) - return -ENOMEM; - - range->asma = asma; - range->pgstart = start; - range->pgend = end; - range->purged = purged; - - list_add_tail(&range->unpinned, &prev_range->unpinned); - - if (range_on_lru(range)) - lru_add(range); - - return 0; -} - -static void range_del(struct ashmem_range *range) -{ - list_del(&range->unpinned); - if (range_on_lru(range)) - lru_del(range); - kmem_cache_free(ashmem_range_cachep, range); -} - -/* - * range_shrink - shrinks a range - * - * Caller must hold ashmem_mutex. - */ -static inline void range_shrink(struct ashmem_range *range, - size_t start, size_t end) -{ - size_t pre = range_size(range); - - range->pgstart = start; - range->pgend = end; - - if (range_on_lru(range)) - lru_count -= pre - range_size(range); -} static int ashmem_open(struct inode *inode, struct file *file) { @@ -198,12 +85,6 @@ static int ashmem_open(struct inode *inode, struct file *file) static int ashmem_release(struct inode *ignored, struct file *file) { struct ashmem_area *asma = file->private_data; - struct ashmem_range *range, *next; - - mutex_lock(&ashmem_mutex); - list_for_each_entry_safe(range, next, &asma->unpinned_list, unpinned) - range_del(range); - mutex_unlock(&ashmem_mutex); if (asma->file) fput(asma->file); @@ -337,56 +218,6 @@ out: return ret; } -/* - * ashmem_shrink - our cache shrinker, called from mm/vmscan.c :: shrink_slab - * - * 'nr_to_scan' is the number of objects (pages) to prune, or 0 to query how - * many objects (pages) we have in total. - * - * 'gfp_mask' is the mask of the allocation that got us into this mess. - * - * Return value is the number of objects (pages) remaining, or -1 if we cannot - * proceed without risk of deadlock (due to gfp_mask). - * - * We approximate LRU via least-recently-unpinned, jettisoning unpinned partial - * chunks of ashmem regions LRU-wise one-at-a-time until we hit 'nr_to_scan' - * pages freed. - */ -static int ashmem_shrink(struct shrinker *s, struct shrink_control *sc) -{ - struct ashmem_range *range, *next; - - /* We might recurse into filesystem code, so bail out if necessary */ - if (sc->nr_to_scan && !(sc->gfp_mask & __GFP_FS)) - return -1; - if (!sc->nr_to_scan) - return lru_count; - - mutex_lock(&ashmem_mutex); - list_for_each_entry_safe(range, next, &ashmem_lru_list, lru) { - loff_t start = range->pgstart * PAGE_SIZE; - loff_t end = (range->pgend + 1) * PAGE_SIZE; - - do_fallocate(range->asma->file, - FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, - start, end - start); - range->purged = ASHMEM_WAS_PURGED; - lru_del(range); - - sc->nr_to_scan -= range_size(range); - if (sc->nr_to_scan <= 0) - break; - } - mutex_unlock(&ashmem_mutex); - - return lru_count; -} - -static struct shrinker ashmem_shrinker = { - .shrink = ashmem_shrink, - .seeks = DEFAULT_SEEKS * 4, -}; - static int set_prot_mask(struct ashmem_area *asma, unsigned long prot) { int ret = 0; @@ -459,136 +290,10 @@ static int get_name(struct ashmem_area *asma, void __user *name) return ret; } -/* - * ashmem_pin - pin the given ashmem region, returning whether it was - * previously purged (ASHMEM_WAS_PURGED) or not (ASHMEM_NOT_PURGED). - * - * Caller must hold ashmem_mutex. - */ -static int ashmem_pin(struct ashmem_area *asma, size_t pgstart, size_t pgend) -{ - struct ashmem_range *range, *next; - int ret = ASHMEM_NOT_PURGED; - - list_for_each_entry_safe(range, next, &asma->unpinned_list, unpinned) { - /* moved past last applicable page; we can short circuit */ - if (range_before_page(range, pgstart)) - break; - - /* - * The user can ask us to pin pages that span multiple ranges, - * or to pin pages that aren't even unpinned, so this is messy. - * - * Four cases: - * 1. The requested range subsumes an existing range, so we - * just remove the entire matching range. - * 2. The requested range overlaps the start of an existing - * range, so we just update that range. - * 3. The requested range overlaps the end of an existing - * range, so we just update that range. - * 4. The requested range punches a hole in an existing range, - * so we have to update one side of the range and then - * create a new range for the other side. - */ - if (page_range_in_range(range, pgstart, pgend)) { - ret |= range->purged; - - /* Case #1: Easy. Just nuke the whole thing. */ - if (page_range_subsumes_range(range, pgstart, pgend)) { - range_del(range); - continue; - } - - /* Case #2: We overlap from the start, so adjust it */ - if (range->pgstart >= pgstart) { - range_shrink(range, pgend + 1, range->pgend); - continue; - } - - /* Case #3: We overlap from the rear, so adjust it */ - if (range->pgend <= pgend) { - range_shrink(range, range->pgstart, pgstart-1); - continue; - } - - /* - * Case #4: We eat a chunk out of the middle. A bit - * more complicated, we allocate a new range for the - * second half and adjust the first chunk's endpoint. - */ - range_alloc(asma, range, range->purged, - pgend + 1, range->pgend); - range_shrink(range, range->pgstart, pgstart - 1); - break; - } - } - - return ret; -} - -/* - * ashmem_unpin - unpin the given range of pages. Returns zero on success. - * - * Caller must hold ashmem_mutex. - */ -static int ashmem_unpin(struct ashmem_area *asma, size_t pgstart, size_t pgend) -{ - struct ashmem_range *range, *next; - unsigned int purged = ASHMEM_NOT_PURGED; - -restart: - list_for_each_entry_safe(range, next, &asma->unpinned_list, unpinned) { - /* short circuit: this is our insertion point */ - if (range_before_page(range, pgstart)) - break; - - /* - * The user can ask us to unpin pages that are already entirely - * or partially pinned. We handle those two cases here. - */ - if (page_range_subsumed_by_range(range, pgstart, pgend)) - return 0; - if (page_range_in_range(range, pgstart, pgend)) { - pgstart = min_t(size_t, range->pgstart, pgstart), - pgend = max_t(size_t, range->pgend, pgend); - purged |= range->purged; - range_del(range); - goto restart; - } - } - - return range_alloc(asma, range, purged, pgstart, pgend); -} - -/* - * ashmem_get_pin_status - Returns ASHMEM_IS_UNPINNED if _any_ pages in the - * given interval are unpinned and ASHMEM_IS_PINNED otherwise. - * - * Caller must hold ashmem_mutex. - */ -static int ashmem_get_pin_status(struct ashmem_area *asma, size_t pgstart, - size_t pgend) -{ - struct ashmem_range *range; - int ret = ASHMEM_IS_PINNED; - - list_for_each_entry(range, &asma->unpinned_list, unpinned) { - if (range_before_page(range, pgstart)) - break; - if (page_range_in_range(range, pgstart, pgend)) { - ret = ASHMEM_IS_UNPINNED; - break; - } - } - - return ret; -} - static int ashmem_pin_unpin(struct ashmem_area *asma, unsigned long cmd, void __user *p) { struct ashmem_pin pin; - size_t pgstart, pgend; int ret = -EINVAL; if (unlikely(!asma->file)) @@ -610,20 +315,24 @@ static int ashmem_pin_unpin(struct ashmem_area *asma, unsigned long cmd, if (unlikely(PAGE_ALIGN(asma->size) < pin.offset + pin.len)) return -EINVAL; - pgstart = pin.offset / PAGE_SIZE; - pgend = pgstart + (pin.len / PAGE_SIZE) - 1; mutex_lock(&ashmem_mutex); switch (cmd) { case ASHMEM_PIN: - ret = ashmem_pin(asma, pgstart, pgend); + ret = do_fallocate(asma->file, FALLOC_FL_MARK_VOLATILE, + pin.offset, pin.len); break; case ASHMEM_UNPIN: - ret = ashmem_unpin(asma, pgstart, pgend); + ret = do_fallocate(asma->file, FALLOC_FL_UNMARK_VOLATILE, + pin.offset, pin.len); break; case ASHMEM_GET_PIN_STATUS: - ret = ashmem_get_pin_status(asma, pgstart, pgend); + /* + * XXX - volatile ranges currently don't provide status, + * due to questionable utility + */ + ret = -EINVAL; break; } @@ -667,15 +376,6 @@ static long ashmem_ioctl(struct file *file, unsigned int cmd, unsigned long arg) break; case ASHMEM_PURGE_ALL_CACHES: ret = -EPERM; - if (capable(CAP_SYS_ADMIN)) { - struct shrink_control sc = { - .gfp_mask = GFP_KERNEL, - .nr_to_scan = 0, - }; - ret = ashmem_shrink(&ashmem_shrinker, &sc); - sc.nr_to_scan = ret; - ashmem_shrink(&ashmem_shrinker, &sc); - } break; } @@ -711,22 +411,12 @@ static int __init ashmem_init(void) return -ENOMEM; } - ashmem_range_cachep = kmem_cache_create("ashmem_range_cache", - sizeof(struct ashmem_range), - 0, 0, NULL); - if (unlikely(!ashmem_range_cachep)) { - printk(KERN_ERR "ashmem: failed to create slab cache\n"); - return -ENOMEM; - } - ret = misc_register(&ashmem_misc); if (unlikely(ret)) { printk(KERN_ERR "ashmem: failed to register misc device!\n"); return ret; } - register_shrinker(&ashmem_shrinker); - printk(KERN_INFO "ashmem: initialized\n"); return 0; @@ -736,13 +426,10 @@ static void __exit ashmem_exit(void) { int ret; - unregister_shrinker(&ashmem_shrinker); - ret = misc_deregister(&ashmem_misc); if (unlikely(ret)) printk(KERN_ERR "ashmem: failed to unregister misc device!\n"); - kmem_cache_destroy(ashmem_range_cachep); kmem_cache_destroy(ashmem_area_cachep); printk(KERN_INFO "ashmem: unloaded\n"); -- 1.7.9.5 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/