Messages in this thread Patch in this message | | | Date | Sun, 26 Feb 2006 22:49:47 +0300 | From | Oleg Nesterov <> | Subject | [PATCH] readahead: ->prev_page can overrun the ahead window |
| |
If get_next_ra_size() does not grow fast enough, ->prev_page can overrun the ahead window. This means the caller will read the pages from ->ahead_start + ->ahead_size to ->prev_page synchronously.
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
--- 2.6.16-rc3/mm/readahead.c~ 2006-02-27 00:11:13.070848680 +0300 +++ 2.6.16-rc3/mm/readahead.c 2006-02-27 00:53:17.881019192 +0300 @@ -52,13 +52,24 @@ static inline unsigned long get_min_read return (VM_MIN_READAHEAD * 1024) / PAGE_CACHE_SIZE; } +static inline void reset_ahead_window(struct file_ra_state *ra) +{ + /* + * ... but preserve ahead_start + ahead_size value, + * see 'recheck:' label in page_cache_readahead(). + * Note: We never use ->ahead_size as rvalue without + * checking ->ahead_start != 0 first. + */ + ra->ahead_size += ra->ahead_start; + ra->ahead_start = 0; +} + static inline void ra_off(struct file_ra_state *ra) { ra->start = 0; ra->flags = 0; ra->size = 0; - ra->ahead_start = 0; - ra->ahead_size = 0; + reset_ahead_window(ra); return; } @@ -426,8 +437,7 @@ static int make_ahead_window(struct addr * congestion. The ahead window will any way be closed * in case we failed due to excessive page cache hits. */ - ra->ahead_start = 0; - ra->ahead_size = 0; + reset_ahead_window(ra); } return ret; @@ -520,11 +530,11 @@ page_cache_readahead(struct address_spac * If we get here we are doing sequential IO and this was not the first * occurence (ie we have an existing window) */ - if (ra->ahead_start == 0) { /* no ahead window yet */ if (!make_ahead_window(mapping, filp, ra, 0)) - goto out; + goto recheck; } + /* * Already have an ahead window, check if we crossed into it. * If so, shift windows and issue a new ahead window. @@ -536,6 +546,10 @@ page_cache_readahead(struct address_spac ra->start = ra->ahead_start; ra->size = ra->ahead_size; make_ahead_window(mapping, filp, ra, 0); +recheck: + /* prev_page shouldn't overrun the ahead window */ + ra->prev_page = min(ra->prev_page, + ra->ahead_start + ra->ahead_size - 1); } out: - 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/
| |