diff options
author | Nicolai Stange <nicstange@gmail.com> | 2015-08-06 15:46:16 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-08-07 04:39:40 +0300 |
commit | d3cd131d935ab3bab700491edbbd7cad4040ce50 (patch) | |
tree | 50d9755ae9dfbb3105761b3f87e37fe9454d7a1b /mm | |
parent | 7ace99170789bc53cbb7e9e352d7a3851208fbcf (diff) |
mm, meminit: replace rwsem with completion
Commit 0e1cc95b4cc7 ("mm: meminit: finish initialisation of struct pages
before basic setup") introduced a rwsem to signal completion of the
initialization workers.
Lockdep complains about possible recursive locking:
=============================================
[ INFO: possible recursive locking detected ]
4.1.0-12802-g1dc51b8 #3 Not tainted
---------------------------------------------
swapper/0/1 is trying to acquire lock:
(pgdat_init_rwsem){++++.+},
at: [<ffffffff8424c7fb>] page_alloc_init_late+0xc7/0xe6
but task is already holding lock:
(pgdat_init_rwsem){++++.+},
at: [<ffffffff8424c772>] page_alloc_init_late+0x3e/0xe6
Replace the rwsem by a completion together with an atomic
"outstanding work counter".
[peterz@infradead.org: Barrier removal on the grounds of being pointless]
[mgorman@suse.de: Applied review feedback]
Signed-off-by: Nicolai Stange <nicstange@gmail.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Alex Ng <alexng@microsoft.com>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r-- | mm/page_alloc.c | 22 |
1 files changed, 15 insertions, 7 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ea0e6a6e7a11..322628278ae4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -18,7 +18,6 @@ #include <linux/mm.h> #include <linux/swap.h> #include <linux/interrupt.h> -#include <linux/rwsem.h> #include <linux/pagemap.h> #include <linux/jiffies.h> #include <linux/bootmem.h> @@ -1060,7 +1059,15 @@ static void __init deferred_free_range(struct page *page, __free_pages_boot_core(page, pfn, 0); } -static __initdata DECLARE_RWSEM(pgdat_init_rwsem); +/* Completion tracking for deferred_init_memmap() threads */ +static atomic_t pgdat_init_n_undone __initdata; +static __initdata DECLARE_COMPLETION(pgdat_init_all_done_comp); + +static inline void __init pgdat_init_report_one_done(void) +{ + if (atomic_dec_and_test(&pgdat_init_n_undone)) + complete(&pgdat_init_all_done_comp); +} /* Initialise remaining memory on a node */ static int __init deferred_init_memmap(void *data) @@ -1077,7 +1084,7 @@ static int __init deferred_init_memmap(void *data) const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); if (first_init_pfn == ULONG_MAX) { - up_read(&pgdat_init_rwsem); + pgdat_init_report_one_done(); return 0; } @@ -1177,7 +1184,8 @@ free_range: pr_info("node %d initialised, %lu pages in %ums\n", nid, nr_pages, jiffies_to_msecs(jiffies - start)); - up_read(&pgdat_init_rwsem); + + pgdat_init_report_one_done(); return 0; } @@ -1185,14 +1193,14 @@ void __init page_alloc_init_late(void) { int nid; + /* There will be num_node_state(N_MEMORY) threads */ + atomic_set(&pgdat_init_n_undone, num_node_state(N_MEMORY)); for_each_node_state(nid, N_MEMORY) { - down_read(&pgdat_init_rwsem); kthread_run(deferred_init_memmap, NODE_DATA(nid), "pgdatinit%d", nid); } /* Block until all are initialised */ - down_write(&pgdat_init_rwsem); - up_write(&pgdat_init_rwsem); + wait_for_completion(&pgdat_init_all_done_comp); } #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ |