| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20161015165405.GA31568@infradead.org>
Date: Sat, 15 Oct 2016 09:54:05 -0700
From: Christoph Hellwig <hch@...radead.org>
To: Joel Fernandes <joelaf@...gle.com>
Cc: linux-kernel@...r.kernel.org, linux-rt-users@...r.kernel.org,
Chris Wilson <chris@...is-wilson.co.uk>,
Jisheng Zhang <jszhang@...vell.com>,
John Dias <joaodias@...gle.com>,
Andrew Morton <akpm@...ux-foundation.org>,
"open list:MEMORY MANAGEMENT" <linux-mm@...ck.org>
Subject: Re: [PATCH v3] mm: vmalloc: Replace purge_lock spinlock with atomic
refcount
And now with a proper changelog, and the accidentall dropped call to
flush_tlb_kernel_range reinstated:
---
>From f720cc324498ab5e7931c7ccb1653bd9b8cddc63 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@....de>
Date: Sat, 15 Oct 2016 18:39:44 +0200
Subject: mm: rewrite __purge_vmap_area_lazy
Remove the purge lock, there was nothing left to be protected:
- purge_fragmented_blocks seems to has it's own local protection.
- all handling of of valist is implicity protected by the atomic
list deletion in llist_del_all, which also avoids multiple callers
stomping on each other here.
- the manipulation of vmap_lazy_nr already is atomic
- flush_tlb_kernel_range does not require any synchronization
- the calls to __free_vmap_area are sychronized by vmap_area_lock
- *start and *end always point to on-stack variables, never mind
that the caller never looks at the updated values anyway.
Once that is done we can remove the sync argument by moving the calls
to purge_fragmented_blocks_allcpus into the callers that need it,
and the forced flush_tlb_kernel_range call even if no entries were
found into the one caller that cares, and we can also pass start and
end by reference.
Signed-off-by: Christoph Hellwig <hch@....de>
---
mm/vmalloc.c | 84 +++++++++++++++++++-----------------------------------------
1 file changed, 26 insertions(+), 58 deletions(-)
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index f2481cb..c3ca992 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -613,82 +613,44 @@ void set_iounmap_nonlazy(void)
atomic_set(&vmap_lazy_nr, lazy_max_pages()+1);
}
-/*
- * Purges all lazily-freed vmap areas.
- *
- * If sync is 0 then don't purge if there is already a purge in progress.
- * If force_flush is 1, then flush kernel TLBs between *start and *end even
- * if we found no lazy vmap areas to unmap (callers can use this to optimise
- * their own TLB flushing).
- * Returns with *start = min(*start, lowest purged address)
- * *end = max(*end, highest purged address)
- */
-static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end,
- int sync, int force_flush)
+static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end)
{
- static DEFINE_SPINLOCK(purge_lock);
struct llist_node *valist;
struct vmap_area *va;
struct vmap_area *n_va;
int nr = 0;
- /*
- * If sync is 0 but force_flush is 1, we'll go sync anyway but callers
- * should not expect such behaviour. This just simplifies locking for
- * the case that isn't actually used at the moment anyway.
- */
- if (!sync && !force_flush) {
- if (!spin_trylock(&purge_lock))
- return;
- } else
- spin_lock(&purge_lock);
-
- if (sync)
- purge_fragmented_blocks_allcpus();
-
valist = llist_del_all(&vmap_purge_list);
llist_for_each_entry(va, valist, purge_list) {
- if (va->va_start < *start)
- *start = va->va_start;
- if (va->va_end > *end)
- *end = va->va_end;
+ if (va->va_start < start)
+ start = va->va_start;
+ if (va->va_end > end)
+ end = va->va_end;
nr += (va->va_end - va->va_start) >> PAGE_SHIFT;
}
- if (nr)
- atomic_sub(nr, &vmap_lazy_nr);
-
- if (nr || force_flush)
- flush_tlb_kernel_range(*start, *end);
-
- if (nr) {
- spin_lock(&vmap_area_lock);
- llist_for_each_entry_safe(va, n_va, valist, purge_list)
- __free_vmap_area(va);
- spin_unlock(&vmap_area_lock);
- }
- spin_unlock(&purge_lock);
-}
+ if (!nr)
+ return false;
-/*
- * Kick off a purge of the outstanding lazy areas. Don't bother if somebody
- * is already purging.
- */
-static void try_purge_vmap_area_lazy(void)
-{
- unsigned long start = ULONG_MAX, end = 0;
+ atomic_sub(nr, &vmap_lazy_nr);
+ flush_tlb_kernel_range(start, end);
- __purge_vmap_area_lazy(&start, &end, 0, 0);
+ spin_lock(&vmap_area_lock);
+ llist_for_each_entry_safe(va, n_va, valist, purge_list)
+ __free_vmap_area(va);
+ spin_unlock(&vmap_area_lock);
+ return true;
}
/*
- * Kick off a purge of the outstanding lazy areas.
+ * Kick off a purge of the outstanding lazy areas, including the fragment
+ * blocks on the per-cpu lists.
*/
static void purge_vmap_area_lazy(void)
{
- unsigned long start = ULONG_MAX, end = 0;
+ purge_fragmented_blocks_allcpus();
+ __purge_vmap_area_lazy(ULONG_MAX, 0);
- __purge_vmap_area_lazy(&start, &end, 1, 0);
}
/*
@@ -706,8 +668,12 @@ static void free_vmap_area_noflush(struct vmap_area *va)
/* After this point, we may free va at any time */
llist_add(&va->purge_list, &vmap_purge_list);
+ /*
+ * Kick off a purge of the outstanding lazy areas. Don't bother to
+ * to purge the per-cpu lists of fragmented blocks.
+ */
if (unlikely(nr_lazy > lazy_max_pages()))
- try_purge_vmap_area_lazy();
+ __purge_vmap_area_lazy(ULONG_MAX, 0);
}
/*
@@ -1094,7 +1060,9 @@ void vm_unmap_aliases(void)
rcu_read_unlock();
}
- __purge_vmap_area_lazy(&start, &end, 1, flush);
+ purge_fragmented_blocks_allcpus();
+ if (!__purge_vmap_area_lazy(start, end) && flush)
+ flush_tlb_kernel_range(start, end);
}
EXPORT_SYMBOL_GPL(vm_unmap_aliases);
--
2.1.4
Powered by blists - more mailing lists