mm: turn vmap_purge_lock into a mutex (f9e09977) · Commits · 戴 / test

The purge_lock spinlock causes high latencies with non RT kernel. This has been reported multiple times on lkml [1] [2] and affects applications like audio. This patch replaces it with a mutex to allow preemption while holding the lock. Thanks to Joel Fernandes for the detailed report and analysis as well as an earlier attempt at fixing this issue. [1] http://lists.openwall.net/linux-kernel/2016/03/23/29 [2] https://lkml.org/lkml/2016/10/9/59 Link: http://lkml.kernel.org/r/1479474236-4139-10-git-send-email-hch@lst.de Signed-off-by:

Christoph Hellwig <hch@lst.de> Tested-by:

Jisheng Zhang <jszhang@marvell.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Joel Fernandes <joelaf@google.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: John Dias <joaodias@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@elte.hu> Signed-off-by:

Andrew Morton <akpm@linux-foundation.org> Signed-off-by:

Linus Torvalds <torvalds@linux-foundation.org>

mm/vmalloc.c

+7 −7

Original line number	Diff line number	Diff line
		@@ -606,7 +606,7 @@ static atomic_t vmap_lazy_nr = ATOMIC_INIT(0);
		* by this look, but we want to avoid concurrent calls for performance
		* reasons and to make the pcpu_get_vm_areas more deterministic.
		*/
		static DEFINE_SPINLOCK(vmap_purge_lock);
		static DEFINE_MUTEX(vmap_purge_lock);

		/* for per-CPU blocks */
		static void purge_fragmented_blocks_allcpus(void);
		@@ -660,9 +660,9 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end)
		*/
		static void try_purge_vmap_area_lazy(void)
		{
		if (spin_trylock(&vmap_purge_lock)) {
		if (mutex_trylock(&vmap_purge_lock)) {
		__purge_vmap_area_lazy(ULONG_MAX, 0);
		spin_unlock(&vmap_purge_lock);
		mutex_unlock(&vmap_purge_lock);
		}
		}

		@@ -671,10 +671,10 @@ static void try_purge_vmap_area_lazy(void)
		*/
		static void purge_vmap_area_lazy(void)
		{
		spin_lock(&vmap_purge_lock);
		mutex_lock(&vmap_purge_lock);
		purge_fragmented_blocks_allcpus();
		__purge_vmap_area_lazy(ULONG_MAX, 0);
		spin_unlock(&vmap_purge_lock);
		mutex_unlock(&vmap_purge_lock);
		}

		/*
		@@ -1063,11 +1063,11 @@ void vm_unmap_aliases(void)
		rcu_read_unlock();
		}

		spin_lock(&vmap_purge_lock);
		mutex_lock(&vmap_purge_lock);
		purge_fragmented_blocks_allcpus();
		if (!__purge_vmap_area_lazy(start, end) && flush)
		flush_tlb_kernel_range(start, end);
		spin_unlock(&vmap_purge_lock);
		mutex_unlock(&vmap_purge_lock);
		}
		EXPORT_SYMBOL_GPL(vm_unmap_aliases);

Admin message