linux/arch/sparc
David S. Miller f36391d279 sparc64: Fix race in TLB batch processing.
As reported by Dave Kleikamp, when we emit cross calls to do batched
TLB flush processing we have a race because we do not synchronize on
the sibling cpus completing the cross call.

So meanwhile the TLB batch can be reset (tb->tlb_nr set to zero, etc.)
and either flushes are missed or flushes will flush the wrong
addresses.

Fix this by using generic infrastructure to synchonize on the
completion of the cross call.

This first required getting the flush_tlb_pending() call out from
switch_to() which operates with locks held and interrupts disabled.
The problem is that smp_call_function_many() cannot be invoked with
IRQs disabled and this is explicitly checked for with WARN_ON_ONCE().

We get the batch processing outside of locked IRQ disabled sections by
using some ideas from the powerpc port. Namely, we only batch inside
of arch_{enter,leave}_lazy_mmu_mode() calls.  If we're not in such a
region, we flush TLBs synchronously.

1) Get rid of xcall_flush_tlb_pending and per-cpu type
   implementations.

2) Do TLB batch cross calls instead via:

	smp_call_function_many()
		tlb_pending_func()
			__flush_tlb_pending()

3) Batch only in lazy mmu sequences:

	a) Add 'active' member to struct tlb_batch
	b) Define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
	c) Set 'active' in arch_enter_lazy_mmu_mode()
	d) Run batch and clear 'active' in arch_leave_lazy_mmu_mode()
	e) Check 'active' in tlb_batch_add_one() and do a synchronous
           flush if it's clear.

4) Add infrastructure for synchronous TLB page flushes.

	a) Implement __flush_tlb_page and per-cpu variants, patch
	   as needed.
	b) Likewise for xcall_flush_tlb_page.
	c) Implement smp_flush_tlb_page() to invoke the cross-call.
	d) Wire up global_flush_tlb_page() to the right routine based
           upon CONFIG_SMP

5) It turns out that singleton batches are very common, 2 out of every
   3 batch flushes have only a single entry in them.

   The batch flush waiting is very expensive, both because of the poll
   on sibling cpu completeion, as well as because passing the tlb batch
   pointer to the sibling cpus invokes a shared memory dereference.

   Therefore, in flush_tlb_pending(), if there is only one entry in
   the batch perform a completely asynchronous global_flush_tlb_page()
   instead.

Reported-by: Dave Kleikamp <dave.kleikamp@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Dave Kleikamp <dave.kleikamp@oracle.com>
2013-04-19 17:26:26 -04:00
..
boot sparc: Fix piggyback with newer binutils. 2012-12-03 11:24:25 -08:00
configs perf: Remove PERF_COUNTERS config option 2012-04-26 13:52:52 +02:00
crypto sparc64: Set CRYPTO_TFM_REQ_MAY_SLEEP consistently in CAMELLIA code. 2012-12-19 15:44:31 -08:00
include sparc64: Fix race in TLB batch processing. 2013-04-19 17:26:26 -04:00
kernel sparc64: Fix race in TLB batch processing. 2013-04-19 17:26:26 -04:00
lib sparc/srmmu: clear trailing edge of bitmap properly 2013-03-31 19:29:12 -04:00
math-emu sparc64: Make montmul/montsqr/mpmul usable in 32-bit threads. 2012-10-26 15:18:37 -07:00
mm sparc64: Fix race in TLB batch processing. 2013-04-19 17:26:26 -04:00
net sparc: bpf_jit_comp: add VLAN instructions for BPF JIT 2012-11-06 17:41:42 -05:00
oprofile sparc: using HZ needs an include of linux/param.h 2009-10-05 00:46:08 -07:00
prom sparc32: Remove superfluous extern declarations for prom_*() functions 2012-06-27 01:27:45 -07:00
Kbuild sparc64: Add SHA1 driver making use of the 'sha1' instruction. 2012-08-20 15:08:49 -07:00
Kconfig sparc: remove unused "config BITS" 2013-03-19 16:23:51 -04:00
Kconfig.debug lib: consolidate DEBUG_STACK_USAGE option 2011-05-25 08:39:54 -07:00
Makefile Merge branch 'smp-hotplug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2012-05-21 19:43:57 -07:00