linux-toradex.git/arch/sparc, branch v3.2.50

sparc: tsb must be flushed before tlb

2013-08-02T20:14:51+00:00

commit 23a01138efe216f8084cfaa74b0b90dd4b097441 upstream.

This fixes a race where a cpu may re-load a tlb from a stale tsb right
after it has been flushed by a remote function call.

I still see some instability when stressing the system with parallel
kernel builds while creating memory pressure by writing to
/proc/sys/vm/nr_hugepages, but this patch improves the stability
significantly.

Signed-off-by: Dave Kleikamp 
Acked-by: Bob Picco 
Signed-off-by: David S. Miller 
Signed-off-by: Ben Hutchings

sparc64 address-congruence property

2013-08-02T20:14:51+00:00

commit 771a37ff4d80b80db3b0df3e7696f14b298c67b7 upstream.

The Machine Description (MD) property "address-congruence-offset" is
optional. According to the MD specification the value is assumed 0UL when
not present. This caused early boot failure on T5.

Signed-off-by: Bob Picco 
CC: sparclinux@vger.kernel.org
Signed-off-by: David S. Miller 
Signed-off-by: Ben Hutchings

sparc32: vm_area_struct access for old Sun SPARCs.

2013-08-02T20:14:51+00:00

commit 961246b4ed8da3bcf4ee1eb9147f341013553e3c upstream.

Commit e4c6bfd2d79d063017ab19a18915f0bc759f32d9 ("mm: rearrange
vm_area_struct for fewer cache misses") changed the layout of the
vm_area_struct structure, it broke several SPARC32 assembly routines
which used numerical constants for accessing the vm_mm field.

This patch defines the VMA_VM_MM constant to replace the immediate values.

Signed-off-by: Olivier DANET 
Signed-off-by: David S. Miller 
Signed-off-by: Ben Hutchings

sparc64: Fix race in TLB batch processing.

2013-05-13T14:02:42+00:00

[ Commits f36391d2790d04993f48da6a45810033a2cdf847 and
  f0af97070acbad5d6a361f485828223a4faaa0ee upstream. ]

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 
Signed-off-by: David S. Miller 
Acked-by: Dave Kleikamp 
Signed-off-by: Ben Hutchings

signal: Define __ARCH_HAS_SA_RESTORER so we know whether to clear sa_restorer

2013-03-27T02:41:25+00:00

flush_signal_handlers() needs to know whether sigaction::sa_restorer
is defined, not whether SA_RESTORER is defined.  Define the
__ARCH_HAS_SA_RESTORER macro to indicate this.

Vaguely based on upstream commit 574c4866e33d 'consolidate kernel-side
struct sigaction declarations'.

Signed-off-by: Ben Hutchings 
Cc: Al Viro

sparc: huge_ptep_set_* functions need to call set_huge_pte_at()

2013-01-16T01:13:24+00:00

[ Upstream commit 6cb9c3697585c47977c42c5cc1b9fc49247ac530 ]

Modifying the huge pte's requires that all the underlying pte's be
modified.

Version 2: added missing flush_tlb_page()

Signed-off-by: Dave Kleikamp 
Cc: "David S. Miller" 
Cc: sparclinux@vger.kernel.org
Signed-off-by: David S. Miller 
Signed-off-by: Ben Hutchings

sparc64: not any error from do_sigaltstack() should fail rt_sigreturn()

2012-12-06T11:20:26+00:00

commit fae2ae2a900a5c7bb385fe4075f343e7e2d5daa2 upstream.

If a signal handler is executed on altstack and another signal comes,
we will end up with rt_sigreturn() on return from the second handler
getting -EPERM from do_sigaltstack().  It's perfectly OK, since we
are not asking to change the settings; in fact, they couldn't have been
changed during the second handler execution exactly because we'd been
on altstack all along.  64bit sigreturn on sparc treats any error from
do_sigaltstack() as "SIGSEGV now"; we need to switch to the same semantics
we are using on other architectures.

Signed-off-by: Al Viro 
Signed-off-by: David S. Miller 
Signed-off-by: Ben Hutchings

sparc64: Be less verbose during vmemmap population.

2012-10-30T23:26:32+00:00

[ Upstream commit 2856cc2e4d0852c3ddaae9dcb19cb9396512eb08 ]

On a 2-node machine with 256GB of ram we get 512 lines of
console output, which is just too much.

This mimicks Yinghai Lu's x86 commit c2b91e2eec9678dbda274e906cc32ea8f711da3b
(x86_64/mm: check and print vmemmap allocation continuous) except that
we aren't ever going to get contiguous block pointers in between calls
so just print when the virtual address or node changes.

This decreases the output by an order of 16.

Also demote this to KERN_DEBUG.

Signed-off-by: David S. Miller 
Signed-off-by: Ben Hutchings

sparc64: do not clobber personality flags in sys_sparc64_personality()

2012-10-30T23:26:32+00:00

[ Upstream commit a27032eee8cb6e16516f13c8a9752e9d5d4cc430 ]

There are multiple errors in how sys_sparc64_personality() handles
personality flags stored in top three bytes.

- directly comparing current->personality against PER_LINUX32 doesn't work
  in cases when any of the personality flags stored in the top three bytes
  are used.
- directly forcefully setting personality to PER_LINUX32 or PER_LINUX
  discards any flags stored in the top three bytes

Fix the first one by properly using personality() macro to compare only
PER_MASK bytes.
Fix the second one by setting only the bits that should be set, instead of
overwriting the whole value.

Signed-off-by: Jiri Kosina 
Signed-off-by: David S. Miller 
Signed-off-by: Ben Hutchings

sparc64: Fix bit twiddling in sparc_pmu_enable_event().

2012-10-30T23:26:31+00:00

[ Upstream commit e793d8c6740f8fe704fa216e95685f4d92c4c4b9 ]

There was a serious disconnect in the logic happening in
sparc_pmu_disable_event() vs. sparc_pmu_enable_event().

Event disable is implemented by programming a NOP event into the PCR.

However, event enable was not reversing this operation.  Instead, it
was setting the User/Priv/Hypervisor trace enable bits.

That's not sparc_pmu_enable_event()'s job, that's what
sparc_pmu_enable() and sparc_pmu_disable() do .

The intent of sparc_pmu_enable_event() is clear, since it first clear
out the event type encoding field.  So fix this by OR'ing in the event
encoding rather than the trace enable bits.

Signed-off-by: David S. Miller 
Signed-off-by: Ben Hutchings