From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: Andrea Arcangeli <aarcange@redhat.com>,
Avi Kivity <avi@redhat.com>, Thomas Gleixner <tglx@linutronix.de>,
Rik van Riel <riel@redhat.com>, Ingo Molnar <mingo@elte.hu>,
akpm@linux-foundation.org,
Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org,
Benjamin Herrenschmidt <benh@kernel.crashing.org>,
David Miller <davem@davemloft.net>,
Hugh Dickins <hugh.dickins@tiscali.co.uk>,
Mel Gorman <mel@csn.ul.ie>, Nick Piggin <npiggin@suse.de>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Subject: [PATCH 12/28] powerpc: Preemptible mmu_gather
Date: Mon, 07 Jun 2010 13:07:06 +0200 [thread overview]
Message-ID: <20100607111407.492512670@chello.nl> (raw)
In-Reply-To: 20100607110654.606530953@chello.nl
[-- Attachment #1: mm-preempt-tlb-gather-power.patch --]
[-- Type: text/plain, Size: 8656 bytes --]
Fix up powerpc to the new mmu_gather stuffs.
PPC has an extra batching queue to RCU free the actual pagetable
allocations, use the ARCH extentions for that for now.
For the ppc64_tlb_batch, which tracks the vaddrs to unhash from the
hardware hash-table, keep using per-cpu arrays but flush on context
switch and use a TLF bit to track the laxy_mmu state.
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
arch/powerpc/include/asm/pgalloc.h | 4 ++--
arch/powerpc/include/asm/thread_info.h | 2 ++
arch/powerpc/include/asm/tlb.h | 10 ++++++++++
arch/powerpc/kernel/process.c | 19 +++++++++++++++++++
arch/powerpc/mm/pgtable.c | 14 ++++----------
arch/powerpc/mm/tlb_hash32.c | 2 +-
arch/powerpc/mm/tlb_hash64.c | 12 +++++++-----
arch/powerpc/mm/tlb_nohash.c | 2 +-
8 files changed, 46 insertions(+), 19 deletions(-)
Index: linux-2.6/arch/powerpc/include/asm/tlb.h
===================================================================
--- linux-2.6.orig/arch/powerpc/include/asm/tlb.h
+++ linux-2.6/arch/powerpc/include/asm/tlb.h
@@ -28,6 +28,16 @@
#define tlb_start_vma(tlb, vma) do { } while (0)
#define tlb_end_vma(tlb, vma) do { } while (0)
+#define HAVE_ARCH_MMU_GATHER 1
+
+struct pte_freelist_batch;
+
+struct arch_mmu_gather {
+ struct pte_freelist_batch *batch;
+};
+
+#define ARCH_MMU_GATHER_INIT (struct arch_mmu_gather){ .batch = NULL, }
+
extern void tlb_flush(struct mmu_gather *tlb);
/* Get the generic bits... */
Index: linux-2.6/arch/powerpc/kernel/process.c
===================================================================
--- linux-2.6.orig/arch/powerpc/kernel/process.c
+++ linux-2.6/arch/powerpc/kernel/process.c
@@ -392,6 +392,9 @@ struct task_struct *__switch_to(struct t
struct thread_struct *new_thread, *old_thread;
unsigned long flags;
struct task_struct *last;
+#ifdef CONFIG_PPC64
+ struct ppc64_tlb_batch *batch;
+#endif
#ifdef CONFIG_SMP
/* avoid complexity of lazy save/restore of fpu
@@ -482,6 +485,14 @@ struct task_struct *__switch_to(struct t
old_thread->accum_tb += (current_tb - start_tb);
new_thread->start_tb = current_tb;
}
+
+ batch = &__get_cpu_var(ppc64_tlb_batch);
+ if (batch->active) {
+ task_thread_info(prev)->local_flags |= _TLF_LAZY_MMU;
+ if (batch->index)
+ __flush_tlb_pending(batch);
+ batch->active = 0;
+ }
#endif
local_irq_save(flags);
@@ -498,6 +509,14 @@ struct task_struct *__switch_to(struct t
hard_irq_disable();
last = _switch(old_thread, new_thread);
+#ifdef CONFIG_PPC64
+ if (task_thread_info(new)->local_flags & _TLF_LAZY_MMU) {
+ task_thread_info(new)->local_flags &= ~_TLF_LAZY_MMU;
+ batch = &__get_cpu_var(ppc64_tlb_batch);
+ batch->active = 1;
+ }
+#endif
+
local_irq_restore(flags);
return last;
Index: linux-2.6/arch/powerpc/mm/pgtable.c
===================================================================
--- linux-2.6.orig/arch/powerpc/mm/pgtable.c
+++ linux-2.6/arch/powerpc/mm/pgtable.c
@@ -33,8 +33,6 @@
#include "mmu_decl.h"
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
#ifdef CONFIG_SMP
/*
@@ -43,7 +41,6 @@ DEFINE_PER_CPU(struct mmu_gather, mmu_ga
* freeing a page table page that is being walked without locks
*/
-static DEFINE_PER_CPU(struct pte_freelist_batch *, pte_freelist_cur);
static unsigned long pte_freelist_forced_free;
struct pte_freelist_batch
@@ -98,12 +95,10 @@ static void pte_free_submit(struct pte_f
void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift)
{
- /* This is safe since tlb_gather_mmu has disabled preemption */
- struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
+ struct pte_freelist_batch **batchp = &tlb->arch.batch;
unsigned long pgf;
- if (atomic_read(&tlb->mm->mm_users) < 2 ||
- cpumask_equal(mm_cpumask(tlb->mm), cpumask_of(smp_processor_id()))){
+ if (atomic_read(&tlb->mm->mm_users) < 2) {
pgtable_free(table, shift);
return;
}
@@ -125,10 +120,9 @@ void pgtable_free_tlb(struct mmu_gather
}
}
-void pte_free_finish(void)
+void pte_free_finish(struct mmu_gather *tlb)
{
- /* This is safe since tlb_gather_mmu has disabled preemption */
- struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
+ struct pte_freelist_batch **batchp = &tlb->arch.batch;
if (*batchp == NULL)
return;
Index: linux-2.6/arch/powerpc/mm/tlb_hash64.c
===================================================================
--- linux-2.6.orig/arch/powerpc/mm/tlb_hash64.c
+++ linux-2.6/arch/powerpc/mm/tlb_hash64.c
@@ -38,13 +38,11 @@ DEFINE_PER_CPU(struct ppc64_tlb_batch, p
* neesd to be flushed. This function will either perform the flush
* immediately or will batch it up if the current CPU has an active
* batch on it.
- *
- * Must be called from within some kind of spinlock/non-preempt region...
*/
void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, unsigned long pte, int huge)
{
- struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
+ struct ppc64_tlb_batch *batch = &get_cpu_var(ppc64_tlb_batch);
unsigned long vsid, vaddr;
unsigned int psize;
int ssize;
@@ -99,6 +97,7 @@ void hpte_need_flush(struct mm_struct *m
*/
if (!batch->active) {
flush_hash_page(vaddr, rpte, psize, ssize, 0);
+ put_cpu_var(ppc64_tlb_batch);
return;
}
@@ -127,6 +126,7 @@ void hpte_need_flush(struct mm_struct *m
batch->index = ++i;
if (i >= PPC64_TLB_BATCH_NR)
__flush_tlb_pending(batch);
+ put_cpu_var(ppc64_tlb_batch);
}
/*
@@ -155,7 +155,7 @@ void __flush_tlb_pending(struct ppc64_tl
void tlb_flush(struct mmu_gather *tlb)
{
- struct ppc64_tlb_batch *tlbbatch = &__get_cpu_var(ppc64_tlb_batch);
+ struct ppc64_tlb_batch *tlbbatch = &get_cpu_var(ppc64_tlb_batch);
/* If there's a TLB batch pending, then we must flush it because the
* pages are going to be freed and we really don't want to have a CPU
@@ -164,8 +164,10 @@ void tlb_flush(struct mmu_gather *tlb)
if (tlbbatch->index)
__flush_tlb_pending(tlbbatch);
+ put_cpu_var(ppc64_tlb_batch);
+
/* Push out batch of freed page tables */
- pte_free_finish();
+ pte_free_finish(tlb);
}
/**
Index: linux-2.6/arch/powerpc/include/asm/thread_info.h
===================================================================
--- linux-2.6.orig/arch/powerpc/include/asm/thread_info.h
+++ linux-2.6/arch/powerpc/include/asm/thread_info.h
@@ -139,10 +139,12 @@ static inline struct thread_info *curren
#define TLF_NAPPING 0 /* idle thread enabled NAP mode */
#define TLF_SLEEPING 1 /* suspend code enabled SLEEP mode */
#define TLF_RESTORE_SIGMASK 2 /* Restore signal mask in do_signal */
+#define TLF_LAZY_MMU 3 /* tlb_batch is active */
#define _TLF_NAPPING (1 << TLF_NAPPING)
#define _TLF_SLEEPING (1 << TLF_SLEEPING)
#define _TLF_RESTORE_SIGMASK (1 << TLF_RESTORE_SIGMASK)
+#define _TLF_LAZY_MMU (1 << TLF_LAZY_MMU)
#ifndef __ASSEMBLY__
#define HAVE_SET_RESTORE_SIGMASK 1
Index: linux-2.6/arch/powerpc/include/asm/pgalloc.h
===================================================================
--- linux-2.6.orig/arch/powerpc/include/asm/pgalloc.h
+++ linux-2.6/arch/powerpc/include/asm/pgalloc.h
@@ -32,13 +32,13 @@ static inline void pte_free(struct mm_st
#ifdef CONFIG_SMP
extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift);
-extern void pte_free_finish(void);
+extern void pte_free_finish(struct mmu_gather *tlb);
#else /* CONFIG_SMP */
static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift)
{
pgtable_free(table, shift);
}
-static inline void pte_free_finish(void) { }
+static inline void pte_free_finish(struct mmu_gather *tlb) { }
#endif /* !CONFIG_SMP */
static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *ptepage,
Index: linux-2.6/arch/powerpc/mm/tlb_hash32.c
===================================================================
--- linux-2.6.orig/arch/powerpc/mm/tlb_hash32.c
+++ linux-2.6/arch/powerpc/mm/tlb_hash32.c
@@ -73,7 +73,7 @@ void tlb_flush(struct mmu_gather *tlb)
}
/* Push out batch of freed page tables */
- pte_free_finish();
+ pte_free_finish(tlb);
}
/*
Index: linux-2.6/arch/powerpc/mm/tlb_nohash.c
===================================================================
--- linux-2.6.orig/arch/powerpc/mm/tlb_nohash.c
+++ linux-2.6/arch/powerpc/mm/tlb_nohash.c
@@ -298,7 +298,7 @@ void tlb_flush(struct mmu_gather *tlb)
flush_tlb_mm(tlb->mm);
/* Push out batch of freed page tables */
- pte_free_finish();
+ pte_free_finish(tlb);
}
/*
next prev parent reply other threads:[~2010-06-07 11:20 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-06-07 11:06 [PATCH 00/28] mm: preemptibility -v3 Peter Zijlstra
2010-06-07 11:06 ` [PATCH 01/28] powerpc: Use call_rcu_sched() for pagetables Peter Zijlstra
2010-06-07 11:06 ` [PATCH 02/28] mm: Improve page_lock_anon_vma() comment Peter Zijlstra
2010-06-09 10:50 ` Mel Gorman
2010-06-07 11:06 ` [PATCH 03/28] rename anon_vma_lock to vma_lock_anon_vma Peter Zijlstra
2010-06-07 15:01 ` Peter Zijlstra
2010-06-09 10:59 ` Mel Gorman
2010-06-07 11:06 ` [PATCH 04/28] change direct call of spin_lock(anon_vma->lock) to inline function Peter Zijlstra
2010-06-07 11:06 ` [PATCH 05/28] track the root (oldest) anon_vma Peter Zijlstra
2010-06-07 11:07 ` [PATCH 06/28] always lock " Peter Zijlstra
2010-06-07 11:07 ` [PATCH 07/28] extend KSM refcounts to the anon_vma root Peter Zijlstra
2010-06-09 10:55 ` Mel Gorman
2010-06-07 11:07 ` [PATCH 08/28] mm: Rename drop_anon_vma to put_anon_vma Peter Zijlstra
2010-06-07 11:07 ` [PATCH 09/28] mm: Move anon_vma ref out from under CONFIG_KSM Peter Zijlstra
2010-06-09 11:05 ` Mel Gorman
2010-06-07 11:07 ` [PATCH 10/28] mm: Make use of the anon_vma ref count Peter Zijlstra
2010-06-09 13:22 ` Mel Gorman
2010-06-09 13:32 ` Peter Zijlstra
2010-06-07 11:07 ` [PATCH 11/28] mm: Preemptible mmu_gather Peter Zijlstra
2010-06-07 11:07 ` Peter Zijlstra [this message]
2010-06-07 11:07 ` [PATCH 13/28] sparc: " Peter Zijlstra
2010-06-07 11:07 ` [PATCH 14/28] s390: preemptible mmu_gather Peter Zijlstra
2010-06-07 11:07 ` [PATCH 15/28] arm: Preemptible mmu_gather Peter Zijlstra
2010-06-07 11:07 ` [PATCH 16/28] sh: " Peter Zijlstra
2010-06-07 11:38 ` Peter Zijlstra
2010-06-07 11:07 ` [PATCH 17/28] um: " Peter Zijlstra
2010-06-07 11:07 ` [PATCH 18/28] ia64: " Peter Zijlstra
2010-06-07 11:07 ` [PATCH 19/28] mm, powerpc: Move the RCU page-table freeing into generic code Peter Zijlstra
2010-06-07 11:07 ` [PATCH 20/28] sparc64: Kill page table quicklists Peter Zijlstra
2010-06-07 11:07 ` [PATCH 21/28] sparc64: Use RCU page table freeing Peter Zijlstra
2010-06-07 11:07 ` [PATCH 22/28] sparc64: Add support for _PAGE_SPECIAL Peter Zijlstra
2010-06-07 11:07 ` [PATCH 23/28] sparc64: Implement get_user_pages_fast() Peter Zijlstra
2010-06-07 11:07 ` [PATCH 24/28] lockdep, mutex: Provide mutex_lock_nest_lock Peter Zijlstra
2010-06-07 11:07 ` [PATCH 25/28] mutex: Provide mutex_is_contended Peter Zijlstra
2010-06-07 11:07 ` [PATCH 26/28] mm: Convert i_mmap_lock and anon_vma->lock to mutexes Peter Zijlstra
2010-06-07 11:07 ` [PATCH 27/28] mm: Extended batches for generic mmu_gather Peter Zijlstra
2010-06-07 11:07 ` [PATCH 28/28] mm: Optimize page_lock_anon_vma() fast-path Peter Zijlstra
2010-06-07 13:57 ` [PATCH 00/28] mm: preemptibility -v3 Sam Ravnborg
2010-06-07 15:02 ` Peter Zijlstra
2010-06-07 16:36 ` Andi Kleen
2010-06-07 16:39 ` Peter Zijlstra
2010-06-10 1:45 ` Zhang, Yanmin
2010-06-10 6:52 ` Peter Zijlstra
2010-06-10 6:59 ` Zhang, Yanmin
2010-06-21 10:21 ` Peter Zijlstra
2010-06-24 9:55 ` Peter Zijlstra
2010-06-29 7:40 ` Zhang, Yanmin
2010-06-29 7:48 ` Peter Zijlstra
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20100607111407.492512670@chello.nl \
--to=a.p.zijlstra@chello.nl \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=avi@redhat.com \
--cc=benh@kernel.crashing.org \
--cc=davem@davemloft.net \
--cc=hugh.dickins@tiscali.co.uk \
--cc=linux-arch@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mel@csn.ul.ie \
--cc=mingo@elte.hu \
--cc=npiggin@suse.de \
--cc=paulmck@linux.vnet.ibm.com \
--cc=riel@redhat.com \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).