From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To: linux-kernel@vger.kernel.org
Cc: tony@bakeyournoodle.com, paulus@samba.org,
benh@kernel.crashing.org, dino@in.ibm.com, tytso@us.ibm.com,
dvhltc@us.ibm.com, niv@us.ibm.com, antonb@us.ibm.com,
rostedt@goodmis.org
Subject: [PATCH, RFC] improved hacks to allow -rt to run kernbench on POWER
Date: Fri, 9 Nov 2007 10:10:28 -0800 [thread overview]
Message-ID: <20071109181028.GA26800@linux.vnet.ibm.com> (raw)
Hello again!
A few random patches that permit POWER to pass kernbench on -rt.
Many of these have more focus on expediency than care for correctness,
so might best be thought of as workarounds than as complete solutions.
There are still issues not addressed by this patch, including:
o kmem_cache_alloc() from non-preemptible context during
bootup (xics_startup() building the irq_radix_revmap()).
o unmap_vmas() freeing pages with preemption disabled.
Might be able to address this by linking the pages together,
then freeing them en masse after preemption has been re-enabled,
but there is likely a better approach.
This patch handles the batched TLB-flush mechanism more cleanly (many
thanks to Ben Herrenschmidt for his guidance here). It is also restricted
to powerpc arch-specific files along with one open-firmware file.
Thoughts?
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
arch/powerpc/kernel/process.c | 18 ++++++++++++++++++
arch/powerpc/kernel/prom.c | 2 +-
arch/powerpc/mm/fault.c | 3 +++
arch/powerpc/mm/tlb_64.c | 5 ++++-
arch/powerpc/platforms/pseries/eeh.c | 2 +-
drivers/of/base.c | 2 +-
include/asm-powerpc/tlb.h | 5 ++++-
include/asm-powerpc/tlbflush.h | 15 ++++++++++-----
8 files changed, 42 insertions(+), 10 deletions(-)
diff -urpNa -X dontdiff linux-2.6.23.1-rt4/arch/powerpc/kernel/process.c linux-2.6.23.1-rt4-fix/arch/powerpc/kernel/process.c
--- linux-2.6.23.1-rt4/arch/powerpc/kernel/process.c 2007-10-12 09:43:44.000000000 -0700
+++ linux-2.6.23.1-rt4-fix/arch/powerpc/kernel/process.c 2007-11-08 20:33:59.000000000 -0800
@@ -245,6 +245,8 @@ struct task_struct *__switch_to(struct t
struct thread_struct *new_thread, *old_thread;
unsigned long flags;
struct task_struct *last;
+ struct ppc64_tlb_batch *batch;
+ int hadbatch;
#ifdef CONFIG_SMP
/* avoid complexity of lazy save/restore of fpu
@@ -325,6 +327,16 @@ struct task_struct *__switch_to(struct t
}
#endif
+ batch = &get_cpu_var(ppc64_tlb_batch);
+ if (batch->active) {
+ hadbatch = 1;
+ if (batch->index) {
+ __flush_tlb_pending(batch);
+ }
+ batch->active = 0;
+ }
+ put_cpu_var(ppc64_tlb_batch);
+
local_irq_save(flags);
account_system_vtime(current);
@@ -335,6 +347,12 @@ struct task_struct *__switch_to(struct t
local_irq_restore(flags);
+ if (hadbatch) {
+ batch = &get_cpu_var(ppc64_tlb_batch);
+ batch->active = 1;
+ put_cpu_var(ppc64_tlb_batch);
+ }
+
return last;
}
diff -urpNa -X dontdiff linux-2.6.23.1-rt4/arch/powerpc/kernel/prom.c linux-2.6.23.1-rt4-fix/arch/powerpc/kernel/prom.c
--- linux-2.6.23.1-rt4/arch/powerpc/kernel/prom.c 2007-10-12 09:43:44.000000000 -0700
+++ linux-2.6.23.1-rt4-fix/arch/powerpc/kernel/prom.c 2007-10-28 13:37:23.000000000 -0700
@@ -80,7 +80,7 @@ struct boot_param_header *initial_boot_p
extern struct device_node *allnodes; /* temporary while merging */
-extern rwlock_t devtree_lock; /* temporary while merging */
+extern raw_rwlock_t devtree_lock; /* temporary while merging */
/* export that to outside world */
struct device_node *of_chosen;
diff -urpNa -X dontdiff linux-2.6.23.1-rt4/arch/powerpc/mm/fault.c linux-2.6.23.1-rt4-fix/arch/powerpc/mm/fault.c
--- linux-2.6.23.1-rt4/arch/powerpc/mm/fault.c 2007-10-27 22:20:57.000000000 -0700
+++ linux-2.6.23.1-rt4-fix/arch/powerpc/mm/fault.c 2007-10-28 13:49:07.000000000 -0700
@@ -301,6 +301,7 @@ good_area:
if (get_pteptr(mm, address, &ptep, &pmdp)) {
spinlock_t *ptl = pte_lockptr(mm, pmdp);
spin_lock(ptl);
+ preempt_disable();
if (pte_present(*ptep)) {
struct page *page = pte_page(*ptep);
@@ -310,10 +311,12 @@ good_area:
}
pte_update(ptep, 0, _PAGE_HWEXEC);
_tlbie(address);
+ preempt_enable();
pte_unmap_unlock(ptep, ptl);
up_read(&mm->mmap_sem);
return 0;
}
+ preempt_enable();
pte_unmap_unlock(ptep, ptl);
}
#endif
diff -urpNa -X dontdiff linux-2.6.23.1-rt4/arch/powerpc/mm/tlb_64.c linux-2.6.23.1-rt4-fix/arch/powerpc/mm/tlb_64.c
--- linux-2.6.23.1-rt4/arch/powerpc/mm/tlb_64.c 2007-10-27 22:20:57.000000000 -0700
+++ linux-2.6.23.1-rt4-fix/arch/powerpc/mm/tlb_64.c 2007-11-08 16:49:04.000000000 -0800
@@ -133,7 +133,7 @@ void pgtable_free_tlb(struct mmu_gather
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;
real_pte_t rpte;
@@ -180,6 +180,7 @@ void hpte_need_flush(struct mm_struct *m
*/
if (!batch->active) {
flush_hash_page(vaddr, rpte, psize, 0);
+ put_cpu_var(ppc64_tlb_batch);
return;
}
@@ -212,12 +213,14 @@ void hpte_need_flush(struct mm_struct *m
*/
if (machine_is(celleb)) {
__flush_tlb_pending(batch);
+ put_cpu_var(ppc64_tlb_batch);
return;
}
#endif /* CONFIG_PREEMPT_RT */
if (i >= PPC64_TLB_BATCH_NR)
__flush_tlb_pending(batch);
+ put_cpu_var(ppc64_tlb_batch);
}
/*
diff -urpNa -X dontdiff linux-2.6.23.1-rt4/arch/powerpc/platforms/pseries/eeh.c linux-2.6.23.1-rt4-fix/arch/powerpc/platforms/pseries/eeh.c
--- linux-2.6.23.1-rt4/arch/powerpc/platforms/pseries/eeh.c 2007-10-12 09:43:44.000000000 -0700
+++ linux-2.6.23.1-rt4-fix/arch/powerpc/platforms/pseries/eeh.c 2007-10-28 15:43:54.000000000 -0700
@@ -97,7 +97,7 @@ int eeh_subsystem_enabled;
EXPORT_SYMBOL(eeh_subsystem_enabled);
/* Lock to avoid races due to multiple reports of an error */
-static DEFINE_SPINLOCK(confirm_error_lock);
+static DEFINE_RAW_SPINLOCK(confirm_error_lock);
/* Buffer for reporting slot-error-detail rtas calls. Its here
* in BSS, and not dynamically alloced, so that it ends up in
diff -urpNa -X dontdiff linux-2.6.23.1-rt4/drivers/of/base.c linux-2.6.23.1-rt4-fix/drivers/of/base.c
--- linux-2.6.23.1-rt4/drivers/of/base.c 2007-10-12 09:43:44.000000000 -0700
+++ linux-2.6.23.1-rt4-fix/drivers/of/base.c 2007-10-28 13:38:36.000000000 -0700
@@ -25,7 +25,7 @@ struct device_node *allnodes;
/* use when traversing tree through the allnext, child, sibling,
* or parent members of struct device_node.
*/
-DEFINE_RWLOCK(devtree_lock);
+DEFINE_RAW_RWLOCK(devtree_lock);
int of_n_addr_cells(struct device_node *np)
{
diff -urpNa -X dontdiff linux-2.6.23.1-rt4/include/asm-powerpc/tlbflush.h linux-2.6.23.1-rt4-fix/include/asm-powerpc/tlbflush.h
--- linux-2.6.23.1-rt4/include/asm-powerpc/tlbflush.h 2007-10-12 09:43:44.000000000 -0700
+++ linux-2.6.23.1-rt4-fix/include/asm-powerpc/tlbflush.h 2007-11-08 17:11:18.000000000 -0800
@@ -109,18 +109,23 @@ extern void hpte_need_flush(struct mm_st
static inline void arch_enter_lazy_mmu_mode(void)
{
- struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
+ struct ppc64_tlb_batch *batch = &get_cpu_var(ppc64_tlb_batch);
batch->active = 1;
+ put_cpu_var(ppc64_tlb_batch);
}
static inline void arch_leave_lazy_mmu_mode(void)
{
- struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
+ struct ppc64_tlb_batch *batch = &get_cpu_var(ppc64_tlb_batch);
- if (batch->index)
- __flush_tlb_pending(batch);
- batch->active = 0;
+ if (batch->active) {
+ if (batch->index) {
+ __flush_tlb_pending(batch);
+ }
+ batch->active = 0;
+ }
+ put_cpu_var(ppc64_tlb_batch);
}
#define arch_flush_lazy_mmu_mode() do {} while (0)
diff -urpNa -X dontdiff linux-2.6.23.1-rt4/include/asm-powerpc/tlb.h linux-2.6.23.1-rt4-fix/include/asm-powerpc/tlb.h
--- linux-2.6.23.1-rt4/include/asm-powerpc/tlb.h 2007-10-12 09:43:44.000000000 -0700
+++ linux-2.6.23.1-rt4-fix/include/asm-powerpc/tlb.h 2007-10-28 11:36:05.000000000 -0700
@@ -44,8 +44,11 @@ static inline void tlb_flush(struct mmu_
* pages are going to be freed and we really don't want to have a CPU
* access a freed page because it has a stale TLB
*/
- if (tlbbatch->index)
+ if (tlbbatch->index) {
+ preempt_disable();
__flush_tlb_pending(tlbbatch);
+ preempt_enable();
+ }
pte_free_finish();
}
next reply other threads:[~2007-11-09 18:11 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-11-09 18:10 Paul E. McKenney [this message]
2007-11-09 20:52 ` [PATCH, RFC] improved hacks to allow -rt to run kernbench on POWER Benjamin Herrenschmidt
2007-11-09 22:07 ` Paul E. McKenney
2007-11-11 3:59 ` Benjamin Herrenschmidt
2007-11-11 14:45 ` Steven Rostedt
2007-11-11 20:48 ` Benjamin Herrenschmidt
2007-11-12 17:05 ` Paul E. McKenney
2007-11-12 19:15 ` Paul E. McKenney
2007-11-12 21:12 ` Benjamin Herrenschmidt
2007-11-13 9:10 ` Peter Zijlstra
2007-11-13 9:43 ` Benjamin Herrenschmidt
2007-11-13 10:05 ` Peter Zijlstra
2007-11-13 10:59 ` Peter Zijlstra
2007-11-13 11:09 ` Benjamin Herrenschmidt
2007-11-10 1:18 ` Nick Piggin
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=20071109181028.GA26800@linux.vnet.ibm.com \
--to=paulmck@linux.vnet.ibm.com \
--cc=antonb@us.ibm.com \
--cc=benh@kernel.crashing.org \
--cc=dino@in.ibm.com \
--cc=dvhltc@us.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=niv@us.ibm.com \
--cc=paulus@samba.org \
--cc=rostedt@goodmis.org \
--cc=tony@bakeyournoodle.com \
--cc=tytso@us.ibm.com \
/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