linuxppc-dev.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
To: benh@kernel.crashing.org, paulus@samba.org, mpe@ellerman.id.au,
	Madhavan Srinivasan <masriniv@in.ibm.com>,
	Anton Blanchard <anton@ozlabs.org>
Cc: linuxppc-dev@lists.ozlabs.org,
	"Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Subject: [RFC PATCH] powerpc/mm/radix: Optimize tlbiel flush
Date: Thu, 20 Apr 2017 12:58:25 +0530	[thread overview]
Message-ID: <1492673305-29526-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com> (raw)

For a page walk cache flush, we don't need to loop with set number. The set
number is ignored with RIC=1 (pwc flush).

For RIC=2 (flush all), inorder to flush implementation dependent caches, we can
ignore the set number. Hence we do a RIC=2 flush with set no: 0, so we do both
the tlb flush for set 0 and the implementation dependent cache flushes. This is
then followed with tbl flush for set 1-127

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
Note: not yet tested.

 arch/powerpc/mm/tlb-radix.c | 28 +++++++++++++++++++++++-----
 1 file changed, 23 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index b68b5219cf45..b827aef38b90 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -43,12 +43,30 @@ static inline void __tlbiel_pid(unsigned long pid, int set,
  */
 static inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
 {
-	int set;
+	int set = 0;
 
 	asm volatile("ptesync": : :"memory");
-	for (set = 0; set < POWER9_TLB_SETS_RADIX ; set++) {
-		__tlbiel_pid(pid, set, ric);
+	if (ric == RIC_FLUSH_ALL) {
+		ric = RIC_FLUSH_TLB;
+		set = 1;
+		/* Use set 0 to flush all */
+		__tlbiel_pid(pid, 0, RIC_FLUSH_ALL);
 	}
+
+	for (; set < POWER9_TLB_SETS_RADIX ; set++)
+		__tlbiel_pid(pid, set, ric);
+
+	asm volatile("ptesync": : :"memory");
+	asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory");
+}
+
+static inline void _tlbiel_pwc(unsigned long pid)
+{
+	asm volatile("ptesync": : :"memory");
+	/*
+	 * for PWC flush, we don't look at set number
+	 */
+	__tlbiel_pid(pid, 0, RIC_FLUSH_PWC);
 	asm volatile("ptesync": : :"memory");
 	asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory");
 }
@@ -140,7 +158,7 @@ void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
 
 	pid = mm->context.id;
 	if (pid != MMU_NO_CONTEXT)
-		_tlbiel_pid(pid, RIC_FLUSH_PWC);
+		_tlbiel_pwc(pid);
 
 	preempt_enable();
 }
@@ -222,7 +240,7 @@ void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
 		if (lock_tlbie)
 			raw_spin_unlock(&native_tlbie_lock);
 	} else
-		_tlbiel_pid(pid, RIC_FLUSH_PWC);
+		_tlbiel_pwc(pid);
 no_context:
 	preempt_enable();
 }
-- 
2.7.4

             reply	other threads:[~2017-04-20  7:28 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-04-20  7:28 Aneesh Kumar K.V [this message]
2017-04-20  8:23 ` [RFC PATCH] powerpc/mm/radix: Optimize tlbiel flush Anton Blanchard

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=1492673305-29526-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com \
    --to=aneesh.kumar@linux.vnet.ibm.com \
    --cc=anton@ozlabs.org \
    --cc=benh@kernel.crashing.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=masriniv@in.ibm.com \
    --cc=mpe@ellerman.id.au \
    --cc=paulus@samba.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).