linux-mips.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Paul Burton <paul.burton@mips.com>
To: "linux-mips@vger.kernel.org" <linux-mips@vger.kernel.org>
Cc: Paul Burton <pburton@wavecomp.com>
Subject: [PATCH 04/14] MIPS: mm: Avoid HTW stop/start when dropping an inactive mm
Date: Sat, 2 Feb 2019 01:43:18 +0000	[thread overview]
Message-ID: <20190202014242.30680-5-paul.burton@mips.com> (raw)
In-Reply-To: <20190202014242.30680-1-paul.burton@mips.com>

If drop_mmu_context() is called with an mm that is not currently active
on the local CPU then there's no need for us to stop & start a hardware
page table walker because it can't be fetching entries for the ASID
corresponding to the mm we're operating on.

Move the htw_stop() & htw_start() calls into the block which we run only
if the mm is currently active, in order to avoid the redundant work.

Signed-off-by: Paul Burton <paul.burton@mips.com>
---

 arch/mips/include/asm/mmu_context.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/mips/include/asm/mmu_context.h b/arch/mips/include/asm/mmu_context.h
index 0d050d781737..5d0a73a5cf40 100644
--- a/arch/mips/include/asm/mmu_context.h
+++ b/arch/mips/include/asm/mmu_context.h
@@ -184,17 +184,18 @@ drop_mmu_context(struct mm_struct *mm)
 	unsigned int cpu;
 
 	local_irq_save(flags);
-	htw_stop();
 
 	cpu = smp_processor_id();
 	if (cpumask_test_cpu(cpu, mm_cpumask(mm)))  {
+		htw_stop();
 		get_new_mmu_context(mm);
 		write_c0_entryhi(cpu_asid(cpu, mm));
+		htw_start();
 	} else {
 		/* will get a new context next time */
 		cpu_context(cpu, mm) = 0;
 	}
-	htw_start();
+
 	local_irq_restore(flags);
 }
 
-- 
2.20.1


  parent reply	other threads:[~2019-02-02  1:43 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-02-02  1:43 [PATCH 00/14] MIPS: MemoryMapID (MMID) & GINVT Support Paul Burton
2019-02-02  1:43 ` [PATCH 01/14] MIPS: mm: Define activate_mm() using switch_mm() Paul Burton
2019-02-02  1:43 ` [PATCH 02/14] MIPS: mm: Remove redundant drop_mmu_context() cpu argument Paul Burton
2019-02-02  1:43 ` [PATCH 03/14] MIPS: mm: Remove redundant get_new_mmu_context() " Paul Burton
2019-02-02  1:43 ` Paul Burton [this message]
2019-02-02  1:43 ` [PATCH 05/14] MIPS: mm: Consolidate drop_mmu_context() has-ASID checks Paul Burton
2019-02-02  1:43 ` [PATCH 06/14] MIPS: mm: Move drop_mmu_context() comment into appropriate block Paul Burton
2019-02-02  1:43 ` [PATCH 07/14] MIPS: mm: Remove redundant preempt_disable in local_flush_tlb_mm() Paul Burton
2019-02-02  1:43 ` [PATCH 08/14] MIPS: mm: Remove local_flush_tlb_mm() Paul Burton
2019-02-02  1:43 ` [PATCH 09/14] MIPS: mm: Split obj-y to a file per line Paul Burton
2019-02-02  1:43 ` [PATCH 10/14] MIPS: mm: Un-inline get_new_mmu_context Paul Burton
2019-02-02  1:43 ` [PATCH 12/14] MIPS: mm: Add set_cpu_context() for ASID assignments Paul Burton
2019-02-02  1:43 ` [PATCH 11/14] MIPS: mm: Unify ASID version checks Paul Burton
2019-02-02  1:43 ` [PATCH 13/14] MIPS: Add GINVT instruction helpers Paul Burton
2019-02-02  1:43 ` [PATCH 14/14] MIPS: MemoryMapID (MMID) Support Paul Burton
2019-02-04 21:18 ` [PATCH 00/14] MIPS: MemoryMapID (MMID) & GINVT Support Paul Burton

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=20190202014242.30680-5-paul.burton@mips.com \
    --to=paul.burton@mips.com \
    --cc=linux-mips@vger.kernel.org \
    --cc=pburton@wavecomp.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;
as well as URLs for NNTP newsgroup(s).