All of lore.kernel.org
 help / color / mirror / Atom feed
From: Nicholas Piggin <npiggin@gmail.com>
To: linuxppc-dev@lists.ozlabs.org
Cc: Nicholas Piggin <npiggin@gmail.com>
Subject: [PATCH 09/13] powerpc/64: runlatch CTRL[RUN] set optimisation
Date: Sun,  6 Aug 2017 03:02:37 +1000	[thread overview]
Message-ID: <20170805170241.22966-10-npiggin@gmail.com> (raw)
In-Reply-To: <20170805170241.22966-1-npiggin@gmail.com>

The CTRL register is read-only except bit 63 which is the run latch
control. This means it can be updated with a mtspr rather than
mfspr/mtspr.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kernel/process.c | 35 +++++++++++++++++++++++++++--------
 1 file changed, 27 insertions(+), 8 deletions(-)

diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 9f3e2c932dcc..75306b6e1812 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1994,11 +1994,25 @@ void show_stack(struct task_struct *tsk, unsigned long *stack)
 void notrace __ppc64_runlatch_on(void)
 {
 	struct thread_info *ti = current_thread_info();
-	unsigned long ctrl;
 
-	ctrl = mfspr(SPRN_CTRLF);
-	ctrl |= CTRL_RUNLATCH;
-	mtspr(SPRN_CTRLT, ctrl);
+	if (cpu_has_feature(CPU_FTR_ARCH_206)) {
+		/*
+		 * Least significant bit (RUN) is the only writable bit of
+		 * the CTRL register, so we can avoid mfspr. 2.06 is not the
+		 * earliest ISA where this is the case, but it's convenient.
+		 */
+		mtspr(SPRN_CTRLT, CTRL_RUNLATCH);
+	} else {
+		unsigned long ctrl;
+
+		/*
+		 * Some architectures (e.g., Cell) have writable fields other
+		 * than RUN, so do the read-modify-write.
+		 */
+		ctrl = mfspr(SPRN_CTRLF);
+		ctrl |= CTRL_RUNLATCH;
+		mtspr(SPRN_CTRLT, ctrl);
+	}
 
 	ti->local_flags |= _TLF_RUNLATCH;
 }
@@ -2007,13 +2021,18 @@ void notrace __ppc64_runlatch_on(void)
 void notrace __ppc64_runlatch_off(void)
 {
 	struct thread_info *ti = current_thread_info();
-	unsigned long ctrl;
 
 	ti->local_flags &= ~_TLF_RUNLATCH;
 
-	ctrl = mfspr(SPRN_CTRLF);
-	ctrl &= ~CTRL_RUNLATCH;
-	mtspr(SPRN_CTRLT, ctrl);
+	if (cpu_has_feature(CPU_FTR_ARCH_206)) {
+		mtspr(SPRN_CTRLT, 0);
+	} else {
+		unsigned long ctrl;
+
+		ctrl = mfspr(SPRN_CTRLF);
+		ctrl &= ~CTRL_RUNLATCH;
+		mtspr(SPRN_CTRLT, ctrl);
+	}
 }
 #endif /* CONFIG_PPC64 */
 
-- 
2.11.0

  parent reply	other threads:[~2017-08-05 17:03 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-08-05 17:02 [PATCH 00/13] idle and soft-irq improvements and POWER9 idle optimisation Nicholas Piggin
2017-08-05 17:02 ` [PATCH 01/13] powerpc/64s: masked interrupt avoid branch Nicholas Piggin
2017-08-05 17:02 ` [PATCH 02/13] powerpc/64s: masked interrupt avoid instruction Nicholas Piggin
2017-08-05 17:02 ` [PATCH 03/13] powerpc/64s: masked interrupt returns to kernel so avoid r13 restore Nicholas Piggin
2017-08-05 17:02 ` [PATCH 04/13] powerpc/64: cleanup __check_irq_replay Nicholas Piggin
2017-08-05 17:02 ` [PATCH 05/13] powerpc/64s: irq replay merge HV and non-HV paths for doorbell replay Nicholas Piggin
2017-08-05 17:02 ` [PATCH 06/13] powerpc/64s: irq replay external use the HV handler in HV mode on POWER9 Nicholas Piggin
2017-08-05 17:02 ` [PATCH 07/13] powerpc/64: remove redundant instruction in interrupt replay Nicholas Piggin
2017-08-05 17:02 ` [PATCH 08/13] powerpc/64s: irq replay remove spurious irq reason Nicholas Piggin
2017-08-05 23:00   ` Benjamin Herrenschmidt
2017-08-06  0:51     ` Nicholas Piggin
2017-08-10 13:12       ` Michael Ellerman
2017-08-05 17:02 ` Nicholas Piggin [this message]
2017-08-05 17:02 ` [PATCH 10/13] powerpc/64s: idle simplify KVM idle on POWER9 Nicholas Piggin
2017-08-05 17:02   ` Nicholas Piggin
2017-08-08 10:36   ` Gautham R Shenoy
2017-08-08 10:48     ` Gautham R Shenoy
2017-08-08 12:42     ` Nicholas Piggin
2017-08-08 12:42       ` Nicholas Piggin
2017-08-10  6:24       ` Gautham R Shenoy
2017-08-10  6:36         ` Gautham R Shenoy
2017-08-10 13:14   ` Michael Ellerman
2017-08-10 13:14     ` Michael Ellerman
2017-08-10 13:53     ` Nicholas Piggin
2017-08-10 13:53       ` Nicholas Piggin
2017-08-05 17:02 ` [PATCH 11/13] powerpc/64s: idle POWER9 can execute stop without ptesync Nicholas Piggin
2017-08-08 10:37   ` Gautham R Shenoy
2017-08-10 13:15   ` Michael Ellerman
2017-08-10 14:03     ` Nicholas Piggin
2017-08-05 17:02 ` [PATCH 12/13] powerpc/64s: idle POWER9 can execute stop in virtual mode Nicholas Piggin
2017-08-05 22:57   ` Benjamin Herrenschmidt
2017-08-08 10:45   ` Gautham R Shenoy
2017-08-05 17:02 ` [PATCH 13/13] powerpc/64s: idle ESL=0 stop can avoid all save/restore overhead Nicholas Piggin
2017-08-05 17:11   ` Nicholas Piggin
2017-08-08 10:49   ` Gautham R Shenoy

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=20170805170241.22966-10-npiggin@gmail.com \
    --to=npiggin@gmail.com \
    --cc=linuxppc-dev@lists.ozlabs.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.