All of lore.kernel.org
 help / color / mirror / Atom feed
From: riel@redhat.com
To: linux-kernel@vger.kernel.org
Cc: hpa@zytor.com, mingo@kernel.org, bp@alien8.de,
	dave.hansen@linux.intel.com, luto@kernel.org, oleg@redhat.comm
Subject: [PATCH 2/2] x86/fpu: split old & new fpu handling into separate functions
Date: Fri, 14 Oct 2016 08:15:31 -0400	[thread overview]
Message-ID: <1476447331-21566-3-git-send-email-riel@redhat.com> (raw)
In-Reply-To: <1476447331-21566-1-git-send-email-riel@redhat.com>

From: Rik van Riel <riel@redhat.com>

By moving all of the new fpu state handling into switch_fpu_finish,
the code can be simplified some more. This does get rid of the
prefetch, but given the size of the fpu register state on modern
CPUs, and the amount of work done by __switch_to in-between both
functions, the value of a single cache line prefetch seems somewhat
dubious anyway.

Signed-off-by: Rik van Riel <riel@redhat.com>
---
 arch/x86/include/asm/fpu/internal.h | 48 ++++++++++++-------------------------
 arch/x86/kernel/process_32.c        |  5 ++--
 arch/x86/kernel/process_64.c        |  5 ++--
 3 files changed, 19 insertions(+), 39 deletions(-)

diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index a75324675311..621ba3bfa2a7 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -552,27 +552,15 @@ static inline int fpregs_active(void)
  *
  * This is a two-stage process:
  *
- *  - switch_fpu_prepare() saves the old state and
- *    sets the new state of the CR0.TS bit. This is
- *    done within the context of the old process.
+ *  - switch_fpu_prepare() saves the old state.
+ *    This is done within the context of the old process.
  *
  *  - switch_fpu_finish() restores the new state as
  *    necessary.
  */
-typedef struct { int preload; } fpu_switch_t;
-
-static inline fpu_switch_t
-switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
+static inline void
+switch_fpu_prepare(struct fpu *old_fpu, int cpu)
 {
-	fpu_switch_t fpu;
-
-	/*
-	 * If the task has used the math, pre-load the FPU on xsave processors
-	 * or if the past 5 consecutive context-switches used math.
-	 */
-	fpu.preload = static_cpu_has(X86_FEATURE_FPU) &&
-		      new_fpu->fpstate_active;
-
 	if (old_fpu->fpregs_active) {
 		if (!copy_fpregs_to_fpstate(old_fpu))
 			old_fpu->last_cpu = -1;
@@ -584,16 +572,6 @@ switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
 		trace_x86_fpu_regs_deactivated(old_fpu);
 	} else
 		old_fpu->last_cpu = -1;
-
-	if (fpu.preload) {
-		if (fpregs_state_valid(new_fpu, cpu))
-			fpu.preload = 0;
-		else
-			prefetch(&new_fpu->state);
-		fpregs_activate(new_fpu);
-	}
-
-	return fpu;
 }
 
 /*
@@ -601,15 +579,19 @@ switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
  */
 
 /*
- * By the time this gets called, we've already cleared CR0.TS and
- * given the process the FPU if we are going to preload the FPU
- * state - all we need to do is to conditionally restore the register
- * state itself.
+ * Set up the userspace FPU context for the new task, if the task
+ * has used the FPU.
  */
-static inline void switch_fpu_finish(struct fpu *new_fpu, fpu_switch_t fpu_switch)
+static inline void switch_fpu_finish(struct fpu *new_fpu, int cpu)
 {
-	if (fpu_switch.preload)
-		copy_kernel_to_fpregs(&new_fpu->state);
+	bool preload = static_cpu_has(X86_FEATURE_FPU) &&
+		       new_fpu->fpstate_active;
+
+	if (preload) {
+		if (!fpregs_state_valid(new_fpu, cpu))
+			copy_kernel_to_fpregs(&new_fpu->state);
+		fpregs_activate(new_fpu);
+	}
 }
 
 /*
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index bd7be8efdc4c..7dc8c9c3d801 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -232,11 +232,10 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	struct fpu *next_fpu = &next->fpu;
 	int cpu = smp_processor_id();
 	struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
-	fpu_switch_t fpu_switch;
 
 	/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 
-	fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu);
+	switch_fpu_prepare(prev_fpu, cpu);
 
 	/*
 	 * Save away %gs. No need to save %fs, as it was saved on the
@@ -295,7 +294,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	if (prev->gs | next->gs)
 		lazy_load_gs(next->gs);
 
-	switch_fpu_finish(next_fpu, fpu_switch);
+	switch_fpu_finish(next_fpu, cpu);
 
 	this_cpu_write(current_task, next_p);
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index ee944bd2310d..705669efb762 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -264,9 +264,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	int cpu = smp_processor_id();
 	struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
 	unsigned prev_fsindex, prev_gsindex;
-	fpu_switch_t fpu_switch;
 
-	fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu);
+	switch_fpu_prepare(prev_fpu, cpu);
 
 	/* We must save %fs and %gs before load_TLS() because
 	 * %fs and %gs may be cleared by load_TLS().
@@ -416,7 +415,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 		prev->gsbase = 0;
 	prev->gsindex = prev_gsindex;
 
-	switch_fpu_finish(next_fpu, fpu_switch);
+	switch_fpu_finish(next_fpu, cpu);
 
 	/*
 	 * Switch the PDA and FPU contexts.
-- 
2.7.4

  parent reply	other threads:[~2016-10-14 12:16 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-10-14 12:15 [PATCH 0/2] x86/fpu: two more FPU cleanups riel
2016-10-14 12:15 ` [PATCH 1/2] x86/fpu: remove cpu argument to __cpu_invalidate_fpregs_state riel
2016-10-14 16:53   ` Dave Hansen
2016-10-16 11:25   ` [tip:x86/fpu] x86/fpu: Remove 'cpu' argument from __cpu_invalidate_fpregs_state() tip-bot for Rik van Riel
2016-10-14 12:15 ` riel [this message]
2016-10-14 17:14   ` [PATCH 2/2] x86/fpu: split old & new fpu handling into separate functions Dave Hansen
2016-10-16 11:25   ` [tip:x86/fpu] x86/fpu: Split old_fpu & new_fpu " tip-bot for Rik van Riel
2017-01-24 12:13     ` you have a new message from... c92Y Izuchukwu Francis
2017-02-10 13:52       ` Izuchukwu Francis

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=1476447331-21566-3-git-send-email-riel@redhat.com \
    --to=riel@redhat.com \
    --cc=bp@alien8.de \
    --cc=dave.hansen@linux.intel.com \
    --cc=hpa@zytor.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luto@kernel.org \
    --cc=mingo@kernel.org \
    --cc=oleg@redhat.comm \
    /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.