All of lore.kernel.org
 help / color / mirror / Atom feed
From: Alex Shi <alex.shi@intel.com>
To: tglx@linutronix.de, mingo@redhat.com, hpa@zytor.com,
	arnd@arndb.de, rostedt@goodmis.org, fweisbec@gmail.com
Cc: jeremy@goop.org, riel@redhat.com, luto@mit.edu,
	alex.shi@intel.com, avi@redhat.com, len.brown@intel.com,
	dhowells@redhat.com, fenghua.yu@intel.com,
	borislav.petkov@amd.com, yinghai@kernel.org, ak@linux.intel.com,
	cpw@sgi.com, steiner@sgi.com, akpm@linux-foundation.org,
	penberg@kernel.org, hughd@google.com, rientjes@google.com,
	kosaki.motohiro@jp.fujitsu.com, n-horiguchi@ah.jp.nec.com,
	tj@kernel.org, oleg@redhat.com, axboe@kernel.dk,
	jmorris@namei.org, a.p.zijlstra@chello.nl,
	kamezawa.hiroyu@jp.fujitsu.com, viro@zeniv.linux.org.uk,
	linux-kernel@vger.kernel.org, yongjie.ren@intel.com
Subject: [PATCH v5 7/7] x86/tlb: add tlb_flushall_shift knob into debugfs
Date: Tue, 15 May 2012 16:55:38 +0800	[thread overview]
Message-ID: <1337072138-8323-8-git-send-email-alex.shi@intel.com> (raw)
In-Reply-To: <1337072138-8323-1-git-send-email-alex.shi@intel.com>

kernel will replace cr3 rewrite with invlpg when
  tlb_flush_entries <= active_tlb_entries / 2^tlb_flushall_factor
if tlb_flushall_factor is -1, kernel won't do this replacement.

User can modify its value according to specific CPU/applications.

Thanks for Borislav providing the help message of
CONFIG_DEBUG_TLBFLUSH.

Signed-off-by: Alex Shi <alex.shi@intel.com>
---
 arch/x86/Kconfig.debug |   19 +++++++++++++++++++
 arch/x86/mm/tlb.c      |   48 ++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 67 insertions(+), 0 deletions(-)

diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index e46c214..b322f12 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -129,6 +129,25 @@ config DOUBLEFAULT
 	  option saves about 4k and might cause you much additional grey
 	  hair.
 
+config DEBUG_TLBFLUSH
+	bool "Set upper limit of TLB entries to flush one-by-one"
+	depends on DEBUG_KERNEL && (X86_64 || X86_INVLPG)
+	---help---
+
+	X86-only for now.
+
+	This option allows the user to tune the amount of TLB entries the
+	kernel flushes one-by-one instead of doing a full TLB flush. In
+	certain situations, the former is cheaper. This is controlled by the
+	tlb_flushall_shift knob under /sys/kernel/debug/x86. If you set it
+	to -1, the code flushes the whole TLB unconditionally. Otherwise,
+	for positive values of it, the kernel will use single TLB entry
+	invalidating instructions according to the following formula:
+
+	flush_entries <= active_tlb_entries / 2^tlb_flushall_shift
+
+	If in doubt, say "N".
+
 config IOMMU_DEBUG
 	bool "Enable IOMMU debugging"
 	depends on GART_IOMMU && DEBUG_KERNEL
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index b2e25e8..b77c764 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -12,6 +12,7 @@
 #include <asm/cache.h>
 #include <asm/apic.h>
 #include <asm/uv/uv.h>
+#include <linux/debugfs.h>
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate)
 			= { &init_mm, 0, };
@@ -429,3 +430,50 @@ void flush_tlb_all(void)
 {
 	on_each_cpu(do_flush_tlb_all, NULL, 1);
 }
+
+#ifdef CONFIG_DEBUG_TLBFLUSH
+static ssize_t tlbflush_read_file(struct file *file, char __user *user_buf,
+			     size_t count, loff_t *ppos)
+{
+	char buf[32];
+	unsigned int len;
+
+	len = sprintf(buf, "%hd\n", tlb_flushall_shift);
+	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+static ssize_t tlbflush_write_file(struct file *file,
+		 const char __user *user_buf, size_t count, loff_t *ppos)
+{
+	char buf[32];
+	ssize_t len;
+	u16 shift;
+
+	len = min(count, sizeof(buf) - 1);
+	if (copy_from_user(buf, user_buf, len))
+		return -EFAULT;
+
+	buf[len] = '\0';
+	if (kstrtos16(buf, 0, &shift))
+		return -EINVAL;
+
+	tlb_flushall_shift = shift;
+	return count;
+}
+
+static const struct file_operations fops_tlbflush = {
+	.read = tlbflush_read_file,
+	.write = tlbflush_write_file,
+	.llseek = default_llseek,
+};
+
+static int __cpuinit create_tlb_flushall_shift(void)
+{
+	if (cpu_has_invlpg) {
+		debugfs_create_file("tlb_flushall_shift", S_IRUSR | S_IWUSR,
+			arch_debugfs_dir, NULL, &fops_tlbflush);
+	}
+	return 0;
+}
+late_initcall(create_tlb_flushall_shift);
+#endif
-- 
1.7.5.4


      parent reply	other threads:[~2012-05-15  8:57 UTC|newest]

Thread overview: 50+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-05-15  8:55 [PATCH v5 0/7] tlb flush optimization for x86 Alex Shi
2012-05-15  8:55 ` [PATCH v5 1/7] x86/tlb: unify TLB_FLUSH_ALL definition Alex Shi
2012-05-15  8:55 ` [PATCH v5 2/7] x86/tlb_info: get last level TLB entry number of CPU Alex Shi
2012-05-15  8:55 ` [PATCH v5 3/7] x86/flush_tlb: try flush_tlb_single one by one in flush_tlb_range Alex Shi
2012-05-15  8:55 ` [PATCH v5 4/7] x86/tlb: fall back to flush all when meet a THP large page Alex Shi
2012-05-15  8:55 ` [PATCH v5 5/7] x86/tlb: add tlb_flushall_shift for specific CPU Alex Shi
2012-05-16  6:49   ` Alex Shi
2012-05-16 17:55     ` H. Peter Anvin
2012-05-17  1:46       ` Alex Shi
2012-05-15  8:55 ` [PATCH v5 6/7] x86/tlb: optimizing flush_tlb_mm Alex Shi
2012-05-15  9:11   ` Peter Zijlstra
2012-05-15  9:15   ` Nick Piggin
2012-05-15  9:17     ` Nick Piggin
2012-05-15 12:58       ` Luming Yu
2012-05-15 13:06         ` Peter Zijlstra
2012-05-15 13:27           ` Luming Yu
2012-05-15 13:28             ` Alex Shi
2012-05-15 13:33           ` Alex Shi
2012-05-15 13:39           ` Steven Rostedt
2012-05-15 14:04             ` Borislav Petkov
2012-05-15 13:08         ` Luming Yu
2012-05-15 14:07       ` Alex Shi
2012-05-15  9:18     ` Peter Zijlstra
2012-05-15  9:52       ` Nick Piggin
2012-05-15 10:00         ` Peter Zijlstra
2012-05-15 10:06           ` Nick Piggin
2012-05-15 10:13             ` Peter Zijlstra
2012-05-15 14:04       ` Alex Shi
2012-05-15 13:24     ` Alex Shi
2012-05-15 14:36       ` Peter Zijlstra
2012-05-15 14:57         ` Peter Zijlstra
2012-05-15 15:01           ` Alex Shi
2012-05-16  6:46           ` Alex Shi
2012-05-16  6:46             ` Alex Shi
2012-05-16  8:00             ` Peter Zijlstra
2012-05-16  8:04               ` Peter Zijlstra
2012-05-16  8:53                 ` Alex Shi
2012-05-16  8:58                   ` Peter Zijlstra
2012-05-16 10:58                     ` Alex Shi
2012-05-16 11:04                       ` Peter Zijlstra
2012-05-16 12:57                         ` Alex Shi
2012-05-16 13:34               ` Alex Shi
2012-05-16 13:34                 ` Alex Shi
2012-05-16 21:09                 ` Peter Zijlstra
2012-05-17  0:43                   ` Alex Shi
2012-05-17  2:07                     ` Steven Rostedt
2012-05-17  8:04                       ` Alex Shi
2012-05-17  2:14                   ` Paul Mundt
2012-05-16 13:44               ` Alex Shi
2012-05-15  8:55 ` Alex Shi [this message]

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=1337072138-8323-8-git-send-email-alex.shi@intel.com \
    --to=alex.shi@intel.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=ak@linux.intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=arnd@arndb.de \
    --cc=avi@redhat.com \
    --cc=axboe@kernel.dk \
    --cc=borislav.petkov@amd.com \
    --cc=cpw@sgi.com \
    --cc=dhowells@redhat.com \
    --cc=fenghua.yu@intel.com \
    --cc=fweisbec@gmail.com \
    --cc=hpa@zytor.com \
    --cc=hughd@google.com \
    --cc=jeremy@goop.org \
    --cc=jmorris@namei.org \
    --cc=kamezawa.hiroyu@jp.fujitsu.com \
    --cc=kosaki.motohiro@jp.fujitsu.com \
    --cc=len.brown@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luto@mit.edu \
    --cc=mingo@redhat.com \
    --cc=n-horiguchi@ah.jp.nec.com \
    --cc=oleg@redhat.com \
    --cc=penberg@kernel.org \
    --cc=riel@redhat.com \
    --cc=rientjes@google.com \
    --cc=rostedt@goodmis.org \
    --cc=steiner@sgi.com \
    --cc=tglx@linutronix.de \
    --cc=tj@kernel.org \
    --cc=viro@zeniv.linux.org.uk \
    --cc=yinghai@kernel.org \
    --cc=yongjie.ren@intel.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 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.