LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Don Zickus <dzickus@redhat.com>, Andi Kleen <ak@linux.intel.com>,
	dave.hansen@linux.intel.com,
	Stephane Eranian <eranian@google.com>,
	jmario@redhat.com,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	Arnaldo Carvalho de Melo <acme@infradead.org>,
	Ingo Molnar <mingo@kernel.org>
Subject: Re: [PATCH] perf, x86: Optimize intel_pmu_pebs_fixup_ip()
Date: Thu, 24 Oct 2013 12:52:06 +0200
Message-ID: <20131024105206.GM2490@laptop.programming.kicks-ass.net> (raw)
In-Reply-To: <20131023204838.GB19466@laptop.lan>

On Wed, Oct 23, 2013 at 10:48:38PM +0200, Peter Zijlstra wrote:
> I'll also make sure to test we actually hit the fault path
> by concurrently running something like:
> 
>  while :; echo 1 > /proc/sys/vm/drop_caches ; done
> 
> while doing perf top or so.. 

So the below appears to work; I've ran:

  while :; do echo 1 > /proc/sys/vm/drop_caches; sleep 1; done &
  while :; do make O=defconfig-build/ clean; perf record -a -g fp -e cycles:pp make O=defconfig-build/ -s -j64; done

And verified that the if (in_nmi()) trace_printk() was visible in the
trace output verifying we indeed took the fault from the NMI code.

I've had this running for ~ 30 minutes or so and the machine is still
healthy.

Don, can you give this stuff a spin on your system?

---
 arch/x86/lib/usercopy.c | 43 +++++++++++++++----------------------------
 arch/x86/mm/fault.c     | 43 +++++++++++++++++++++++--------------------
 2 files changed, 38 insertions(+), 48 deletions(-)

diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index 4f74d94c8d97..5465b8613944 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -11,39 +11,26 @@
 #include <linux/sched.h>
 
 /*
- * best effort, GUP based copy_from_user() that is NMI-safe
+ * We rely on the nested NMI work to allow atomic faults from the NMI path; the
+ * nested NMI paths are careful to preserve CR2.
  */
 unsigned long
 copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 {
-	unsigned long offset, addr = (unsigned long)from;
-	unsigned long size, len = 0;
-	struct page *page;
-	void *map;
-	int ret;
+	unsigned long ret;
 
 	if (__range_not_ok(from, n, TASK_SIZE))
-		return len;
-
-	do {
-		ret = __get_user_pages_fast(addr, 1, 0, &page);
-		if (!ret)
-			break;
-
-		offset = addr & (PAGE_SIZE - 1);
-		size = min(PAGE_SIZE - offset, n - len);
-
-		map = kmap_atomic(page);
-		memcpy(to, map+offset, size);
-		kunmap_atomic(map);
-		put_page(page);
-
-		len  += size;
-		to   += size;
-		addr += size;
-
-	} while (len < n);
-
-	return len;
+		return 0;
+
+	/*
+	 * Even though this function is typically called from NMI/IRQ context
+	 * disable pagefaults so that its behaviour is consistent even when
+	 * called form other contexts.
+	 */
+	pagefault_disable();
+	ret = __copy_from_user_inatomic(to, from, n);
+	pagefault_enable();
+
+	return n - ret;
 }
 EXPORT_SYMBOL_GPL(copy_from_user_nmi);
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 3aaeffcfd67a..506564b13ba7 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -51,7 +51,7 @@ kmmio_fault(struct pt_regs *regs, unsigned long addr)
 	return 0;
 }
 
-static inline int __kprobes notify_page_fault(struct pt_regs *regs)
+static inline int __kprobes kprobes_fault(struct pt_regs *regs)
 {
 	int ret = 0;
 
@@ -1048,7 +1048,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
 			return;
 
 		/* kprobes don't want to hook the spurious faults: */
-		if (notify_page_fault(regs))
+		if (kprobes_fault(regs))
 			return;
 		/*
 		 * Don't take the mm semaphore here. If we fixup a prefetch
@@ -1060,23 +1060,8 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	}
 
 	/* kprobes don't want to hook the spurious faults: */
-	if (unlikely(notify_page_fault(regs)))
+	if (unlikely(kprobes_fault(regs)))
 		return;
-	/*
-	 * It's safe to allow irq's after cr2 has been saved and the
-	 * vmalloc fault has been handled.
-	 *
-	 * User-mode registers count as a user access even for any
-	 * potential system fault or CPU buglet:
-	 */
-	if (user_mode_vm(regs)) {
-		local_irq_enable();
-		error_code |= PF_USER;
-		flags |= FAULT_FLAG_USER;
-	} else {
-		if (regs->flags & X86_EFLAGS_IF)
-			local_irq_enable();
-	}
 
 	if (unlikely(error_code & PF_RSVD))
 		pgtable_bad(regs, error_code, address);
@@ -1088,17 +1073,35 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
 		}
 	}
 
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
-
 	/*
 	 * If we're in an interrupt, have no user context or are running
 	 * in an atomic region then we must not take the fault:
 	 */
 	if (unlikely(in_atomic() || !mm)) {
+		if (in_nmi())
+			trace_printk("YIPEE!!!\n");
 		bad_area_nosemaphore(regs, error_code, address);
 		return;
 	}
 
+	/*
+	 * It's safe to allow irq's after cr2 has been saved and the
+	 * vmalloc fault has been handled.
+	 *
+	 * User-mode registers count as a user access even for any
+	 * potential system fault or CPU buglet:
+	 */
+	if (user_mode_vm(regs)) {
+		local_irq_enable();
+		error_code |= PF_USER;
+		flags |= FAULT_FLAG_USER;
+	} else {
+		if (regs->flags & X86_EFLAGS_IF)
+			local_irq_enable();
+	}
+
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
+
 	if (error_code & PF_WRITE)
 		flags |= FAULT_FLAG_WRITE;
 

  reply index

Thread overview: 47+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-10-14 20:35 x86, perf: throttling issues with long nmi latencies Don Zickus
2013-10-14 21:28 ` Andi Kleen
2013-10-15 10:14 ` Peter Zijlstra
2013-10-15 13:02   ` Peter Zijlstra
2013-10-15 14:32     ` Peter Zijlstra
2013-10-15 15:07       ` Peter Zijlstra
2013-10-15 15:41         ` Don Zickus
2013-10-16 10:57           ` [PATCH] perf, x86: Optimize intel_pmu_pebs_fixup_ip() Peter Zijlstra
2013-10-16 12:46             ` Don Zickus
2013-10-16 13:31               ` Peter Zijlstra
2013-10-16 13:54                 ` Don Zickus
2013-10-17 11:21                 ` Peter Zijlstra
2013-10-17 13:33                 ` Peter Zijlstra
2013-10-29 14:07                   ` [tip:perf/urgent] perf/x86: Fix NMI measurements tip-bot for Peter Zijlstra
2013-10-16 20:52             ` [PATCH] perf, x86: Optimize intel_pmu_pebs_fixup_ip() Andi Kleen
2013-10-16 21:03               ` Peter Zijlstra
2013-10-16 23:07                 ` Peter Zijlstra
2013-10-17  9:41                   ` Peter Zijlstra
2013-10-17 16:00                     ` Don Zickus
2013-10-17 16:04                       ` Don Zickus
2013-10-17 16:30                         ` Peter Zijlstra
2013-10-17 18:26                           ` Linus Torvalds
2013-10-17 21:08                             ` Peter Zijlstra
2013-10-17 21:11                               ` Peter Zijlstra
2013-10-17 22:01                             ` Peter Zijlstra
2013-10-17 22:27                               ` Linus Torvalds
2013-10-22 21:12                                 ` Peter Zijlstra
2013-10-23  7:09                                   ` Linus Torvalds
2013-10-23 20:48                                     ` Peter Zijlstra
2013-10-24 10:52                                       ` Peter Zijlstra [this message]
2013-10-24 13:47                                         ` Don Zickus
2013-10-24 14:06                                           ` Peter Zijlstra
2013-10-25 16:33                                         ` Don Zickus
2013-10-25 17:03                                           ` Peter Zijlstra
2013-10-26 10:36                                           ` Ingo Molnar
2013-10-28 13:19                                             ` Don Zickus
2013-10-29 14:08                                         ` [tip:perf/core] perf/x86: Further optimize copy_from_user_nmi() tip-bot for Peter Zijlstra
2013-10-23  7:44                                   ` [PATCH] perf, x86: Optimize intel_pmu_pebs_fixup_ip() Ingo Molnar
2013-10-17 14:49             ` Don Zickus
2013-10-17 14:51               ` Peter Zijlstra
2013-10-17 15:03                 ` Don Zickus
2013-10-17 15:09                   ` Peter Zijlstra
2013-10-17 15:11                     ` Peter Zijlstra
2013-10-17 16:50             ` [tip:perf/core] perf/x86: " tip-bot for Peter Zijlstra
2013-10-15 16:22         ` x86, perf: throttling issues with long nmi latencies Don Zickus
2013-10-15 14:36     ` Don Zickus
2013-10-15 14:39       ` Peter Zijlstra

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=20131024105206.GM2490@laptop.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=acme@infradead.org \
    --cc=ak@linux.intel.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=dzickus@redhat.com \
    --cc=eranian@google.com \
    --cc=jmario@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=torvalds@linux-foundation.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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git
	git clone --mirror https://lore.kernel.org/lkml/10 lkml/git/10.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git