From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: Ingo Molnar <mingo@elte.hu>, Paul Mackerras <paulus@samba.org>,
David Miller <davem@davemloft.net>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Jens Axboe <jens.axboe@oracle.com>,
linux-kernel@vger.kernel.org,
Peter Zijlstra <a.p.zijlstra@chello.nl>
Subject: [RFC][PATCH 2/2] perf,sparc: Use vmalloc to back the mmap() array
Date: Mon, 21 Sep 2009 16:08:50 +0200 [thread overview]
Message-ID: <20090921141751.310933291@chello.nl> (raw)
In-Reply-To: 20090921140848.444528343@chello.nl
[-- Attachment #1: perf-sparc-mmap-vmalloc.patch --]
[-- Type: text/plain, Size: 2389 bytes --]
Implement vmalloc() backed storage for perf_mmap().
Alternatively we could put this code in kernel/perf_counter_vmalloc.c
and conditionally compile that or something, since there really isn't
anything Sparc specific about it.
Suggested-by: David Miller <davem@davemloft.net>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
---
arch/sparc/kernel/perf_counter.c | 72 +++++++++++++++++++++++++++++++++++++++
1 file changed, 72 insertions(+)
Index: linux-2.6/arch/sparc/kernel/perf_counter.c
===================================================================
--- linux-2.6.orig/arch/sparc/kernel/perf_counter.c
+++ linux-2.6/arch/sparc/kernel/perf_counter.c
@@ -14,6 +14,7 @@
#include <linux/perf_counter.h>
#include <linux/kprobes.h>
+#include <linux/vmalloc.h>
#include <linux/kernel.h>
#include <linux/kdebug.h>
#include <linux/mutex.h>
@@ -554,3 +555,74 @@ void __init init_hw_perf_counters(void)
register_die_notifier(&perf_counter_nmi_notifier);
}
+
+struct page *perf_mmap_to_page(void *addr)
+{
+ return vmalloc_to_page(addr);
+}
+
+static void perf_mmap_unmark_page(void *addr)
+{
+ struct page *page = vmalloc_to_page(addr);
+
+ page->mapping = NULL;
+}
+
+static void perf_mmap_data_free_work(struct work_struct *work)
+{
+ struct perf_mmap_data *data;
+ void *base;
+ int i;
+
+ data = container_of(work, struct perf_mmap_data, work);
+
+ base = data->user_page;
+ for (i = 0; i < data->nr_pages + 1; i++)
+ perf_mmap_unmark_page(base + (i * PAGE_SIZE));
+
+ vfree(base);
+}
+
+void perf_mmap_data_free(struct perf_mmap_data *data)
+{
+ schedule_work(&data->work);
+}
+
+struct perf_mmap_data *
+perf_mmap_data_alloc(struct perf_counter *counter, int nr_pages)
+{
+ struct perf_mmap_data *data;
+ unsigned long size;
+ void *all_buf;
+ int i;
+
+ WARN_ON(atomic_read(&counter->mmap_count));
+
+ size = sizeof(struct perf_mmap_data);
+ size += nr_pages * sizeof(void *);
+
+ data = kzalloc(size, GFP_KERNEL);
+ if (!data)
+ goto fail;
+
+ INIT_WORK(&data->work, perf_mmap_data_free_work);
+
+ all_buf = vmalloc_user((nr_pages + 1) * PAGE_SIZE);
+ if (!all_buf)
+ goto fail_all_buf;
+
+ data->user_page = all_buf;
+
+ for (i = 0; i < nr_pages; i++)
+ data->data_pages[i] = all_buf + ((i + 1) * PAGE_SIZE);
+
+ data->nr_pages = nr_pages;
+
+ return data;
+
+fail_all_buf:
+ kfree(data);
+
+fail:
+ return NULL;
+}
--
next prev parent reply other threads:[~2009-09-21 14:20 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-09-21 14:08 [RFC][PATCH 0/2] perf vs d-cache aliasses Peter Zijlstra
2009-09-21 14:08 ` [RFC][PATCH 1/2] perf: Provide weak interfaces to mmap() backing Peter Zijlstra
2009-09-21 14:08 ` Peter Zijlstra [this message]
2009-09-21 17:10 ` [RFC][PATCH 0/2] perf vs d-cache aliasses David Miller
2009-09-22 9:02 ` Ingo Molnar
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=20090921141751.310933291@chello.nl \
--to=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=davem@davemloft.net \
--cc=jens.axboe@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=paulus@samba.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox