From: Juan Quintela <quintela@redhat.com>
To: qemu-devel@nongnu.org
Subject: [Qemu-devel] [PATCH 35/38] memory: syncronize kvm bitmap using bitmaps operations
Date: Tue, 17 Dec 2013 16:26:11 +0100 [thread overview]
Message-ID: <1387293974-24718-36-git-send-email-quintela@redhat.com> (raw)
In-Reply-To: <1387293974-24718-1-git-send-email-quintela@redhat.com>
If bitmaps are aligned properly, use bitmap operations. If they are
not, just use old bit at a time code.
Signed-off-by: Juan Quintela <quintela@redhat.com>
---
include/exec/ram_addr.h | 54 ++++++++++++++++++++++++++++++++-----------------
1 file changed, 36 insertions(+), 18 deletions(-)
diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h
index c6736ed..33c8acc 100644
--- a/include/exec/ram_addr.h
+++ b/include/exec/ram_addr.h
@@ -83,29 +83,47 @@ static inline void cpu_physical_memory_set_dirty_lebitmap(unsigned long *bitmap,
ram_addr_t start,
ram_addr_t pages)
{
- unsigned int i, j;
+ unsigned long i, j;
unsigned long page_number, c;
hwaddr addr;
ram_addr_t ram_addr;
- unsigned int len = (pages + HOST_LONG_BITS - 1) / HOST_LONG_BITS;
+ unsigned long len = (pages + HOST_LONG_BITS - 1) / HOST_LONG_BITS;
unsigned long hpratio = getpagesize() / TARGET_PAGE_SIZE;
+ unsigned long page = BIT_WORD(start >> TARGET_PAGE_BITS);
- /*
- * bitmap-traveling is faster than memory-traveling (for addr...)
- * especially when most of the memory is not dirty.
- */
- for (i = 0; i < len; i++) {
- if (bitmap[i] != 0) {
- c = leul_to_cpu(bitmap[i]);
- do {
- j = ffsl(c) - 1;
- c &= ~(1ul << j);
- page_number = (i * HOST_LONG_BITS + j) * hpratio;
- addr = page_number * TARGET_PAGE_SIZE;
- ram_addr = start + addr;
- cpu_physical_memory_set_dirty_range(ram_addr,
- TARGET_PAGE_SIZE * hpratio);
- } while (c != 0);
+ /* start address is aligned at the start of a word? */
+ if (((page * BITS_PER_LONG) << TARGET_PAGE_BITS) == start) {
+ long k;
+ long nr = BITS_TO_LONGS(pages);
+
+ for (k = 0; k < nr; k++) {
+ if (bitmap[k]) {
+ unsigned long temp = leul_to_cpu(bitmap[k]);
+
+ ram_list.dirty_memory[DIRTY_MEMORY_MIGRATION][page + k] |= temp;
+ ram_list.dirty_memory[DIRTY_MEMORY_VGA][page + k] |= temp;
+ ram_list.dirty_memory[DIRTY_MEMORY_CODE][page + k] |= temp;
+ }
+ }
+ xen_modified_memory(start, pages);
+ } else {
+ /*
+ * bitmap-traveling is faster than memory-traveling (for addr...)
+ * especially when most of the memory is not dirty.
+ */
+ for (i = 0; i < len; i++) {
+ if (bitmap[i] != 0) {
+ c = leul_to_cpu(bitmap[i]);
+ do {
+ j = ffsl(c) - 1;
+ c &= ~(1ul << j);
+ page_number = (i * HOST_LONG_BITS + j) * hpratio;
+ addr = page_number * TARGET_PAGE_SIZE;
+ ram_addr = start + addr;
+ cpu_physical_memory_set_dirty_range(ram_addr,
+ TARGET_PAGE_SIZE * hpratio);
+ } while (c != 0);
+ }
}
}
}
--
1.8.3.1
next prev parent reply other threads:[~2013-12-17 15:27 UTC|newest]
Thread overview: 78+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-12-17 15:25 [Qemu-devel] [PATCH v3 00/38] bitmap queue Juan Quintela
2013-12-17 15:25 ` [Qemu-devel] [PATCH 01/38] bitmap: use long as index Juan Quintela
2013-12-17 18:05 ` Eric Blake
2013-12-17 18:27 ` Stefan Weil
2013-12-17 20:21 ` Juan Quintela
2013-12-24 13:24 ` Orit Wasserman
2013-12-17 15:25 ` [Qemu-devel] [PATCH 02/38] memory: cpu_physical_memory_set_dirty_flags() result is never used Juan Quintela
2013-12-17 15:25 ` [Qemu-devel] [PATCH 03/38] memory: cpu_physical_memory_set_dirty_range() return void Juan Quintela
2013-12-17 15:25 ` [Qemu-devel] [PATCH 04/38] exec: use accessor function to know if memory is dirty Juan Quintela
2013-12-17 15:25 ` [Qemu-devel] [PATCH 05/38] memory: create function to set a single dirty bit Juan Quintela
2013-12-17 15:25 ` [Qemu-devel] [PATCH 06/38] exec: create function to get " Juan Quintela
2013-12-17 15:25 ` [Qemu-devel] [PATCH 07/38] memory: make cpu_physical_memory_is_dirty return bool Juan Quintela
2013-12-18 10:08 ` Orit Wasserman
2013-12-17 15:25 ` [Qemu-devel] [PATCH 08/38] memory: all users of cpu_physical_memory_get_dirty used only one flag Juan Quintela
2013-12-18 10:09 ` Orit Wasserman
2013-12-17 15:25 ` [Qemu-devel] [PATCH 09/38] memory: set single dirty flags when possible Juan Quintela
2013-12-18 10:10 ` Orit Wasserman
2013-12-17 15:25 ` [Qemu-devel] [PATCH 10/38] memory: cpu_physical_memory_set_dirty_range() always dirty all flags Juan Quintela
2013-12-18 10:12 ` Orit Wasserman
2013-12-17 15:25 ` [Qemu-devel] [PATCH 11/38] memory: cpu_physical_memory_mask_dirty_range() always clears a single flag Juan Quintela
2013-12-18 10:14 ` Orit Wasserman
2013-12-17 15:25 ` [Qemu-devel] [PATCH 12/38] memory: use bit 2 for migration Juan Quintela
2013-12-18 10:15 ` Orit Wasserman
2013-12-17 15:25 ` [Qemu-devel] [PATCH 13/38] memory: make sure that client is always inside range Juan Quintela
2013-12-18 10:16 ` Orit Wasserman
2013-12-17 15:25 ` [Qemu-devel] [PATCH 14/38] memory: only resize dirty bitmap when memory size increases Juan Quintela
2013-12-18 10:17 ` Orit Wasserman
2013-12-17 15:25 ` [Qemu-devel] [PATCH 15/38] memory: cpu_physical_memory_clear_dirty_flag() result is never used Juan Quintela
2013-12-18 10:17 ` Orit Wasserman
2013-12-17 15:25 ` [Qemu-devel] [PATCH 16/38] bitmap: Add bitmap_zero_extend operation Juan Quintela
2013-12-18 10:18 ` Orit Wasserman
2013-12-17 15:25 ` [Qemu-devel] [PATCH 17/38] memory: split dirty bitmap into three Juan Quintela
2013-12-18 10:22 ` Orit Wasserman
2013-12-17 15:25 ` [Qemu-devel] [PATCH 18/38] memory: unfold cpu_physical_memory_clear_dirty_flag() in its only user Juan Quintela
2013-12-18 10:28 ` Orit Wasserman
2013-12-18 10:36 ` Orit Wasserman
2013-12-17 15:25 ` [Qemu-devel] [PATCH 19/38] memory: unfold cpu_physical_memory_set_dirty() " Juan Quintela
2013-12-18 10:28 ` Orit Wasserman
2013-12-17 15:25 ` [Qemu-devel] [PATCH 20/38] memory: unfold cpu_physical_memory_set_dirty_flag() Juan Quintela
2013-12-18 10:29 ` Orit Wasserman
2013-12-17 15:25 ` [Qemu-devel] [PATCH 21/38] memory: make cpu_physical_memory_get_dirty() the main function Juan Quintela
2013-12-18 10:30 ` Orit Wasserman
2013-12-17 15:25 ` [Qemu-devel] [PATCH 22/38] memory: cpu_physical_memory_get_dirty() is used as returning a bool Juan Quintela
2013-12-18 10:33 ` Orit Wasserman
2013-12-17 15:25 ` [Qemu-devel] [PATCH 23/38] memory: s/mask/clear/ cpu_physical_memory_mask_dirty_range Juan Quintela
2013-12-18 10:38 ` Orit Wasserman
2013-12-17 15:26 ` [Qemu-devel] [PATCH 24/38] memory: use find_next_bit() to find dirty bits Juan Quintela
2013-12-18 11:48 ` Orit Wasserman
2013-12-17 15:26 ` [Qemu-devel] [PATCH 25/38] memory: cpu_physical_memory_set_dirty_range() now uses bitmap operations Juan Quintela
2013-12-18 11:50 ` Orit Wasserman
2013-12-17 15:26 ` [Qemu-devel] [PATCH 26/38] memory: cpu_physical_memory_clear_dirty_range() " Juan Quintela
2013-12-18 11:50 ` Orit Wasserman
2013-12-17 15:26 ` [Qemu-devel] [PATCH 27/38] memory: s/dirty/clean/ in cpu_physical_memory_is_dirty() Juan Quintela
2013-12-18 11:51 ` Orit Wasserman
2013-12-17 15:26 ` [Qemu-devel] [PATCH 28/38] memory: make cpu_physical_memory_reset_dirty() take a length parameter Juan Quintela
2013-12-18 11:53 ` Orit Wasserman
2013-12-17 15:26 ` [Qemu-devel] [PATCH 29/38] memory: cpu_physical_memory_set_dirty_tracking() should return void Juan Quintela
2013-12-18 11:54 ` Orit Wasserman
2013-12-17 15:26 ` [Qemu-devel] [PATCH 30/38] memory: split cpu_physical_memory_* functions to its own include Juan Quintela
2013-12-18 12:12 ` Orit Wasserman
2013-12-17 15:26 ` [Qemu-devel] [PATCH 31/38] memory: unfold memory_region_test_and_clear() Juan Quintela
2013-12-18 12:25 ` Orit Wasserman
2013-12-17 15:26 ` [Qemu-devel] [PATCH 32/38] kvm: use directly cpu_physical_memory_* api for tracking dirty pages Juan Quintela
2013-12-19 10:03 ` Orit Wasserman
2013-12-19 10:06 ` Peter Maydell
2013-12-19 13:24 ` Juan Quintela
2013-12-17 15:26 ` [Qemu-devel] [PATCH 33/38] kvm: refactor start address calculation Juan Quintela
2013-12-19 10:04 ` Orit Wasserman
2013-12-17 15:26 ` [Qemu-devel] [PATCH 34/38] memory: move bitmap synchronization to its own function Juan Quintela
2013-12-19 10:08 ` Orit Wasserman
2013-12-17 15:26 ` Juan Quintela [this message]
2013-12-19 10:25 ` [Qemu-devel] [PATCH 35/38] memory: syncronize kvm bitmap using bitmaps operations Orit Wasserman
2013-12-17 15:26 ` [Qemu-devel] [PATCH 36/38] ram: split function that synchronizes a range Juan Quintela
2013-12-19 10:45 ` Orit Wasserman
2013-12-17 15:26 ` [Qemu-devel] [PATCH 37/38] migration: synchronize memory bitmap 64bits at a time Juan Quintela
2013-12-19 11:22 ` Orit Wasserman
2013-12-17 15:26 ` [Qemu-devel] [PATCH 38/38] ram: align ram_addr_t's regions in multiples of 64 Juan Quintela
2013-12-17 16:05 ` Juan Quintela
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=1387293974-24718-36-git-send-email-quintela@redhat.com \
--to=quintela@redhat.com \
--cc=qemu-devel@nongnu.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;
as well as URLs for NNTP newsgroup(s).