From: John Garry <john.garry@huawei.com>
To: Cong Wang <xiyou.wangcong@gmail.com>, <iommu@lists.linux-foundation.org>
Cc: <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 1/3] iommu: match the original algorithm
Date: Wed, 27 Nov 2019 18:00:58 +0000 [thread overview]
Message-ID: <9ac29292-bc3d-ae57-daff-5b3264020fe2@huawei.com> (raw)
In-Reply-To: <20191121001348.27230-2-xiyou.wangcong@gmail.com>
On 21/11/2019 00:13, Cong Wang wrote:
> The IOVA cache algorithm implemented in IOMMU code does not
> exactly match the original algorithm described in the paper.
>
> Particularly, it doesn't need to free the loaded empty magazine
> when trying to put it back to global depot.
>
> This patch makes it exactly match the original algorithm.
>
I haven't gone into the details, but this patch alone is giving this:
root@(none)$ [ 123.857024] kmemleak: 8 new suspected memory leaks (see
/sys/kernel/debug/kmemleak)
root@(none)$ cat /sys/kernel/debug/kmemleak
unreferenced object 0xffff002339843000 (size 2048):
comm "swapper/0", pid 1, jiffies 4294898165 (age 122.688s)
hex dump (first 32 bytes):
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
backtrace:
[<000000001d2710bf>] kmem_cache_alloc+0x188/0x260
[<00000000cc229a78>] init_iova_domain+0x1e8/0x2a8
[<000000002646fc92>] iommu_setup_dma_ops+0x200/0x710
[<00000000acc5fe46>] arch_setup_dma_ops+0x80/0x128
[<00000000994e1e43>] acpi_dma_configure+0x11c/0x140
[<00000000effe9374>] pci_dma_configure+0xe0/0x108
[<00000000f614ae1e>] really_probe+0x210/0x548
[<0000000087884b1b>] driver_probe_device+0x7c/0x148
[<0000000010af2936>] device_driver_attach+0x94/0xa0
[<00000000c92b2971>] __driver_attach+0xa4/0x110
[<00000000c873500f>] bus_for_each_dev+0xe8/0x158
[<00000000c7d0e008>] driver_attach+0x30/0x40
[<000000003cf39ba8>] bus_add_driver+0x234/0x2f0
[<0000000043830a45>] driver_register+0xbc/0x1d0
[<00000000c8a41162>] __pci_register_driver+0xb0/0xc8
[<00000000e562eeec>] sas_v3_pci_driver_init+0x20/0x28
unreferenced object 0xffff002339844000 (size 2048):
comm "swapper/0", pid 1, jiffies 4294898165 (age 122.688s)
[snip]
And I don't feel like continuing until it's resolved....
Thanks,
John
> Cc: Joerg Roedel <joro@8bytes.org>
> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
> ---
> drivers/iommu/iova.c | 14 ++++++++------
> 1 file changed, 8 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
> index 41c605b0058f..92f72a85e62a 100644
> --- a/drivers/iommu/iova.c
> +++ b/drivers/iommu/iova.c
> @@ -900,7 +900,7 @@ static bool __iova_rcache_insert(struct iova_domain *iovad,
>
> if (!iova_magazine_full(cpu_rcache->loaded)) {
> can_insert = true;
> - } else if (!iova_magazine_full(cpu_rcache->prev)) {
> + } else if (iova_magazine_empty(cpu_rcache->prev)) {
> swap(cpu_rcache->prev, cpu_rcache->loaded);
> can_insert = true;
> } else {
> @@ -909,8 +909,9 @@ static bool __iova_rcache_insert(struct iova_domain *iovad,
> if (new_mag) {
> spin_lock(&rcache->lock);
> if (rcache->depot_size < MAX_GLOBAL_MAGS) {
> - rcache->depot[rcache->depot_size++] =
> - cpu_rcache->loaded;
> + swap(rcache->depot[rcache->depot_size], cpu_rcache->prev);
> + swap(cpu_rcache->prev, cpu_rcache->loaded);
> + rcache->depot_size++;
> } else {
> mag_to_free = cpu_rcache->loaded;
> }
> @@ -963,14 +964,15 @@ static unsigned long __iova_rcache_get(struct iova_rcache *rcache,
>
> if (!iova_magazine_empty(cpu_rcache->loaded)) {
> has_pfn = true;
> - } else if (!iova_magazine_empty(cpu_rcache->prev)) {
> + } else if (iova_magazine_full(cpu_rcache->prev)) {
> swap(cpu_rcache->prev, cpu_rcache->loaded);
> has_pfn = true;
> } else {
> spin_lock(&rcache->lock);
> if (rcache->depot_size > 0) {
> - iova_magazine_free(cpu_rcache->loaded);
> - cpu_rcache->loaded = rcache->depot[--rcache->depot_size];
> + swap(rcache->depot[rcache->depot_size - 1], cpu_rcache->prev);
> + swap(cpu_rcache->prev, cpu_rcache->loaded);
> + rcache->depot_size--;
> has_pfn = true;
> }
> spin_unlock(&rcache->lock);
>
next prev parent reply other threads:[~2019-11-27 18:01 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-11-21 0:13 [PATCH 0/3] iommu: reduce spinlock contention on fast path Cong Wang
2019-11-21 0:13 ` [PATCH 1/3] iommu: match the original algorithm Cong Wang
2019-11-27 18:00 ` John Garry [this message]
2019-11-27 18:38 ` Qian Cai
2019-11-28 19:30 ` Cong Wang
2019-11-21 0:13 ` [PATCH 2/3] iommu: optimize iova_magazine_free_pfns() Cong Wang
2019-11-21 0:13 ` [PATCH 3/3] iommu: avoid taking iova_rbtree_lock twice Cong Wang
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=9ac29292-bc3d-ae57-daff-5b3264020fe2@huawei.com \
--to=john.garry@huawei.com \
--cc=iommu@lists.linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=xiyou.wangcong@gmail.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 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).