All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Kuehling, Felix" <Felix.Kuehling@amd.com>
To: "jglisse@redhat.com" <jglisse@redhat.com>,
	"alex.deucher@amd.com" <alex.deucher@amd.com>,
	"airlied@gmail.com" <airlied@gmail.com>,
	"linux-mm@kvack.org" <linux-mm@kvack.org>,
	"dri-devel@lists.freedesktop.org"
	<dri-devel@lists.freedesktop.org>,
	"amd-gfx@lists.freedesktop.org" <amd-gfx@lists.freedesktop.org>
Cc: "Yang, Philip" <Philip.Yang@amd.com>
Subject: [PATCH 1/2] mm/hmm: support automatic NUMA balancing
Date: Fri, 10 May 2019 19:53:23 +0000	[thread overview]
Message-ID: <20190510195258.9930-2-Felix.Kuehling@amd.com> (raw)
In-Reply-To: <20190510195258.9930-1-Felix.Kuehling@amd.com>

From: Philip Yang <Philip.Yang@amd.com>

While the page is migrating by NUMA balancing, HMM failed to detect this
condition and still return the old page. Application will use the new
page migrated, but driver pass the old page physical address to GPU,
this crash the application later.

Use pte_protnone(pte) to return this condition and then hmm_vma_do_fault
will allocate new page.

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
---
 mm/hmm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/hmm.c b/mm/hmm.c
index 75d2ea906efb..b65c27d5c119 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -554,7 +554,7 @@ static int hmm_vma_handle_pmd(struct mm_walk *walk,
 
 static inline uint64_t pte_to_hmm_pfn_flags(struct hmm_range *range, pte_t pte)
 {
-	if (pte_none(pte) || !pte_present(pte))
+	if (pte_none(pte) || !pte_present(pte) || pte_protnone(pte))
 		return 0;
 	return pte_write(pte) ? range->flags[HMM_PFN_VALID] |
 				range->flags[HMM_PFN_WRITE] :
-- 
2.17.1


WARNING: multiple messages have this Message-ID (diff)
From: "Kuehling, Felix" <Felix.Kuehling-5C7GfCeVMHo@public.gmane.org>
To: "jglisse-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org"
	<jglisse-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
	"alex.deucher-5C7GfCeVMHo@public.gmane.org"
	<alex.deucher-5C7GfCeVMHo@public.gmane.org>,
	"airlied-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org"
	<airlied-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>,
	"linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org"
	<linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org>,
	"dri-devel-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org"
	<dri-devel-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>,
	"amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org"
	<amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Cc: "Yang, Philip" <Philip.Yang-5C7GfCeVMHo@public.gmane.org>
Subject: [PATCH 1/2] mm/hmm: support automatic NUMA balancing
Date: Fri, 10 May 2019 19:53:23 +0000	[thread overview]
Message-ID: <20190510195258.9930-2-Felix.Kuehling@amd.com> (raw)
In-Reply-To: <20190510195258.9930-1-Felix.Kuehling-5C7GfCeVMHo@public.gmane.org>

From: Philip Yang <Philip.Yang@amd.com>

While the page is migrating by NUMA balancing, HMM failed to detect this
condition and still return the old page. Application will use the new
page migrated, but driver pass the old page physical address to GPU,
this crash the application later.

Use pte_protnone(pte) to return this condition and then hmm_vma_do_fault
will allocate new page.

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
---
 mm/hmm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/hmm.c b/mm/hmm.c
index 75d2ea906efb..b65c27d5c119 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -554,7 +554,7 @@ static int hmm_vma_handle_pmd(struct mm_walk *walk,
 
 static inline uint64_t pte_to_hmm_pfn_flags(struct hmm_range *range, pte_t pte)
 {
-	if (pte_none(pte) || !pte_present(pte))
+	if (pte_none(pte) || !pte_present(pte) || pte_protnone(pte))
 		return 0;
 	return pte_write(pte) ? range->flags[HMM_PFN_VALID] |
 				range->flags[HMM_PFN_WRITE] :
-- 
2.17.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

  reply	other threads:[~2019-05-10 19:53 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-05-10 19:53 [PATCH 0/2] Two bug-fixes for HMM Kuehling, Felix
2019-05-10 19:53 ` Kuehling, Felix
2019-05-10 19:53 ` Kuehling, Felix [this message]
2019-05-10 19:53   ` [PATCH 1/2] mm/hmm: support automatic NUMA balancing Kuehling, Felix
2019-05-10 20:13   ` Jerome Glisse
2019-05-10 20:13     ` Jerome Glisse
2019-05-13 21:27   ` Andrew Morton
2019-05-13 21:27     ` Andrew Morton
2019-05-13 22:37     ` Jerome Glisse
2019-05-13 22:37       ` Jerome Glisse
2019-05-14 21:14     ` Kuehling, Felix
2019-05-14 21:14       ` Kuehling, Felix
2019-05-10 19:53 ` [PATCH 2/2] mm/hmm: Only set FAULT_FLAG_ALLOW_RETRY for non-blocking Kuehling, Felix
2019-05-10 19:53   ` Kuehling, Felix
2019-05-10 20:14   ` Jerome Glisse
2019-05-10 20:14     ` Jerome Glisse
2019-05-13 19:36     ` Kuehling, Felix
2019-05-13 19:36       ` Kuehling, Felix
2019-05-13 19:49       ` Jerome Glisse
2019-05-13 19:49         ` Jerome Glisse
2019-05-13 20:31         ` Kuehling, Felix
2019-05-13 20:31           ` Kuehling, Felix
2019-05-13 20:21       ` Deucher, Alexander
2019-05-13 20:21         ` Deucher, Alexander
2019-05-14 21:12         ` Kuehling, Felix
2019-05-14 21:12           ` Kuehling, Felix
2019-05-14 21:58           ` Alex Deucher
2019-05-14 21:58             ` Alex Deucher
2019-06-06 15:11 ` [PATCH 0/2] Two bug-fixes for HMM Jason Gunthorpe
2019-06-06 15:11   ` Jason Gunthorpe
2019-06-06 19:04   ` Kuehling, Felix
2019-06-06 19:04     ` Kuehling, Felix
2019-06-06 19:20     ` Jason Gunthorpe
2019-06-06 19:20       ` Jason Gunthorpe
2019-06-06 19:16   ` Kuehling, Felix
2019-06-06 19:16     ` Kuehling, Felix

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=20190510195258.9930-2-Felix.Kuehling@amd.com \
    --to=felix.kuehling@amd.com \
    --cc=Philip.Yang@amd.com \
    --cc=airlied@gmail.com \
    --cc=alex.deucher@amd.com \
    --cc=amd-gfx@lists.freedesktop.org \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=jglisse@redhat.com \
    --cc=linux-mm@kvack.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 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.