[PATCH] video: hyperv_fb: Fix the cache type when mapping the VRAM

Subsystems: framebuffer layer, the rest

STALE2159d LANDED: 1 (0M)

1 review trailer; landed in mainline as 5f1251a48c17 on 2020-11-20.

4 messages, 4 authors, 2020-11-18 · open the first message on its own page

[PATCH] video: hyperv_fb: Fix the cache type when mapping the VRAM

From: Dexuan Cui <decui@microsoft.com>
Date: 2020-11-18 00:04:13

x86 Hyper-V used to essentially always overwrite the effective cache type
of guest memory accesses to WB. This was problematic in cases where there
is a physical device assigned to the VM, since that often requires that
the VM should have control over cache types. Thus, on newer Hyper-V since
2018, Hyper-V always honors the VM's cache type, but unexpectedly Linux VM
users start to complain that Linux VM's VRAM becomes very slow, and it
turns out that Linux VM should not map the VRAM uncacheable by ioremap().
Fix this slowness issue by using ioremap_cache().

On ARM64, ioremap_cache() is also required as the host also maps the VRAM
cacheable, otherwise VM Connect can't display properly with ioremap() or
ioremap_wc().

With this change, the VRAM on new Hyper-V is as fast as regular RAM, so
it's no longer necessary to use the hacks we added to mitigate the
slowness, i.e. we no longer need to allocate physical memory and use
it to back up the VRAM in Generation-1 VM, and we also no longer need to
allocate physical memory to back up the framebuffer in a Generation-2 VM
and copy the framebuffer to the real VRAM. A further big change will
address these for v5.11.

Fixes: 68a2d20b79b1 ("drivers/video: add Hyper-V Synthetic Video Frame Buffer Driver")
Tested-by: Boqun Feng <redacted>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
---

Hi Wei Liu, can you please pick this up into the hyperv/linux.git tree's
hyperv-fixes branch? I really hope this patch can be in v5.10 since it
fixes a longstanding issue: https://github.com/LIS/lis-next/issues/655

 drivers/video/fbdev/hyperv_fb.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c
index 5bc86f481a78..c8b0ae676809 100644
--- a/drivers/video/fbdev/hyperv_fb.c
+++ b/drivers/video/fbdev/hyperv_fb.c
@@ -1093,7 +1093,12 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info)
 		goto err1;
 	}
 
-	fb_virt = ioremap(par->mem->start, screen_fb_size);
+	/*
+	 * Map the VRAM cacheable for performance. This is also required for
+	 * VM Connect to display properly for ARM64 Linux VM, as the host also
+	 * maps the VRAM cacheable.
+	 */
+	fb_virt = ioremap_cache(par->mem->start, screen_fb_size);
 	if (!fb_virt)
 		goto err2;
 
-- 
2.19.1

RE: [PATCH] video: hyperv_fb: Fix the cache type when mapping the VRAM

From: Michael Kelley <hidden>
Date: 2020-11-18 00:20:28

From: Dexuan Cui <decui@microsoft.com> Sent: Tuesday, November 17, 2020 4:03 PM
quoted hunk
x86 Hyper-V used to essentially always overwrite the effective cache type
of guest memory accesses to WB. This was problematic in cases where there
is a physical device assigned to the VM, since that often requires that
the VM should have control over cache types. Thus, on newer Hyper-V since
2018, Hyper-V always honors the VM's cache type, but unexpectedly Linux VM
users start to complain that Linux VM's VRAM becomes very slow, and it
turns out that Linux VM should not map the VRAM uncacheable by ioremap().
Fix this slowness issue by using ioremap_cache().

On ARM64, ioremap_cache() is also required as the host also maps the VRAM
cacheable, otherwise VM Connect can't display properly with ioremap() or
ioremap_wc().

With this change, the VRAM on new Hyper-V is as fast as regular RAM, so
it's no longer necessary to use the hacks we added to mitigate the
slowness, i.e. we no longer need to allocate physical memory and use
it to back up the VRAM in Generation-1 VM, and we also no longer need to
allocate physical memory to back up the framebuffer in a Generation-2 VM
and copy the framebuffer to the real VRAM. A further big change will
address these for v5.11.

Fixes: 68a2d20b79b1 ("drivers/video: add Hyper-V Synthetic Video Frame Buffer Driver")
Tested-by: Boqun Feng <redacted>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
---

Hi Wei Liu, can you please pick this up into the hyperv/linux.git tree's
hyperv-fixes branch? I really hope this patch can be in v5.10 since it
fixes a longstanding issue: https://github.com/LIS/lis-next/issues/655

 drivers/video/fbdev/hyperv_fb.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c
index 5bc86f481a78..c8b0ae676809 100644
--- a/drivers/video/fbdev/hyperv_fb.c
+++ b/drivers/video/fbdev/hyperv_fb.c
@@ -1093,7 +1093,12 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info
*info)
 		goto err1;
 	}

-	fb_virt = ioremap(par->mem->start, screen_fb_size);
+	/*
+	 * Map the VRAM cacheable for performance. This is also required for
+	 * VM Connect to display properly for ARM64 Linux VM, as the host also
+	 * maps the VRAM cacheable.
+	 */
+	fb_virt = ioremap_cache(par->mem->start, screen_fb_size);
 	if (!fb_virt)
 		goto err2;

--
2.19.1
Reviewed-by: Michael Kelley <redacted>

Re: [PATCH] video: hyperv_fb: Fix the cache type when mapping the VRAM

From: Wei Liu <wei.liu@kernel.org>
Date: 2020-11-18 09:32:18

On Wed, Nov 18, 2020 at 12:20:11AM +0000, Michael Kelley wrote:
From: Dexuan Cui <decui@microsoft.com> Sent: Tuesday, November 17, 2020 4:03 PM
quoted
x86 Hyper-V used to essentially always overwrite the effective cache type
of guest memory accesses to WB. This was problematic in cases where there
is a physical device assigned to the VM, since that often requires that
the VM should have control over cache types. Thus, on newer Hyper-V since
2018, Hyper-V always honors the VM's cache type, but unexpectedly Linux VM
users start to complain that Linux VM's VRAM becomes very slow, and it
turns out that Linux VM should not map the VRAM uncacheable by ioremap().
Fix this slowness issue by using ioremap_cache().

On ARM64, ioremap_cache() is also required as the host also maps the VRAM
cacheable, otherwise VM Connect can't display properly with ioremap() or
ioremap_wc().

With this change, the VRAM on new Hyper-V is as fast as regular RAM, so
it's no longer necessary to use the hacks we added to mitigate the
slowness, i.e. we no longer need to allocate physical memory and use
it to back up the VRAM in Generation-1 VM, and we also no longer need to
allocate physical memory to back up the framebuffer in a Generation-2 VM
and copy the framebuffer to the real VRAM. A further big change will
address these for v5.11.

Fixes: 68a2d20b79b1 ("drivers/video: add Hyper-V Synthetic Video Frame Buffer Driver")
Tested-by: Boqun Feng <redacted>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <redacted>
Applied to hyperv-fixes. Thanks.

RE: [PATCH] video: hyperv_fb: Fix the cache type when mapping the VRAM

From: Haiyang Zhang <haiyangz@microsoft.com>
Date: 2020-11-18 21:10:42

quoted hunk
-----Original Message-----
From: Dexuan Cui <decui@microsoft.com>
Sent: Tuesday, November 17, 2020 7:03 PM
To: KY Srinivasan <redacted>; Haiyang Zhang
[off-list ref]; Stephen Hemminger
[off-list ref]; wei.liu@kernel.org;
b.zolnierkie@samsung.com; linux-hyperv@vger.kernel.org; dri-
devel@lists.freedesktop.org; linux-fbdev@vger.kernel.org; linux-
kernel@vger.kernel.org; Michael Kelley [off-list ref]
Cc: Wei Hu <redacted>; Dexuan Cui <decui@microsoft.com>
Subject: [PATCH] video: hyperv_fb: Fix the cache type when mapping the
VRAM

x86 Hyper-V used to essentially always overwrite the effective cache type of
guest memory accesses to WB. This was problematic in cases where there is
a physical device assigned to the VM, since that often requires that the VM
should have control over cache types. Thus, on newer Hyper-V since 2018,
Hyper-V always honors the VM's cache type, but unexpectedly Linux VM
users start to complain that Linux VM's VRAM becomes very slow, and it
turns out that Linux VM should not map the VRAM uncacheable by ioremap().
Fix this slowness issue by using ioremap_cache().

On ARM64, ioremap_cache() is also required as the host also maps the VRAM
cacheable, otherwise VM Connect can't display properly with ioremap() or
ioremap_wc().

With this change, the VRAM on new Hyper-V is as fast as regular RAM, so it's
no longer necessary to use the hacks we added to mitigate the slowness, i.e.
we no longer need to allocate physical memory and use it to back up the
VRAM in Generation-1 VM, and we also no longer need to allocate physical
memory to back up the framebuffer in a Generation-2 VM and copy the
framebuffer to the real VRAM. A further big change will address these for
v5.11.

Fixes: 68a2d20b79b1 ("drivers/video: add Hyper-V Synthetic Video Frame
Buffer Driver")
Tested-by: Boqun Feng <redacted>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
---

Hi Wei Liu, can you please pick this up into the hyperv/linux.git tree's hyperv-
fixes branch? I really hope this patch can be in v5.10 since it fixes a
longstanding issue:
https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgith
ub.com%2FLIS%2Flis-
next%2Fissues%2F655&amp;data=04%7C01%7Chaiyangz%40microsoft.com%
7C7e371bb6f79f41aae12208d88b556c85%7C72f988bf86f141af91ab2d7cd011d
b47%7C1%7C0%7C637412546297591335%7CUnknown%7CTWFpbGZsb3d8eyJ
WIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%
7C1000&amp;sdata=StqnT%2Fx1XVoVWUZbJz5BNjaCIdtuNmSf2JoyLSt0c%2B
Q%3D&amp;reserved=0

 drivers/video/fbdev/hyperv_fb.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/video/fbdev/hyperv_fb.c
b/drivers/video/fbdev/hyperv_fb.c index 5bc86f481a78..c8b0ae676809
100644
--- a/drivers/video/fbdev/hyperv_fb.c
+++ b/drivers/video/fbdev/hyperv_fb.c
@@ -1093,7 +1093,12 @@ static int hvfb_getmem(struct hv_device *hdev,
struct fb_info *info)
 		goto err1;
 	}

-	fb_virt = ioremap(par->mem->start, screen_fb_size);
+	/*
+	 * Map the VRAM cacheable for performance. This is also required
for
+	 * VM Connect to display properly for ARM64 Linux VM, as the host
also
+	 * maps the VRAM cacheable.
+	 */
+	fb_virt = ioremap_cache(par->mem->start, screen_fb_size);
 	if (!fb_virt)
 		goto err2;
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Thank you!
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help