From: Christoph Hellwig <hch@lst.de>
To: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: "Christoph Hellwig" <hch@lst.de>,
"Marek Marczykowski-Górecki" <marmarek@invisiblethingslab.com>,
"Juergen Gross" <jgross@suse.com>,
"Stefano Stabellini" <sstabellini@kernel.org>,
"Thomas Gleixner" <tglx@linutronix.de>,
"Ingo Molnar" <mingo@redhat.com>,
"Borislav Petkov" <bp@alien8.de>,
"Dave Hansen" <dave.hansen@linux.intel.com>,
x86@kernel.org, "H. Peter Anvin" <hpa@zytor.com>,
"Ben Skeggs" <bskeggs@redhat.com>,
"Karol Herbst" <kherbst@redhat.com>,
"Lyude Paul" <lyude@redhat.com>,
xen-devel@lists.xenproject.org, iommu@lists.linux.dev,
linux-kernel@vger.kernel.org, nouveau@lists.freedesktop.org
Subject: Re: [PATCH 2/4] x86: always initialize xen-swiotlb when xen-pcifront is enabling
Date: Sat, 20 May 2023 08:21:03 +0200 [thread overview]
Message-ID: <20230520062103.GA1225@lst.de> (raw)
In-Reply-To: <20230519125857.GA6994@lst.de>
On Fri, May 19, 2023 at 02:58:57PM +0200, Christoph Hellwig wrote:
> On Fri, May 19, 2023 at 01:49:46PM +0100, Andrew Cooper wrote:
> > > The alternative would be to finally merge swiotlb-xen into swiotlb, in
> > > which case we might be able to do this later. Let me see what I can
> > > do there.
> >
> > If that is an option, it would be great to reduce the special-cashing.
>
> I think it's doable, and I've been wanting it for a while. I just
> need motivated testers, but it seems like I just found at least two :)
So looking at swiotlb-xen it does these off things where it takes a value
generated originally be xen_phys_to_dma, then only does a dma_to_phys
to go back and call pfn_valid on the result. Does this make sense, or
is it wrong and just works by accident? I.e. is the patch below correct?
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 67aa74d201627d..3396c5766f0dd8 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -90,9 +90,7 @@ static inline int range_straddles_page_boundary(phys_addr_t p, size_t size)
static int is_xen_swiotlb_buffer(struct device *dev, dma_addr_t dma_addr)
{
- unsigned long bfn = XEN_PFN_DOWN(dma_to_phys(dev, dma_addr));
- unsigned long xen_pfn = bfn_to_local_pfn(bfn);
- phys_addr_t paddr = (phys_addr_t)xen_pfn << XEN_PAGE_SHIFT;
+ phys_addr_t paddr = xen_dma_to_phys(dev, dma_addr);
/* If the address is outside our domain, it CAN
* have the same virtual address as another address
@@ -234,7 +232,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
done:
if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
- if (pfn_valid(PFN_DOWN(dma_to_phys(dev, dev_addr))))
+ if (pfn_valid(PFN_DOWN(phys)))
arch_sync_dma_for_device(phys, size, dir);
else
xen_dma_sync_for_device(dev, dev_addr, size, dir);
@@ -258,7 +256,7 @@ static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
BUG_ON(dir == DMA_NONE);
if (!dev_is_dma_coherent(hwdev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
- if (pfn_valid(PFN_DOWN(dma_to_phys(hwdev, dev_addr))))
+ if (pfn_valid(PFN_DOWN(paddr)))
arch_sync_dma_for_cpu(paddr, size, dir);
else
xen_dma_sync_for_cpu(hwdev, dev_addr, size, dir);
@@ -276,7 +274,7 @@ xen_swiotlb_sync_single_for_cpu(struct device *dev, dma_addr_t dma_addr,
phys_addr_t paddr = xen_dma_to_phys(dev, dma_addr);
if (!dev_is_dma_coherent(dev)) {
- if (pfn_valid(PFN_DOWN(dma_to_phys(dev, dma_addr))))
+ if (pfn_valid(PFN_DOWN(paddr)))
arch_sync_dma_for_cpu(paddr, size, dir);
else
xen_dma_sync_for_cpu(dev, dma_addr, size, dir);
@@ -296,7 +294,7 @@ xen_swiotlb_sync_single_for_device(struct device *dev, dma_addr_t dma_addr,
swiotlb_sync_single_for_device(dev, paddr, size, dir);
if (!dev_is_dma_coherent(dev)) {
- if (pfn_valid(PFN_DOWN(dma_to_phys(dev, dma_addr))))
+ if (pfn_valid(PFN_DOWN(paddr)))
arch_sync_dma_for_device(paddr, size, dir);
else
xen_dma_sync_for_device(dev, dma_addr, size, dir);
WARNING: multiple messages have this Message-ID (diff)
From: Christoph Hellwig <hch@lst.de>
To: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: "Juergen Gross" <jgross@suse.com>,
x86@kernel.org, "Stefano Stabellini" <sstabellini@kernel.org>,
nouveau@lists.freedesktop.org,
"Dave Hansen" <dave.hansen@linux.intel.com>,
"Marek Marczykowski-Górecki" <marmarek@invisiblethingslab.com>,
linux-kernel@vger.kernel.org, iommu@lists.linux.dev,
"Ingo Molnar" <mingo@redhat.com>,
"Borislav Petkov" <bp@alien8.de>,
"Ben Skeggs" <bskeggs@redhat.com>,
"H. Peter Anvin" <hpa@zytor.com>,
xen-devel@lists.xenproject.org,
"Thomas Gleixner" <tglx@linutronix.de>,
"Christoph Hellwig" <hch@lst.de>
Subject: Re: [Nouveau] [PATCH 2/4] x86: always initialize xen-swiotlb when xen-pcifront is enabling
Date: Sat, 20 May 2023 08:21:03 +0200 [thread overview]
Message-ID: <20230520062103.GA1225@lst.de> (raw)
In-Reply-To: <20230519125857.GA6994@lst.de>
On Fri, May 19, 2023 at 02:58:57PM +0200, Christoph Hellwig wrote:
> On Fri, May 19, 2023 at 01:49:46PM +0100, Andrew Cooper wrote:
> > > The alternative would be to finally merge swiotlb-xen into swiotlb, in
> > > which case we might be able to do this later. Let me see what I can
> > > do there.
> >
> > If that is an option, it would be great to reduce the special-cashing.
>
> I think it's doable, and I've been wanting it for a while. I just
> need motivated testers, but it seems like I just found at least two :)
So looking at swiotlb-xen it does these off things where it takes a value
generated originally be xen_phys_to_dma, then only does a dma_to_phys
to go back and call pfn_valid on the result. Does this make sense, or
is it wrong and just works by accident? I.e. is the patch below correct?
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 67aa74d201627d..3396c5766f0dd8 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -90,9 +90,7 @@ static inline int range_straddles_page_boundary(phys_addr_t p, size_t size)
static int is_xen_swiotlb_buffer(struct device *dev, dma_addr_t dma_addr)
{
- unsigned long bfn = XEN_PFN_DOWN(dma_to_phys(dev, dma_addr));
- unsigned long xen_pfn = bfn_to_local_pfn(bfn);
- phys_addr_t paddr = (phys_addr_t)xen_pfn << XEN_PAGE_SHIFT;
+ phys_addr_t paddr = xen_dma_to_phys(dev, dma_addr);
/* If the address is outside our domain, it CAN
* have the same virtual address as another address
@@ -234,7 +232,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
done:
if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
- if (pfn_valid(PFN_DOWN(dma_to_phys(dev, dev_addr))))
+ if (pfn_valid(PFN_DOWN(phys)))
arch_sync_dma_for_device(phys, size, dir);
else
xen_dma_sync_for_device(dev, dev_addr, size, dir);
@@ -258,7 +256,7 @@ static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
BUG_ON(dir == DMA_NONE);
if (!dev_is_dma_coherent(hwdev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
- if (pfn_valid(PFN_DOWN(dma_to_phys(hwdev, dev_addr))))
+ if (pfn_valid(PFN_DOWN(paddr)))
arch_sync_dma_for_cpu(paddr, size, dir);
else
xen_dma_sync_for_cpu(hwdev, dev_addr, size, dir);
@@ -276,7 +274,7 @@ xen_swiotlb_sync_single_for_cpu(struct device *dev, dma_addr_t dma_addr,
phys_addr_t paddr = xen_dma_to_phys(dev, dma_addr);
if (!dev_is_dma_coherent(dev)) {
- if (pfn_valid(PFN_DOWN(dma_to_phys(dev, dma_addr))))
+ if (pfn_valid(PFN_DOWN(paddr)))
arch_sync_dma_for_cpu(paddr, size, dir);
else
xen_dma_sync_for_cpu(dev, dma_addr, size, dir);
@@ -296,7 +294,7 @@ xen_swiotlb_sync_single_for_device(struct device *dev, dma_addr_t dma_addr,
swiotlb_sync_single_for_device(dev, paddr, size, dir);
if (!dev_is_dma_coherent(dev)) {
- if (pfn_valid(PFN_DOWN(dma_to_phys(dev, dma_addr))))
+ if (pfn_valid(PFN_DOWN(paddr)))
arch_sync_dma_for_device(paddr, size, dir);
else
xen_dma_sync_for_device(dev, dma_addr, size, dir);
next prev parent reply other threads:[~2023-05-20 6:21 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-05-18 13:42 unexport swiotlb_active Christoph Hellwig
2023-05-18 13:42 ` [Nouveau] " Christoph Hellwig
2023-05-18 13:42 ` [PATCH 1/4] x86: move a check out of pci_xen_swiotlb_init Christoph Hellwig
2023-05-18 13:42 ` [Nouveau] " Christoph Hellwig
2023-05-18 13:42 ` [PATCH 2/4] x86: always initialize xen-swiotlb when xen-pcifront is enabling Christoph Hellwig
2023-05-18 13:42 ` [Nouveau] " Christoph Hellwig
2023-05-18 18:18 ` Marek Marczykowski-Górecki
2023-05-18 18:18 ` [Nouveau] " Marek Marczykowski-Górecki
2023-05-19 4:04 ` Christoph Hellwig
2023-05-19 4:04 ` [Nouveau] " Christoph Hellwig
2023-05-19 10:10 ` Marek Marczykowski-Górecki
2023-05-19 10:10 ` [Nouveau] " Marek Marczykowski-Górecki
2023-05-19 12:41 ` Christoph Hellwig
2023-05-19 12:41 ` [Nouveau] " Christoph Hellwig
2023-05-19 12:49 ` Andrew Cooper
2023-05-19 12:49 ` [Nouveau] " Andrew Cooper
2023-05-19 12:58 ` Christoph Hellwig
2023-05-19 12:58 ` [Nouveau] " Christoph Hellwig
2023-05-20 6:21 ` Christoph Hellwig [this message]
2023-05-20 6:21 ` Christoph Hellwig
2023-05-22 7:52 ` Petr Tesařík
2023-05-22 7:52 ` [Nouveau] " Petr Tesařík
2023-05-22 7:54 ` Petr Tesařík
2023-05-22 7:54 ` [Nouveau] " Petr Tesařík
2023-05-22 8:37 ` Juergen Gross
2023-05-22 8:37 ` [Nouveau] " Juergen Gross
2023-06-07 13:12 ` Christoph Hellwig
2023-06-07 13:12 ` [Nouveau] " Christoph Hellwig
2023-06-09 15:38 ` Juergen Gross
2023-06-09 15:38 ` [Nouveau] " Juergen Gross
2023-06-12 6:47 ` Christoph Hellwig
2023-06-12 6:47 ` [Nouveau] " Christoph Hellwig
2023-06-12 8:08 ` Juergen Gross
2023-06-12 8:08 ` [Nouveau] " Juergen Gross
2023-06-12 8:23 ` Christoph Hellwig
2023-06-12 8:23 ` [Nouveau] " Christoph Hellwig
2023-05-18 13:42 ` [PATCH 3/4] drm/nouveau: stop using is_swiotlb_active Christoph Hellwig
2023-05-18 13:42 ` [Nouveau] " Christoph Hellwig
2023-05-18 20:30 ` Lyude Paul
2023-05-18 20:30 ` [Nouveau] " Lyude Paul
2023-06-07 13:11 ` Christoph Hellwig
2023-06-07 13:11 ` [Nouveau] " Christoph Hellwig
2023-05-18 13:42 ` [PATCH 4/4] swiotlb: unexport is_swiotlb_active Christoph Hellwig
2023-05-18 13:42 ` [Nouveau] " Christoph Hellwig
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=20230520062103.GA1225@lst.de \
--to=hch@lst.de \
--cc=andrew.cooper3@citrix.com \
--cc=bp@alien8.de \
--cc=bskeggs@redhat.com \
--cc=dave.hansen@linux.intel.com \
--cc=hpa@zytor.com \
--cc=iommu@lists.linux.dev \
--cc=jgross@suse.com \
--cc=kherbst@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lyude@redhat.com \
--cc=marmarek@invisiblethingslab.com \
--cc=mingo@redhat.com \
--cc=nouveau@lists.freedesktop.org \
--cc=sstabellini@kernel.org \
--cc=tglx@linutronix.de \
--cc=x86@kernel.org \
--cc=xen-devel@lists.xenproject.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.