On Tue, Jan 14, 2025 at 10:50:49AM -0800, Dan Williams wrote:
> Alistair Popple wrote:
> > The devmap PTE special bit was used to detect mappings of FS DAX
> > pages. This tracking was required to ensure the generic mm did not
> > manipulate the page reference counts as FS DAX implemented it's own
On Tue, Jan 14, 2025 at 09:22:00AM -0800, Dan Williams wrote:
> David Hildenbrand wrote:
> > > +vm_fault_t vmf_insert_folio_pmd(struct vm_fault *vmf, struct folio
> > > *folio, bool write)
> > > +{
> > > + struct vm_area_struct *vma = vmf->vma;
> > > + unsigned long addr = vmf->address & PMD_MASK;
On 1/14/2025 9:02 PM, Andrew Lunn wrote:
I would like to clarify that representing the bridge and its slave ports
inside PPE (using a VSI - virtual switch instance) is a pre-requisite before
learning can take place on a port. At this point, since switchdev
is not enabled, VSI is not created fo
On Tue, Jan 14, 2025 at 05:22:15PM +0100, David Hildenbrand wrote:
> On 10.01.25 07:00, Alistair Popple wrote:
> > Currently DAX folio/page reference counts are managed differently to
> > normal pages. To allow these to be managed the same as normal pages
> > introduce vmf_insert_folio_pud. This wi
On Tue, Jan 14, 2025 at 05:15:54PM +0100, David Hildenbrand wrote:
> On 10.01.25 07:00, Alistair Popple wrote:
> > Currently to map a DAX page the DAX driver calls vmf_insert_pfn. This
> > creates a special devmap PTE entry for the pfn but does not take a
> > reference on the underlying struct page
Alistair Popple wrote:
[..]
> > How does this case happen? I don't think any page would ever enter with
> > both ->mapping and ->share set, right?
>
> Sigh. You're right - it can't. This patch series is getting a litte bit large
> and unweildy with all the prerequisite bugfixes and cleanups. Obvio
On Mon, Jan 13, 2025 at 05:08:31PM -0800, Dan Williams wrote:
> Alistair Popple wrote:
> > In preparation for using insert_page() for DAX, enhance
> > insert_page_into_pte_locked() to handle establishing writable
> > mappings. Recall that DAX returns VM_FAULT_NOPAGE after installing a
> > PTE whic
On Mon, Jan 13, 2025 at 04:52:34PM -0800, Dan Williams wrote:
> Alistair Popple wrote:
> > PAGE_MAPPING_DAX_SHARED is the same as PAGE_MAPPING_ANON.
>
> I think a bit a bit more detail is warranted, how about?
>
> The page ->mapping pointer can have magic values like
> PAGE_MAPPING_DAX_SHARED an
On 2025/01/13 12:04, Jason Wang wrote:
On Fri, Jan 10, 2025 at 7:12 PM Akihiko Odaki wrote:
On 2025/01/10 19:23, Michael S. Tsirkin wrote:
On Fri, Jan 10, 2025 at 11:27:13AM +0800, Jason Wang wrote:
On Thu, Jan 9, 2025 at 2:59 PM Akihiko Odaki wrote:
The specification says the device MUST
Enabling cbo.clean and cbo.flush in user mode makes it more
convenient to manage the cache state and achieve better performance.
Reviewed-by: Andrew Jones
Signed-off-by: Yunhui Cui
---
arch/riscv/kernel/cpufeature.c | 8
1 file changed, 8 insertions(+)
diff --git a/arch/riscv/kernel/c
Add test for Zicbom and its block size into CBO tests, when
Zicbom is present, test that cbo.clean/flush may be issued and works.
As the software can't verify the clean/flush functions, we just judged
that cbo.clean/flush isn't executed illegally.
Reviewed-by: Andrew Jones
Reviewed-by: Samuel Hol
Expose Zicbom through hwprobe and also provide a key to extract its
respective block size.
Signed-off-by: Yunhui Cui
---
Documentation/arch/riscv/hwprobe.rst | 6 ++
arch/riscv/include/asm/hwprobe.h | 2 +-
arch/riscv/include/uapi/asm/hwprobe.h | 2 ++
arch/riscv/kernel/sys_hwprobe.c
v1/v2:
There is only the first patch: RISC-V: Enable cbo.clean/flush in usermode,
which mainly removes the enabling of cbo.inval in user mode.
v3:
Add the functionality of Expose Zicbom and selftests for Zicbom.
v4:
Modify the order of macros, The test_no_cbo_inval function is added
separately.
Ira Weiny wrote:
> Devices which optionally support Dynamic Capacity (DC) are configured
> via mailbox commands. CXL 3.1 requires the host to issue the Get DC
> Configuration command in order to properly configure DCDs. Without the
> Get DC Configuration command DCD can't be supported.
>
> Imple
On Sun, Jan 12, 2025 at 10:50:32AM -0500, Neal Gompa wrote:
> On Sun, Jan 12, 2025 at 10:30 AM Miguel Ojeda wrote:
> >
> > Newcomers to the kernel need to learn the different tags that are
> > used in commit messages and when to apply them. Acked-by is sometimes
> > misunderstood, since the docume
On Tue, Jan 07, 2025 at 09:10:04AM -0800, Nicolin Chen wrote:
> Reorder the existing OBJ/IOCTL lists.
>
> Also run clang-format for the same coding style at line wrappings.
>
> No functional change.
>
> Reviewed-by: Lu Baolu
> Signed-off-by: Nicolin Chen
> ---
> drivers/iommu/iommufd/main.c |
On Tue, Jan 14, 2025 at 07:29:14PM +0100, Brendan Jackman wrote:
> > Tweaks aimed at checkpatch are only useful during the code review stage, so
> > once that code is accepted upstream, they become wholly irrelevant. A
> > checkpatch trailer in the permanent commit record serves no purpose, not
>
Alistair Popple wrote:
> DEVMAP PTEs are no longer required to support ZONE_DEVICE so remove
> them.
>
> Signed-off-by: Alistair Popple
> Suggested-by: Chunyan Zhang
> Reviewed-by: Björn Töpel
This and the next are candidates to squash into the previous remove
patch, right? ...and I am not sur
On Tue, Jan 14, 2025 at 10:22:15AM +0900, Masahiro Yamada wrote:
> On Tue, Jan 14, 2025 at 5:04 AM Sami Tolvanen wrote:
> >
> > Hi Masahiro,
> >
> > On Fri, Jan 10, 2025 at 6:26 PM Masahiro Yamada
> > wrote:
> > >
> > > On Sat, Jan 4, 2025 at 2:37 AM Matthew Maurer wrote:
> > > >
> > > > From:
Alistair Popple wrote:
> Now that DAX and all other reference counts to ZONE_DEVICE pages are
> managed normally there is no need for the special devmap PTE/PMD/PUD
> page table bits. So drop all references to these, freeing up a
> software defined page table bit on architectures supporting it.
>
Alistair Popple wrote:
> The devmap PTE special bit was used to detect mappings of FS DAX
> pages. This tracking was required to ensure the generic mm did not
> manipulate the page reference counts as FS DAX implemented it's own
> reference counting scheme.
>
> Now that FS DAX pages have their ref
On Tue, 14 Jan 2025 at 17:04, Konstantin Ryabitsev
wrote:
>
> On Tue, Jan 14, 2025 at 03:25:41PM +0100, Brendan Jackman wrote:
> > wrote:
> > > Do we really want this to become part of the permanent commit message? I'm
> > > pretty sure this won't go over well with many.
> >
> > Why not?
>
> Twea
David Hildenbrand wrote:
> > +vm_fault_t vmf_insert_folio_pmd(struct vm_fault *vmf, struct folio *folio,
> > bool write)
> > +{
> > + struct vm_area_struct *vma = vmf->vma;
> > + unsigned long addr = vmf->address & PMD_MASK;
> > + struct mm_struct *mm = vma->vm_mm;
> > + spinlock_t *ptl;
>
On 14.01.25 03:28, Dan Williams wrote:
Alistair Popple wrote:
The procfs mmu files such as smaps and pagemap currently ignore devdax and
fsdax pages because these pages are considered special. A future change
will start treating these as normal pages, meaning they can be exposed via
smaps and pa
+vm_fault_t vmf_insert_folio_pmd(struct vm_fault *vmf, struct folio *folio,
bool write)
+{
+ struct vm_area_struct *vma = vmf->vma;
+ unsigned long addr = vmf->address & PMD_MASK;
+ struct mm_struct *mm = vma->vm_mm;
+ spinlock_t *ptl;
+ pgtable_t pgtable = NULL;
+
+
On 1/13/2025 6:56 AM, mhkelle...@gmail.com wrote:
From: Michael Kelley
[...]
An incredible read, thank you, Michael!
Reviewed-by: Roman Kisel
diff --git a/Documentation/virt/hyperv/index.rst
b/Documentation/virt/hyperv/index.rst
index 79bc4080329e..c84c40fd61c9 100644
--- a/Documentat
On 10.01.25 07:00, Alistair Popple wrote:
Currently DAX folio/page reference counts are managed differently to
normal pages. To allow these to be managed the same as normal pages
introduce vmf_insert_folio_pud. This will map the entire PUD-sized folio
and take references as it would for a normall
On 10.01.25 07:00, Alistair Popple wrote:
Currently to map a DAX page the DAX driver calls vmf_insert_pfn. This
creates a special devmap PTE entry for the pfn but does not take a
reference on the underlying struct page for the mapping. This is
because DAX page refcounts are treated specially, as
On Tue, Jan 14, 2025 at 03:25:41PM +0100, Brendan Jackman wrote:
> wrote:
> > Do we really want this to become part of the permanent commit message? I'm
> > pretty sure this won't go over well with many.
>
> Why not?
Tweaks aimed at checkpatch are only useful during the code review stage, so
onc
Enable Launch Time Control (LTC) support to XDP zero copy via XDP Tx
metadata framework.
This patch is tested with tools/testing/selftests/bpf/xdp_hw_metadata on
Intel I225-LM Ethernet controller. Below are the test steps and result.
Test Steps:
1. At DUT, start xdp_hw_metadata selftest applicati
Enable launch time (Time-Based Scheduling) support to XDP zero copy via XDP
Tx metadata framework.
This patch is tested with tools/testing/selftests/bpf/xdp_hw_metadata on
Intel Tiger Lake platform. Below are the test steps and result.
Test Steps:
1. At DUT, start xdp_hw_metadata selftest applica
Add launch time hardware offload request to xdp_hw_metadata. Users can
configure the delta of launch time relative to HW RX-time using the "-l"
argument. By default, the delta is set to 0 ns, which means the launch time
is disabled. By setting the delta to a non-zero value, the launch time
hardware
Extend the XDP Tx metadata framework so that user can requests launch time
hardware offload, where the Ethernet device will schedule the packet for
transmission at a pre-determined time called launch time. The value of
launch time is communicated from user space to Ethernet driver via
launch_time f
This series expands the XDP TX metadata framework to allow user
applications to pass per packet 64-bit launch time directly to the kernel
driver, requesting launch time hardware offload support. The XDP TX
metadata framework will not perform any clock conversion or packet
reordering.
Please note t
On 10.01.25 07:00, Alistair Popple wrote:
In preparation for using insert_page() for DAX, enhance
insert_page_into_pte_locked() to handle establishing writable
mappings. Recall that DAX returns VM_FAULT_NOPAGE after installing a
PTE which bypasses the typical set_pte_range() in finish_fault.
Si
On 10.01.25 07:00, Alistair Popple wrote:
Zone device pages are used to represent various type of device memory
managed by device drivers. Currently compound zone device pages are
not supported. This is because MEMORY_DEVICE_FS_DAX pages are the only
user of higher order zone device pages and hav
On 10.01.25 07:00, Alistair Popple wrote:
Currently ZONE_DEVICE page reference counts are initialised by core
memory management code in __init_zone_device_page() as part of the
memremap() call which driver modules make to obtain ZONE_DEVICE
pages. This initialises page refcounts to 1 before retur
On 10.01.25 07:00, Alistair Popple wrote:
PAGE_MAPPING_DAX_SHARED is the same as PAGE_MAPPING_ANON. This isn't
currently a problem because FS DAX pages are treated
specially. However a future change will make FS DAX pages more like
normal pages, so folio_test_anon() must not return true for a FS
On Tue, 14 Jan 2025 at 14:34, Konstantin Ryabitsev
wrote:
> Do we really want this to become part of the permanent commit message? I'm
> pretty sure this won't go over well with many.
Why not?
On Mon, Jan 13, 2025 at 12:44:37PM -0800, Nicolin Chen wrote:
> > You'd want to push a special event when the first overflow happens and
> > probably also report a counter so userspace can know how many events
> > got lost.
>
> How about this:
>
> enum iommufd_veventq_header_type {
> IOMMU
On Mon, Jan 13, 2025 at 04:04:22PM +, Brendan Jackman wrote:
> Checkpatch sometimes has false positives. This makes it less useful for
> automatic usage: tools like b4 [0] can run checkpatch on all of your
> patches and give you a quick overview. When iterating on a branch, it's
> tiresome to m
> I would like to clarify that representing the bridge and its slave ports
> inside PPE (using a VSI - virtual switch instance) is a pre-requisite before
> learning can take place on a port. At this point, since switchdev
> is not enabled, VSI is not created for port/bridge and hence FDB learning
>
On Tue, Jan 14, 2025 at 11:43:08AM +0100, Marco Elver wrote:
> On Tue, 14 Jan 2025 at 06:35, Jiao, Joey wrote:
> >
> > Hi,
> >
> > This patch series introduces new kcov unique modes:
> > `KCOV_TRACE_UNIQ_[PC|EDGE|CMP]`, which are used to collect unique PC, EDGE,
> > CMP information.
> >
> > Backgr
On Tue, Jan 14, 2025 at 08:17:02PM +0800, yunhui cui wrote:
> Hi Samuel，
>
> On Tue, Jan 14, 2025 at 1:28 PM Samuel Holland
> wrote:
> >
> > Hi Yunhui,
> >
> > On 2025-01-13 8:19 PM, Yunhui Cui wrote:
> > > Expose Zicbom through hwprobe and also provide a key to extract its
> > > respective block
On Tue, Jan 14, 2025 at 12:02:31PM +0100, Dmitry Vyukov wrote:
> On Tue, 14 Jan 2025 at 11:43, Marco Elver wrote:
> > On Tue, 14 Jan 2025 at 06:35, Jiao, Joey wrote:
> > >
> > > Hi,
> > >
> > > This patch series introduces new kcov unique modes:
> > > `KCOV_TRACE_UNIQ_[PC|EDGE|CMP]`, which are us
Hi Samuel，
On Tue, Jan 14, 2025 at 1:28 PM Samuel Holland
wrote:
>
> Hi Yunhui,
>
> On 2025-01-13 8:19 PM, Yunhui Cui wrote:
> > Expose Zicbom through hwprobe and also provide a key to extract its
> > respective block size.
> >
> > Signed-off-by: Yunhui Cui
> > ---
> > Documentation/arch/riscv/
On Tue, 14 Jan 2025 at 12:42, Brendan Jackman wrote:
> I think that's a downgrade from the Checkpatch-args approach
(Sorry I mean Checkpatch-ignore of course)
On Mon, 13 Jan 2025, 20:15 Joe Perches, wrote:
>
> On Mon, 2025-01-13 at 16:04 +, Brendan Jackman wrote:
> > Checkpatch sometimes has false positives. This makes it less useful for
> > automatic usage: tools like b4 [0] can run checkpatch on all of your
> > patches and give you a quick overvie
On 1/13/2025 9:37 PM, Andrew Lunn wrote:
Why is learning needed on physical ports? In general, switches forward
unknown destination addresses to the CPU. Which is what you want when
the ports are isolated from each other. Everything goes to the
CPU. But maybe this switch does not work like thi
On Tue, 14 Jan 2025 at 11:43, Marco Elver wrote:
> On Tue, 14 Jan 2025 at 06:35, Jiao, Joey wrote:
> >
> > Hi,
> >
> > This patch series introduces new kcov unique modes:
> > `KCOV_TRACE_UNIQ_[PC|EDGE|CMP]`, which are used to collect unique PC, EDGE,
> > CMP information.
> >
> > Background
> > --
On Tue, 14 Jan 2025 at 06:35, Jiao, Joey wrote:
>
> Hi,
>
> This patch series introduces new kcov unique modes:
> `KCOV_TRACE_UNIQ_[PC|EDGE|CMP]`, which are used to collect unique PC, EDGE,
> CMP information.
>
> Background
> --
>
> In the current kcov implementation, when `__sanitizer_cov
On Tue, Jan 14, 2025 at 10:19:36AM +0800, Yunhui Cui wrote:
> Add test for Zicbom and its block size into CBO tests, when
> Zicbom is present, test that cbo.clean/flush may be issued and works.
> As the software can't verify the clean/flush functions, we just judged
> that cbo.clean/flush isn't exe
52 matches
Mail list logo
