From: Leon Romanovsky <leon@kernel.org>
To: Christoph Hellwig <hch@lst.de>,
Robin Murphy <robin.murphy@arm.com>,
Marek Szyprowski <m.szyprowski@samsung.com>,
Joerg Roedel <joro@8bytes.org>, Will Deacon <will@kernel.org>,
Jason Gunthorpe <jgg@ziepe.ca>,
Chaitanya Kulkarni <chaitanyak@nvidia.com>
Cc: "Leon Romanovsky" <leonro@nvidia.com>,
"Jonathan Corbet" <corbet@lwn.net>,
"Jens Axboe" <axboe@kernel.dk>, "Keith Busch" <kbusch@kernel.org>,
"Sagi Grimberg" <sagi@grimberg.me>,
"Yishai Hadas" <yishaih@nvidia.com>,
"Shameer Kolothum" <shameerali.kolothum.thodi@huawei.com>,
"Kevin Tian" <kevin.tian@intel.com>,
"Alex Williamson" <alex.williamson@redhat.com>,
"Jérôme Glisse" <jglisse@redhat.com>,
"Andrew Morton" <akpm@linux-foundation.org>,
linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-block@vger.kernel.org, linux-rdma@vger.kernel.org,
iommu@lists.linux.dev, linux-nvme@lists.infradead.org,
kvm@vger.kernel.org, linux-mm@kvack.org,
"Bart Van Assche" <bvanassche@acm.org>,
"Damien Le Moal" <damien.lemoal@opensource.wdc.com>,
"Amir Goldstein" <amir73il@gmail.com>,
"josef@toxicpanda.com" <josef@toxicpanda.com>,
"Martin K. Petersen" <martin.petersen@oracle.com>,
"daniel@iogearbox.net" <daniel@iogearbox.net>,
"Dan Williams" <dan.j.williams@intel.com>,
"jack@suse.com" <jack@suse.com>,
"Zhu Yanjun" <zyjzyj2000@gmail.com>
Subject: [RFC RESEND 01/16] mm/hmm: let users to tag specific PFNs
Date: Tue, 5 Mar 2024 13:18:32 +0200 [thread overview]
Message-ID: <a77609c9c9a09214e38b04133e44eee67fe50ab0.1709635535.git.leon@kernel.org> (raw)
In-Reply-To: <cover.1709635535.git.leon@kernel.org>
From: Leon Romanovsky <leonro@nvidia.com>
Introduce new sticky flag, which isn't overwritten by HMM range fault.
Such flag allows users to tag specific PFNs with extra data in addition
to already filled by HMM.
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
include/linux/hmm.h | 3 +++
mm/hmm.c | 34 +++++++++++++++++++++-------------
2 files changed, 24 insertions(+), 13 deletions(-)
diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index 126a36571667..b90902baa593 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -23,6 +23,7 @@ struct mmu_interval_notifier;
* HMM_PFN_WRITE - if the page memory can be written to (requires HMM_PFN_VALID)
* HMM_PFN_ERROR - accessing the pfn is impossible and the device should
* fail. ie poisoned memory, special pages, no vma, etc
+ * HMM_PFN_STICKY - Flag preserved on input-to-output transformation
*
* On input:
* 0 - Return the current state of the page, do not fault it.
@@ -36,6 +37,8 @@ enum hmm_pfn_flags {
HMM_PFN_VALID = 1UL << (BITS_PER_LONG - 1),
HMM_PFN_WRITE = 1UL << (BITS_PER_LONG - 2),
HMM_PFN_ERROR = 1UL << (BITS_PER_LONG - 3),
+ /* Sticky lag, carried from Input to Output */
+ HMM_PFN_STICKY = 1UL << (BITS_PER_LONG - 7),
HMM_PFN_ORDER_SHIFT = (BITS_PER_LONG - 8),
/* Input flags */
diff --git a/mm/hmm.c b/mm/hmm.c
index 277ddcab4947..9645a72beec0 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -44,8 +44,10 @@ static int hmm_pfns_fill(unsigned long addr, unsigned long end,
{
unsigned long i = (addr - range->start) >> PAGE_SHIFT;
- for (; addr < end; addr += PAGE_SIZE, i++)
- range->hmm_pfns[i] = cpu_flags;
+ for (; addr < end; addr += PAGE_SIZE, i++) {
+ range->hmm_pfns[i] &= HMM_PFN_STICKY;
+ range->hmm_pfns[i] |= cpu_flags;
+ }
return 0;
}
@@ -202,8 +204,10 @@ static int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
return hmm_vma_fault(addr, end, required_fault, walk);
pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
- for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++)
- hmm_pfns[i] = pfn | cpu_flags;
+ for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++) {
+ hmm_pfns[i] &= HMM_PFN_STICKY;
+ hmm_pfns[i] |= pfn | cpu_flags;
+ }
return 0;
}
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
@@ -236,7 +240,7 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0);
if (required_fault)
goto fault;
- *hmm_pfn = 0;
+ *hmm_pfn = *hmm_pfn & HMM_PFN_STICKY;
return 0;
}
@@ -253,14 +257,14 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
cpu_flags = HMM_PFN_VALID;
if (is_writable_device_private_entry(entry))
cpu_flags |= HMM_PFN_WRITE;
- *hmm_pfn = swp_offset_pfn(entry) | cpu_flags;
+ *hmm_pfn = (*hmm_pfn & HMM_PFN_STICKY) | swp_offset_pfn(entry) | cpu_flags;
return 0;
}
required_fault =
hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0);
if (!required_fault) {
- *hmm_pfn = 0;
+ *hmm_pfn = *hmm_pfn & HMM_PFN_STICKY;
return 0;
}
@@ -304,11 +308,11 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
pte_unmap(ptep);
return -EFAULT;
}
- *hmm_pfn = HMM_PFN_ERROR;
+ *hmm_pfn = (*hmm_pfn & HMM_PFN_STICKY) | HMM_PFN_ERROR;
return 0;
}
- *hmm_pfn = pte_pfn(pte) | cpu_flags;
+ *hmm_pfn = (*hmm_pfn & HMM_PFN_STICKY) | pte_pfn(pte) | cpu_flags;
return 0;
fault:
@@ -453,8 +457,10 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
}
pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
- for (i = 0; i < npages; ++i, ++pfn)
- hmm_pfns[i] = pfn | cpu_flags;
+ for (i = 0; i < npages; ++i, ++pfn) {
+ hmm_pfns[i] &= HMM_PFN_STICKY;
+ hmm_pfns[i] |= pfn | cpu_flags;
+ }
goto out_unlock;
}
@@ -512,8 +518,10 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
}
pfn = pte_pfn(entry) + ((start & ~hmask) >> PAGE_SHIFT);
- for (; addr < end; addr += PAGE_SIZE, i++, pfn++)
- range->hmm_pfns[i] = pfn | cpu_flags;
+ for (; addr < end; addr += PAGE_SIZE, i++, pfn++) {
+ range->hmm_pfns[i] &= HMM_PFN_STICKY;
+ range->hmm_pfns[i] |= pfn | cpu_flags;
+ }
spin_unlock(ptl);
return 0;
--
2.44.0
next prev parent reply other threads:[~2024-03-05 11:19 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-03-05 11:18 [RFC RESEND 00/16] Split IOMMU DMA mapping operation to two steps Leon Romanovsky
2024-03-05 11:18 ` Leon Romanovsky [this message]
2024-03-05 11:18 ` [RFC RESEND 02/16] dma-mapping: provide an interface to allocate IOVA Leon Romanovsky
2024-03-05 11:18 ` [RFC RESEND 03/16] dma-mapping: provide callbacks to link/unlink pages to specific IOVA Leon Romanovsky
2024-03-05 11:18 ` [RFC RESEND 04/16] iommu/dma: Provide an interface to allow preallocate IOVA Leon Romanovsky
2024-03-05 11:18 ` [RFC RESEND 05/16] iommu/dma: Prepare map/unmap page functions to receive IOVA Leon Romanovsky
2024-03-05 11:18 ` [RFC RESEND 06/16] iommu/dma: Implement link/unlink page callbacks Leon Romanovsky
2024-03-05 11:18 ` [RFC RESEND 07/16] RDMA/umem: Preallocate and cache IOVA for UMEM ODP Leon Romanovsky
2024-03-05 11:18 ` [RFC RESEND 08/16] RDMA/umem: Store ODP access mask information in PFN Leon Romanovsky
2024-03-05 11:18 ` [RFC RESEND 09/16] RDMA/core: Separate DMA mapping to caching IOVA and page linkage Leon Romanovsky
2024-03-05 11:18 ` [RFC RESEND 10/16] RDMA/umem: Prevent UMEM ODP creation with SWIOTLB Leon Romanovsky
2024-03-05 11:18 ` [RFC RESEND 11/16] vfio/mlx5: Explicitly use number of pages instead of allocated length Leon Romanovsky
2024-03-05 11:18 ` [RFC RESEND 12/16] vfio/mlx5: Rewrite create mkey flow to allow better code reuse Leon Romanovsky
2024-03-05 11:18 ` [RFC RESEND 13/16] vfio/mlx5: Explicitly store page list Leon Romanovsky
2024-03-05 11:18 ` [RFC RESEND 14/16] vfio/mlx5: Convert vfio to use DMA link API Leon Romanovsky
2024-03-05 11:18 ` [RFC RESEND 15/16] block: add dma_link_range() based API Leon Romanovsky
2024-03-05 11:18 ` [RFC RESEND 16/16] nvme-pci: use blk_rq_dma_map() for NVMe SGL Leon Romanovsky
2024-03-05 15:51 ` Keith Busch
2024-03-05 16:08 ` Jens Axboe
2024-03-05 16:39 ` Chaitanya Kulkarni
2024-03-05 16:46 ` Chaitanya Kulkarni
2024-03-06 14:33 ` Christoph Hellwig
2024-03-06 15:05 ` Jason Gunthorpe
2024-03-06 16:14 ` Christoph Hellwig
2024-05-03 14:41 ` Zhu Yanjun
2024-05-05 13:23 ` Leon Romanovsky
2024-05-06 7:25 ` Zhu Yanjun
2024-03-05 12:05 ` [RFC RESEND 00/16] Split IOMMU DMA mapping operation to two steps Robin Murphy
2024-03-05 12:29 ` Leon Romanovsky
2024-03-06 14:44 ` Christoph Hellwig
2024-03-06 15:43 ` Jason Gunthorpe
2024-03-06 16:20 ` Christoph Hellwig
2024-03-06 17:44 ` Jason Gunthorpe
2024-03-06 22:14 ` Christoph Hellwig
2024-03-07 0:00 ` Jason Gunthorpe
2024-03-07 15:05 ` Christoph Hellwig
2024-03-07 21:01 ` Jason Gunthorpe
2024-03-08 16:49 ` Christoph Hellwig
2024-03-08 20:23 ` Jason Gunthorpe
2024-03-09 16:14 ` Christoph Hellwig
2024-03-10 9:35 ` Leon Romanovsky
2024-03-12 21:28 ` Christoph Hellwig
2024-03-13 7:46 ` Leon Romanovsky
2024-03-13 21:44 ` Christoph Hellwig
2024-03-19 15:36 ` Jason Gunthorpe
2024-03-20 8:55 ` Leon Romanovsky
2024-03-21 22:40 ` Christoph Hellwig
2024-03-22 17:46 ` Leon Romanovsky
2024-03-24 23:16 ` Christoph Hellwig
2024-03-21 22:39 ` Christoph Hellwig
2024-03-22 18:43 ` Jason Gunthorpe
2024-03-24 23:22 ` Christoph Hellwig
2024-03-27 17:14 ` Jason Gunthorpe
2024-03-07 6:01 ` Zhu Yanjun
2024-04-09 20:39 ` Zhu Yanjun
2024-05-02 23:32 ` Zeng, Oak
2024-05-03 11:57 ` Zhu Yanjun
2024-05-03 16:42 ` Jason Gunthorpe
2024-05-03 20:59 ` Zeng, Oak
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=a77609c9c9a09214e38b04133e44eee67fe50ab0.1709635535.git.leon@kernel.org \
--to=leon@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=alex.williamson@redhat.com \
--cc=amir73il@gmail.com \
--cc=axboe@kernel.dk \
--cc=bvanassche@acm.org \
--cc=chaitanyak@nvidia.com \
--cc=corbet@lwn.net \
--cc=damien.lemoal@opensource.wdc.com \
--cc=dan.j.williams@intel.com \
--cc=daniel@iogearbox.net \
--cc=hch@lst.de \
--cc=iommu@lists.linux.dev \
--cc=jack@suse.com \
--cc=jgg@ziepe.ca \
--cc=jglisse@redhat.com \
--cc=joro@8bytes.org \
--cc=josef@toxicpanda.com \
--cc=kbusch@kernel.org \
--cc=kevin.tian@intel.com \
--cc=kvm@vger.kernel.org \
--cc=leonro@nvidia.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-nvme@lists.infradead.org \
--cc=linux-rdma@vger.kernel.org \
--cc=m.szyprowski@samsung.com \
--cc=martin.petersen@oracle.com \
--cc=robin.murphy@arm.com \
--cc=sagi@grimberg.me \
--cc=shameerali.kolothum.thodi@huawei.com \
--cc=will@kernel.org \
--cc=yishaih@nvidia.com \
--cc=zyjzyj2000@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).