From: Alistair Popple <apopple@nvidia.com>
To: linux-mm@kvack.org, cgroups@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, jgg@nvidia.com,
jhubbard@nvidia.com, tjmercier@google.com, hannes@cmpxchg.org,
surenb@google.com, mkoutny@suse.com, daniel@ffwll.ch,
Alistair Popple <apopple@nvidia.com>,
Alex Williamson <alex.williamson@redhat.com>,
Cornelia Huck <cohuck@redhat.com>,
kvm@vger.kernel.org
Subject: [RFC PATCH 07/19] vfio/type1: Charge pinned pages to pinned_vm instead of locked_vm
Date: Tue, 24 Jan 2023 16:42:36 +1100 [thread overview]
Message-ID: <1235619c5394aa67fe116f89f22fafa370707c90.1674538665.git-series.apopple@nvidia.com> (raw)
In-Reply-To: <cover.f52b9eb2792bccb8a9ecd6bc95055705cfe2ae03.1674538665.git-series.apopple@nvidia.com>
This switches the charge to pinned_vm to be consistent with other
drivers that pin pages with FOLL_LONGTERM. It also allows the use of
the vm_account helper struct which makes a future change to implement
cgroup accounting of pinned pages easier to implement as that requires
a reference to the cgroup to be maintained.
Signed-off-by: Alistair Popple <apopple@nvidia.com>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Cornelia Huck <cohuck@redhat.com>
Cc: kvm@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
---
drivers/vfio/vfio_iommu_type1.c | 59 +++++++++-------------------------
1 file changed, 16 insertions(+), 43 deletions(-)
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 23c24fe..828f6c7 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -95,11 +95,11 @@ struct vfio_dma {
size_t size; /* Map size (bytes) */
int prot; /* IOMMU_READ/WRITE */
bool iommu_mapped;
- bool lock_cap; /* capable(CAP_IPC_LOCK) */
bool vaddr_invalid;
struct task_struct *task;
struct rb_root pfn_list; /* Ex-user pinned pfn list */
unsigned long *bitmap;
+ struct vm_account vm_account;
};
struct vfio_batch {
@@ -412,31 +412,6 @@ static int vfio_iova_put_vfio_pfn(struct vfio_dma *dma, struct vfio_pfn *vpfn)
return ret;
}
-static int vfio_lock_acct(struct vfio_dma *dma, long npage, bool async)
-{
- struct mm_struct *mm;
- int ret;
-
- if (!npage)
- return 0;
-
- mm = async ? get_task_mm(dma->task) : dma->task->mm;
- if (!mm)
- return -ESRCH; /* process exited */
-
- ret = mmap_write_lock_killable(mm);
- if (!ret) {
- ret = __account_locked_vm(mm, abs(npage), npage > 0, dma->task,
- dma->lock_cap);
- mmap_write_unlock(mm);
- }
-
- if (async)
- mmput(mm);
-
- return ret;
-}
-
/*
* Some mappings aren't backed by a struct page, for example an mmap'd
* MMIO range for our own or another device. These use a different
@@ -715,16 +690,8 @@ static long vfio_pin_pages_remote(struct vfio_dma *dma, unsigned long vaddr,
* externally pinned pages are already counted against
* the user.
*/
- if (!rsvd && !vfio_find_vpfn(dma, iova)) {
- if (!dma->lock_cap &&
- mm->locked_vm + lock_acct + 1 > limit) {
- pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n",
- __func__, limit << PAGE_SHIFT);
- ret = -ENOMEM;
- goto unpin_out;
- }
+ if (!rsvd && !vfio_find_vpfn(dma, iova))
lock_acct++;
- }
pinned++;
npage--;
@@ -744,7 +711,11 @@ static long vfio_pin_pages_remote(struct vfio_dma *dma, unsigned long vaddr,
}
out:
- ret = vfio_lock_acct(dma, lock_acct, false);
+ if (vm_account_pinned(&dma->vm_account, lock_acct)) {
+ ret = -ENOMEM;
+ lock_acct = 0;
+ pr_warn("%s: RLIMIT_MEMLOCK exceeded\n", __func__);
+ }
unpin_out:
if (batch->size == 1 && !batch->offset) {
@@ -759,6 +730,7 @@ static long vfio_pin_pages_remote(struct vfio_dma *dma, unsigned long vaddr,
put_pfn(pfn, dma->prot);
}
vfio_batch_unpin(batch, dma);
+ vm_unaccount_pinned(&dma->vm_account, lock_acct);
return ret;
}
@@ -782,7 +754,7 @@ static long vfio_unpin_pages_remote(struct vfio_dma *dma, dma_addr_t iova,
}
if (do_accounting)
- vfio_lock_acct(dma, locked - unlocked, true);
+ vm_unaccount_pinned(&dma->vm_account, locked - unlocked);
return unlocked;
}
@@ -805,7 +777,7 @@ static int vfio_pin_page_external(struct vfio_dma *dma, unsigned long vaddr,
ret = 0;
if (do_accounting && !is_invalid_reserved_pfn(*pfn_base)) {
- ret = vfio_lock_acct(dma, 1, true);
+ ret = vm_account_pinned(&dma->vm_account, 1);
if (ret) {
put_pfn(*pfn_base, dma->prot);
if (ret == -ENOMEM)
@@ -833,7 +805,7 @@ static int vfio_unpin_page_external(struct vfio_dma *dma, dma_addr_t iova,
unlocked = vfio_iova_put_vfio_pfn(dma, vpfn);
if (do_accounting)
- vfio_lock_acct(dma, -unlocked, true);
+ vm_unaccount_pinned(&dma->vm_account, unlocked);
return unlocked;
}
@@ -921,7 +893,7 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,
ret = vfio_add_to_pfn_list(dma, iova, phys_pfn);
if (ret) {
if (put_pfn(phys_pfn, dma->prot) && do_accounting)
- vfio_lock_acct(dma, -1, true);
+ vm_unaccount_pinned(&dma->vm_account, 1);
goto pin_unwind;
}
@@ -1162,7 +1134,7 @@ static long vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma,
}
if (do_accounting) {
- vfio_lock_acct(dma, -unlocked, true);
+ vm_unaccount_pinned(&dma->vm_account, unlocked);
return 0;
}
return unlocked;
@@ -1674,7 +1646,8 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
*/
get_task_struct(current->group_leader);
dma->task = current->group_leader;
- dma->lock_cap = capable(CAP_IPC_LOCK);
+ vm_account_init(&dma->vm_account, dma->task, NULL, VM_ACCOUNT_TASK |
+ (capable(CAP_IPC_LOCK) ? VM_ACCOUNT_BYPASS : 0));
dma->pfn_list = RB_ROOT;
@@ -2398,7 +2371,7 @@ static void vfio_iommu_unmap_unpin_reaccount(struct vfio_iommu *iommu)
if (!is_invalid_reserved_pfn(vpfn->pfn))
locked++;
}
- vfio_lock_acct(dma, locked - unlocked, true);
+ vm_unaccount_pinned(&dma->vm_account, locked - unlocked);
}
}
--
git-series 0.9.1
next prev parent reply other threads:[~2023-01-24 5:45 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-01-24 5:42 [RFC PATCH 00/19] mm: Introduce a cgroup to limit the amount of locked and pinned memory Alistair Popple
2023-01-24 5:42 ` [RFC PATCH 01/19] mm: Introduce vm_account Alistair Popple
2023-01-24 6:29 ` Christoph Hellwig
2023-01-24 14:32 ` Jason Gunthorpe
2023-01-30 11:36 ` Alistair Popple
2023-01-31 14:00 ` David Hildenbrand
2023-01-24 5:42 ` [RFC PATCH 02/19] drivers/vhost: Convert to use vm_account Alistair Popple
2023-01-24 5:55 ` Michael S. Tsirkin
2023-01-30 10:43 ` Alistair Popple
2023-01-24 14:34 ` Jason Gunthorpe
2023-01-24 5:42 ` [RFC PATCH 03/19] drivers/vdpa: Convert vdpa to use the new vm_structure Alistair Popple
2023-01-24 14:35 ` Jason Gunthorpe
2023-01-24 5:42 ` [RFC PATCH 04/19] infiniband/umem: Convert to use vm_account Alistair Popple
2023-01-24 5:42 ` [RFC PATCH 05/19] RMDA/siw: " Alistair Popple
2023-01-24 14:37 ` Jason Gunthorpe
2023-01-24 15:22 ` Bernard Metzler
2023-01-24 15:56 ` Bernard Metzler
2023-01-30 11:34 ` Alistair Popple
2023-01-30 13:27 ` Bernard Metzler
2023-01-24 5:42 ` [RFC PATCH 06/19] RDMA/usnic: convert " Alistair Popple
2023-01-24 14:41 ` Jason Gunthorpe
2023-01-30 11:10 ` Alistair Popple
2023-01-24 5:42 ` Alistair Popple [this message]
2023-01-24 5:42 ` [RFC PATCH 08/19] vfio/spapr_tce: Convert accounting to pinned_vm Alistair Popple
2023-01-24 5:42 ` [RFC PATCH 09/19] io_uring: convert to use vm_account Alistair Popple
2023-01-24 14:44 ` Jason Gunthorpe
2023-01-30 11:12 ` Alistair Popple
2023-01-30 13:21 ` Jason Gunthorpe
2023-01-24 5:42 ` [RFC PATCH 10/19] net: skb: Switch to using vm_account Alistair Popple
2023-01-24 14:51 ` Jason Gunthorpe
2023-01-30 11:17 ` Alistair Popple
2023-02-06 4:36 ` Alistair Popple
2023-02-06 13:14 ` Jason Gunthorpe
2023-01-24 5:42 ` [RFC PATCH 11/19] xdp: convert to use vm_account Alistair Popple
2023-01-24 5:42 ` [RFC PATCH 12/19] kvm/book3s_64_vio: Convert account_locked_vm() to vm_account_pinned() Alistair Popple
2023-01-24 5:42 ` [RFC PATCH 13/19] fpga: dfl: afu: convert to use vm_account Alistair Popple
2023-01-24 5:42 ` [RFC PATCH 14/19] mm: Introduce a cgroup for pinned memory Alistair Popple
2023-01-27 21:44 ` Tejun Heo
2023-01-30 13:20 ` Jason Gunthorpe
2023-01-24 5:42 ` [RFC PATCH 15/19] mm/util: Extend vm_account to charge pages against the pin cgroup Alistair Popple
2023-01-24 5:42 ` [RFC PATCH 16/19] mm/util: Refactor account_locked_vm Alistair Popple
2023-01-24 5:42 ` [RFC PATCH 17/19] mm: Convert mmap and mlock to use account_locked_vm Alistair Popple
2023-01-24 5:42 ` [RFC PATCH 18/19] mm/mmap: Charge locked memory to pins cgroup Alistair Popple
2023-01-24 5:42 ` [RFC PATCH 19/19] selftests/vm: Add pins-cgroup selftest for mlock/mmap Alistair Popple
2023-01-24 18:26 ` [RFC PATCH 00/19] mm: Introduce a cgroup to limit the amount of locked and pinned memory Yosry Ahmed
2023-01-31 0:54 ` Alistair Popple
2023-01-31 5:14 ` Yosry Ahmed
2023-01-31 11:22 ` Alistair Popple
2023-01-31 19:49 ` Yosry Ahmed
2023-01-24 20:12 ` Jason Gunthorpe
2023-01-31 13:57 ` David Hildenbrand
2023-01-31 14:03 ` Jason Gunthorpe
2023-01-31 14:06 ` David Hildenbrand
2023-01-31 14:10 ` Jason Gunthorpe
2023-01-31 14:15 ` David Hildenbrand
2023-01-31 14:21 ` Jason Gunthorpe
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=1235619c5394aa67fe116f89f22fafa370707c90.1674538665.git-series.apopple@nvidia.com \
--to=apopple@nvidia.com \
--cc=alex.williamson@redhat.com \
--cc=cgroups@vger.kernel.org \
--cc=cohuck@redhat.com \
--cc=daniel@ffwll.ch \
--cc=hannes@cmpxchg.org \
--cc=jgg@nvidia.com \
--cc=jhubbard@nvidia.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mkoutny@suse.com \
--cc=surenb@google.com \
--cc=tjmercier@google.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).