PCI/P2PDMA: Allow userspace VMA allocations through sysfs

Create a sysfs bin attribute called "allocate" under the existing
"p2pmem" group. The only allowable operation on this file is the mmap()
call.

When mmap() is called on this attribute, the kernel allocates a chunk of
memory from the genalloc and inserts the pages into the VMA. The
dev_pagemap .page_free callback will indicate when these pages are no
longer used and they will be put back into the genalloc.

On device unbind, remove the sysfs file before the memremap_pages are
cleaned up. This ensures unmap_mapping_range() is called on the files
inode and no new mappings can be created.

Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Link: https://lore.kernel.org/r/20221021174116.7200-9-logang@deltatee.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This commit is contained in:
Logan Gunthorpe 2022-10-21 11:41:15 -06:00 committed by Jens Axboe
parent 7ee4ccf574
commit 7e9c7ef83d

View File

@ -89,6 +89,90 @@ static ssize_t published_show(struct device *dev, struct device_attribute *attr,
}
static DEVICE_ATTR_RO(published);
static int p2pmem_alloc_mmap(struct file *filp, struct kobject *kobj,
struct bin_attribute *attr, struct vm_area_struct *vma)
{
struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj));
size_t len = vma->vm_end - vma->vm_start;
struct pci_p2pdma *p2pdma;
struct percpu_ref *ref;
unsigned long vaddr;
void *kaddr;
int ret;
/* prevent private mappings from being established */
if ((vma->vm_flags & VM_MAYSHARE) != VM_MAYSHARE) {
pci_info_ratelimited(pdev,
"%s: fail, attempted private mapping\n",
current->comm);
return -EINVAL;
}
if (vma->vm_pgoff) {
pci_info_ratelimited(pdev,
"%s: fail, attempted mapping with non-zero offset\n",
current->comm);
return -EINVAL;
}
rcu_read_lock();
p2pdma = rcu_dereference(pdev->p2pdma);
if (!p2pdma) {
ret = -ENODEV;
goto out;
}
kaddr = (void *)gen_pool_alloc_owner(p2pdma->pool, len, (void **)&ref);
if (!kaddr) {
ret = -ENOMEM;
goto out;
}
/*
* vm_insert_page() can sleep, so a reference is taken to mapping
* such that rcu_read_unlock() can be done before inserting the
* pages
*/
if (unlikely(!percpu_ref_tryget_live_rcu(ref))) {
ret = -ENODEV;
goto out_free_mem;
}
rcu_read_unlock();
for (vaddr = vma->vm_start; vaddr < vma->vm_end; vaddr += PAGE_SIZE) {
ret = vm_insert_page(vma, vaddr, virt_to_page(kaddr));
if (ret) {
gen_pool_free(p2pdma->pool, (uintptr_t)kaddr, len);
return ret;
}
percpu_ref_get(ref);
put_page(virt_to_page(kaddr));
kaddr += PAGE_SIZE;
len -= PAGE_SIZE;
}
percpu_ref_put(ref);
return 0;
out_free_mem:
gen_pool_free(p2pdma->pool, (uintptr_t)kaddr, len);
out:
rcu_read_unlock();
return ret;
}
static struct bin_attribute p2pmem_alloc_attr = {
.attr = { .name = "allocate", .mode = 0660 },
.mmap = p2pmem_alloc_mmap,
/*
* Some places where we want to call mmap (ie. python) will check
* that the file size is greater than the mmap size before allowing
* the mmap to continue. To work around this, just set the size
* to be very large.
*/
.size = SZ_1T,
};
static struct attribute *p2pmem_attrs[] = {
&dev_attr_size.attr,
&dev_attr_available.attr,
@ -96,11 +180,32 @@ static struct attribute *p2pmem_attrs[] = {
NULL,
};
static struct bin_attribute *p2pmem_bin_attrs[] = {
&p2pmem_alloc_attr,
NULL,
};
static const struct attribute_group p2pmem_group = {
.attrs = p2pmem_attrs,
.bin_attrs = p2pmem_bin_attrs,
.name = "p2pmem",
};
static void p2pdma_page_free(struct page *page)
{
struct pci_p2pdma_pagemap *pgmap = to_p2p_pgmap(page->pgmap);
struct percpu_ref *ref;
gen_pool_free_owner(pgmap->provider->p2pdma->pool,
(uintptr_t)page_to_virt(page), PAGE_SIZE,
(void **)&ref);
percpu_ref_put(ref);
}
static const struct dev_pagemap_ops p2pdma_pgmap_ops = {
.page_free = p2pdma_page_free,
};
static void pci_p2pdma_release(void *data)
{
struct pci_dev *pdev = data;
@ -152,6 +257,19 @@ out:
return error;
}
static void pci_p2pdma_unmap_mappings(void *data)
{
struct pci_dev *pdev = data;
/*
* Removing the alloc attribute from sysfs will call
* unmap_mapping_range() on the inode, teardown any existing userspace
* mappings and prevent new ones from being created.
*/
sysfs_remove_file_from_group(&pdev->dev.kobj, &p2pmem_alloc_attr.attr,
p2pmem_group.name);
}
/**
* pci_p2pdma_add_resource - add memory for use as p2p memory
* @pdev: the device to add the memory to
@ -198,6 +316,7 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
pgmap->range.end = pgmap->range.start + size - 1;
pgmap->nr_range = 1;
pgmap->type = MEMORY_DEVICE_PCI_P2PDMA;
pgmap->ops = &p2pdma_pgmap_ops;
p2p_pgmap->provider = pdev;
p2p_pgmap->bus_offset = pci_bus_address(pdev, bar) -
@ -209,6 +328,11 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
goto pgmap_free;
}
error = devm_add_action_or_reset(&pdev->dev, pci_p2pdma_unmap_mappings,
pdev);
if (error)
goto pages_free;
p2pdma = rcu_dereference_protected(pdev->p2pdma, 1);
error = gen_pool_add_owner(p2pdma->pool, (unsigned long)addr,
pci_bus_address(pdev, bar) + offset,