On Fri, Mar 26, 2021 at 12:20:35PM +1100, Alistair Popple wrote:
> request_free_mem_region() is used to find an empty range of physical
> addresses for hotplugging ZONE_DEVICE memory. It does this by iterating
> over the range of possible addresses using region_intersects() to see if
> the range is free.
>
> region_intersects() obtains a read lock before walking the resource tree
> to protect against concurrent changes. However it drops the lock prior
> to returning. This means by the time request_mem_region() is called in
> request_free_mem_region() another thread may have already reserved the
> requested region resulting in unexpected failures and a message in the
> kernel log from hitting this condition:
>
> /*
> * mm/hmm.c reserves physical addresses which then
> * become unavailable to other users. Conflicts are
> * not expected. Warn to aid debugging if encountered.
> */
> if (conflict->desc == IORES_DESC_DEVICE_PRIVATE_MEMORY) {
> pr_warn("Unaddressable device %s %pR conflicts with %pR",
> conflict->name, conflict, res);
>
> To fix this create versions of region_intersects() and
> request_mem_region() that allow the caller to take the appropriate lock
> such that it may be held over the required calls.
>
> Instead of creating another version of devm_request_mem_region() that
> doesn't take the lock open-code it to allow the caller to pre-allocate
> the required memory prior to taking the lock.
>
> Fixes: 0c385190392d8 ("resource: add a not device managed
> request_free_mem_region variant")
> Fixes: 0092908d16c60 ("mm: factor out a devm_request_free_mem_region helper")
> Fixes: 4ef589dc9b10c ("mm/hmm/devmem: device memory hotplug using
> ZONE_DEVICE")
> Signed-off-by: Alistair Popple <apop...@nvidia.com>
>
> ---
>
> v2:
> - Added Fixes tag
>
> ---
> kernel/resource.c | 146 +++++++++++++++++++++++++++++-----------------
> 1 file changed, 94 insertions(+), 52 deletions(-)
>
> diff --git a/kernel/resource.c b/kernel/resource.c
> index 627e61b0c124..2d4652383dd2 100644
> --- a/kernel/resource.c
> +++ b/kernel/resource.c
> @@ -523,6 +523,34 @@ int __weak page_is_ram(unsigned long pfn)
> }
> EXPORT_SYMBOL_GPL(page_is_ram);
>
> +static int __region_intersects(resource_size_t start, size_t size,
> + unsigned long flags, unsigned long desc)
> +{
> + struct resource res;
> + int type = 0; int other = 0;
> + struct resource *p;
> +
> + res.start = start;
> + res.end = start + size - 1;
> +
> + for (p = iomem_resource.child; p ; p = p->sibling) {
> + bool is_type = (((p->flags & flags) == flags) &&
> + ((desc == IORES_DESC_NONE) ||
> + (desc == p->desc)));
is_type is a bad name, are we saying "is" as in boolean question?
Or is it short for something like intersection_type? I know you've
just moved the code over :)
> +
> + if (resource_overlaps(p, &res))
> + is_type ? type++ : other++;
> + }
> +
> + if (type == 0)
> + return REGION_DISJOINT;
> +
> + if (other == 0)
> + return REGION_INTERSECTS;
> +
> + return REGION_MIXED;
> +}
> +
> /**
> * region_intersects() - determine intersection of region with known
> resources
> * @start: region start address
> @@ -546,31 +574,12 @@ EXPORT_SYMBOL_GPL(page_is_ram);
> int region_intersects(resource_size_t start, size_t size, unsigned long
> flags,
> unsigned long desc)
> {
> - struct resource res;
> - int type = 0; int other = 0;
> - struct resource *p;
> -
> - res.start = start;
> - res.end = start + size - 1;
> + int rc;
>
> read_lock(&resource_lock);
> - for (p = iomem_resource.child; p ; p = p->sibling) {
> - bool is_type = (((p->flags & flags) == flags) &&
> - ((desc == IORES_DESC_NONE) ||
> - (desc == p->desc)));
> -
> - if (resource_overlaps(p, &res))
> - is_type ? type++ : other++;
> - }
> + rc = __region_intersects(start, size, flags, desc);
> read_unlock(&resource_lock);
> -
> - if (type == 0)
> - return REGION_DISJOINT;
> -
> - if (other == 0)
> - return REGION_INTERSECTS;
> -
> - return REGION_MIXED;
> + return rc;
> }
> EXPORT_SYMBOL_GPL(region_intersects);
>
> @@ -1171,31 +1180,17 @@ struct address_space *iomem_get_mapping(void)
> return smp_load_acquire(&iomem_inode)->i_mapping;
> }
>
> -/**
> - * __request_region - create a new busy resource region
> - * @parent: parent resource descriptor
> - * @start: resource start address
> - * @n: resource region size
> - * @name: reserving caller's ID string
> - * @flags: IO resource flags
> - */
> -struct resource * __request_region(struct resource *parent,
> - resource_size_t start, resource_size_t n,
> - const char *name, int flags)
> +static bool request_region_locked(struct resource *parent,
> + struct resource *res, resource_size_t start,
> + resource_size_t n, const char *name, int
> flags)
> {
> - DECLARE_WAITQUEUE(wait, current);
> - struct resource *res = alloc_resource(GFP_KERNEL);
> struct resource *orig_parent = parent;
> -
> - if (!res)
> - return NULL;
> + DECLARE_WAITQUEUE(wait, current);
This part of the diff looks confusing, do we have a waitqueue and we call
schedule() within a function called with the lock held?
>
> res->name = name;
> res->start = start;
> res->end = start + n - 1;
>
> - write_lock(&resource_lock);
> -
> for (;;) {
> struct resource *conflict;
>
> @@ -1230,16 +1225,39 @@ struct resource * __request_region(struct resource
> *parent,
> write_lock(&resource_lock);
> continue;
> }
> - /* Uhhuh, that didn't work out.. */
> - free_resource(res);
> - res = NULL;
> - break;
> + return false;
> }
> - write_unlock(&resource_lock);
>
> if (res && orig_parent == &iomem_resource)
> revoke_iomem(res);
>
> + return true;
> +}
> +
> +/**
> + * __request_region - create a new busy resource region
> + * @parent: parent resource descriptor
> + * @start: resource start address
> + * @n: resource region size
> + * @name: reserving caller's ID string
> + * @flags: IO resource flags
> + */
> +struct resource *__request_region(struct resource *parent,
> + resource_size_t start, resource_size_t n,
> + const char *name, int flags)
> +{
> + struct resource *res = alloc_resource(GFP_KERNEL);
> +
> + if (!res)
> + return NULL;
> +
> + write_lock(&resource_lock);
> + if (!request_region_locked(parent, res, start, n, name, flags)) {
> + /* Uhhuh, that didn't work out.. */
> + free_resource(res);
> + res = NULL;
> + }
> + write_unlock(&resource_lock);
Should the function be called __request_region_locked?
> return res;
> }
> EXPORT_SYMBOL(__request_region);
> @@ -1779,26 +1797,50 @@ static struct resource
> *__request_free_mem_region(struct device *dev,
> {
> resource_size_t end, addr;
> struct resource *res;
> + struct region_devres *dr = NULL;
> +
> + res = alloc_resource(GFP_KERNEL);
> + if (!res)
> + return ERR_PTR(-ENOMEM);
> +
> + if (dev) {
> + dr = devres_alloc(devm_region_release, sizeof(struct
> region_devres),
> + GFP_KERNEL);
> + if (!dr) {
> + free_resource(res);
> + return ERR_PTR(-ENOMEM);
> + }
> + }
>
> size = ALIGN(size, 1UL << PA_SECTION_SHIFT);
> end = min_t(unsigned long, base->end, (1UL << MAX_PHYSMEM_BITS) - 1);
> addr = end - size + 1UL;
>
> + write_lock(&resource_lock);
> for (; addr > size && addr >= base->start; addr -= size) {
> - if (region_intersects(addr, size, 0, IORES_DESC_NONE) !=
> + if (__region_intersects(addr, size, 0, IORES_DESC_NONE) !=
> REGION_DISJOINT)
> continue;
>
> - if (dev)
> - res = devm_request_mem_region(dev, addr, size, name);
> - else
> - res = request_mem_region(addr, size, name);
> - if (!res)
> - return ERR_PTR(-ENOMEM);
> + if (!request_region_locked(&iomem_resource, res, addr,
> + size, name, 0))
> + break;
> +
> res->desc = IORES_DESC_DEVICE_PRIVATE_MEMORY;
> + if (dev) {
> + dr->parent = &iomem_resource;
> + dr->start = addr;
> + dr->n = size;
> + devres_add(dev, dr);
> + }
> +
> + write_unlock(&resource_lock);
> return res;
> }
>
> + write_unlock(&resource_lock);
> + free_resource(res);
> +
> return ERR_PTR(-ERANGE);
> }
>
Balbir Singh.
