Commit 14b80582 authored by Dan Williams's avatar Dan Williams

resource: Introduce alloc_free_mem_region()

The core of devm_request_free_mem_region() is a helper that searches for
free space in iomem_resource and performs __request_region_locked() on
the result of that search. The policy choices of the implementation
conform to what CONFIG_DEVICE_PRIVATE users want which is memory that is
immediately marked busy, and a preference to search for the first-fit
free range in descending order from the top of the physical address
space.

CXL has a need for a similar allocator, but with the following tweaks:

1/ Search for free space in ascending order

2/ Search for free space relative to a given CXL window

3/ 'insert' rather than 'request' the new resource given downstream
   drivers from the CXL Region driver (like the pmem or dax drivers) are
   responsible for request_mem_region() when they activate the memory
   range.

Rework __request_free_mem_region() into get_free_mem_region() which
takes a set of GFR_* (Get Free Region) flags to control the allocation
policy (ascending vs descending), and "busy" policy (insert_resource()
vs request_region()).

As part of the consolidation of the legacy GFR_REQUEST_REGION case with
the new default of just inserting a new resource into the free space
some minor cleanups like not checking for NULL before calling
devres_free() (which does its own check) is included.
Suggested-by: default avatarJason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/linux-cxl/20220420143406.GY2120790@nvidia.com/
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Christoph Hellwig <hch@lst.de>
Reviewed-by: default avatarJonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/165784333333.1758207.13703329337805274043.stgit@dwillia2-xfh.jf.intel.comSigned-off-by: default avatarDan Williams <dan.j.williams@intel.com>
parent 7f8faf96
...@@ -330,6 +330,8 @@ struct resource *devm_request_free_mem_region(struct device *dev, ...@@ -330,6 +330,8 @@ struct resource *devm_request_free_mem_region(struct device *dev,
struct resource *base, unsigned long size); struct resource *base, unsigned long size);
struct resource *request_free_mem_region(struct resource *base, struct resource *request_free_mem_region(struct resource *base,
unsigned long size, const char *name); unsigned long size, const char *name);
struct resource *alloc_free_mem_region(struct resource *base,
unsigned long size, unsigned long align, const char *name);
static inline void irqresource_disabled(struct resource *res, u32 irq) static inline void irqresource_disabled(struct resource *res, u32 irq)
{ {
......
...@@ -489,8 +489,9 @@ int __weak page_is_ram(unsigned long pfn) ...@@ -489,8 +489,9 @@ int __weak page_is_ram(unsigned long pfn)
} }
EXPORT_SYMBOL_GPL(page_is_ram); EXPORT_SYMBOL_GPL(page_is_ram);
static int __region_intersects(resource_size_t start, size_t size, static int __region_intersects(struct resource *parent, resource_size_t start,
unsigned long flags, unsigned long desc) size_t size, unsigned long flags,
unsigned long desc)
{ {
struct resource res; struct resource res;
int type = 0; int other = 0; int type = 0; int other = 0;
...@@ -499,7 +500,7 @@ static int __region_intersects(resource_size_t start, size_t size, ...@@ -499,7 +500,7 @@ static int __region_intersects(resource_size_t start, size_t size,
res.start = start; res.start = start;
res.end = start + size - 1; res.end = start + size - 1;
for (p = iomem_resource.child; p ; p = p->sibling) { for (p = parent->child; p ; p = p->sibling) {
bool is_type = (((p->flags & flags) == flags) && bool is_type = (((p->flags & flags) == flags) &&
((desc == IORES_DESC_NONE) || ((desc == IORES_DESC_NONE) ||
(desc == p->desc))); (desc == p->desc)));
...@@ -543,7 +544,7 @@ int region_intersects(resource_size_t start, size_t size, unsigned long flags, ...@@ -543,7 +544,7 @@ int region_intersects(resource_size_t start, size_t size, unsigned long flags,
int ret; int ret;
read_lock(&resource_lock); read_lock(&resource_lock);
ret = __region_intersects(start, size, flags, desc); ret = __region_intersects(&iomem_resource, start, size, flags, desc);
read_unlock(&resource_lock); read_unlock(&resource_lock);
return ret; return ret;
...@@ -1780,62 +1781,139 @@ void resource_list_free(struct list_head *head) ...@@ -1780,62 +1781,139 @@ void resource_list_free(struct list_head *head)
} }
EXPORT_SYMBOL(resource_list_free); EXPORT_SYMBOL(resource_list_free);
#ifdef CONFIG_DEVICE_PRIVATE #ifdef CONFIG_GET_FREE_REGION
static struct resource *__request_free_mem_region(struct device *dev, #define GFR_DESCENDING (1UL << 0)
struct resource *base, unsigned long size, const char *name) #define GFR_REQUEST_REGION (1UL << 1)
#define GFR_DEFAULT_ALIGN (1UL << PA_SECTION_SHIFT)
static resource_size_t gfr_start(struct resource *base, resource_size_t size,
resource_size_t align, unsigned long flags)
{
if (flags & GFR_DESCENDING) {
resource_size_t end;
end = min_t(resource_size_t, base->end,
(1ULL << MAX_PHYSMEM_BITS) - 1);
return end - size + 1;
}
return ALIGN(base->start, align);
}
static bool gfr_continue(struct resource *base, resource_size_t addr,
resource_size_t size, unsigned long flags)
{
if (flags & GFR_DESCENDING)
return addr > size && addr >= base->start;
/*
* In the ascend case be careful that the last increment by
* @size did not wrap 0.
*/
return addr > addr - size &&
addr <= min_t(resource_size_t, base->end,
(1ULL << MAX_PHYSMEM_BITS) - 1);
}
static resource_size_t gfr_next(resource_size_t addr, resource_size_t size,
unsigned long flags)
{
if (flags & GFR_DESCENDING)
return addr - size;
return addr + size;
}
static void remove_free_mem_region(void *_res)
{
struct resource *res = _res;
if (res->parent)
remove_resource(res);
free_resource(res);
}
static struct resource *
get_free_mem_region(struct device *dev, struct resource *base,
resource_size_t size, const unsigned long align,
const char *name, const unsigned long desc,
const unsigned long flags)
{ {
resource_size_t end, addr; resource_size_t addr;
struct resource *res; struct resource *res;
struct region_devres *dr = NULL; struct region_devres *dr = NULL;
size = ALIGN(size, 1UL << PA_SECTION_SHIFT); size = ALIGN(size, align);
end = min_t(unsigned long, base->end, (1UL << MAX_PHYSMEM_BITS) - 1);
addr = end - size + 1UL;
res = alloc_resource(GFP_KERNEL); res = alloc_resource(GFP_KERNEL);
if (!res) if (!res)
return ERR_PTR(-ENOMEM); return ERR_PTR(-ENOMEM);
if (dev) { if (dev && (flags & GFR_REQUEST_REGION)) {
dr = devres_alloc(devm_region_release, dr = devres_alloc(devm_region_release,
sizeof(struct region_devres), GFP_KERNEL); sizeof(struct region_devres), GFP_KERNEL);
if (!dr) { if (!dr) {
free_resource(res); free_resource(res);
return ERR_PTR(-ENOMEM); return ERR_PTR(-ENOMEM);
} }
} else if (dev) {
if (devm_add_action_or_reset(dev, remove_free_mem_region, res))
return ERR_PTR(-ENOMEM);
} }
write_lock(&resource_lock); write_lock(&resource_lock);
for (; addr > size && addr >= base->start; addr -= size) { for (addr = gfr_start(base, size, align, flags);
if (__region_intersects(addr, size, 0, IORES_DESC_NONE) != gfr_continue(base, addr, size, flags);
REGION_DISJOINT) addr = gfr_next(addr, size, flags)) {
if (__region_intersects(base, addr, size, 0, IORES_DESC_NONE) !=
REGION_DISJOINT)
continue; continue;
if (__request_region_locked(res, &iomem_resource, addr, size, if (flags & GFR_REQUEST_REGION) {
name, 0)) if (__request_region_locked(res, &iomem_resource, addr,
break; size, name, 0))
break;
if (dev) { if (dev) {
dr->parent = &iomem_resource; dr->parent = &iomem_resource;
dr->start = addr; dr->start = addr;
dr->n = size; dr->n = size;
devres_add(dev, dr); devres_add(dev, dr);
} }
res->desc = IORES_DESC_DEVICE_PRIVATE_MEMORY; res->desc = desc;
write_unlock(&resource_lock); write_unlock(&resource_lock);
/*
* A driver is claiming this region so revoke any
* mappings.
*/
revoke_iomem(res);
} else {
res->start = addr;
res->end = addr + size - 1;
res->name = name;
res->desc = desc;
res->flags = IORESOURCE_MEM;
/*
* Only succeed if the resource hosts an exclusive
* range after the insert
*/
if (__insert_resource(base, res) || res->child)
break;
write_unlock(&resource_lock);
}
/*
* A driver is claiming this region so revoke any mappings.
*/
revoke_iomem(res);
return res; return res;
} }
write_unlock(&resource_lock); write_unlock(&resource_lock);
free_resource(res); if (flags & GFR_REQUEST_REGION) {
if (dr) free_resource(res);
devres_free(dr); devres_free(dr);
} else if (dev)
devm_release_action(dev, remove_free_mem_region, res);
return ERR_PTR(-ERANGE); return ERR_PTR(-ERANGE);
} }
...@@ -1854,18 +1932,48 @@ static struct resource *__request_free_mem_region(struct device *dev, ...@@ -1854,18 +1932,48 @@ static struct resource *__request_free_mem_region(struct device *dev,
struct resource *devm_request_free_mem_region(struct device *dev, struct resource *devm_request_free_mem_region(struct device *dev,
struct resource *base, unsigned long size) struct resource *base, unsigned long size)
{ {
return __request_free_mem_region(dev, base, size, dev_name(dev)); unsigned long flags = GFR_DESCENDING | GFR_REQUEST_REGION;
return get_free_mem_region(dev, base, size, GFR_DEFAULT_ALIGN,
dev_name(dev),
IORES_DESC_DEVICE_PRIVATE_MEMORY, flags);
} }
EXPORT_SYMBOL_GPL(devm_request_free_mem_region); EXPORT_SYMBOL_GPL(devm_request_free_mem_region);
struct resource *request_free_mem_region(struct resource *base, struct resource *request_free_mem_region(struct resource *base,
unsigned long size, const char *name) unsigned long size, const char *name)
{ {
return __request_free_mem_region(NULL, base, size, name); unsigned long flags = GFR_DESCENDING | GFR_REQUEST_REGION;
return get_free_mem_region(NULL, base, size, GFR_DEFAULT_ALIGN, name,
IORES_DESC_DEVICE_PRIVATE_MEMORY, flags);
} }
EXPORT_SYMBOL_GPL(request_free_mem_region); EXPORT_SYMBOL_GPL(request_free_mem_region);
#endif /* CONFIG_DEVICE_PRIVATE */ /**
* alloc_free_mem_region - find a free region relative to @base
* @base: resource that will parent the new resource
* @size: size in bytes of memory to allocate from @base
* @align: alignment requirements for the allocation
* @name: resource name
*
* Buses like CXL, that can dynamically instantiate new memory regions,
* need a method to allocate physical address space for those regions.
* Allocate and insert a new resource to cover a free, unclaimed by a
* descendant of @base, range in the span of @base.
*/
struct resource *alloc_free_mem_region(struct resource *base,
unsigned long size, unsigned long align,
const char *name)
{
/* Default of ascending direction and insert resource */
unsigned long flags = 0;
return get_free_mem_region(NULL, base, size, align, name,
IORES_DESC_NONE, flags);
}
EXPORT_SYMBOL_NS_GPL(alloc_free_mem_region, CXL);
#endif /* CONFIG_GET_FREE_REGION */
static int __init strict_iomem(char *str) static int __init strict_iomem(char *str)
{ {
......
...@@ -994,9 +994,14 @@ config HMM_MIRROR ...@@ -994,9 +994,14 @@ config HMM_MIRROR
bool bool
depends on MMU depends on MMU
config GET_FREE_REGION
depends on SPARSEMEM
bool
config DEVICE_PRIVATE config DEVICE_PRIVATE
bool "Unaddressable device memory (GPU memory, ...)" bool "Unaddressable device memory (GPU memory, ...)"
depends on ZONE_DEVICE depends on ZONE_DEVICE
select GET_FREE_REGION
help help
Allows creation of struct pages to represent unaddressable device Allows creation of struct pages to represent unaddressable device
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment