#include <linux/mount.h>
#include <linux/resource_ext.h>
#include <uapi/linux/magic.h>
+#include <linux/string.h>
+#include <linux/vmalloc.h>
#include <asm/io.h>
static DEFINE_RWLOCK(resource_lock);
-static struct resource *next_resource(struct resource *p)
+static struct resource *next_resource(struct resource *p, bool skip_children)
{
- if (p->child)
+ if (!skip_children && p->child)
return p->child;
while (!p->sibling && p->parent)
p = p->parent;
return p->sibling;
}
-static struct resource *next_resource_skip_children(struct resource *p)
-{
- while (!p->sibling && p->parent)
- p = p->parent;
- return p->sibling;
-}
-
#define for_each_resource(_root, _p, _skip_children) \
- for ((_p) = (_root)->child; (_p); \
- (_p) = (_skip_children) ? next_resource_skip_children(_p) : \
- next_resource(_p))
-
-static void *r_next(struct seq_file *m, void *v, loff_t *pos)
-{
- struct resource *p = v;
- (*pos)++;
- return (void *)next_resource(p);
-}
+ for ((_p) = (_root)->child; (_p); (_p) = next_resource(_p, _skip_children))
#ifdef CONFIG_PROC_FS
static void *r_start(struct seq_file *m, loff_t *pos)
__acquires(resource_lock)
{
- struct resource *p = pde_data(file_inode(m->file));
- loff_t l = 0;
+ struct resource *root = pde_data(file_inode(m->file));
+ struct resource *p;
+ loff_t l = *pos;
+
read_lock(&resource_lock);
- for (p = p->child; p && l < *pos; p = r_next(m, p, &l))
- ;
+ for_each_resource(root, p, false) {
+ if (l-- == 0)
+ break;
+ }
+
return p;
}
+static void *r_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ struct resource *p = v;
+
+ (*pos)++;
+
+ return (void *)next_resource(p, false);
+}
+
static void r_stop(struct seq_file *m, void *v)
__releases(resource_lock)
{
read_lock(&resource_lock);
- for (p = iomem_resource.child; p; p = next_resource(p)) {
+ for_each_resource(&iomem_resource, p, false) {
/* If we passed the resource we are looking for, stop */
if (p->start > end) {
p = NULL;
func);
}
+/*
+ * This function, being a variant of walk_system_ram_res(), calls the @func
+ * callback against all memory ranges of type System RAM which are marked as
+ * IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY in reversed order, i.e., from
+ * higher to lower.
+ */
+int walk_system_ram_res_rev(u64 start, u64 end, void *arg,
+ int (*func)(struct resource *, void *))
+{
+ struct resource res, *rams;
+ int rams_size = 16, i;
+ unsigned long flags;
+ int ret = -1;
+
+ /* create a list */
+ rams = kvcalloc(rams_size, sizeof(struct resource), GFP_KERNEL);
+ if (!rams)
+ return ret;
+
+ flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+ i = 0;
+ while ((start < end) &&
+ (!find_next_iomem_res(start, end, flags, IORES_DESC_NONE, &res))) {
+ if (i >= rams_size) {
+ /* re-alloc */
+ struct resource *rams_new;
+
+ rams_new = kvrealloc(rams, rams_size * sizeof(struct resource),
+ (rams_size + 16) * sizeof(struct resource),
+ GFP_KERNEL);
+ if (!rams_new)
+ goto out;
+
+ rams = rams_new;
+ rams_size += 16;
+ }
+
+ rams[i].start = res.start;
+ rams[i++].end = res.end;
+
+ start = res.end + 1;
+ }
+
+ /* go reverse */
+ for (i--; i >= 0; i--) {
+ ret = (*func)(&rams[i], arg);
+ if (ret)
+ break;
+ }
+
+out:
+ kvfree(rams);
+ return ret;
+}
+
/*
* This function calls the @func callback against all memory ranges, which
* are ranges marked as IORESOURCE_MEM and IORESOUCE_BUSY.
}
EXPORT_SYMBOL_GPL(page_is_ram);
-static int __region_intersects(resource_size_t start, size_t size,
- unsigned long flags, unsigned long desc)
+static int __region_intersects(struct resource *parent, resource_size_t start,
+ size_t size, unsigned long flags,
+ unsigned long desc)
{
struct resource res;
int type = 0; int other = 0;
res.start = start;
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) &&
((desc == IORES_DESC_NONE) ||
(desc == p->desc)));
int ret;
read_lock(&resource_lock);
- ret = __region_intersects(start, size, flags, desc);
+ ret = __region_intersects(&iomem_resource, start, size, flags, desc);
read_unlock(&resource_lock);
return ret;
if (conflict->end > new->end)
new->end = conflict->end;
- printk("Expanded resource %s due to conflict with %s\n", new->name, conflict->name);
+ pr_info("Expanded resource %s due to conflict with %s\n", new->name, conflict->name);
}
write_unlock(&resource_lock);
}
+/*
+ * Not for general consumption, only early boot memory map parsing, PCI
+ * resource discovery, and late discovery of CXL resources are expected
+ * to use this interface. The former are built-in and only the latter,
+ * CXL, is a module.
+ */
+EXPORT_SYMBOL_NS_GPL(insert_resource_expand_to_fit, CXL);
/**
* remove_resource - Remove a resource in the resource tree
write_unlock(&resource_lock);
- printk(KERN_WARNING "Trying to free nonexistent resource "
- "<%016llx-%016llx>\n", (unsigned long long)start,
- (unsigned long long)end);
+ pr_warn("Trying to free nonexistent resource <%pa-%pa>\n", &start, &end);
}
EXPORT_SYMBOL(__release_region);
continue;
}
- /*
- * All memory regions added from memory-hotplug path have the
- * flag IORESOURCE_SYSTEM_RAM. If the resource does not have
- * this flag, we know that we are dealing with a resource coming
- * from HMM/devm. HMM/devm use another mechanism to add/release
- * a resource. This goes via devm_request_mem_region and
- * devm_release_mem_region.
- * HMM/devm take care to release their resources when they want,
- * so if we are dealing with them, let us just back off here.
- */
- if (!(res->flags & IORESOURCE_SYSRAM)) {
- break;
- }
-
if (!(res->flags & IORESOURCE_MEM))
break;
*/
int iomem_map_sanity_check(resource_size_t addr, unsigned long size)
{
- struct resource *p = &iomem_resource;
+ resource_size_t end = addr + size - 1;
+ struct resource *p;
int err = 0;
- loff_t l;
read_lock(&resource_lock);
- for (p = p->child; p ; p = r_next(NULL, p, &l)) {
+ for_each_resource(&iomem_resource, p, false) {
/*
* We can probably skip the resources without
* IORESOURCE_IO attribute?
*/
- if (p->start >= addr + size)
+ if (p->start > end)
continue;
if (p->end < addr)
continue;
if (PFN_DOWN(p->start) <= PFN_DOWN(addr) &&
- PFN_DOWN(p->end) >= PFN_DOWN(addr + size - 1))
+ PFN_DOWN(p->end) >= PFN_DOWN(end))
continue;
/*
* if a resource is "BUSY", it's not a hardware resource
if (p->flags & IORESOURCE_BUSY)
continue;
- printk(KERN_WARNING "resource sanity check: requesting [mem %#010llx-%#010llx], which spans more than %s %pR\n",
- (unsigned long long)addr,
- (unsigned long long)(addr + size - 1),
- p->name, p);
+ pr_warn("resource sanity check: requesting [mem %pa-%pa], which spans more than %s %pR\n",
+ &addr, &end, p->name, p);
err = -1;
break;
}
*
* Returns true if exclusive to the kernel, otherwise returns false.
*/
-bool iomem_is_exclusive(u64 addr)
+bool resource_is_exclusive(struct resource *root, u64 addr, resource_size_t size)
{
const unsigned int exclusive_system_ram = IORESOURCE_SYSTEM_RAM |
IORESOURCE_EXCLUSIVE;
bool skip_children = false, err = false;
- int size = PAGE_SIZE;
struct resource *p;
- addr = addr & PAGE_MASK;
-
read_lock(&resource_lock);
- for_each_resource(&iomem_resource, p, skip_children) {
+ for_each_resource(root, p, skip_children) {
if (p->start >= addr + size)
break;
if (p->end < addr) {
return err;
}
+bool iomem_is_exclusive(u64 addr)
+{
+ return resource_is_exclusive(&iomem_resource, addr & PAGE_MASK,
+ PAGE_SIZE);
+}
+
struct resource_entry *resource_list_create_entry(struct resource *res,
size_t extra_size)
{
}
EXPORT_SYMBOL(resource_list_free);
-#ifdef CONFIG_DEVICE_PRIVATE
-static struct resource *__request_free_mem_region(struct device *dev,
- struct resource *base, unsigned long size, const char *name)
+#ifdef CONFIG_GET_FREE_REGION
+#define GFR_DESCENDING (1UL << 0)
+#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 region_devres *dr = NULL;
- size = ALIGN(size, 1UL << PA_SECTION_SHIFT);
- end = min_t(unsigned long, base->end, (1UL << MAX_PHYSMEM_BITS) - 1);
- addr = end - size + 1UL;
+ size = ALIGN(size, align);
res = alloc_resource(GFP_KERNEL);
if (!res)
return ERR_PTR(-ENOMEM);
- if (dev) {
+ if (dev && (flags & GFR_REQUEST_REGION)) {
dr = devres_alloc(devm_region_release,
sizeof(struct region_devres), GFP_KERNEL);
if (!dr) {
free_resource(res);
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);
- for (; addr > size && addr >= base->start; addr -= size) {
- if (__region_intersects(addr, size, 0, IORES_DESC_NONE) !=
- REGION_DISJOINT)
+ for (addr = gfr_start(base, size, align, flags);
+ gfr_continue(base, addr, align, flags);
+ addr = gfr_next(addr, align, flags)) {
+ if (__region_intersects(base, addr, size, 0, IORES_DESC_NONE) !=
+ REGION_DISJOINT)
continue;
- if (__request_region_locked(res, &iomem_resource, addr, size,
- name, 0))
- break;
+ if (flags & GFR_REQUEST_REGION) {
+ if (__request_region_locked(res, &iomem_resource, addr,
+ size, name, 0))
+ break;
- if (dev) {
- dr->parent = &iomem_resource;
- dr->start = addr;
- dr->n = size;
- devres_add(dev, dr);
- }
+ if (dev) {
+ dr->parent = &iomem_resource;
+ dr->start = addr;
+ dr->n = size;
+ devres_add(dev, dr);
+ }
- res->desc = IORES_DESC_DEVICE_PRIVATE_MEMORY;
- write_unlock(&resource_lock);
+ res->desc = desc;
+ 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;
}
write_unlock(&resource_lock);
- free_resource(res);
- if (dr)
+ if (flags & GFR_REQUEST_REGION) {
+ free_resource(res);
devres_free(dr);
+ } else if (dev)
+ devm_release_action(dev, remove_free_mem_region, res);
return ERR_PTR(-ERANGE);
}
struct resource *devm_request_free_mem_region(struct device *dev,
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);
struct resource *request_free_mem_region(struct resource *base,
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);
-#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)
{