From d2ccde1c8e90d38cee87a1b0309ad2827f3fd30d Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Mon, 11 Dec 2023 02:45:28 +0000
Subject: [PATCH] add boot partition size
---
kernel/kernel/resource.c | 336 ++++++++++++++++++++++++++++++++++++++++++-------------
1 files changed, 255 insertions(+), 81 deletions(-)
diff --git a/kernel/kernel/resource.c b/kernel/kernel/resource.c
index 8205d8e..817545f 100644
--- a/kernel/kernel/resource.c
+++ b/kernel/kernel/resource.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/kernel/resource.c
*
@@ -139,7 +140,7 @@
{
proc_create_seq_data("ioports", 0, NULL, &resource_op,
&ioport_resource);
- proc_create_seq_data("iomem", 0400, NULL, &resource_op, &iomem_resource);
+ proc_create_seq_data("iomem", 0, NULL, &resource_op, &iomem_resource);
return 0;
}
__initcall(ioresources_init);
@@ -319,52 +320,75 @@
EXPORT_SYMBOL(release_resource);
/**
- * Finds the lowest iomem resource that covers part of [start..end]. The
- * caller must specify start, end, flags, and desc (which may be
+ * Finds the lowest iomem resource that covers part of [@start..@end]. The
+ * caller must specify @start, @end, @flags, and @desc (which may be
* IORES_DESC_NONE).
*
- * If a resource is found, returns 0 and *res is overwritten with the part
- * of the resource that's within [start..end]; if none is found, returns
+ * If a resource is found, returns 0 and @*res is overwritten with the part
+ * of the resource that's within [@start..@end]; if none is found, returns
* -ENODEV. Returns -EINVAL for invalid parameters.
*
* This function walks the whole tree and not just first level children
- * unless @first_level_children_only is true.
+ * unless @first_lvl is true.
+ *
+ * @start: start address of the resource searched for
+ * @end: end address of same resource
+ * @flags: flags which the resource must have
+ * @desc: descriptor the resource must have
+ * @first_lvl: walk only the first level children, if set
+ * @res: return ptr, if resource found
*/
static int find_next_iomem_res(resource_size_t start, resource_size_t end,
unsigned long flags, unsigned long desc,
- bool first_level_children_only,
- struct resource *res)
+ bool first_lvl, struct resource *res)
{
+ bool siblings_only = true;
struct resource *p;
- bool sibling_only = false;
- BUG_ON(!res);
- BUG_ON(start >= end);
+ if (!res)
+ return -EINVAL;
- if (first_level_children_only)
- sibling_only = true;
+ if (start >= end)
+ return -EINVAL;
read_lock(&resource_lock);
- for (p = iomem_resource.child; p; p = next_resource(p, sibling_only)) {
- if ((p->flags & flags) != flags)
- continue;
- if ((desc != IORES_DESC_NONE) && (desc != p->desc))
- continue;
+ for (p = iomem_resource.child; p; p = next_resource(p, siblings_only)) {
+ /* If we passed the resource we are looking for, stop */
if (p->start > end) {
p = NULL;
break;
}
- if ((p->end >= start) && (p->start <= end))
- break;
+
+ /* Skip until we find a range that matches what we look for */
+ if (p->end < start)
+ continue;
+
+ /*
+ * Now that we found a range that matches what we look for,
+ * check the flags and the descriptor. If we were not asked to
+ * use only the first level, start looking at children as well.
+ */
+ siblings_only = first_lvl;
+
+ if ((p->flags & flags) != flags)
+ continue;
+ if ((desc != IORES_DESC_NONE) && (desc != p->desc))
+ continue;
+
+ /* Found a match, break */
+ break;
}
if (p) {
/* copy data */
- res->start = max(start, p->start);
- res->end = min(end, p->end);
- res->flags = p->flags;
- res->desc = p->desc;
+ *res = (struct resource) {
+ .start = max(start, p->start),
+ .end = min(end, p->end),
+ .flags = p->flags,
+ .desc = p->desc,
+ .parent = p->parent,
+ };
}
read_unlock(&resource_lock);
@@ -373,15 +397,14 @@
static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end,
unsigned long flags, unsigned long desc,
- bool first_level_children_only, void *arg,
+ bool first_lvl, void *arg,
int (*func)(struct resource *, void *))
{
struct resource res;
- int ret = -1;
+ int ret = -EINVAL;
while (start < end &&
- !find_next_iomem_res(start, end, flags, desc,
- first_level_children_only, &res)) {
+ !find_next_iomem_res(start, end, flags, desc, first_lvl, &res)) {
ret = (*func)(&res, arg);
if (ret)
break;
@@ -392,7 +415,7 @@
return ret;
}
-/*
+/**
* Walks through iomem resources and calls func() with matching resource
* ranges. This walks through whole tree and not just first level children.
* All the memory ranges which overlap start,end and also match flags and
@@ -402,6 +425,8 @@
* @flags: I/O resource flags
* @start: start addr
* @end: end addr
+ * @arg: function argument for the callback @func
+ * @func: callback function that is called for each qualifying resource area
*
* NOTE: For a new descriptor search, define a new IORES_DESC in
* <linux/ioport.h> and set it in 'desc' of a target resource entry.
@@ -421,11 +446,11 @@
* ranges.
*/
int walk_system_ram_res(u64 start, u64 end, void *arg,
- int (*func)(struct resource *, void *))
+ int (*func)(struct resource *, void *))
{
unsigned long flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
- return __walk_iomem_res_desc(start, end, flags, IORES_DESC_NONE, true,
+ return __walk_iomem_res_desc(start, end, flags, IORES_DESC_NONE, false,
arg, func);
}
@@ -438,34 +463,35 @@
{
unsigned long flags = IORESOURCE_MEM | IORESOURCE_BUSY;
- return __walk_iomem_res_desc(start, end, flags, IORES_DESC_NONE, true,
+ return __walk_iomem_res_desc(start, end, flags, IORES_DESC_NONE, false,
arg, func);
}
-
-#if !defined(CONFIG_ARCH_HAS_WALK_MEMORY)
/*
* This function calls the @func callback against all memory ranges of type
* System RAM which are marked as IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY.
* It is to be used only for System RAM.
+ *
+ * This will find System RAM ranges that are children of top-level resources
+ * in addition to top-level System RAM resources.
*/
int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
- void *arg, int (*func)(unsigned long, unsigned long, void *))
+ void *arg, int (*func)(unsigned long, unsigned long, void *))
{
resource_size_t start, end;
unsigned long flags;
struct resource res;
unsigned long pfn, end_pfn;
- int ret = -1;
+ int ret = -EINVAL;
start = (u64) start_pfn << PAGE_SHIFT;
end = ((u64)(start_pfn + nr_pages) << PAGE_SHIFT) - 1;
flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
while (start < end &&
!find_next_iomem_res(start, end, flags, IORES_DESC_NONE,
- true, &res)) {
- pfn = (res.start + PAGE_SIZE - 1) >> PAGE_SHIFT;
- end_pfn = (res.end + 1) >> PAGE_SHIFT;
+ false, &res)) {
+ pfn = PFN_UP(res.start);
+ end_pfn = PFN_DOWN(res.end + 1);
if (end_pfn > pfn)
ret = (*func)(pfn, end_pfn - pfn, arg);
if (ret)
@@ -474,8 +500,6 @@
}
return ret;
}
-
-#endif
static int __is_ram(unsigned long pfn, unsigned long nr_pages, void *arg)
{
@@ -515,9 +539,12 @@
int region_intersects(resource_size_t start, size_t size, unsigned long flags,
unsigned long desc)
{
- resource_size_t end = start + size - 1;
+ struct resource res;
int type = 0; int other = 0;
struct resource *p;
+
+ res.start = start;
+ res.end = start + size - 1;
read_lock(&resource_lock);
for (p = iomem_resource.child; p ; p = p->sibling) {
@@ -525,11 +552,7 @@
((desc == IORES_DESC_NONE) ||
(desc == p->desc)));
- if (start >= p->start && start <= p->end)
- is_type ? type++ : other++;
- if (end >= p->start && end <= p->end)
- is_type ? type++ : other++;
- if (p->start >= start && p->end <= end)
+ if (resource_overlaps(p, &res))
is_type ? type++ : other++;
}
read_unlock(&resource_lock);
@@ -646,8 +669,8 @@
* @constraint: the size and alignment constraints to be met.
*/
static int reallocate_resource(struct resource *root, struct resource *old,
- resource_size_t newsize,
- struct resource_constraint *constraint)
+ resource_size_t newsize,
+ struct resource_constraint *constraint)
{
int err=0;
struct resource new = *old;
@@ -960,7 +983,7 @@
* Existing children of the resource are assumed to be immutable.
*/
int adjust_resource(struct resource *res, resource_size_t start,
- resource_size_t size)
+ resource_size_t size)
{
int result;
@@ -971,9 +994,9 @@
}
EXPORT_SYMBOL(adjust_resource);
-static void __init __reserve_region_with_split(struct resource *root,
- resource_size_t start, resource_size_t end,
- const char *name)
+static void __init
+__reserve_region_with_split(struct resource *root, resource_size_t start,
+ resource_size_t end, const char *name)
{
struct resource *parent = root;
struct resource *conflict;
@@ -1032,9 +1055,9 @@
}
-void __init reserve_region_with_split(struct resource *root,
- resource_size_t start, resource_size_t end,
- const char *name)
+void __init
+reserve_region_with_split(struct resource *root, resource_size_t start,
+ resource_size_t end, const char *name)
{
int abort = 0;
@@ -1106,6 +1129,7 @@
{
DECLARE_WAITQUEUE(wait, current);
struct resource *res = alloc_resource(GFP_KERNEL);
+ struct resource *orig_parent = parent;
if (!res)
return NULL;
@@ -1126,6 +1150,15 @@
conflict = __request_resource(parent, res);
if (!conflict)
break;
+ /*
+ * 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);
+ }
if (conflict != parent) {
if (!(conflict->flags & IORESOURCE_BUSY)) {
parent = conflict;
@@ -1147,6 +1180,10 @@
break;
}
write_unlock(&resource_lock);
+
+ if (res && orig_parent == &iomem_resource)
+ revoke_devmem(res);
+
return res;
}
EXPORT_SYMBOL(__request_region);
@@ -1160,7 +1197,7 @@
* The described resource region must match a currently busy region.
*/
void __release_region(struct resource *parent, resource_size_t start,
- resource_size_t n)
+ resource_size_t n)
{
struct resource **p;
resource_size_t end;
@@ -1203,7 +1240,6 @@
#ifdef CONFIG_MEMORY_HOTREMOVE
/**
* release_mem_region_adjustable - release a previously reserved memory region
- * @parent: parent resource descriptor
* @start: resource start address
* @size: resource region size
*
@@ -1221,21 +1257,28 @@
* assumes that all children remain in the lower address entry for
* simplicity. Enhance this logic when necessary.
*/
-int release_mem_region_adjustable(struct resource *parent,
- resource_size_t start, resource_size_t size)
+void release_mem_region_adjustable(resource_size_t start, resource_size_t size)
{
+ struct resource *parent = &iomem_resource;
+ struct resource *new_res = NULL;
+ bool alloc_nofail = false;
struct resource **p;
struct resource *res;
- struct resource *new_res;
resource_size_t end;
- int ret = -EINVAL;
end = start + size - 1;
- if ((start < parent->start) || (end > parent->end))
- return ret;
+ if (WARN_ON_ONCE((start < parent->start) || (end > parent->end)))
+ return;
- /* The alloc_resource() result gets checked later */
- new_res = alloc_resource(GFP_KERNEL);
+ /*
+ * We free up quite a lot of memory on memory hotunplug (esp., memap),
+ * just before releasing the region. This is highly unlikely to
+ * fail - let's play save and make it never fail as the caller cannot
+ * perform any error handling (e.g., trying to re-add memory will fail
+ * similarly).
+ */
+retry:
+ new_res = alloc_resource(GFP_KERNEL | (alloc_nofail ? __GFP_NOFAIL : 0));
p = &parent->child;
write_lock(&resource_lock);
@@ -1248,6 +1291,20 @@
if (res->start > start || res->end < end) {
p = &res->sibling;
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))
@@ -1263,20 +1320,23 @@
/* free the whole entry */
*p = res->sibling;
free_resource(res);
- ret = 0;
} else if (res->start == start && res->end != end) {
/* adjust the start */
- ret = __adjust_resource(res, end + 1,
- res->end - end);
+ WARN_ON_ONCE(__adjust_resource(res, end + 1,
+ res->end - end));
} else if (res->start != start && res->end == end) {
/* adjust the end */
- ret = __adjust_resource(res, res->start,
- start - res->start);
+ WARN_ON_ONCE(__adjust_resource(res, res->start,
+ start - res->start));
} else {
- /* split into two entries */
+ /* split into two entries - we need a new resource */
if (!new_res) {
- ret = -ENOMEM;
- break;
+ new_res = alloc_resource(GFP_ATOMIC);
+ if (!new_res) {
+ alloc_nofail = true;
+ write_unlock(&resource_lock);
+ goto retry;
+ }
}
new_res->name = res->name;
new_res->start = end + 1;
@@ -1287,9 +1347,8 @@
new_res->sibling = res->sibling;
new_res->child = NULL;
- ret = __adjust_resource(res, res->start,
- start - res->start);
- if (ret)
+ if (WARN_ON_ONCE(__adjust_resource(res, res->start,
+ start - res->start)))
break;
res->sibling = new_res;
new_res = NULL;
@@ -1300,9 +1359,68 @@
write_unlock(&resource_lock);
free_resource(new_res);
- return ret;
}
#endif /* CONFIG_MEMORY_HOTREMOVE */
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+static bool system_ram_resources_mergeable(struct resource *r1,
+ struct resource *r2)
+{
+ /* We assume either r1 or r2 is IORESOURCE_SYSRAM_MERGEABLE. */
+ return r1->flags == r2->flags && r1->end + 1 == r2->start &&
+ r1->name == r2->name && r1->desc == r2->desc &&
+ !r1->child && !r2->child;
+}
+
+/*
+ * merge_system_ram_resource - mark the System RAM resource mergeable and try to
+ * merge it with adjacent, mergeable resources
+ * @res: resource descriptor
+ *
+ * This interface is intended for memory hotplug, whereby lots of contiguous
+ * system ram resources are added (e.g., via add_memory*()) by a driver, and
+ * the actual resource boundaries are not of interest (e.g., it might be
+ * relevant for DIMMs). Only resources that are marked mergeable, that have the
+ * same parent, and that don't have any children are considered. All mergeable
+ * resources must be immutable during the request.
+ *
+ * Note:
+ * - The caller has to make sure that no pointers to resources that are
+ * marked mergeable are used anymore after this call - the resource might
+ * be freed and the pointer might be stale!
+ * - release_mem_region_adjustable() will split on demand on memory hotunplug
+ */
+void merge_system_ram_resource(struct resource *res)
+{
+ const unsigned long flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+ struct resource *cur;
+
+ if (WARN_ON_ONCE((res->flags & flags) != flags))
+ return;
+
+ write_lock(&resource_lock);
+ res->flags |= IORESOURCE_SYSRAM_MERGEABLE;
+
+ /* Try to merge with next item in the list. */
+ cur = res->sibling;
+ if (cur && system_ram_resources_mergeable(res, cur)) {
+ res->end = cur->end;
+ res->sibling = cur->sibling;
+ free_resource(cur);
+ }
+
+ /* Try to merge with previous item in the list. */
+ cur = res->parent->child;
+ while (cur && cur->sibling != res)
+ cur = cur->sibling;
+ if (cur && system_ram_resources_mergeable(cur, res)) {
+ cur->end = res->end;
+ cur->sibling = res->sibling;
+ free_resource(res);
+ }
+ write_unlock(&resource_lock);
+}
+#endif /* CONFIG_MEMORY_HOTPLUG */
/*
* Managed region resource
@@ -1398,9 +1516,9 @@
this->start == match->start && this->n == match->n;
}
-struct resource * __devm_request_region(struct device *dev,
- struct resource *parent, resource_size_t start,
- resource_size_t n, const char *name)
+struct resource *
+__devm_request_region(struct device *dev, struct resource *parent,
+ resource_size_t start, resource_size_t n, const char *name)
{
struct region_devres *dr = NULL;
struct resource *res;
@@ -1599,6 +1717,62 @@
}
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)
+{
+ resource_size_t end, addr;
+ struct resource *res;
+
+ size = ALIGN(size, 1UL << PA_SECTION_SHIFT);
+ end = min_t(unsigned long, base->end, (1UL << MAX_PHYSMEM_BITS) - 1);
+ addr = end - size + 1UL;
+
+ for (; addr > size && addr >= base->start; addr -= size) {
+ 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);
+ res->desc = IORES_DESC_DEVICE_PRIVATE_MEMORY;
+ return res;
+ }
+
+ return ERR_PTR(-ERANGE);
+}
+
+/**
+ * devm_request_free_mem_region - find free region for device private memory
+ *
+ * @dev: device struct to bind the resource to
+ * @size: size in bytes of the device memory to add
+ * @base: resource tree to look in
+ *
+ * This function tries to find an empty range of physical address big enough to
+ * contain the new resource, so that it can later be hotplugged as ZONE_DEVICE
+ * memory, which in turn allocates struct pages.
+ */
+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));
+}
+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);
+}
+EXPORT_SYMBOL_GPL(request_free_mem_region);
+
+#endif /* CONFIG_DEVICE_PRIVATE */
+
static int __init strict_iomem(char *str)
{
if (strstr(str, "relaxed"))
--
Gitblit v1.6.2