linux-next/kernel/resource.c

1321 lines
31 KiB
C
Raw Normal View History

/*
* linux/kernel/resource.c
*
* Copyright (C) 1999 Linus Torvalds
* Copyright (C) 1999 Martin Mares <mj@ucw.cz>
*
* Arbitrary resource management.
*/
resource: make sure requested range is included in the root range When the requested range is outside of the root range the logic in __reserve_region_with_split will cause an infinite recursion which will overflow the stack as seen in the warning bellow. This particular stack overflow was caused by requesting the (100000000-107ffffff) range while the root range was (0-ffffffff). In this case __request_resource would return the whole root range as conflict range (i.e. 0-ffffffff). Then, the logic in __reserve_region_with_split would continue the recursion requesting the new range as (conflict->end+1, end) which incidentally in this case equals the originally requested range. This patch aborts looking for an usable range when the request does not intersect with the root range. When the request partially overlaps with the root range, it ajust the request to fall in the root range and then continues with the new request. When the request is modified or aborted errors and a stack trace are logged to allow catching the errors in the upper layers. [ 5.968374] WARNING: at kernel/sched.c:4129 sub_preempt_count+0x63/0x89() [ 5.975150] Modules linked in: [ 5.978184] Pid: 1, comm: swapper Not tainted 3.0.22-mid27-00004-gb72c817 #46 [ 5.985324] Call Trace: [ 5.987759] [<c1039dfc>] ? console_unlock+0x17b/0x18d [ 5.992891] [<c1039620>] warn_slowpath_common+0x48/0x5d [ 5.998194] [<c1031758>] ? sub_preempt_count+0x63/0x89 [ 6.003412] [<c1039644>] warn_slowpath_null+0xf/0x13 [ 6.008453] [<c1031758>] sub_preempt_count+0x63/0x89 [ 6.013499] [<c14d60c4>] _raw_spin_unlock+0x27/0x3f [ 6.018453] [<c10c6349>] add_partial+0x36/0x3b [ 6.022973] [<c10c7c0a>] deactivate_slab+0x96/0xb4 [ 6.027842] [<c14cf9d9>] __slab_alloc.isra.54.constprop.63+0x204/0x241 [ 6.034456] [<c103f78f>] ? kzalloc.constprop.5+0x29/0x38 [ 6.039842] [<c103f78f>] ? kzalloc.constprop.5+0x29/0x38 [ 6.045232] [<c10c7dc9>] kmem_cache_alloc_trace+0x51/0xb0 [ 6.050710] [<c103f78f>] ? kzalloc.constprop.5+0x29/0x38 [ 6.056100] [<c103f78f>] kzalloc.constprop.5+0x29/0x38 [ 6.061320] [<c17b45e9>] __reserve_region_with_split+0x1c/0xd1 [ 6.067230] [<c17b4693>] __reserve_region_with_split+0xc6/0xd1 ... [ 7.179057] [<c17b4693>] __reserve_region_with_split+0xc6/0xd1 [ 7.184970] [<c17b4779>] reserve_region_with_split+0x30/0x42 [ 7.190709] [<c17a8ebf>] e820_reserve_resources_late+0xd1/0xe9 [ 7.196623] [<c17c9526>] pcibios_resource_survey+0x23/0x2a [ 7.202184] [<c17cad8a>] pcibios_init+0x23/0x35 [ 7.206789] [<c17ca574>] pci_subsys_init+0x3f/0x44 [ 7.211659] [<c1002088>] do_one_initcall+0x72/0x122 [ 7.216615] [<c17ca535>] ? pci_legacy_init+0x3d/0x3d [ 7.221659] [<c17a27ff>] kernel_init+0xa6/0x118 [ 7.226265] [<c17a2759>] ? start_kernel+0x334/0x334 [ 7.231223] [<c14d7482>] kernel_thread_helper+0x6/0x10 Signed-off-by: Octavian Purdila <octavian.purdila@intel.com> Signed-off-by: Ram Pai <linuxram@us.ibm.com> Cc: Jesse Barnes <jbarnes@virtuousgeek.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-30 21:42:58 +00:00
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/export.h>
#include <linux/errno.h>
#include <linux/ioport.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/fs.h>
#include <linux/proc_fs.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/device.h>
#include <linux/pfn.h>
#include <asm/io.h>
struct resource ioport_resource = {
.name = "PCI IO",
.start = 0,
.end = IO_SPACE_LIMIT,
.flags = IORESOURCE_IO,
};
EXPORT_SYMBOL(ioport_resource);
struct resource iomem_resource = {
.name = "PCI mem",
.start = 0,
.end = -1,
.flags = IORESOURCE_MEM,
};
EXPORT_SYMBOL(iomem_resource);
/* constraints to be met while allocating resources */
struct resource_constraint {
resource_size_t min, max, align;
resource_size_t (*alignf)(void *, const struct resource *,
resource_size_t, resource_size_t);
void *alignf_data;
};
static DEFINE_RWLOCK(resource_lock);
static void *r_next(struct seq_file *m, void *v, loff_t *pos)
{
struct resource *p = v;
(*pos)++;
if (p->child)
return p->child;
while (!p->sibling && p->parent)
p = p->parent;
return p->sibling;
}
#ifdef CONFIG_PROC_FS
enum { MAX_IORES_LEVEL = 5 };
static void *r_start(struct seq_file *m, loff_t *pos)
__acquires(resource_lock)
{
struct resource *p = m->private;
loff_t l = 0;
read_lock(&resource_lock);
for (p = p->child; p && l < *pos; p = r_next(m, p, &l))
;
return p;
}
static void r_stop(struct seq_file *m, void *v)
__releases(resource_lock)
{
read_unlock(&resource_lock);
}
static int r_show(struct seq_file *m, void *v)
{
struct resource *root = m->private;
struct resource *r = v, *p;
int width = root->end < 0x10000 ? 4 : 8;
int depth;
for (depth = 0, p = r; depth < MAX_IORES_LEVEL; depth++, p = p->parent)
if (p->parent == root)
break;
seq_printf(m, "%*s%0*llx-%0*llx : %s\n",
depth * 2, "",
width, (unsigned long long) r->start,
width, (unsigned long long) r->end,
r->name ? r->name : "<BAD>");
return 0;
}
static const struct seq_operations resource_op = {
.start = r_start,
.next = r_next,
.stop = r_stop,
.show = r_show,
};
static int ioports_open(struct inode *inode, struct file *file)
{
int res = seq_open(file, &resource_op);
if (!res) {
struct seq_file *m = file->private_data;
m->private = &ioport_resource;
}
return res;
}
static int iomem_open(struct inode *inode, struct file *file)
{
int res = seq_open(file, &resource_op);
if (!res) {
struct seq_file *m = file->private_data;
m->private = &iomem_resource;
}
return res;
}
static const struct file_operations proc_ioports_operations = {
.open = ioports_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
static const struct file_operations proc_iomem_operations = {
.open = iomem_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
static int __init ioresources_init(void)
{
proc_create("ioports", 0, NULL, &proc_ioports_operations);
proc_create("iomem", 0, NULL, &proc_iomem_operations);
return 0;
}
__initcall(ioresources_init);
#endif /* CONFIG_PROC_FS */
/* Return the conflict entry if you can't request it */
static struct resource * __request_resource(struct resource *root, struct resource *new)
{
resource_size_t start = new->start;
resource_size_t end = new->end;
struct resource *tmp, **p;
if (end < start)
return root;
if (start < root->start)
return root;
if (end > root->end)
return root;
p = &root->child;
for (;;) {
tmp = *p;
if (!tmp || tmp->start > end) {
new->sibling = tmp;
*p = new;
new->parent = root;
return NULL;
}
p = &tmp->sibling;
if (tmp->end < start)
continue;
return tmp;
}
}
static int __release_resource(struct resource *old)
{
struct resource *tmp, **p;
p = &old->parent->child;
for (;;) {
tmp = *p;
if (!tmp)
break;
if (tmp == old) {
*p = tmp->sibling;
old->parent = NULL;
return 0;
}
p = &tmp->sibling;
}
return -EINVAL;
}
static void __release_child_resources(struct resource *r)
{
struct resource *tmp, *p;
resource_size_t size;
p = r->child;
r->child = NULL;
while (p) {
tmp = p;
p = p->sibling;
tmp->parent = NULL;
tmp->sibling = NULL;
__release_child_resources(tmp);
printk(KERN_DEBUG "release child resource %pR\n", tmp);
/* need to restore size, and keep flags */
size = resource_size(tmp);
tmp->start = 0;
tmp->end = size - 1;
}
}
void release_child_resources(struct resource *r)
{
write_lock(&resource_lock);
__release_child_resources(r);
write_unlock(&resource_lock);
}
/**
* request_resource_conflict - request and reserve an I/O or memory resource
* @root: root resource descriptor
* @new: resource descriptor desired by caller
*
* Returns 0 for success, conflict resource on error.
*/
struct resource *request_resource_conflict(struct resource *root, struct resource *new)
{
struct resource *conflict;
write_lock(&resource_lock);
conflict = __request_resource(root, new);
write_unlock(&resource_lock);
return conflict;
}
/**
* request_resource - request and reserve an I/O or memory resource
* @root: root resource descriptor
* @new: resource descriptor desired by caller
*
* Returns 0 for success, negative error code on error.
*/
int request_resource(struct resource *root, struct resource *new)
{
struct resource *conflict;
conflict = request_resource_conflict(root, new);
return conflict ? -EBUSY : 0;
}
EXPORT_SYMBOL(request_resource);
/**
* release_resource - release a previously reserved resource
* @old: resource pointer
*/
int release_resource(struct resource *old)
{
int retval;
write_lock(&resource_lock);
retval = __release_resource(old);
write_unlock(&resource_lock);
return retval;
}
EXPORT_SYMBOL(release_resource);
#if !defined(CONFIG_ARCH_HAS_WALK_MEMORY)
/*
* Finds the lowest memory reosurce exists within [res->start.res->end)
* the caller must specify res->start, res->end, res->flags and "name".
* If found, returns 0, res is overwritten, if not found, returns -1.
*/
static int find_next_system_ram(struct resource *res, char *name)
{
resource_size_t start, end;
struct resource *p;
BUG_ON(!res);
start = res->start;
end = res->end;
BUG_ON(start >= end);
read_lock(&resource_lock);
for (p = iomem_resource.child; p ; p = p->sibling) {
/* system ram is just marked as IORESOURCE_MEM */
if (p->flags != res->flags)
continue;
if (name && strcmp(p->name, name))
continue;
if (p->start > end) {
p = NULL;
break;
}
if ((p->end >= start) && (p->start < end))
break;
}
read_unlock(&resource_lock);
if (!p)
return -1;
/* copy data */
if (res->start < p->start)
res->start = p->start;
if (res->end > p->end)
res->end = p->end;
return 0;
}
/*
* This function calls callback against all memory range of "System RAM"
* which are marked as IORESOURCE_MEM and IORESOUCE_BUSY.
* Now, this function is only for "System RAM".
*/
int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
void *arg, int (*func)(unsigned long, unsigned long, void *))
{
struct resource res;
resource: Fix generic page_is_ram() for partial RAM pages The System RAM walk shall skip partial RAM pages and avoid calling func() on them. So that page_is_ram() return 0 for a partial RAM page. In particular, it shall not call func() with len=0. This fixes a boot time bug reported by Sachin and root caused by Thomas: > >>> WARNING: at arch/x86/mm/ioremap.c:111 __ioremap_caller+0x169/0x2f1() > >>> Hardware name: BladeCenter LS21 -[79716AA]- > >>> Modules linked in: > >>> Pid: 0, comm: swapper Not tainted 2.6.33-git6-autotest #1 > >>> Call Trace: > >>> [<ffffffff81047cff>] ? __ioremap_caller+0x169/0x2f1 > >>> [<ffffffff81063b7d>] warn_slowpath_common+0x77/0xa4 > >>> [<ffffffff81063bb9>] warn_slowpath_null+0xf/0x11 > >>> [<ffffffff81047cff>] __ioremap_caller+0x169/0x2f1 > >>> [<ffffffff813747a3>] ? acpi_os_map_memory+0x12/0x1b > >>> [<ffffffff81047f10>] ioremap_nocache+0x12/0x14 > >>> [<ffffffff813747a3>] acpi_os_map_memory+0x12/0x1b > >>> [<ffffffff81282fa0>] acpi_tb_verify_table+0x29/0x5b > >>> [<ffffffff812827f0>] acpi_load_tables+0x39/0x15a > >>> [<ffffffff8191c8f8>] acpi_early_init+0x60/0xf5 > >>> [<ffffffff818f2cad>] start_kernel+0x397/0x3a7 > >>> [<ffffffff818f2295>] x86_64_start_reservations+0xa5/0xa9 > >>> [<ffffffff818f237a>] x86_64_start_kernel+0xe1/0xe8 > >>> ---[ end trace 4eaa2a86a8e2da22 ]--- > >>> ioremap reserve_memtype failed -22 The return code is -EINVAL, so it failed in the is_ram check, which is not too surprising > BIOS-provided physical RAM map: > BIOS-e820: 0000000000000000 - 000000000009c000 (usable) > BIOS-e820: 000000000009c000 - 00000000000a0000 (reserved) > BIOS-e820: 00000000000e0000 - 0000000000100000 (reserved) > BIOS-e820: 0000000000100000 - 00000000cffa3900 (usable) > BIOS-e820: 00000000cffa3900 - 00000000cffa7400 (ACPI data) The ACPI data is not starting on a page boundary and neither does the usable RAM area end on a page boundary. Very useful ! > ACPI: DSDT 00000000cffa3900 036CE (v01 IBM SERLEWIS 00001000 INTL 20060912) ACPI is trying to map DSDT at cffa3900, which results in a check vs. cffa3000 which is the relevant page boundary. The generic is_ram check correctly identifies that as RAM because it's in the usable resource area. The old e820 based is_ram check does not take overlapping resource areas into account. That's why it works. CC: Sachin Sant <sachinp@in.ibm.com> CC: Thomas Gleixner <tglx@linutronix.de> CC: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> LKML-Reference: <20100301135551.GA9998@localhost> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-03-01 13:55:51 +00:00
unsigned long pfn, end_pfn;
u64 orig_end;
int ret = -1;
res.start = (u64) start_pfn << PAGE_SHIFT;
res.end = ((u64)(start_pfn + nr_pages) << PAGE_SHIFT) - 1;
res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
orig_end = res.end;
while ((res.start < res.end) &&
(find_next_system_ram(&res, "System RAM") >= 0)) {
resource: Fix generic page_is_ram() for partial RAM pages The System RAM walk shall skip partial RAM pages and avoid calling func() on them. So that page_is_ram() return 0 for a partial RAM page. In particular, it shall not call func() with len=0. This fixes a boot time bug reported by Sachin and root caused by Thomas: > >>> WARNING: at arch/x86/mm/ioremap.c:111 __ioremap_caller+0x169/0x2f1() > >>> Hardware name: BladeCenter LS21 -[79716AA]- > >>> Modules linked in: > >>> Pid: 0, comm: swapper Not tainted 2.6.33-git6-autotest #1 > >>> Call Trace: > >>> [<ffffffff81047cff>] ? __ioremap_caller+0x169/0x2f1 > >>> [<ffffffff81063b7d>] warn_slowpath_common+0x77/0xa4 > >>> [<ffffffff81063bb9>] warn_slowpath_null+0xf/0x11 > >>> [<ffffffff81047cff>] __ioremap_caller+0x169/0x2f1 > >>> [<ffffffff813747a3>] ? acpi_os_map_memory+0x12/0x1b > >>> [<ffffffff81047f10>] ioremap_nocache+0x12/0x14 > >>> [<ffffffff813747a3>] acpi_os_map_memory+0x12/0x1b > >>> [<ffffffff81282fa0>] acpi_tb_verify_table+0x29/0x5b > >>> [<ffffffff812827f0>] acpi_load_tables+0x39/0x15a > >>> [<ffffffff8191c8f8>] acpi_early_init+0x60/0xf5 > >>> [<ffffffff818f2cad>] start_kernel+0x397/0x3a7 > >>> [<ffffffff818f2295>] x86_64_start_reservations+0xa5/0xa9 > >>> [<ffffffff818f237a>] x86_64_start_kernel+0xe1/0xe8 > >>> ---[ end trace 4eaa2a86a8e2da22 ]--- > >>> ioremap reserve_memtype failed -22 The return code is -EINVAL, so it failed in the is_ram check, which is not too surprising > BIOS-provided physical RAM map: > BIOS-e820: 0000000000000000 - 000000000009c000 (usable) > BIOS-e820: 000000000009c000 - 00000000000a0000 (reserved) > BIOS-e820: 00000000000e0000 - 0000000000100000 (reserved) > BIOS-e820: 0000000000100000 - 00000000cffa3900 (usable) > BIOS-e820: 00000000cffa3900 - 00000000cffa7400 (ACPI data) The ACPI data is not starting on a page boundary and neither does the usable RAM area end on a page boundary. Very useful ! > ACPI: DSDT 00000000cffa3900 036CE (v01 IBM SERLEWIS 00001000 INTL 20060912) ACPI is trying to map DSDT at cffa3900, which results in a check vs. cffa3000 which is the relevant page boundary. The generic is_ram check correctly identifies that as RAM because it's in the usable resource area. The old e820 based is_ram check does not take overlapping resource areas into account. That's why it works. CC: Sachin Sant <sachinp@in.ibm.com> CC: Thomas Gleixner <tglx@linutronix.de> CC: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> LKML-Reference: <20100301135551.GA9998@localhost> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-03-01 13:55:51 +00:00
pfn = (res.start + PAGE_SIZE - 1) >> PAGE_SHIFT;
end_pfn = (res.end + 1) >> PAGE_SHIFT;
if (end_pfn > pfn)
ret = (*func)(pfn, end_pfn - pfn, arg);
if (ret)
break;
res.start = res.end + 1;
res.end = orig_end;
}
return ret;
}
#endif
static int __is_ram(unsigned long pfn, unsigned long nr_pages, void *arg)
{
return 1;
}
/*
* This generic page_is_ram() returns true if specified address is
* registered as "System RAM" in iomem_resource list.
*/
int __weak page_is_ram(unsigned long pfn)
{
return walk_system_ram_range(pfn, 1, NULL, __is_ram) == 1;
}
void __weak arch_remove_reservations(struct resource *avail)
{
}
static resource_size_t simple_align_resource(void *data,
const struct resource *avail,
resource_size_t size,
resource_size_t align)
{
return avail->start;
}
static void resource_clip(struct resource *res, resource_size_t min,
resource_size_t max)
{
if (res->start < min)
res->start = min;
if (res->end > max)
res->end = max;
}
static bool resource_contains(struct resource *res1, struct resource *res2)
{
return res1->start <= res2->start && res1->end >= res2->end;
}
/*
* Find empty slot in the resource tree with the given range and
* alignment constraints
*/
static int __find_resource(struct resource *root, struct resource *old,
struct resource *new,
resource_size_t size,
struct resource_constraint *constraint)
{
struct resource *this = root->child;
struct resource tmp = *new, avail, alloc;
tmp.flags = new->flags;
tmp.start = root->start;
/*
* Skip past an allocated resource that starts at 0, since the assignment
* of this->start - 1 to tmp->end below would cause an underflow.
*/
if (this && this->start == root->start) {
tmp.start = (this == old) ? old->start : this->end + 1;
this = this->sibling;
}
for(;;) {
if (this)
tmp.end = (this == old) ? this->end : this->start - 1;
else
tmp.end = root->end;
if (tmp.end < tmp.start)
goto next;
resource_clip(&tmp, constraint->min, constraint->max);
arch_remove_reservations(&tmp);
/* Check for overflow after ALIGN() */
avail = *new;
avail.start = ALIGN(tmp.start, constraint->align);
avail.end = tmp.end;
if (avail.start >= tmp.start) {
alloc.start = constraint->alignf(constraint->alignf_data, &avail,
size, constraint->align);
alloc.end = alloc.start + size - 1;
if (resource_contains(&avail, &alloc)) {
new->start = alloc.start;
new->end = alloc.end;
return 0;
}
}
next: if (!this || this->end == root->end)
break;
if (this != old)
tmp.start = this->end + 1;
this = this->sibling;
}
return -EBUSY;
}
/*
* Find empty slot in the resource tree given range and alignment.
*/
static int find_resource(struct resource *root, struct resource *new,
resource_size_t size,
struct resource_constraint *constraint)
{
return __find_resource(root, NULL, new, size, constraint);
}
/**
* reallocate_resource - allocate a slot in the resource tree given range & alignment.
* The resource will be relocated if the new size cannot be reallocated in the
* current location.
*
* @root: root resource descriptor
* @old: resource descriptor desired by caller
* @newsize: new size of the resource descriptor
* @constraint: the size and alignment constraints to be met.
*/
int reallocate_resource(struct resource *root, struct resource *old,
resource_size_t newsize,
struct resource_constraint *constraint)
{
int err=0;
struct resource new = *old;
struct resource *conflict;
write_lock(&resource_lock);
if ((err = __find_resource(root, old, &new, newsize, constraint)))
goto out;
if (resource_contains(&new, old)) {
old->start = new.start;
old->end = new.end;
goto out;
}
if (old->child) {
err = -EBUSY;
goto out;
}
if (resource_contains(old, &new)) {
old->start = new.start;
old->end = new.end;
} else {
__release_resource(old);
*old = new;
conflict = __request_resource(root, old);
BUG_ON(conflict);
}
out:
write_unlock(&resource_lock);
return err;
}
/**
* allocate_resource - allocate empty slot in the resource tree given range & alignment.
* The resource will be reallocated with a new size if it was already allocated
* @root: root resource descriptor
* @new: resource descriptor desired by caller
* @size: requested resource region size
* @min: minimum boundary to allocate
* @max: maximum boundary to allocate
* @align: alignment requested, in bytes
* @alignf: alignment function, optional, called if not NULL
* @alignf_data: arbitrary data to pass to the @alignf function
*/
int allocate_resource(struct resource *root, struct resource *new,
resource_size_t size, resource_size_t min,
resource_size_t max, resource_size_t align,
resource_size_t (*alignf)(void *,
const struct resource *,
resource_size_t,
resource_size_t),
void *alignf_data)
{
int err;
struct resource_constraint constraint;
if (!alignf)
alignf = simple_align_resource;
constraint.min = min;
constraint.max = max;
constraint.align = align;
constraint.alignf = alignf;
constraint.alignf_data = alignf_data;
if ( new->parent ) {
/* resource is already allocated, try reallocating with
the new constraints */
return reallocate_resource(root, new, size, &constraint);
}
write_lock(&resource_lock);
err = find_resource(root, new, size, &constraint);
if (err >= 0 && __request_resource(root, new))
err = -EBUSY;
write_unlock(&resource_lock);
return err;
}
EXPORT_SYMBOL(allocate_resource);
/**
* lookup_resource - find an existing resource by a resource start address
* @root: root resource descriptor
* @start: resource start address
*
* Returns a pointer to the resource if found, NULL otherwise
*/
struct resource *lookup_resource(struct resource *root, resource_size_t start)
{
struct resource *res;
read_lock(&resource_lock);
for (res = root->child; res; res = res->sibling) {
if (res->start == start)
break;
}
read_unlock(&resource_lock);
return res;
}
/*
* Insert a resource into the resource tree. If successful, return NULL,
* otherwise return the conflicting resource (compare to __request_resource())
*/
static struct resource * __insert_resource(struct resource *parent, struct resource *new)
{
struct resource *first, *next;
for (;; parent = first) {
first = __request_resource(parent, new);
if (!first)
return first;
if (first == parent)
return first;
if (WARN_ON(first == new)) /* duplicated insertion */
return first;
if ((first->start > new->start) || (first->end < new->end))
break;
if ((first->start == new->start) && (first->end == new->end))
break;
}
for (next = first; ; next = next->sibling) {
/* Partial overlap? Bad, and unfixable */
if (next->start < new->start || next->end > new->end)
return next;
if (!next->sibling)
break;
if (next->sibling->start > new->end)
break;
}
new->parent = parent;
new->sibling = next->sibling;
new->child = first;
next->sibling = NULL;
for (next = first; next; next = next->sibling)
next->parent = new;
if (parent->child == first) {
parent->child = new;
} else {
next = parent->child;
while (next->sibling != first)
next = next->sibling;
next->sibling = new;
}
return NULL;
}
/**
* insert_resource_conflict - Inserts resource in the resource tree
* @parent: parent of the new resource
* @new: new resource to insert
*
* Returns 0 on success, conflict resource if the resource can't be inserted.
*
* This function is equivalent to request_resource_conflict when no conflict
* happens. If a conflict happens, and the conflicting resources
* entirely fit within the range of the new resource, then the new
* resource is inserted and the conflicting resources become children of
* the new resource.
*/
struct resource *insert_resource_conflict(struct resource *parent, struct resource *new)
{
struct resource *conflict;
write_lock(&resource_lock);
conflict = __insert_resource(parent, new);
write_unlock(&resource_lock);
return conflict;
}
/**
* insert_resource - Inserts a resource in the resource tree
* @parent: parent of the new resource
* @new: new resource to insert
*
* Returns 0 on success, -EBUSY if the resource can't be inserted.
*/
int insert_resource(struct resource *parent, struct resource *new)
{
struct resource *conflict;
conflict = insert_resource_conflict(parent, new);
return conflict ? -EBUSY : 0;
}
/**
* insert_resource_expand_to_fit - Insert a resource into the resource tree
* @root: root resource descriptor
* @new: new resource to insert
*
* Insert a resource into the resource tree, possibly expanding it in order
* to make it encompass any conflicting resources.
*/
void insert_resource_expand_to_fit(struct resource *root, struct resource *new)
{
if (new->parent)
return;
write_lock(&resource_lock);
for (;;) {
struct resource *conflict;
conflict = __insert_resource(root, new);
if (!conflict)
break;
if (conflict == root)
break;
/* Ok, expand resource to cover the conflict, then try again .. */
if (conflict->start < new->start)
new->start = conflict->start;
if (conflict->end > new->end)
new->end = conflict->end;
printk("Expanded resource %s due to conflict with %s\n", new->name, conflict->name);
}
write_unlock(&resource_lock);
}
static int __adjust_resource(struct resource *res, resource_size_t start,
resource_size_t size)
{
struct resource *tmp, *parent = res->parent;
resource_size_t end = start + size - 1;
int result = -EBUSY;
if (!parent)
goto skip;
if ((start < parent->start) || (end > parent->end))
goto out;
if (res->sibling && (res->sibling->start <= end))
goto out;
tmp = parent->child;
if (tmp != res) {
while (tmp->sibling != res)
tmp = tmp->sibling;
if (start <= tmp->end)
goto out;
}
skip:
for (tmp = res->child; tmp; tmp = tmp->sibling)
if ((tmp->start < start) || (tmp->end > end))
goto out;
res->start = start;
res->end = end;
result = 0;
out:
return result;
}
/**
* adjust_resource - modify a resource's start and size
* @res: resource to modify
* @start: new start value
* @size: new size
*
* Given an existing resource, change its start and size to match the
* arguments. Returns 0 on success, -EBUSY if it can't fit.
* Existing children of the resource are assumed to be immutable.
*/
int adjust_resource(struct resource *res, resource_size_t start,
resource_size_t size)
{
int result;
write_lock(&resource_lock);
result = __adjust_resource(res, start, size);
write_unlock(&resource_lock);
return result;
}
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)
{
struct resource *parent = root;
struct resource *conflict;
struct resource *res = kzalloc(sizeof(*res), GFP_ATOMIC);
struct resource *next_res = NULL;
if (!res)
return;
res->name = name;
res->start = start;
res->end = end;
res->flags = IORESOURCE_BUSY;
while (1) {
conflict = __request_resource(parent, res);
if (!conflict) {
if (!next_res)
break;
res = next_res;
next_res = NULL;
continue;
}
/* conflict covered whole area */
if (conflict->start <= res->start &&
conflict->end >= res->end) {
kfree(res);
WARN_ON(next_res);
break;
}
/* failed, split and try again */
if (conflict->start > res->start) {
end = res->end;
res->end = conflict->start - 1;
if (conflict->end < end) {
next_res = kzalloc(sizeof(*next_res),
GFP_ATOMIC);
if (!next_res) {
kfree(res);
break;
}
next_res->name = name;
next_res->start = conflict->end + 1;
next_res->end = end;
next_res->flags = IORESOURCE_BUSY;
}
} else {
res->start = conflict->end + 1;
}
}
}
void __init reserve_region_with_split(struct resource *root,
resource_size_t start, resource_size_t end,
const char *name)
{
resource: make sure requested range is included in the root range When the requested range is outside of the root range the logic in __reserve_region_with_split will cause an infinite recursion which will overflow the stack as seen in the warning bellow. This particular stack overflow was caused by requesting the (100000000-107ffffff) range while the root range was (0-ffffffff). In this case __request_resource would return the whole root range as conflict range (i.e. 0-ffffffff). Then, the logic in __reserve_region_with_split would continue the recursion requesting the new range as (conflict->end+1, end) which incidentally in this case equals the originally requested range. This patch aborts looking for an usable range when the request does not intersect with the root range. When the request partially overlaps with the root range, it ajust the request to fall in the root range and then continues with the new request. When the request is modified or aborted errors and a stack trace are logged to allow catching the errors in the upper layers. [ 5.968374] WARNING: at kernel/sched.c:4129 sub_preempt_count+0x63/0x89() [ 5.975150] Modules linked in: [ 5.978184] Pid: 1, comm: swapper Not tainted 3.0.22-mid27-00004-gb72c817 #46 [ 5.985324] Call Trace: [ 5.987759] [<c1039dfc>] ? console_unlock+0x17b/0x18d [ 5.992891] [<c1039620>] warn_slowpath_common+0x48/0x5d [ 5.998194] [<c1031758>] ? sub_preempt_count+0x63/0x89 [ 6.003412] [<c1039644>] warn_slowpath_null+0xf/0x13 [ 6.008453] [<c1031758>] sub_preempt_count+0x63/0x89 [ 6.013499] [<c14d60c4>] _raw_spin_unlock+0x27/0x3f [ 6.018453] [<c10c6349>] add_partial+0x36/0x3b [ 6.022973] [<c10c7c0a>] deactivate_slab+0x96/0xb4 [ 6.027842] [<c14cf9d9>] __slab_alloc.isra.54.constprop.63+0x204/0x241 [ 6.034456] [<c103f78f>] ? kzalloc.constprop.5+0x29/0x38 [ 6.039842] [<c103f78f>] ? kzalloc.constprop.5+0x29/0x38 [ 6.045232] [<c10c7dc9>] kmem_cache_alloc_trace+0x51/0xb0 [ 6.050710] [<c103f78f>] ? kzalloc.constprop.5+0x29/0x38 [ 6.056100] [<c103f78f>] kzalloc.constprop.5+0x29/0x38 [ 6.061320] [<c17b45e9>] __reserve_region_with_split+0x1c/0xd1 [ 6.067230] [<c17b4693>] __reserve_region_with_split+0xc6/0xd1 ... [ 7.179057] [<c17b4693>] __reserve_region_with_split+0xc6/0xd1 [ 7.184970] [<c17b4779>] reserve_region_with_split+0x30/0x42 [ 7.190709] [<c17a8ebf>] e820_reserve_resources_late+0xd1/0xe9 [ 7.196623] [<c17c9526>] pcibios_resource_survey+0x23/0x2a [ 7.202184] [<c17cad8a>] pcibios_init+0x23/0x35 [ 7.206789] [<c17ca574>] pci_subsys_init+0x3f/0x44 [ 7.211659] [<c1002088>] do_one_initcall+0x72/0x122 [ 7.216615] [<c17ca535>] ? pci_legacy_init+0x3d/0x3d [ 7.221659] [<c17a27ff>] kernel_init+0xa6/0x118 [ 7.226265] [<c17a2759>] ? start_kernel+0x334/0x334 [ 7.231223] [<c14d7482>] kernel_thread_helper+0x6/0x10 Signed-off-by: Octavian Purdila <octavian.purdila@intel.com> Signed-off-by: Ram Pai <linuxram@us.ibm.com> Cc: Jesse Barnes <jbarnes@virtuousgeek.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-30 21:42:58 +00:00
int abort = 0;
write_lock(&resource_lock);
resource: make sure requested range is included in the root range When the requested range is outside of the root range the logic in __reserve_region_with_split will cause an infinite recursion which will overflow the stack as seen in the warning bellow. This particular stack overflow was caused by requesting the (100000000-107ffffff) range while the root range was (0-ffffffff). In this case __request_resource would return the whole root range as conflict range (i.e. 0-ffffffff). Then, the logic in __reserve_region_with_split would continue the recursion requesting the new range as (conflict->end+1, end) which incidentally in this case equals the originally requested range. This patch aborts looking for an usable range when the request does not intersect with the root range. When the request partially overlaps with the root range, it ajust the request to fall in the root range and then continues with the new request. When the request is modified or aborted errors and a stack trace are logged to allow catching the errors in the upper layers. [ 5.968374] WARNING: at kernel/sched.c:4129 sub_preempt_count+0x63/0x89() [ 5.975150] Modules linked in: [ 5.978184] Pid: 1, comm: swapper Not tainted 3.0.22-mid27-00004-gb72c817 #46 [ 5.985324] Call Trace: [ 5.987759] [<c1039dfc>] ? console_unlock+0x17b/0x18d [ 5.992891] [<c1039620>] warn_slowpath_common+0x48/0x5d [ 5.998194] [<c1031758>] ? sub_preempt_count+0x63/0x89 [ 6.003412] [<c1039644>] warn_slowpath_null+0xf/0x13 [ 6.008453] [<c1031758>] sub_preempt_count+0x63/0x89 [ 6.013499] [<c14d60c4>] _raw_spin_unlock+0x27/0x3f [ 6.018453] [<c10c6349>] add_partial+0x36/0x3b [ 6.022973] [<c10c7c0a>] deactivate_slab+0x96/0xb4 [ 6.027842] [<c14cf9d9>] __slab_alloc.isra.54.constprop.63+0x204/0x241 [ 6.034456] [<c103f78f>] ? kzalloc.constprop.5+0x29/0x38 [ 6.039842] [<c103f78f>] ? kzalloc.constprop.5+0x29/0x38 [ 6.045232] [<c10c7dc9>] kmem_cache_alloc_trace+0x51/0xb0 [ 6.050710] [<c103f78f>] ? kzalloc.constprop.5+0x29/0x38 [ 6.056100] [<c103f78f>] kzalloc.constprop.5+0x29/0x38 [ 6.061320] [<c17b45e9>] __reserve_region_with_split+0x1c/0xd1 [ 6.067230] [<c17b4693>] __reserve_region_with_split+0xc6/0xd1 ... [ 7.179057] [<c17b4693>] __reserve_region_with_split+0xc6/0xd1 [ 7.184970] [<c17b4779>] reserve_region_with_split+0x30/0x42 [ 7.190709] [<c17a8ebf>] e820_reserve_resources_late+0xd1/0xe9 [ 7.196623] [<c17c9526>] pcibios_resource_survey+0x23/0x2a [ 7.202184] [<c17cad8a>] pcibios_init+0x23/0x35 [ 7.206789] [<c17ca574>] pci_subsys_init+0x3f/0x44 [ 7.211659] [<c1002088>] do_one_initcall+0x72/0x122 [ 7.216615] [<c17ca535>] ? pci_legacy_init+0x3d/0x3d [ 7.221659] [<c17a27ff>] kernel_init+0xa6/0x118 [ 7.226265] [<c17a2759>] ? start_kernel+0x334/0x334 [ 7.231223] [<c14d7482>] kernel_thread_helper+0x6/0x10 Signed-off-by: Octavian Purdila <octavian.purdila@intel.com> Signed-off-by: Ram Pai <linuxram@us.ibm.com> Cc: Jesse Barnes <jbarnes@virtuousgeek.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-30 21:42:58 +00:00
if (root->start > start || root->end < end) {
pr_err("requested range [0x%llx-0x%llx] not in root %pr\n",
(unsigned long long)start, (unsigned long long)end,
root);
if (start > root->end || end < root->start)
abort = 1;
else {
if (end > root->end)
end = root->end;
if (start < root->start)
start = root->start;
pr_err("fixing request to [0x%llx-0x%llx]\n",
(unsigned long long)start,
(unsigned long long)end);
}
dump_stack();
}
if (!abort)
__reserve_region_with_split(root, start, end, name);
write_unlock(&resource_lock);
}
PCI: clean up resource alignment management Done per Linus' request and suggestions. Linus has explained that better than I'll be able to explain: On Thu, Mar 27, 2008 at 10:12:10AM -0700, Linus Torvalds wrote: > Actually, before we go any further, there might be a less intrusive > alternative: add just a couple of flags to the resource flags field (we > still have something like 8 unused bits on 32-bit), and use those to > implement a generic "resource_alignment()" routine. > > Two flags would do it: > > - IORESOURCE_SIZEALIGN: size indicates alignment (regular PCI device > resources) > > - IORESOURCE_STARTALIGN: start field is alignment (PCI bus resources > during probing) > > and then the case of both flags zero (or both bits set) would actually be > "invalid", and we would also clear the IORESOURCE_STARTALIGN flag when we > actually allocate the resource (so that we don't use the "start" field as > alignment incorrectly when it no longer indicates alignment). > > That wouldn't be totally generic, but it would have the nice property of > automatically at least add sanity checking for that whole "res->start has > the odd meaning of 'alignment' during probing" and remove the need for a > new field, and it would allow us to have a generic "resource_alignment()" > routine that just gets a resource pointer. Besides, I removed IORESOURCE_BUS_HAS_VGA flag which was unused for ages. Signed-off-by: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Gary Hade <garyhade@us.ibm.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-03-30 15:50:14 +00:00
/**
* resource_alignment - calculate resource's alignment
* @res: resource pointer
*
* Returns alignment on success, 0 (invalid alignment) on failure.
*/
resource_size_t resource_alignment(struct resource *res)
{
switch (res->flags & (IORESOURCE_SIZEALIGN | IORESOURCE_STARTALIGN)) {
case IORESOURCE_SIZEALIGN:
return resource_size(res);
PCI: clean up resource alignment management Done per Linus' request and suggestions. Linus has explained that better than I'll be able to explain: On Thu, Mar 27, 2008 at 10:12:10AM -0700, Linus Torvalds wrote: > Actually, before we go any further, there might be a less intrusive > alternative: add just a couple of flags to the resource flags field (we > still have something like 8 unused bits on 32-bit), and use those to > implement a generic "resource_alignment()" routine. > > Two flags would do it: > > - IORESOURCE_SIZEALIGN: size indicates alignment (regular PCI device > resources) > > - IORESOURCE_STARTALIGN: start field is alignment (PCI bus resources > during probing) > > and then the case of both flags zero (or both bits set) would actually be > "invalid", and we would also clear the IORESOURCE_STARTALIGN flag when we > actually allocate the resource (so that we don't use the "start" field as > alignment incorrectly when it no longer indicates alignment). > > That wouldn't be totally generic, but it would have the nice property of > automatically at least add sanity checking for that whole "res->start has > the odd meaning of 'alignment' during probing" and remove the need for a > new field, and it would allow us to have a generic "resource_alignment()" > routine that just gets a resource pointer. Besides, I removed IORESOURCE_BUS_HAS_VGA flag which was unused for ages. Signed-off-by: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Gary Hade <garyhade@us.ibm.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-03-30 15:50:14 +00:00
case IORESOURCE_STARTALIGN:
return res->start;
default:
return 0;
}
}
/*
* This is compatibility stuff for IO resources.
*
* Note how this, unlike the above, knows about
* the IO flag meanings (busy etc).
*
* request_region creates a new busy region.
*
* check_region returns non-zero if the area is already busy.
*
* release_region releases a matching busy region.
*/
static DECLARE_WAIT_QUEUE_HEAD(muxed_resource_wait);
/**
* __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)
{
DECLARE_WAITQUEUE(wait, current);
struct resource *res = kzalloc(sizeof(*res), GFP_KERNEL);
if (!res)
return NULL;
res->name = name;
res->start = start;
res->end = start + n - 1;
res->flags = IORESOURCE_BUSY;
res->flags |= flags;
write_lock(&resource_lock);
for (;;) {
struct resource *conflict;
conflict = __request_resource(parent, res);
if (!conflict)
break;
if (conflict != parent) {
parent = conflict;
if (!(conflict->flags & IORESOURCE_BUSY))
continue;
}
if (conflict->flags & flags & IORESOURCE_MUXED) {
add_wait_queue(&muxed_resource_wait, &wait);
write_unlock(&resource_lock);
set_current_state(TASK_UNINTERRUPTIBLE);
schedule();
remove_wait_queue(&muxed_resource_wait, &wait);
write_lock(&resource_lock);
continue;
}
/* Uhhuh, that didn't work out.. */
kfree(res);
res = NULL;
break;
}
write_unlock(&resource_lock);
return res;
}
EXPORT_SYMBOL(__request_region);
/**
* __check_region - check if a resource region is busy or free
* @parent: parent resource descriptor
* @start: resource start address
* @n: resource region size
*
* Returns 0 if the region is free at the moment it is checked,
* returns %-EBUSY if the region is busy.
*
* NOTE:
* This function is deprecated because its use is racy.
* Even if it returns 0, a subsequent call to request_region()
* may fail because another driver etc. just allocated the region.
* Do NOT use it. It will be removed from the kernel.
*/
int __check_region(struct resource *parent, resource_size_t start,
resource_size_t n)
{
struct resource * res;
res = __request_region(parent, start, n, "check-region", 0);
if (!res)
return -EBUSY;
release_resource(res);
kfree(res);
return 0;
}
EXPORT_SYMBOL(__check_region);
/**
* __release_region - release a previously reserved resource region
* @parent: parent resource descriptor
* @start: resource start address
* @n: resource region size
*
* The described resource region must match a currently busy region.
*/
void __release_region(struct resource *parent, resource_size_t start,
resource_size_t n)
{
struct resource **p;
resource_size_t end;
p = &parent->child;
end = start + n - 1;
write_lock(&resource_lock);
for (;;) {
struct resource *res = *p;
if (!res)
break;
if (res->start <= start && res->end >= end) {
if (!(res->flags & IORESOURCE_BUSY)) {
p = &res->child;
continue;
}
if (res->start != start || res->end != end)
break;
*p = res->sibling;
write_unlock(&resource_lock);
if (res->flags & IORESOURCE_MUXED)
wake_up(&muxed_resource_wait);
kfree(res);
return;
}
p = &res->sibling;
}
write_unlock(&resource_lock);
printk(KERN_WARNING "Trying to free nonexistent resource "
"<%016llx-%016llx>\n", (unsigned long long)start,
(unsigned long long)end);
}
EXPORT_SYMBOL(__release_region);
resource: add release_mem_region_adjustable() Add release_mem_region_adjustable(), which releases a requested region from a currently busy memory resource. This interface adjusts the matched memory resource accordingly even if the requested region does not match exactly but still fits into. This new interface is intended for memory hot-delete. During bootup, memory resources are inserted from the boot descriptor table, such as EFI Memory Table and e820. Each memory resource entry usually covers the whole contigous memory range. Memory hot-delete request, on the other hand, may target to a particular range of memory resource, and its size can be much smaller than the whole contiguous memory. Since the existing release interfaces like __release_region() require a requested region to be exactly matched to a resource entry, they do not allow a partial resource to be released. This new interface is restrictive (i.e. release under certain conditions), which is consistent with other release interfaces, __release_region() and __release_resource(). Additional release conditions, such as an overlapping region to a resource entry, can be supported after they are confirmed as valid cases. There is no change to the existing interfaces since their restriction is valid for I/O resources. [akpm@linux-foundation.org: use GFP_ATOMIC under write_lock()] [akpm@linux-foundation.org: switch back to GFP_KERNEL, less buggily] [akpm@linux-foundation.org: remove unneeded and wrong kfree(), per Toshi] Signed-off-by: Toshi Kani <toshi.kani@hp.com> Reviewed-by : Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Reviewed-by: Ram Pai <linuxram@us.ibm.com> Cc: T Makphaibulchoke <tmac@hp.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Jiang Liu <jiang.liu@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-29 22:08:19 +00:00
#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
*
* This interface is intended for memory hot-delete. The requested region
* is released from a currently busy memory resource. The requested region
* must either match exactly or fit into a single busy resource entry. In
* the latter case, the remaining resource is adjusted accordingly.
* Existing children of the busy memory resource must be immutable in the
* request.
*
* Note:
* - Additional release conditions, such as overlapping region, can be
* supported after they are confirmed as valid cases.
* - When a busy memory resource gets split into two entries, the code
* 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)
{
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;
/* The kzalloc() result gets checked later */
new_res = kzalloc(sizeof(struct resource), GFP_KERNEL);
p = &parent->child;
write_lock(&resource_lock);
while ((res = *p)) {
if (res->start >= end)
break;
/* look for the next resource if it does not fit into */
if (res->start > start || res->end < end) {
p = &res->sibling;
continue;
}
if (!(res->flags & IORESOURCE_MEM))
break;
if (!(res->flags & IORESOURCE_BUSY)) {
p = &res->child;
continue;
}
/* found the target resource; let's adjust accordingly */
if (res->start == start && res->end == end) {
/* free the whole entry */
*p = res->sibling;
kfree(res);
ret = 0;
} else if (res->start == start && res->end != end) {
/* adjust the start */
ret = __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);
} else {
/* split into two entries */
if (!new_res) {
ret = -ENOMEM;
break;
}
new_res->name = res->name;
new_res->start = end + 1;
new_res->end = res->end;
new_res->flags = res->flags;
new_res->parent = res->parent;
new_res->sibling = res->sibling;
new_res->child = NULL;
ret = __adjust_resource(res, res->start,
start - res->start);
if (ret)
break;
res->sibling = new_res;
new_res = NULL;
}
break;
}
write_unlock(&resource_lock);
kfree(new_res);
return ret;
}
#endif /* CONFIG_MEMORY_HOTREMOVE */
/*
* Managed region resource
*/
struct region_devres {
struct resource *parent;
resource_size_t start;
resource_size_t n;
};
static void devm_region_release(struct device *dev, void *res)
{
struct region_devres *this = res;
__release_region(this->parent, this->start, this->n);
}
static int devm_region_match(struct device *dev, void *res, void *match_data)
{
struct region_devres *this = res, *match = match_data;
return this->parent == match->parent &&
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 region_devres *dr = NULL;
struct resource *res;
dr = devres_alloc(devm_region_release, sizeof(struct region_devres),
GFP_KERNEL);
if (!dr)
return NULL;
dr->parent = parent;
dr->start = start;
dr->n = n;
res = __request_region(parent, start, n, name, 0);
if (res)
devres_add(dev, dr);
else
devres_free(dr);
return res;
}
EXPORT_SYMBOL(__devm_request_region);
void __devm_release_region(struct device *dev, struct resource *parent,
resource_size_t start, resource_size_t n)
{
struct region_devres match_data = { parent, start, n };
__release_region(parent, start, n);
WARN_ON(devres_destroy(dev, devm_region_release, devm_region_match,
&match_data));
}
EXPORT_SYMBOL(__devm_release_region);
/*
* Called from init/main.c to reserve IO ports.
*/
#define MAXRESERVE 4
static int __init reserve_setup(char *str)
{
static int reserved;
static struct resource reserve[MAXRESERVE];
for (;;) {
unsigned int io_start, io_num;
int x = reserved;
if (get_option (&str, &io_start) != 2)
break;
if (get_option (&str, &io_num) == 0)
break;
if (x < MAXRESERVE) {
struct resource *res = reserve + x;
res->name = "reserved";
res->start = io_start;
res->end = io_start + io_num - 1;
res->flags = IORESOURCE_BUSY;
res->child = NULL;
if (request_resource(res->start >= 0x10000 ? &iomem_resource : &ioport_resource, res) == 0)
reserved = x+1;
}
}
return 1;
}
__setup("reserve=", reserve_setup);
/*
* Check if the requested addr and size spans more than any slot in the
* iomem resource tree.
*/
int iomem_map_sanity_check(resource_size_t addr, unsigned long size)
{
struct resource *p = &iomem_resource;
int err = 0;
loff_t l;
read_lock(&resource_lock);
for (p = p->child; p ; p = r_next(NULL, p, &l)) {
/*
* We can probably skip the resources without
* IORESOURCE_IO attribute?
*/
if (p->start >= addr + size)
continue;
if (p->end < addr)
continue;
if (PFN_DOWN(p->start) <= PFN_DOWN(addr) &&
PFN_DOWN(p->end) >= PFN_DOWN(addr + size - 1))
continue;
/*
* if a resource is "BUSY", it's not a hardware resource
* but a driver mapping of such a resource; we don't want
* to warn for those; some drivers legitimately map only
* partial hardware resources. (example: vesafb)
*/
if (p->flags & IORESOURCE_BUSY)
continue;
printk(KERN_WARNING "resource map sanity check conflict: "
"0x%llx 0x%llx 0x%llx 0x%llx %s\n",
(unsigned long long)addr,
(unsigned long long)(addr + size - 1),
(unsigned long long)p->start,
(unsigned long long)p->end,
p->name);
err = -1;
break;
}
read_unlock(&resource_lock);
return err;
}
#ifdef CONFIG_STRICT_DEVMEM
static int strict_iomem_checks = 1;
#else
static int strict_iomem_checks;
#endif
/*
* check if an address is reserved in the iomem resource tree
* returns 1 if reserved, 0 if not reserved.
*/
int iomem_is_exclusive(u64 addr)
{
struct resource *p = &iomem_resource;
int err = 0;
loff_t l;
int size = PAGE_SIZE;
if (!strict_iomem_checks)
return 0;
addr = addr & PAGE_MASK;
read_lock(&resource_lock);
for (p = p->child; p ; p = r_next(NULL, p, &l)) {
/*
* We can probably skip the resources without
* IORESOURCE_IO attribute?
*/
if (p->start >= addr + size)
break;
if (p->end < addr)
continue;
if (p->flags & IORESOURCE_BUSY &&
p->flags & IORESOURCE_EXCLUSIVE) {
err = 1;
break;
}
}
read_unlock(&resource_lock);
return err;
}
static int __init strict_iomem(char *str)
{
if (strstr(str, "relaxed"))
strict_iomem_checks = 0;
if (strstr(str, "strict"))
strict_iomem_checks = 1;
return 1;
}
__setup("iomem=", strict_iomem);