Merge branch 'core-resources-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull ram resource handling changes from Ingo Molnar:
 "Core kernel resource handling changes to support NVDIMM error
  injection.

  This tree introduces a new I/O resource type, IORESOURCE_SYSTEM_RAM,
  for System RAM while keeping the current IORESOURCE_MEM type bit set
  for all memory-mapped ranges (including System RAM) for backward
  compatibility.

  With this resource flag it no longer takes a strcmp() loop through the
  resource tree to find "System RAM" resources.

  The new resource type is then used to extend ACPI/APEI error injection
  facility to also support NVDIMM"

* 'core-resources-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  ACPI/EINJ: Allow memory error injection to NVDIMM
  resource: Kill walk_iomem_res()
  x86/kexec: Remove walk_iomem_res() call with GART type
  x86, kexec, nvdimm: Use walk_iomem_res_desc() for iomem search
  resource: Add walk_iomem_res_desc()
  memremap: Change region_intersects() to take @flags and @desc
  arm/samsung: Change s3c_pm_run_res() to use System RAM type
  resource: Change walk_system_ram() to use System RAM type
  drivers: Initialize resource entry to zero
  xen, mm: Set IORESOURCE_SYSTEM_RAM to System RAM
  kexec: Set IORESOURCE_SYSTEM_RAM for System RAM
  arch: Set IORESOURCE_SYSTEM_RAM flag for System RAM
  ia64: Set System RAM type and descriptor
  x86/e820: Set System RAM type and descriptor
  resource: Add I/O resource descriptor
  resource: Handle resource flags properly
  resource: Add System RAM resource type
This commit is contained in:
Linus Torvalds 2016-03-14 15:15:51 -07:00
commit d37a14bb5f
34 changed files with 232 additions and 159 deletions

View file

@ -66,13 +66,15 @@ struct resource crashk_res = {
.name = "Crash kernel",
.start = 0,
.end = 0,
.flags = IORESOURCE_BUSY | IORESOURCE_MEM
.flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM,
.desc = IORES_DESC_CRASH_KERNEL
};
struct resource crashk_low_res = {
.name = "Crash kernel",
.start = 0,
.end = 0,
.flags = IORESOURCE_BUSY | IORESOURCE_MEM
.flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM,
.desc = IORES_DESC_CRASH_KERNEL
};
int kexec_should_crash(struct task_struct *p)
@ -959,7 +961,7 @@ int crash_shrink_memory(unsigned long new_size)
ram_res->start = end;
ram_res->end = crashk_res.end;
ram_res->flags = IORESOURCE_BUSY | IORESOURCE_MEM;
ram_res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM;
ram_res->name = "System RAM";
crashk_res.end = end - 1;

View file

@ -524,10 +524,10 @@ int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz,
/* Walk the RAM ranges and allocate a suitable range for the buffer */
if (image->type == KEXEC_TYPE_CRASH)
ret = walk_iomem_res("Crash kernel",
IORESOURCE_MEM | IORESOURCE_BUSY,
crashk_res.start, crashk_res.end, kbuf,
locate_mem_hole_callback);
ret = walk_iomem_res_desc(crashk_res.desc,
IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
crashk_res.start, crashk_res.end, kbuf,
locate_mem_hole_callback);
else
ret = walk_system_ram_res(0, -1, kbuf,
locate_mem_hole_callback);

View file

@ -47,7 +47,7 @@ static void *try_ram_remap(resource_size_t offset, size_t size)
* being mapped does not have i/o side effects and the __iomem
* annotation is not applicable.
*
* MEMREMAP_WB - matches the default mapping for "System RAM" on
* MEMREMAP_WB - matches the default mapping for System RAM on
* the architecture. This is usually a read-allocate write-back cache.
* Morever, if MEMREMAP_WB is specified and the requested remap region is RAM
* memremap() will bypass establishing a new mapping and instead return
@ -56,11 +56,12 @@ static void *try_ram_remap(resource_size_t offset, size_t size)
* MEMREMAP_WT - establish a mapping whereby writes either bypass the
* cache or are written through to memory and never exist in a
* cache-dirty state with respect to program visibility. Attempts to
* map "System RAM" with this mapping type will fail.
* map System RAM with this mapping type will fail.
*/
void *memremap(resource_size_t offset, size_t size, unsigned long flags)
{
int is_ram = region_intersects(offset, size, "System RAM");
int is_ram = region_intersects(offset, size,
IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
void *addr = NULL;
if (is_ram == REGION_MIXED) {
@ -76,7 +77,7 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags)
* MEMREMAP_WB is special in that it can be satisifed
* from the direct map. Some archs depend on the
* capability of memremap() to autodetect cases where
* the requested range is potentially in "System RAM"
* the requested range is potentially in System RAM.
*/
if (is_ram == REGION_INTERSECTS)
addr = try_ram_remap(offset, size);
@ -88,7 +89,7 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags)
* If we don't have a mapping yet and more request flags are
* pending then we will be attempting to establish a new virtual
* address mapping. Enforce that this mapping is not aliasing
* "System RAM"
* System RAM.
*/
if (!addr && is_ram == REGION_INTERSECTS && flags) {
WARN_ONCE(1, "memremap attempted on ram %pa size: %#lx\n",
@ -279,7 +280,8 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
align_start = res->start & ~(SECTION_SIZE - 1);
align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
- align_start;
is_ram = region_intersects(align_start, align_size, "System RAM");
is_ram = region_intersects(align_start, align_size,
IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
if (is_ram == REGION_MIXED) {
WARN_ONCE(1, "%s attempted on mixed region %pr\n",

View file

@ -333,13 +333,13 @@ int release_resource(struct resource *old)
EXPORT_SYMBOL(release_resource);
/*
* Finds the lowest iomem reosurce exists with-in [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.
* This walks through whole tree and not just first level children
* until and unless first_level_children_only is true.
* Finds the lowest iomem resource existing within [res->start.res->end).
* The caller must specify res->start, res->end, res->flags, and optionally
* desc. If found, returns 0, res is overwritten, if not found, returns -1.
* This function walks the whole tree and not just first level children until
* and unless first_level_children_only is true.
*/
static int find_next_iomem_res(struct resource *res, char *name,
static int find_next_iomem_res(struct resource *res, unsigned long desc,
bool first_level_children_only)
{
resource_size_t start, end;
@ -358,9 +358,9 @@ static int find_next_iomem_res(struct resource *res, char *name,
read_lock(&resource_lock);
for (p = iomem_resource.child; p; p = next_resource(p, sibling_only)) {
if (p->flags != res->flags)
if ((p->flags & res->flags) != res->flags)
continue;
if (name && strcmp(p->name, name))
if ((desc != IORES_DESC_NONE) && (desc != p->desc))
continue;
if (p->start > end) {
p = NULL;
@ -385,15 +385,18 @@ static int find_next_iomem_res(struct resource *res, char *name,
* 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
* name are valid candidates.
* desc are valid candidates.
*
* @name: name of resource
* @flags: resource flags
* @desc: I/O resource descriptor. Use IORES_DESC_NONE to skip @desc check.
* @flags: I/O resource flags
* @start: start addr
* @end: end addr
*
* 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.
*/
int walk_iomem_res(char *name, unsigned long flags, u64 start, u64 end,
void *arg, int (*func)(u64, u64, void *))
int walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start,
u64 end, void *arg, int (*func)(u64, u64, void *))
{
struct resource res;
u64 orig_end;
@ -403,23 +406,27 @@ int walk_iomem_res(char *name, unsigned long flags, u64 start, u64 end,
res.end = end;
res.flags = flags;
orig_end = res.end;
while ((res.start < res.end) &&
(!find_next_iomem_res(&res, name, false))) {
(!find_next_iomem_res(&res, desc, false))) {
ret = (*func)(res.start, res.end, arg);
if (ret)
break;
res.start = res.end + 1;
res.end = orig_end;
}
return ret;
}
/*
* 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". This function deals with
* full ranges and not pfn. If resources are not pfn aligned, dealing
* with pfn can truncate ranges.
* This function calls the @func callback against all memory ranges of type
* System RAM which are marked as IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY.
* Now, this function is only for System RAM, it deals with full ranges and
* not PFNs. If resources are not PFN-aligned, dealing with PFNs can truncate
* ranges.
*/
int walk_system_ram_res(u64 start, u64 end, void *arg,
int (*func)(u64, u64, void *))
@ -430,10 +437,10 @@ int walk_system_ram_res(u64 start, u64 end, void *arg,
res.start = start;
res.end = end;
res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
orig_end = res.end;
while ((res.start < res.end) &&
(!find_next_iomem_res(&res, "System RAM", true))) {
(!find_next_iomem_res(&res, IORES_DESC_NONE, true))) {
ret = (*func)(res.start, res.end, arg);
if (ret)
break;
@ -446,9 +453,9 @@ int walk_system_ram_res(u64 start, u64 end, void *arg,
#if !defined(CONFIG_ARCH_HAS_WALK_MEMORY)
/*
* 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".
* 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.
*/
int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
void *arg, int (*func)(unsigned long, unsigned long, void *))
@ -460,10 +467,10 @@ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
res.start = (u64) start_pfn << PAGE_SHIFT;
res.end = ((u64)(start_pfn + nr_pages) << PAGE_SHIFT) - 1;
res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
orig_end = res.end;
while ((res.start < res.end) &&
(find_next_iomem_res(&res, "System RAM", true) >= 0)) {
(find_next_iomem_res(&res, IORES_DESC_NONE, true) >= 0)) {
pfn = (res.start + PAGE_SIZE - 1) >> PAGE_SHIFT;
end_pfn = (res.end + 1) >> PAGE_SHIFT;
if (end_pfn > pfn)
@ -484,7 +491,7 @@ static int __is_ram(unsigned long pfn, unsigned long nr_pages, void *arg)
}
/*
* This generic page_is_ram() returns true if specified address is
* registered as "System RAM" in iomem_resource list.
* registered as System RAM in iomem_resource list.
*/
int __weak page_is_ram(unsigned long pfn)
{
@ -496,30 +503,34 @@ EXPORT_SYMBOL_GPL(page_is_ram);
* region_intersects() - determine intersection of region with known resources
* @start: region start address
* @size: size of region
* @name: name of resource (in iomem_resource)
* @flags: flags of resource (in iomem_resource)
* @desc: descriptor of resource (in iomem_resource) or IORES_DESC_NONE
*
* Check if the specified region partially overlaps or fully eclipses a
* resource identified by @name. Return REGION_DISJOINT if the region
* does not overlap @name, return REGION_MIXED if the region overlaps
* @type and another resource, and return REGION_INTERSECTS if the
* region overlaps @type and no other defined resource. Note, that
* REGION_INTERSECTS is also returned in the case when the specified
* region overlaps RAM and undefined memory holes.
* resource identified by @flags and @desc (optional with IORES_DESC_NONE).
* Return REGION_DISJOINT if the region does not overlap @flags/@desc,
* return REGION_MIXED if the region overlaps @flags/@desc and another
* resource, and return REGION_INTERSECTS if the region overlaps @flags/@desc
* and no other defined resource. Note that REGION_INTERSECTS is also
* returned in the case when the specified region overlaps RAM and undefined
* memory holes.
*
* region_intersect() is used by memory remapping functions to ensure
* the user is not remapping RAM and is a vast speed up over walking
* through the resource table page by page.
*/
int region_intersects(resource_size_t start, size_t size, const char *name)
int region_intersects(resource_size_t start, size_t size, unsigned long flags,
unsigned long desc)
{
unsigned long flags = IORESOURCE_MEM | IORESOURCE_BUSY;
resource_size_t end = start + size - 1;
int type = 0; int other = 0;
struct resource *p;
read_lock(&resource_lock);
for (p = iomem_resource.child; p ; p = p->sibling) {
bool is_type = strcmp(p->name, name) == 0 && p->flags == flags;
bool is_type = (((p->flags & flags) == flags) &&
((desc == IORES_DESC_NONE) ||
(desc == p->desc)));
if (start >= p->start && start <= p->end)
is_type ? type++ : other++;
@ -538,6 +549,7 @@ int region_intersects(resource_size_t start, size_t size, const char *name)
return REGION_DISJOINT;
}
EXPORT_SYMBOL_GPL(region_intersects);
void __weak arch_remove_reservations(struct resource *avail)
{
@ -948,6 +960,7 @@ static void __init __reserve_region_with_split(struct resource *root,
res->start = start;
res->end = end;
res->flags = IORESOURCE_BUSY;
res->desc = IORES_DESC_NONE;
while (1) {
@ -982,6 +995,7 @@ static void __init __reserve_region_with_split(struct resource *root,
next_res->start = conflict->end + 1;
next_res->end = end;
next_res->flags = IORESOURCE_BUSY;
next_res->desc = IORES_DESC_NONE;
}
} else {
res->start = conflict->end + 1;
@ -1071,8 +1085,9 @@ struct resource * __request_region(struct resource *parent,
res->name = name;
res->start = start;
res->end = start + n - 1;
res->flags = resource_type(parent);
res->flags = resource_type(parent) | resource_ext_type(parent);
res->flags |= IORESOURCE_BUSY | flags;
res->desc = IORES_DESC_NONE;
write_lock(&resource_lock);
@ -1238,6 +1253,7 @@ int release_mem_region_adjustable(struct resource *parent,
new_res->start = end + 1;
new_res->end = res->end;
new_res->flags = res->flags;
new_res->desc = res->desc;
new_res->parent = res->parent;
new_res->sibling = res->sibling;
new_res->child = NULL;
@ -1413,6 +1429,7 @@ static int __init reserve_setup(char *str)
res->start = io_start;
res->end = io_start + io_num - 1;
res->flags = IORESOURCE_BUSY;
res->desc = IORES_DESC_NONE;
res->child = NULL;
if (request_resource(res->start >= 0x10000 ? &iomem_resource : &ioport_resource, res) == 0)
reserved = x+1;