Insert Soft Reserved memory into a dedicated soft_reserve_resource tree
instead of the iomem_resource tree at boot.
Publishing Soft Reserved ranges into iomem too early causes conflicts with
CXL hotplug and region assembly failure, especially when Soft Reserved
overlaps CXL regions.
Re-inserting these ranges into iomem will be handled in follow-up patches,
after ensuring CXL window publication ordering is stabilized and when the
dax_hmem is ready to consume them.
This avoids trimming or deleting resources later and provides a cleaner
handoff between EFI-defined memory and CXL resource management.
Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
arch/x86/kernel/e820.c | 2 +-
drivers/dax/hmem/device.c | 4 +--
drivers/dax/hmem/hmem.c | 8 +++++
include/linux/ioport.h | 24 +++++++++++++
kernel/resource.c | 73 +++++++++++++++++++++++++++++++++------
5 files changed, 97 insertions(+), 14 deletions(-)
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index c3acbd26408b..aef1ff2cabda 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1153,7 +1153,7 @@ void __init e820__reserve_resources_late(void)
res = e820_res;
for (i = 0; i < e820_table->nr_entries; i++) {
if (!res->parent && res->end)
- insert_resource_expand_to_fit(&iomem_resource, res);
+ insert_resource_late(res);
res++;
}
diff --git a/drivers/dax/hmem/device.c b/drivers/dax/hmem/device.c
index f9e1a76a04a9..22732b729017 100644
--- a/drivers/dax/hmem/device.c
+++ b/drivers/dax/hmem/device.c
@@ -83,8 +83,8 @@ static __init int hmem_register_one(struct resource *res, void *data)
static __init int hmem_init(void)
{
- walk_iomem_res_desc(IORES_DESC_SOFT_RESERVED,
- IORESOURCE_MEM, 0, -1, NULL, hmem_register_one);
+ walk_soft_reserve_res_desc(IORES_DESC_SOFT_RESERVED, IORESOURCE_MEM, 0,
+ -1, NULL, hmem_register_one);
return 0;
}
diff --git a/drivers/dax/hmem/hmem.c b/drivers/dax/hmem/hmem.c
index c18451a37e4f..d5b8f06d531e 100644
--- a/drivers/dax/hmem/hmem.c
+++ b/drivers/dax/hmem/hmem.c
@@ -73,10 +73,18 @@ static int hmem_register_device(struct device *host, int target_nid,
return 0;
}
+#ifdef CONFIG_EFI_SOFT_RESERVE
+ rc = region_intersects_soft_reserve(res->start, resource_size(res),
+ IORESOURCE_MEM,
+ IORES_DESC_SOFT_RESERVED);
+ if (rc != REGION_INTERSECTS)
+ return 0;
+#else
rc = region_intersects(res->start, resource_size(res), IORESOURCE_MEM,
IORES_DESC_SOFT_RESERVED);
if (rc != REGION_INTERSECTS)
return 0;
+#endif
id = memregion_alloc(GFP_KERNEL);
if (id < 0) {
diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index e8b2d6aa4013..889bc4982777 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -232,6 +232,9 @@ struct resource_constraint {
/* PC/ISA/whatever - the normal PC address spaces: IO and memory */
extern struct resource ioport_resource;
extern struct resource iomem_resource;
+#ifdef CONFIG_EFI_SOFT_RESERVE
+extern struct resource soft_reserve_resource;
+#endif
extern struct resource *request_resource_conflict(struct resource *root, struct resource *new);
extern int request_resource(struct resource *root, struct resource *new);
@@ -255,6 +258,22 @@ int adjust_resource(struct resource *res, resource_size_t start,
resource_size_t size);
resource_size_t resource_alignment(struct resource *res);
+
+#ifdef CONFIG_EFI_SOFT_RESERVE
+static inline void insert_resource_late(struct resource *new)
+{
+ if (new->desc == IORES_DESC_SOFT_RESERVED)
+ insert_resource_expand_to_fit(&soft_reserve_resource, new);
+ else
+ insert_resource_expand_to_fit(&iomem_resource, new);
+}
+#else
+static inline void insert_resource_late(struct resource *new)
+{
+ insert_resource_expand_to_fit(&iomem_resource, new);
+}
+#endif
+
/**
* resource_set_size - Calculate resource end address from size and start
* @res: Resource descriptor
@@ -409,6 +428,11 @@ walk_system_ram_res_rev(u64 start, u64 end, void *arg,
extern int
walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, u64 end,
void *arg, int (*func)(struct resource *, void *));
+int walk_soft_reserve_res_desc(unsigned long desc, unsigned long flags,
+ u64 start, u64 end, void *arg,
+ int (*func)(struct resource *, void *));
+int region_intersects_soft_reserve(resource_size_t start, size_t size,
+ unsigned long flags, unsigned long desc);
struct resource *devm_request_free_mem_region(struct device *dev,
struct resource *base, unsigned long size);
diff --git a/kernel/resource.c b/kernel/resource.c
index f9bb5481501a..8479a99441e2 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -321,13 +321,14 @@ static bool is_type_match(struct resource *p, unsigned long flags, unsigned long
}
/**
- * find_next_iomem_res - Finds the lowest iomem resource that covers part of
- * [@start..@end].
+ * find_next_res - Finds the lowest resource that covers part of
+ * [@start..@end].
*
* 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.
*
+ * @parent: resource tree root to search
* @start: start address of the resource searched for
* @end: end address of same resource
* @flags: flags which the resource must have
@@ -337,9 +338,9 @@ static bool is_type_match(struct resource *p, unsigned long flags, unsigned long
* The caller must specify @start, @end, @flags, and @desc
* (which may be IORES_DESC_NONE).
*/
-static int find_next_iomem_res(resource_size_t start, resource_size_t end,
- unsigned long flags, unsigned long desc,
- struct resource *res)
+static int find_next_res(struct resource *parent, resource_size_t start,
+ resource_size_t end, unsigned long flags,
+ unsigned long desc, struct resource *res)
{
struct resource *p;
@@ -351,7 +352,7 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end,
read_lock(&resource_lock);
- for_each_resource(&iomem_resource, p, false) {
+ for_each_resource(parent, p, false) {
/* If we passed the resource we are looking for, stop */
if (p->start > end) {
p = NULL;
@@ -382,16 +383,23 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end,
return p ? 0 : -ENODEV;
}
-static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end,
- unsigned long flags, unsigned long desc,
- void *arg,
- int (*func)(struct resource *, void *))
+static int find_next_iomem_res(resource_size_t start, resource_size_t end,
+ unsigned long flags, unsigned long desc,
+ struct resource *res)
+{
+ return find_next_res(&iomem_resource, start, end, flags, desc, res);
+}
+
+static int walk_res_desc(struct resource *parent, resource_size_t start,
+ resource_size_t end, unsigned long flags,
+ unsigned long desc, void *arg,
+ int (*func)(struct resource *, void *))
{
struct resource res;
int ret = -EINVAL;
while (start < end &&
- !find_next_iomem_res(start, end, flags, desc, &res)) {
+ !find_next_res(parent, start, end, flags, desc, &res)) {
ret = (*func)(&res, arg);
if (ret)
break;
@@ -402,6 +410,15 @@ static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end,
return ret;
}
+static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end,
+ unsigned long flags, unsigned long desc,
+ void *arg,
+ int (*func)(struct resource *, void *))
+{
+ return walk_res_desc(&iomem_resource, start, end, flags, desc, arg, func);
+}
+
+
/**
* walk_iomem_res_desc - Walks through iomem resources and calls func()
* with matching resource ranges.
@@ -426,6 +443,26 @@ int walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start,
}
EXPORT_SYMBOL_GPL(walk_iomem_res_desc);
+#ifdef CONFIG_EFI_SOFT_RESERVE
+struct resource soft_reserve_resource = {
+ .name = "Soft Reserved",
+ .start = 0,
+ .end = -1,
+ .desc = IORES_DESC_SOFT_RESERVED,
+ .flags = IORESOURCE_MEM,
+};
+EXPORT_SYMBOL_GPL(soft_reserve_resource);
+
+int walk_soft_reserve_res_desc(unsigned long desc, unsigned long flags,
+ u64 start, u64 end, void *arg,
+ int (*func)(struct resource *, void *))
+{
+ return walk_res_desc(&soft_reserve_resource, start, end, flags, desc,
+ arg, func);
+}
+EXPORT_SYMBOL_GPL(walk_soft_reserve_res_desc);
+#endif
+
/*
* This function calls the @func callback against all memory ranges of type
* System RAM which are marked as IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY.
@@ -648,6 +685,20 @@ int region_intersects(resource_size_t start, size_t size, unsigned long flags,
}
EXPORT_SYMBOL_GPL(region_intersects);
+int region_intersects_soft_reserve(resource_size_t start, size_t size,
+ unsigned long flags, unsigned long desc)
+{
+ int ret;
+
+ read_lock(&resource_lock);
+ ret = __region_intersects(&soft_reserve_resource, start, size, flags,
+ desc);
+ read_unlock(&resource_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(region_intersects_soft_reserve);
+
void __weak arch_remove_reservations(struct resource *avail)
{
}
--
2.17.1On Fri, Aug 22, 2025 at 03:41:57AM +0000, Smita Koralahalli wrote:
> diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
> index c3acbd26408b..aef1ff2cabda 100644
> --- a/arch/x86/kernel/e820.c
> +++ b/arch/x86/kernel/e820.c
> @@ -1153,7 +1153,7 @@ void __init e820__reserve_resources_late(void)
> res = e820_res;
> for (i = 0; i < e820_table->nr_entries; i++) {
> if (!res->parent && res->end)
> - insert_resource_expand_to_fit(&iomem_resource, res);
> + insert_resource_late(res);
> res++;
> }
>
Btw, this doesn't even build and cover letter doesn't say what it applies
ontop so I applied it on my pile of tip/master.
kernel/resource.c: In function ‘region_intersects_soft_reserve’:
kernel/resource.c:694:36: error: ‘soft_reserve_resource’ undeclared (first use in this function); did you mean ‘devm_release_resource’?
694 | ret = __region_intersects(&soft_reserve_resource, start, size, flags,
| ^~~~~~~~~~~~~~~~~~~~~
| devm_release_resource
kernel/resource.c:694:36: note: each undeclared identifier is reported only once for each function it appears in
make[3]: *** [scripts/Makefile.build:287: kernel/resource.o] Error 1
make[2]: *** [scripts/Makefile.build:556: kernel] Error 2
make[2]: *** Waiting for unfinished jobs....
make[1]: *** [/mnt/kernel/kernel/2nd/linux/Makefile:2011: .] Error 2
make: *** [Makefile:248: __sub-make] Error 2
Also, I'd do this resource insertion a bit differently:
insert_resource_expand_to_fit(struct resource *new)
{
struct resource *root = &iomem_resource;
if (new->desc == IORES_DESC_SOFT_RESERVED)
root = &soft_reserve_resource;
return __insert_resource_expand_to_fit(root, new);
}
and rename the current insert_resource_expand_to_fit() to the __ variant.
It looks like you want to intercept all callers of
insert_resource_expand_to_fit() instead of defining a separate set which works
on the soft-reserve thing.
Oh well, the resource code is yucky already.
--
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquette
Hi Boris,
On 9/9/2025 9:12 AM, Borislav Petkov wrote:
> On Fri, Aug 22, 2025 at 03:41:57AM +0000, Smita Koralahalli wrote:
>> diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
>> index c3acbd26408b..aef1ff2cabda 100644
>> --- a/arch/x86/kernel/e820.c
>> +++ b/arch/x86/kernel/e820.c
>> @@ -1153,7 +1153,7 @@ void __init e820__reserve_resources_late(void)
>> res = e820_res;
>> for (i = 0; i < e820_table->nr_entries; i++) {
>> if (!res->parent && res->end)
>> - insert_resource_expand_to_fit(&iomem_resource, res);
>> + insert_resource_late(res);
>> res++;
>> }
>>
>
> Btw, this doesn't even build and cover letter doesn't say what it applies
> ontop so I applied it on my pile of tip/master.
>
> kernel/resource.c: In function ‘region_intersects_soft_reserve’:
> kernel/resource.c:694:36: error: ‘soft_reserve_resource’ undeclared (first use in this function); did you mean ‘devm_release_resource’?
> 694 | ret = __region_intersects(&soft_reserve_resource, start, size, flags,
> | ^~~~~~~~~~~~~~~~~~~~~
> | devm_release_resource
> kernel/resource.c:694:36: note: each undeclared identifier is reported only once for each function it appears in
> make[3]: *** [scripts/Makefile.build:287: kernel/resource.o] Error 1
> make[2]: *** [scripts/Makefile.build:556: kernel] Error 2
> make[2]: *** Waiting for unfinished jobs....
> make[1]: *** [/mnt/kernel/kernel/2nd/linux/Makefile:2011: .] Error 2
> make: *** [Makefile:248: __sub-make] Error 2
Apologies for the delay.
This was based on mainline. I have rebased the series onto the latest
mainline and sent out a new revision and noted it in the cover letter.
https://lore.kernel.org/all/20250930044757.214798-2-Smita.KoralahalliChannabasappa@amd.com/
>
> Also, I'd do this resource insertion a bit differently:
>
> insert_resource_expand_to_fit(struct resource *new)
> {
> struct resource *root = &iomem_resource;
>
> if (new->desc == IORES_DESC_SOFT_RESERVED)
> root = &soft_reserve_resource;
>
> return __insert_resource_expand_to_fit(root, new);
> }
>
> and rename the current insert_resource_expand_to_fit() to the __ variant.
I have made these changes as well.
Thanks
Smita
>
> It looks like you want to intercept all callers of
> insert_resource_expand_to_fit() instead of defining a separate set which works
> on the soft-reserve thing.
>
> Oh well, the resource code is yucky already.
>
[ add Boris and Ard ] Ard, Boris, can you have a look at the touches to early e820/x86 init (insert_resource_late()) and give an ack (or nak). The general problem here is conflicts between e820 memory resources and CXL subsystem memory resources. Smita Koralahalli wrote: > Insert Soft Reserved memory into a dedicated soft_reserve_resource tree > instead of the iomem_resource tree at boot. > > Publishing Soft Reserved ranges into iomem too early causes conflicts with > CXL hotplug and region assembly failure, especially when Soft Reserved > overlaps CXL regions. > > Re-inserting these ranges into iomem will be handled in follow-up patches, > after ensuring CXL window publication ordering is stabilized and when the > dax_hmem is ready to consume them. > > This avoids trimming or deleting resources later and provides a cleaner > handoff between EFI-defined memory and CXL resource management. > > Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com> > Signed-off-by: Dan Williams <dan.j.williams@intel.com> Smita, if you added changes this should have Co-developed-by. Otherwise plain Signed-off-by is interpreted as only chain of custody. Any other patches that you add my Signed-off-by to should also have Co-developed-by or be From: me. Alternatively if you completely rewritel a patch with your own approach then note the source (with a Link:) and leave off the original SOB. Lastly, in this case it looks unmodified from what I wrote? Then it should be: From: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com> ...to show the chain of custody of you forwarding a diff authored completely by someone else.
On 9/8/2025 4:01 PM, dan.j.williams@intel.com wrote: > [ add Boris and Ard ] > > Ard, Boris, can you have a look at the touches to early e820/x86 init > (insert_resource_late()) and give an ack (or nak). The general problem > here is conflicts between e820 memory resources and CXL subsystem memory > resources. > > Smita Koralahalli wrote: >> Insert Soft Reserved memory into a dedicated soft_reserve_resource tree >> instead of the iomem_resource tree at boot. >> >> Publishing Soft Reserved ranges into iomem too early causes conflicts with >> CXL hotplug and region assembly failure, especially when Soft Reserved >> overlaps CXL regions. >> >> Re-inserting these ranges into iomem will be handled in follow-up patches, >> after ensuring CXL window publication ordering is stabilized and when the >> dax_hmem is ready to consume them. >> >> This avoids trimming or deleting resources later and provides a cleaner >> handoff between EFI-defined memory and CXL resource management. >> >> Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com> > > >> Signed-off-by: Dan Williams <dan.j.williams@intel.com> > > Smita, if you added changes this should have Co-developed-by. Otherwise > plain Signed-off-by is interpreted as only chain of custody. Any other > patches that you add my Signed-off-by to should also have > Co-developed-by or be From: me. > > Alternatively if you completely rewritel a patch with your own approach > then note the source (with a Link:) and leave off the original SOB. > > Lastly, in this case it looks unmodified from what I wrote? Then it > should be: > > From: Dan Williams <dan.j.williams@intel.com> > > Signed-off-by: Dan Williams <dan.j.williams@intel.com> > Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com> > > ...to show the chain of custody of you forwarding a diff authored > completely by someone else. Thanks for clarifying, Dan. I wasn’t aware of the distinction before (especially to handle the chain of custody..). I will update to reflect that properly and will also be careful with how I handle authorship and sign-offs in future submissions. Thanks Smita
Koralahalli Channabasappa, Smita wrote: > On 9/8/2025 4:01 PM, dan.j.williams@intel.com wrote: > > [ add Boris and Ard ] > > > > Ard, Boris, can you have a look at the touches to early e820/x86 init > > (insert_resource_late()) and give an ack (or nak). The general problem > > here is conflicts between e820 memory resources and CXL subsystem memory > > resources. > > > > Smita Koralahalli wrote: > >> Insert Soft Reserved memory into a dedicated soft_reserve_resource tree > >> instead of the iomem_resource tree at boot. > >> > >> Publishing Soft Reserved ranges into iomem too early causes conflicts with > >> CXL hotplug and region assembly failure, especially when Soft Reserved > >> overlaps CXL regions. > >> > >> Re-inserting these ranges into iomem will be handled in follow-up patches, > >> after ensuring CXL window publication ordering is stabilized and when the > >> dax_hmem is ready to consume them. > >> > >> This avoids trimming or deleting resources later and provides a cleaner > >> handoff between EFI-defined memory and CXL resource management. > >> > >> Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com> > > > > > >> Signed-off-by: Dan Williams <dan.j.williams@intel.com> > > > > Smita, if you added changes this should have Co-developed-by. Otherwise > > plain Signed-off-by is interpreted as only chain of custody. Any other > > patches that you add my Signed-off-by to should also have > > Co-developed-by or be From: me. > > > > Alternatively if you completely rewritel a patch with your own approach > > then note the source (with a Link:) and leave off the original SOB. > > > > Lastly, in this case it looks unmodified from what I wrote? Then it > > should be: > > > > From: Dan Williams <dan.j.williams@intel.com> > > > > Signed-off-by: Dan Williams <dan.j.williams@intel.com> > > Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com> > > > > ...to show the chain of custody of you forwarding a diff authored > > completely by someone else. > > Thanks for clarifying, Dan. I wasn’t aware of the distinction before > (especially to handle the chain of custody..). I will update to reflect > that properly and will also be careful with how I handle authorship and > sign-offs in future submissions. Yeah, the choice to replace From: is subjective and I usually reserve that for significant rewrites. If any of the original patch remains then add Co-developed-by + Signed-off-by. If none of the original patch remains I do still like to say: "based on an original patch by ..." with a Link: to that inspiration patch. ...and if you just forward the original, keep From: untouched and just add your own Signed-off-by as documented in Documentation/process/submitting-patches.rst.
On 22/08/2025 11:41, Smita Koralahalli wrote:
> Insert Soft Reserved memory into a dedicated soft_reserve_resource tree
> instead of the iomem_resource tree at boot.
>
> Publishing Soft Reserved ranges into iomem too early causes conflicts with
> CXL hotplug and region assembly failure, especially when Soft Reserved
> overlaps CXL regions.
>
> Re-inserting these ranges into iomem will be handled in follow-up patches,
> after ensuring CXL window publication ordering is stabilized and when the
> dax_hmem is ready to consume them.
>
> This avoids trimming or deleting resources later and provides a cleaner
> handoff between EFI-defined memory and CXL resource management.
>
> Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
> ---
> arch/x86/kernel/e820.c | 2 +-
> drivers/dax/hmem/device.c | 4 +--
> drivers/dax/hmem/hmem.c | 8 +++++
> include/linux/ioport.h | 24 +++++++++++++
> kernel/resource.c | 73 +++++++++++++++++++++++++++++++++------
> 5 files changed, 97 insertions(+), 14 deletions(-)
>
> diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
> index c3acbd26408b..aef1ff2cabda 100644
> --- a/arch/x86/kernel/e820.c
> +++ b/arch/x86/kernel/e820.c
> @@ -1153,7 +1153,7 @@ void __init e820__reserve_resources_late(void)
> res = e820_res;
> for (i = 0; i < e820_table->nr_entries; i++) {
> if (!res->parent && res->end)
> - insert_resource_expand_to_fit(&iomem_resource, res);
> + insert_resource_late(res);
> res++;
> }
>
> diff --git a/drivers/dax/hmem/device.c b/drivers/dax/hmem/device.c
> index f9e1a76a04a9..22732b729017 100644
> --- a/drivers/dax/hmem/device.c
> +++ b/drivers/dax/hmem/device.c
> @@ -83,8 +83,8 @@ static __init int hmem_register_one(struct resource *res, void *data)
>
> static __init int hmem_init(void)
> {
> - walk_iomem_res_desc(IORES_DESC_SOFT_RESERVED,
> - IORESOURCE_MEM, 0, -1, NULL, hmem_register_one);
> + walk_soft_reserve_res_desc(IORES_DESC_SOFT_RESERVED, IORESOURCE_MEM, 0,
> + -1, NULL, hmem_register_one);
> return 0;
> }
>
> diff --git a/drivers/dax/hmem/hmem.c b/drivers/dax/hmem/hmem.c
> index c18451a37e4f..d5b8f06d531e 100644
> --- a/drivers/dax/hmem/hmem.c
> +++ b/drivers/dax/hmem/hmem.c
> @@ -73,10 +73,18 @@ static int hmem_register_device(struct device *host, int target_nid,
> return 0;
> }
>
> +#ifdef CONFIG_EFI_SOFT_RESERVE
Note that dax_kmem currently depends on CONFIG_EFI_SOFT_RESERVED, so this conditional check may be redundant.
> + rc = region_intersects_soft_reserve(res->start, resource_size(res),
> + IORESOURCE_MEM,
> + IORES_DESC_SOFT_RESERVED);
> + if (rc != REGION_INTERSECTS)
> + return 0;
> +#else
> rc = region_intersects(res->start, resource_size(res), IORESOURCE_MEM,
> IORES_DESC_SOFT_RESERVED);
> if (rc != REGION_INTERSECTS)
> return 0;
> +#endif
>
Additionally, please add a TODO note here (e.g., "Add soft-reserved memory back to iomem").
> id = memregion_alloc(GFP_KERNEL);
> if (id < 0) {
> diff --git a/include/linux/ioport.h b/include/linux/ioport.h
> index e8b2d6aa4013..889bc4982777 100644
> --- a/include/linux/ioport.h
> +++ b/include/linux/ioport.h
> @@ -232,6 +232,9 @@ struct resource_constraint {
> /* PC/ISA/whatever - the normal PC address spaces: IO and memory */
> extern struct resource ioport_resource;
> extern struct resource iomem_resource;
> +#ifdef CONFIG_EFI_SOFT_RESERVE
> +extern struct resource soft_reserve_resource;
> +#endif
>
> extern struct resource *request_resource_conflict(struct resource *root, struct resource *new);
> extern int request_resource(struct resource *root, struct resource *new);
> @@ -255,6 +258,22 @@ int adjust_resource(struct resource *res, resource_size_t start,
> resource_size_t size);
> resource_size_t resource_alignment(struct resource *res);
>
> +
> +#ifdef CONFIG_EFI_SOFT_RESERVE
> +static inline void insert_resource_late(struct resource *new)
> +{
> + if (new->desc == IORES_DESC_SOFT_RESERVED)
> + insert_resource_expand_to_fit(&soft_reserve_resource, new);
> + else
> + insert_resource_expand_to_fit(&iomem_resource, new);
> +}
> +#else
> +static inline void insert_resource_late(struct resource *new)
> +{
> + insert_resource_expand_to_fit(&iomem_resource, new);
> +}
> +#endif
> +
> /**
> * resource_set_size - Calculate resource end address from size and start
> * @res: Resource descriptor
> @@ -409,6 +428,11 @@ walk_system_ram_res_rev(u64 start, u64 end, void *arg,
> extern int
> walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, u64 end,
> void *arg, int (*func)(struct resource *, void *));
> +int walk_soft_reserve_res_desc(unsigned long desc, unsigned long flags,
> + u64 start, u64 end, void *arg,
> + int (*func)(struct resource *, void *));
> +int region_intersects_soft_reserve(resource_size_t start, size_t size,
> + unsigned long flags, unsigned long desc);
>
> struct resource *devm_request_free_mem_region(struct device *dev,
> struct resource *base, unsigned long size);
> diff --git a/kernel/resource.c b/kernel/resource.c
> index f9bb5481501a..8479a99441e2 100644
> --- a/kernel/resource.c
> +++ b/kernel/resource.c
> @@ -321,13 +321,14 @@ static bool is_type_match(struct resource *p, unsigned long flags, unsigned long
> }
>
> /**
> - * find_next_iomem_res - Finds the lowest iomem resource that covers part of
> - * [@start..@end].
> + * find_next_res - Finds the lowest resource that covers part of
> + * [@start..@end].
> *
> * 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.
> *
> + * @parent: resource tree root to search
> * @start: start address of the resource searched for
> * @end: end address of same resource
> * @flags: flags which the resource must have
> @@ -337,9 +338,9 @@ static bool is_type_match(struct resource *p, unsigned long flags, unsigned long
> * The caller must specify @start, @end, @flags, and @desc
> * (which may be IORES_DESC_NONE).
> */
> -static int find_next_iomem_res(resource_size_t start, resource_size_t end,
> - unsigned long flags, unsigned long desc,
> - struct resource *res)
> +static int find_next_res(struct resource *parent, resource_size_t start,
> + resource_size_t end, unsigned long flags,
> + unsigned long desc, struct resource *res)
> {
> struct resource *p;
>
> @@ -351,7 +352,7 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end,
>
> read_lock(&resource_lock);
>
> - for_each_resource(&iomem_resource, p, false) {
> + for_each_resource(parent, p, false) {
> /* If we passed the resource we are looking for, stop */
> if (p->start > end) {
> p = NULL;
> @@ -382,16 +383,23 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end,
> return p ? 0 : -ENODEV;
> }
>
> -static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end,
> - unsigned long flags, unsigned long desc,
> - void *arg,
> - int (*func)(struct resource *, void *))
> +static int find_next_iomem_res(resource_size_t start, resource_size_t end,
> + unsigned long flags, unsigned long desc,
> + struct resource *res)
> +{
> + return find_next_res(&iomem_resource, start, end, flags, desc, res);
> +}
> +
> +static int walk_res_desc(struct resource *parent, resource_size_t start,
> + resource_size_t end, unsigned long flags,
> + unsigned long desc, void *arg,
> + int (*func)(struct resource *, void *))
> {
> struct resource res;
> int ret = -EINVAL;
>
> while (start < end &&
> - !find_next_iomem_res(start, end, flags, desc, &res)) {
> + !find_next_res(parent, start, end, flags, desc, &res)) {
> ret = (*func)(&res, arg);
> if (ret)
> break;
> @@ -402,6 +410,15 @@ static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end,
> return ret;
> }
>
> +static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end,
> + unsigned long flags, unsigned long desc,
> + void *arg,
> + int (*func)(struct resource *, void *))
> +{
> + return walk_res_desc(&iomem_resource, start, end, flags, desc, arg, func);
> +}
> +
> +
> /**
> * walk_iomem_res_desc - Walks through iomem resources and calls func()
> * with matching resource ranges.
> @@ -426,6 +443,26 @@ int walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start,
> }
> EXPORT_SYMBOL_GPL(walk_iomem_res_desc);
>
> +#ifdef CONFIG_EFI_SOFT_RESERVE
> +struct resource soft_reserve_resource = {
> + .name = "Soft Reserved",
> + .start = 0,
> + .end = -1,
> + .desc = IORES_DESC_SOFT_RESERVED,
> + .flags = IORESOURCE_MEM,
> +};
> +EXPORT_SYMBOL_GPL(soft_reserve_resource);
> +
> +int walk_soft_reserve_res_desc(unsigned long desc, unsigned long flags,
> + u64 start, u64 end, void *arg,
> + int (*func)(struct resource *, void *))
> +{
> + return walk_res_desc(&soft_reserve_resource, start, end, flags, desc,
> + arg, func);
> +}
> +EXPORT_SYMBOL_GPL(walk_soft_reserve_res_desc);
> +#endif
> +
> /*
> * This function calls the @func callback against all memory ranges of type
> * System RAM which are marked as IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY.
> @@ -648,6 +685,20 @@ int region_intersects(resource_size_t start, size_t size, unsigned long flags,
> }
> EXPORT_SYMBOL_GPL(region_intersects);
>
> +int region_intersects_soft_reserve(resource_size_t start, size_t size,
> + unsigned long flags, unsigned long desc)
Shouldn't this function be implemented uder `#if CONFIG_EFI_SOFT_RESERVE`? Otherwise it may cause compilation failures when the config is disabled.
Thanks
Zhijian
Hi Zhijian,
Sorry for the delay here.
On 8/31/2025 7:59 PM, Zhijian Li (Fujitsu) wrote:
>
>
> On 22/08/2025 11:41, Smita Koralahalli wrote:
>> Insert Soft Reserved memory into a dedicated soft_reserve_resource tree
>> instead of the iomem_resource tree at boot.
>>
>> Publishing Soft Reserved ranges into iomem too early causes conflicts with
>> CXL hotplug and region assembly failure, especially when Soft Reserved
>> overlaps CXL regions.
>>
>> Re-inserting these ranges into iomem will be handled in follow-up patches,
>> after ensuring CXL window publication ordering is stabilized and when the
>> dax_hmem is ready to consume them.
>>
>> This avoids trimming or deleting resources later and provides a cleaner
>> handoff between EFI-defined memory and CXL resource management.
>>
>> Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
>> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
>> ---
>> arch/x86/kernel/e820.c | 2 +-
>> drivers/dax/hmem/device.c | 4 +--
>> drivers/dax/hmem/hmem.c | 8 +++++
>> include/linux/ioport.h | 24 +++++++++++++
>> kernel/resource.c | 73 +++++++++++++++++++++++++++++++++------
>> 5 files changed, 97 insertions(+), 14 deletions(-)
>>
>> diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
>> index c3acbd26408b..aef1ff2cabda 100644
>> --- a/arch/x86/kernel/e820.c
>> +++ b/arch/x86/kernel/e820.c
>> @@ -1153,7 +1153,7 @@ void __init e820__reserve_resources_late(void)
>> res = e820_res;
>> for (i = 0; i < e820_table->nr_entries; i++) {
>> if (!res->parent && res->end)
>> - insert_resource_expand_to_fit(&iomem_resource, res);
>> + insert_resource_late(res);
>> res++;
>> }
>>
>> diff --git a/drivers/dax/hmem/device.c b/drivers/dax/hmem/device.c
>> index f9e1a76a04a9..22732b729017 100644
>> --- a/drivers/dax/hmem/device.c
>> +++ b/drivers/dax/hmem/device.c
>> @@ -83,8 +83,8 @@ static __init int hmem_register_one(struct resource *res, void *data)
>>
>> static __init int hmem_init(void)
>> {
>> - walk_iomem_res_desc(IORES_DESC_SOFT_RESERVED,
>> - IORESOURCE_MEM, 0, -1, NULL, hmem_register_one);
>> + walk_soft_reserve_res_desc(IORES_DESC_SOFT_RESERVED, IORESOURCE_MEM, 0,
>> + -1, NULL, hmem_register_one);
>> return 0;
>> }
>>
>> diff --git a/drivers/dax/hmem/hmem.c b/drivers/dax/hmem/hmem.c
>> index c18451a37e4f..d5b8f06d531e 100644
>> --- a/drivers/dax/hmem/hmem.c
>> +++ b/drivers/dax/hmem/hmem.c
>> @@ -73,10 +73,18 @@ static int hmem_register_device(struct device *host, int target_nid,
>> return 0;
>> }
>>
>> +#ifdef CONFIG_EFI_SOFT_RESERVE
>
>
> Note that dax_kmem currently depends on CONFIG_EFI_SOFT_RESERVED, so this conditional check may be redundant.
Removed in v2.
>
>
>
>> + rc = region_intersects_soft_reserve(res->start, resource_size(res),
>> + IORESOURCE_MEM,
>> + IORES_DESC_SOFT_RESERVED);
>> + if (rc != REGION_INTERSECTS)
>> + return 0;
>> +#else
>> rc = region_intersects(res->start, resource_size(res), IORESOURCE_MEM,
>> IORES_DESC_SOFT_RESERVED);
>> if (rc != REGION_INTERSECTS)
>> return 0;
>> +#endif
>>
>
> Additionally, please add a TODO note here (e.g., "Add soft-reserved memory back to iomem").
Added.
>
>
>> id = memregion_alloc(GFP_KERNEL);
>> if (id < 0) {
>> diff --git a/include/linux/ioport.h b/include/linux/ioport.h
>> index e8b2d6aa4013..889bc4982777 100644
>> --- a/include/linux/ioport.h
>> +++ b/include/linux/ioport.h
>> @@ -232,6 +232,9 @@ struct resource_constraint {
>> /* PC/ISA/whatever - the normal PC address spaces: IO and memory */
>> extern struct resource ioport_resource;
>> extern struct resource iomem_resource;
>> +#ifdef CONFIG_EFI_SOFT_RESERVE
>> +extern struct resource soft_reserve_resource;
>> +#endif
>>
>> extern struct resource *request_resource_conflict(struct resource *root, struct resource *new);
>> extern int request_resource(struct resource *root, struct resource *new);
>> @@ -255,6 +258,22 @@ int adjust_resource(struct resource *res, resource_size_t start,
>> resource_size_t size);
>> resource_size_t resource_alignment(struct resource *res);
>>
>> +
>> +#ifdef CONFIG_EFI_SOFT_RESERVE
>> +static inline void insert_resource_late(struct resource *new)
>> +{
>> + if (new->desc == IORES_DESC_SOFT_RESERVED)
>> + insert_resource_expand_to_fit(&soft_reserve_resource, new);
>> + else
>> + insert_resource_expand_to_fit(&iomem_resource, new);
>> +}
>> +#else
>> +static inline void insert_resource_late(struct resource *new)
>> +{
>> + insert_resource_expand_to_fit(&iomem_resource, new);
>> +}
>> +#endif
>> +
>> /**
>> * resource_set_size - Calculate resource end address from size and start
>> * @res: Resource descriptor
>> @@ -409,6 +428,11 @@ walk_system_ram_res_rev(u64 start, u64 end, void *arg,
>> extern int
>> walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, u64 end,
>> void *arg, int (*func)(struct resource *, void *));
>> +int walk_soft_reserve_res_desc(unsigned long desc, unsigned long flags,
>> + u64 start, u64 end, void *arg,
>> + int (*func)(struct resource *, void *));
>> +int region_intersects_soft_reserve(resource_size_t start, size_t size,
>> + unsigned long flags, unsigned long desc);
>>
>> struct resource *devm_request_free_mem_region(struct device *dev,
>> struct resource *base, unsigned long size);
>> diff --git a/kernel/resource.c b/kernel/resource.c
>> index f9bb5481501a..8479a99441e2 100644
>> --- a/kernel/resource.c
>> +++ b/kernel/resource.c
>> @@ -321,13 +321,14 @@ static bool is_type_match(struct resource *p, unsigned long flags, unsigned long
>> }
>>
>> /**
>> - * find_next_iomem_res - Finds the lowest iomem resource that covers part of
>> - * [@start..@end].
>> + * find_next_res - Finds the lowest resource that covers part of
>> + * [@start..@end].
>> *
>> * 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.
>> *
>> + * @parent: resource tree root to search
>> * @start: start address of the resource searched for
>> * @end: end address of same resource
>> * @flags: flags which the resource must have
>> @@ -337,9 +338,9 @@ static bool is_type_match(struct resource *p, unsigned long flags, unsigned long
>> * The caller must specify @start, @end, @flags, and @desc
>> * (which may be IORES_DESC_NONE).
>> */
>> -static int find_next_iomem_res(resource_size_t start, resource_size_t end,
>> - unsigned long flags, unsigned long desc,
>> - struct resource *res)
>> +static int find_next_res(struct resource *parent, resource_size_t start,
>> + resource_size_t end, unsigned long flags,
>> + unsigned long desc, struct resource *res)
>> {
>> struct resource *p;
>>
>> @@ -351,7 +352,7 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end,
>>
>> read_lock(&resource_lock);
>>
>> - for_each_resource(&iomem_resource, p, false) {
>> + for_each_resource(parent, p, false) {
>> /* If we passed the resource we are looking for, stop */
>> if (p->start > end) {
>> p = NULL;
>> @@ -382,16 +383,23 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end,
>> return p ? 0 : -ENODEV;
>> }
>>
>> -static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end,
>> - unsigned long flags, unsigned long desc,
>> - void *arg,
>> - int (*func)(struct resource *, void *))
>> +static int find_next_iomem_res(resource_size_t start, resource_size_t end,
>> + unsigned long flags, unsigned long desc,
>> + struct resource *res)
>> +{
>> + return find_next_res(&iomem_resource, start, end, flags, desc, res);
>> +}
>> +
>> +static int walk_res_desc(struct resource *parent, resource_size_t start,
>> + resource_size_t end, unsigned long flags,
>> + unsigned long desc, void *arg,
>> + int (*func)(struct resource *, void *))
>> {
>> struct resource res;
>> int ret = -EINVAL;
>>
>> while (start < end &&
>> - !find_next_iomem_res(start, end, flags, desc, &res)) {
>> + !find_next_res(parent, start, end, flags, desc, &res)) {
>> ret = (*func)(&res, arg);
>> if (ret)
>> break;
>> @@ -402,6 +410,15 @@ static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end,
>> return ret;
>> }
>>
>> +static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end,
>> + unsigned long flags, unsigned long desc,
>> + void *arg,
>> + int (*func)(struct resource *, void *))
>> +{
>> + return walk_res_desc(&iomem_resource, start, end, flags, desc, arg, func);
>> +}
>> +
>> +
>> /**
>> * walk_iomem_res_desc - Walks through iomem resources and calls func()
>> * with matching resource ranges.
>> @@ -426,6 +443,26 @@ int walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start,
>> }
>> EXPORT_SYMBOL_GPL(walk_iomem_res_desc);
>>
>> +#ifdef CONFIG_EFI_SOFT_RESERVE
>> +struct resource soft_reserve_resource = {
>> + .name = "Soft Reserved",
>> + .start = 0,
>> + .end = -1,
>> + .desc = IORES_DESC_SOFT_RESERVED,
>> + .flags = IORESOURCE_MEM,
>> +};
>> +EXPORT_SYMBOL_GPL(soft_reserve_resource);
>> +
>> +int walk_soft_reserve_res_desc(unsigned long desc, unsigned long flags,
>> + u64 start, u64 end, void *arg,
>> + int (*func)(struct resource *, void *))
>> +{
>> + return walk_res_desc(&soft_reserve_resource, start, end, flags, desc,
>> + arg, func);
>> +}
>> +EXPORT_SYMBOL_GPL(walk_soft_reserve_res_desc);
>> +#endif
>> +
>> /*
>> * This function calls the @func callback against all memory ranges of type
>> * System RAM which are marked as IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY.
>> @@ -648,6 +685,20 @@ int region_intersects(resource_size_t start, size_t size, unsigned long flags,
>> }
>> EXPORT_SYMBOL_GPL(region_intersects);
>>
>> +int region_intersects_soft_reserve(resource_size_t start, size_t size,
>> + unsigned long flags, unsigned long desc)
>
>
> Shouldn't this function be implemented uder `#if CONFIG_EFI_SOFT_RESERVE`? Otherwise it may cause compilation failures when the config is disabled.
Fixed it.
Thanks
Smita
>
> Thanks
> Zhijian
© 2016 - 2025 Red Hat, Inc.