diff mbox series

[v8,4/4] hugetlb: allow to free gigantic pages regardless of the configuration

Message ID 20190327063626.18421-5-alex@ghiti.fr (mailing list archive)
State New, archived
Headers show
Series Fix free/allocation of runtime gigantic pages | expand

Commit Message

Alexandre Ghiti March 27, 2019, 6:36 a.m. UTC
On systems without CONTIG_ALLOC activated but that support gigantic pages,
boottime reserved gigantic pages can not be freed at all. This patch
simply enables the possibility to hand back those pages to memory
allocator.

Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
Acked-by: David S. Miller <davem@davemloft.net> [sparc]
---
 arch/arm64/Kconfig                           |  2 +-
 arch/arm64/include/asm/hugetlb.h             |  4 --
 arch/powerpc/include/asm/book3s/64/hugetlb.h |  5 +-
 arch/powerpc/platforms/Kconfig.cputype       |  2 +-
 arch/s390/Kconfig                            |  2 +-
 arch/s390/include/asm/hugetlb.h              |  8 +--
 arch/sh/Kconfig                              |  2 +-
 arch/sparc/Kconfig                           |  2 +-
 arch/x86/Kconfig                             |  2 +-
 arch/x86/include/asm/hugetlb.h               |  4 --
 include/asm-generic/hugetlb.h                |  7 +++
 include/linux/gfp.h                          |  2 +-
 mm/hugetlb.c                                 | 54 ++++++++++++++------
 mm/page_alloc.c                              |  4 +-
 14 files changed, 61 insertions(+), 39 deletions(-)

Comments

Aneesh Kumar K.V March 27, 2019, 7:01 a.m. UTC | #1
On 3/27/19 12:06 PM, Alexandre Ghiti wrote:
> On systems without CONTIG_ALLOC activated but that support gigantic pages,
> boottime reserved gigantic pages can not be freed at all. This patch
> simply enables the possibility to hand back those pages to memory
> allocator.
> 
> Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
> Acked-by: David S. Miller <davem@davemloft.net> [sparc]
>
> diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h
> index ec2a55a553c7..7013284f0f1b 100644
> --- a/arch/powerpc/include/asm/book3s/64/hugetlb.h
> +++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h
> @@ -36,8 +36,8 @@ static inline int hstate_get_psize(struct hstate *hstate)
>   	}
>   }
>   
> -#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
> -static inline bool gigantic_page_supported(void)
> +#define __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED
> +static inline bool gigantic_page_runtime_supported(void)
>   {
>   	/*
>   	 * We used gigantic page reservation with hypervisor assist in some case.
> @@ -49,7 +49,6 @@ static inline bool gigantic_page_supported(void)
>   
>   	return true;
>   }
> -#endif
>   
>   /* hugepd entry valid bit */
>   #define HUGEPD_VAL_BITS		(0x8000000000000000UL)

Is that correct when CONTIG_ALLOC is not enabled? I guess we want

gigantic_page_runtime_supported to return false when CONTIG_ALLOC is not 
enabled on all architectures and on POWER when it is enabled we want it 
to be conditional as it is now.

-aneesh
Alexandre Ghiti March 27, 2019, 8:44 a.m. UTC | #2
On 03/27/2019 08:01 AM, Aneesh Kumar K.V wrote:
> On 3/27/19 12:06 PM, Alexandre Ghiti wrote:
>> On systems without CONTIG_ALLOC activated but that support gigantic 
>> pages,
>> boottime reserved gigantic pages can not be freed at all. This patch
>> simply enables the possibility to hand back those pages to memory
>> allocator.
>>
>> Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
>> Acked-by: David S. Miller <davem@davemloft.net> [sparc]
>>
>> diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h 
>> b/arch/powerpc/include/asm/book3s/64/hugetlb.h
>> index ec2a55a553c7..7013284f0f1b 100644
>> --- a/arch/powerpc/include/asm/book3s/64/hugetlb.h
>> +++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h
>> @@ -36,8 +36,8 @@ static inline int hstate_get_psize(struct hstate 
>> *hstate)
>>       }
>>   }
>>   -#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
>> -static inline bool gigantic_page_supported(void)
>> +#define __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED
>> +static inline bool gigantic_page_runtime_supported(void)
>>   {
>>       /*
>>        * We used gigantic page reservation with hypervisor assist in 
>> some case.
>> @@ -49,7 +49,6 @@ static inline bool gigantic_page_supported(void)
>>         return true;
>>   }
>> -#endif
>>     /* hugepd entry valid bit */
>>   #define HUGEPD_VAL_BITS        (0x8000000000000000UL)
>
> Is that correct when CONTIG_ALLOC is not enabled? I guess we want
>
> gigantic_page_runtime_supported to return false when CONTIG_ALLOC is 
> not enabled on all architectures and on POWER when it is enabled we 
> want it to be conditional as it is now.
>
> -aneesh
>

CONFIG_ARCH_HAS_GIGANTIC_PAGE is set by default when an architecture 
supports gigantic
pages: on its own, it allows to allocate boottime gigantic pages AND to 
free them at runtime
(this is the goal of this series), but not to allocate runtime gigantic 
pages.
If CONTIG_ALLOC is set, it allows in addition to allocate runtime 
gigantic pages.

I re-introduced the runtime checks because we can't know at compile time 
if powerpc can
or not support gigantic pages.

So for all architectures, gigantic_page_runtime_supported only depends on
CONFIG_ARCH_HAS_GIGANTIC_PAGE enabled or not. The possibility to 
allocate runtime
gigantic pages is dealt with after those runtime checks.

By the way, I forgot to ask you why you think that if an arch cannot 
allocate runtime gigantic
pages, it should not be able to free boottime gigantic pages ?
Aneesh Kumar K.V March 27, 2019, 8:55 a.m. UTC | #3
On 3/27/19 2:14 PM, Alexandre Ghiti wrote:
> 
> 
> On 03/27/2019 08:01 AM, Aneesh Kumar K.V wrote:
>> On 3/27/19 12:06 PM, Alexandre Ghiti wrote:
>>> On systems without CONTIG_ALLOC activated but that support gigantic 
>>> pages,
>>> boottime reserved gigantic pages can not be freed at all. This patch
>>> simply enables the possibility to hand back those pages to memory
>>> allocator.
>>>
>>> Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
>>> Acked-by: David S. Miller <davem@davemloft.net> [sparc]
>>>
>>> diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h 
>>> b/arch/powerpc/include/asm/book3s/64/hugetlb.h
>>> index ec2a55a553c7..7013284f0f1b 100644
>>> --- a/arch/powerpc/include/asm/book3s/64/hugetlb.h
>>> +++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h
>>> @@ -36,8 +36,8 @@ static inline int hstate_get_psize(struct hstate 
>>> *hstate)
>>>       }
>>>   }
>>>   -#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
>>> -static inline bool gigantic_page_supported(void)
>>> +#define __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED
>>> +static inline bool gigantic_page_runtime_supported(void)
>>>   {
>>>       /*
>>>        * We used gigantic page reservation with hypervisor assist in 
>>> some case.
>>> @@ -49,7 +49,6 @@ static inline bool gigantic_page_supported(void)
>>>         return true;
>>>   }
>>> -#endif
>>>     /* hugepd entry valid bit */
>>>   #define HUGEPD_VAL_BITS        (0x8000000000000000UL)
>>
>> Is that correct when CONTIG_ALLOC is not enabled? I guess we want
>>
>> gigantic_page_runtime_supported to return false when CONTIG_ALLOC is 
>> not enabled on all architectures and on POWER when it is enabled we 
>> want it to be conditional as it is now.
>>
>> -aneesh
>>
> 
> CONFIG_ARCH_HAS_GIGANTIC_PAGE is set by default when an architecture 
> supports gigantic
> pages: on its own, it allows to allocate boottime gigantic pages AND to 
> free them at runtime
> (this is the goal of this series), but not to allocate runtime gigantic 
> pages.
> If CONTIG_ALLOC is set, it allows in addition to allocate runtime 
> gigantic pages.
> 
> I re-introduced the runtime checks because we can't know at compile time 
> if powerpc can
> or not support gigantic pages.
> 
> So for all architectures, gigantic_page_runtime_supported only depends on
> CONFIG_ARCH_HAS_GIGANTIC_PAGE enabled or not. The possibility to 
> allocate runtime
> gigantic pages is dealt with after those runtime checks.
> 

you removed that #ifdef in the patch above. ie we had
#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
static inline bool gigantic_page_supported(void)
{
	/*
	 * We used gigantic page reservation with hypervisor assist in some case.
	 * We cannot use runtime allocation of gigantic pages in those platforms
	 * This is hash translation mode LPARs.
	 */
	if (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled())
		return false;

	return true;
}
#endif


This is now
#define __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED
static inline bool gigantic_page_runtime_supported(void)
{
if (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled())
		return false;

	return true;
}


I am wondering whether it should be

#define __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED
static inline bool gigantic_page_runtime_supported(void)
{

    if (!IS_ENABLED(CONFIG_CONTIG_ALLOC))
		return false;

if (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled())
		return false;

	return true;
}

or add that #ifdef back.

> By the way, I forgot to ask you why you think that if an arch cannot 
> allocate runtime gigantic
> pages, it should not be able to free boottime gigantic pages ?
> 

on virtualized platforms like powervm which use a paravirtualized page 
table update mechanism (we dont' have two level table). The ability to 
map a page huge depends on how hypervisor allocated the guest ram. 
Hypervisor also allocates the guest specific page table of a specific 
size depending on how many pages are going to be mapped by what page size.

on POWER we indicate possible guest real address that can be mapped via 
hugepage (in this case 16G) using a device tree node 
(ibm,expected#pages) . It is expected that we will map these pages only 
as 16G pages. Hence we cannot free them back to the buddy where it could 
get mapped via 64K page size.

-aneesh
Alexandre Ghiti March 27, 2019, 9:48 a.m. UTC | #4
On 03/27/2019 09:55 AM, Aneesh Kumar K.V wrote:
> On 3/27/19 2:14 PM, Alexandre Ghiti wrote:
>>
>>
>> On 03/27/2019 08:01 AM, Aneesh Kumar K.V wrote:
>>> On 3/27/19 12:06 PM, Alexandre Ghiti wrote:
>>>> On systems without CONTIG_ALLOC activated but that support gigantic 
>>>> pages,
>>>> boottime reserved gigantic pages can not be freed at all. This patch
>>>> simply enables the possibility to hand back those pages to memory
>>>> allocator.
>>>>
>>>> Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
>>>> Acked-by: David S. Miller <davem@davemloft.net> [sparc]
>>>>
>>>> diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h 
>>>> b/arch/powerpc/include/asm/book3s/64/hugetlb.h
>>>> index ec2a55a553c7..7013284f0f1b 100644
>>>> --- a/arch/powerpc/include/asm/book3s/64/hugetlb.h
>>>> +++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h
>>>> @@ -36,8 +36,8 @@ static inline int hstate_get_psize(struct hstate 
>>>> *hstate)
>>>>       }
>>>>   }
>>>>   -#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
>>>> -static inline bool gigantic_page_supported(void)
>>>> +#define __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED
>>>> +static inline bool gigantic_page_runtime_supported(void)
>>>>   {
>>>>       /*
>>>>        * We used gigantic page reservation with hypervisor assist 
>>>> in some case.
>>>> @@ -49,7 +49,6 @@ static inline bool gigantic_page_supported(void)
>>>>         return true;
>>>>   }
>>>> -#endif
>>>>     /* hugepd entry valid bit */
>>>>   #define HUGEPD_VAL_BITS        (0x8000000000000000UL)
>>>
>>> Is that correct when CONTIG_ALLOC is not enabled? I guess we want
>>>
>>> gigantic_page_runtime_supported to return false when CONTIG_ALLOC is 
>>> not enabled on all architectures and on POWER when it is enabled we 
>>> want it to be conditional as it is now.
>>>
>>> -aneesh
>>>
>>
>> CONFIG_ARCH_HAS_GIGANTIC_PAGE is set by default when an architecture 
>> supports gigantic
>> pages: on its own, it allows to allocate boottime gigantic pages AND 
>> to free them at runtime
>> (this is the goal of this series), but not to allocate runtime 
>> gigantic pages.
>> If CONTIG_ALLOC is set, it allows in addition to allocate runtime 
>> gigantic pages.
>>
>> I re-introduced the runtime checks because we can't know at compile 
>> time if powerpc can
>> or not support gigantic pages.
>>
>> So for all architectures, gigantic_page_runtime_supported only 
>> depends on
>> CONFIG_ARCH_HAS_GIGANTIC_PAGE enabled or not. The possibility to 
>> allocate runtime
>> gigantic pages is dealt with after those runtime checks.
>>
>
> you removed that #ifdef in the patch above. ie we had
> #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
> static inline bool gigantic_page_supported(void)
> {
>     /*
>      * We used gigantic page reservation with hypervisor assist in 
> some case.
>      * We cannot use runtime allocation of gigantic pages in those 
> platforms
>      * This is hash translation mode LPARs.
>      */
>     if (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled())
>         return false;
>
>     return true;
> }
> #endif

Yes, I removed the #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE because it was 
defined only
if CONTIG_ALLOC was set. But now, CONFIG_ARCH_HAS_GIGANTIC_PAGE is 
inconditionally
set for powerpc so I think we don't need it anymore.
Actually I have doubts now, is this true for all configurations ? I see 
that it is only set for
PPC_RADIX_MMU. I think the problem is here: instead of returning true, 
it should do like
the generic version, ie return IS_ENABLED(CONFIG_ARCH_HAS_GIGANTIC_PAGE).
Do you agree ?

>
>
> This is now
> #define __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED
> static inline bool gigantic_page_runtime_supported(void)
> {
> if (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled())
>         return false;
>
>     return true;
> }
>
>
> I am wondering whether it should be
>
> #define __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED
> static inline bool gigantic_page_runtime_supported(void)
> {
>
>    if (!IS_ENABLED(CONFIG_CONTIG_ALLOC))
>         return false;

I don't think this test should happen here, CONFIG_CONTIG_ALLOC only allows
to allocate gigantic pages, doing that check here would prevent powerpc
to free boottime gigantic pages when not a guest. Note that this check
is actually done in set_max_huge_pages.


>
> if (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled())
>         return false;

Maybe I did not understand this check: I understood that, in the case 
the system
is virtualized, we do not want it to hand back gigantic pages. Does this 
check
test if the system is currently being virtualized ?
If yes, I think the patch is correct: it prevents freeing gigantic pages 
when the system
is virtualized but allows a 'normal' system to free gigantic pages.


>
>     return true;
> }
>
> or add that #ifdef back.
>
>> By the way, I forgot to ask you why you think that if an arch cannot 
>> allocate runtime gigantic
>> pages, it should not be able to free boottime gigantic pages ?
>>
>
> on virtualized platforms like powervm which use a paravirtualized page 
> table update mechanism (we dont' have two level table). The ability to 
> map a page huge depends on how hypervisor allocated the guest ram. 
> Hypervisor also allocates the guest specific page table of a specific 
> size depending on how many pages are going to be mapped by what page 
> size.
>
> on POWER we indicate possible guest real address that can be mapped 
> via hugepage (in this case 16G) using a device tree node 
> (ibm,expected#pages) . It is expected that we will map these pages 
> only as 16G pages. Hence we cannot free them back to the buddy where 
> it could get mapped via 64K page size.

Thanks for the explanations.

Alex
>
> -aneesh
>
>
Aneesh Kumar K.V March 27, 2019, 10:05 a.m. UTC | #5
Alexandre Ghiti <alex@ghiti.fr> writes:

> On 03/27/2019 09:55 AM, Aneesh Kumar K.V wrote:
>> On 3/27/19 2:14 PM, Alexandre Ghiti wrote:
>>>
>>>
>>> On 03/27/2019 08:01 AM, Aneesh Kumar K.V wrote:
>>>> On 3/27/19 12:06 PM, Alexandre Ghiti wrote:
>

.....

>>
>> This is now
>> #define __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED
>> static inline bool gigantic_page_runtime_supported(void)
>> {
>> if (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled())
>>         return false;
>>
>>     return true;
>> }
>>
>>
>> I am wondering whether it should be
>>
>> #define __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED
>> static inline bool gigantic_page_runtime_supported(void)
>> {
>>
>>    if (!IS_ENABLED(CONFIG_CONTIG_ALLOC))
>>         return false;
>
> I don't think this test should happen here, CONFIG_CONTIG_ALLOC only allows
> to allocate gigantic pages, doing that check here would prevent powerpc
> to free boottime gigantic pages when not a guest. Note that this check
> is actually done in set_max_huge_pages.
>
>
>>
>> if (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled())
>>         return false;
>
> Maybe I did not understand this check: I understood that, in the case 
> the system
> is virtualized, we do not want it to hand back gigantic pages. Does this 
> check
> test if the system is currently being virtualized ?
> If yes, I think the patch is correct: it prevents freeing gigantic pages 
> when the system
> is virtualized but allows a 'normal' system to free gigantic pages.
>
>
>>

Ok double checked the patch applying the the tree. I got confused by the
removal of that #ifdef. So we now disallow the runtime free by checking
for gigantic_page_runtime_supported() in  __nr_hugepages_store_common.
Now if we allow and if CONFIG_CONTIG_ALLOC is disabled, we still should
allow to free the boot time allocated pages back to buddy.

The patch looks good. You can add for the series

Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>

-aneesh
Alexandre Ghiti March 27, 2019, 12:54 p.m. UTC | #6
On 03/27/2019 11:05 AM, Aneesh Kumar K.V wrote:
> Alexandre Ghiti <alex@ghiti.fr> writes:
>
>> On 03/27/2019 09:55 AM, Aneesh Kumar K.V wrote:
>>> On 3/27/19 2:14 PM, Alexandre Ghiti wrote:
>>>>
>>>> On 03/27/2019 08:01 AM, Aneesh Kumar K.V wrote:
>>>>> On 3/27/19 12:06 PM, Alexandre Ghiti wrote:
> .....
>
>>> This is now
>>> #define __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED
>>> static inline bool gigantic_page_runtime_supported(void)
>>> {
>>> if (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled())
>>>          return false;
>>>
>>>      return true;
>>> }
>>>
>>>
>>> I am wondering whether it should be
>>>
>>> #define __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED
>>> static inline bool gigantic_page_runtime_supported(void)
>>> {
>>>
>>>     if (!IS_ENABLED(CONFIG_CONTIG_ALLOC))
>>>          return false;
>> I don't think this test should happen here, CONFIG_CONTIG_ALLOC only allows
>> to allocate gigantic pages, doing that check here would prevent powerpc
>> to free boottime gigantic pages when not a guest. Note that this check
>> is actually done in set_max_huge_pages.
>>
>>
>>> if (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled())
>>>          return false;
>> Maybe I did not understand this check: I understood that, in the case
>> the system
>> is virtualized, we do not want it to hand back gigantic pages. Does this
>> check
>> test if the system is currently being virtualized ?
>> If yes, I think the patch is correct: it prevents freeing gigantic pages
>> when the system
>> is virtualized but allows a 'normal' system to free gigantic pages.
>>
>>
> Ok double checked the patch applying the the tree. I got confused by the
> removal of that #ifdef. So we now disallow the runtime free by checking
> for gigantic_page_runtime_supported() in  __nr_hugepages_store_common.
> Now if we allow and if CONFIG_CONTIG_ALLOC is disabled, we still should
> allow to free the boot time allocated pages back to buddy.
>
> The patch looks good. You can add for the series
>
> Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
>
> -aneesh
>

Thanks for your time Aneesh,

Alex
Mike Kravetz March 28, 2019, 8:43 p.m. UTC | #7
On 3/26/19 11:36 PM, Alexandre Ghiti wrote:
> On systems without CONTIG_ALLOC activated but that support gigantic pages,
> boottime reserved gigantic pages can not be freed at all. This patch
> simply enables the possibility to hand back those pages to memory
> allocator.
> 
> Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
> Acked-by: David S. Miller <davem@davemloft.net> [sparc]

Thanks for all the updates

Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Alexandre Ghiti March 29, 2019, 6:54 a.m. UTC | #8
On 3/28/19 4:43 PM, Mike Kravetz wrote:
> On 3/26/19 11:36 PM, Alexandre Ghiti wrote:
>> On systems without CONTIG_ALLOC activated but that support gigantic pages,
>> boottime reserved gigantic pages can not be freed at all. This patch
>> simply enables the possibility to hand back those pages to memory
>> allocator.
>>
>> Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
>> Acked-by: David S. Miller <davem@davemloft.net> [sparc]
> Thanks for all the updates
>
> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>

Thanks for all your reviews :)

Alex
diff mbox series

Patch

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index a8380629cb3f..d33c6a7b9fc5 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -18,7 +18,7 @@  config ARM64
 	select ARCH_HAS_FAST_MULTIPLIER
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
-	select ARCH_HAS_GIGANTIC_PAGE if CONTIG_ALLOC
+	select ARCH_HAS_GIGANTIC_PAGE
 	select ARCH_HAS_KCOV
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_PTE_SPECIAL
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index c6a07a3b433e..4aad6382f631 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -70,8 +70,4 @@  extern void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #include <asm-generic/hugetlb.h>
 
-#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
-static inline bool gigantic_page_supported(void) { return true; }
-#endif
-
 #endif /* __ASM_HUGETLB_H */
diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h
index ec2a55a553c7..7013284f0f1b 100644
--- a/arch/powerpc/include/asm/book3s/64/hugetlb.h
+++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h
@@ -36,8 +36,8 @@  static inline int hstate_get_psize(struct hstate *hstate)
 	}
 }
 
-#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
-static inline bool gigantic_page_supported(void)
+#define __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED
+static inline bool gigantic_page_runtime_supported(void)
 {
 	/*
 	 * We used gigantic page reservation with hypervisor assist in some case.
@@ -49,7 +49,6 @@  static inline bool gigantic_page_supported(void)
 
 	return true;
 }
-#endif
 
 /* hugepd entry valid bit */
 #define HUGEPD_VAL_BITS		(0x8000000000000000UL)
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index eb0f592cde69..03ca91439473 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -325,7 +325,7 @@  config ARCH_ENABLE_SPLIT_PMD_PTLOCK
 config PPC_RADIX_MMU
 	bool "Radix MMU Support"
 	depends on PPC_BOOK3S_64
-	select ARCH_HAS_GIGANTIC_PAGE if CONTIG_ALLOC
+	select ARCH_HAS_GIGANTIC_PAGE
 	default y
 	help
 	  Enable support for the Power ISA 3.0 Radix style MMU. Currently this
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 1c8cb55b4e5d..5a9cc12c32c6 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -69,7 +69,7 @@  config S390
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
-	select ARCH_HAS_GIGANTIC_PAGE if CONTIG_ALLOC
+	select ARCH_HAS_GIGANTIC_PAGE
 	select ARCH_HAS_KCOV
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SET_MEMORY
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index 2d1afa58a4b6..bb59dd964590 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -116,7 +116,9 @@  static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot)
 	return pte_modify(pte, newprot);
 }
 
-#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
-static inline bool gigantic_page_supported(void) { return true; }
-#endif
+static inline bool gigantic_page_runtime_supported(void)
+{
+	return true;
+}
+
 #endif /* _ASM_S390_HUGETLB_H */
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 67931bdaf32f..6d3db745ab7c 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -53,7 +53,7 @@  config SUPERH
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_NMI
 	select NEED_SG_DMA_LENGTH
-	select ARCH_HAS_GIGANTIC_PAGE if CONTIG_ALLOC
+	select ARCH_HAS_GIGANTIC_PAGE
 
 	help
 	  The SuperH is a RISC processor targeted for use in embedded systems
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 52193cfb0f32..98f8dd663fd8 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -91,7 +91,7 @@  config SPARC64
 	select ARCH_CLOCKSOURCE_DATA
 	select ARCH_HAS_PTE_SPECIAL
 	select PCI_DOMAINS if PCI
-	select ARCH_HAS_GIGANTIC_PAGE if CONTIG_ALLOC
+	select ARCH_HAS_GIGANTIC_PAGE
 
 config ARCH_DEFCONFIG
 	string
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 749bab313dc1..1b7584d17a5a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -21,7 +21,7 @@  config X86_64
 	def_bool y
 	depends on 64BIT
 	# Options that are inherently 64-bit kernel only:
-	select ARCH_HAS_GIGANTIC_PAGE if CONTIG_ALLOC
+	select ARCH_HAS_GIGANTIC_PAGE
 	select ARCH_SUPPORTS_INT128
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select HAVE_ARCH_SOFT_DIRTY
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index 7469d321f072..f65cfb48cfdd 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -17,8 +17,4 @@  static inline void arch_clear_hugepage_flags(struct page *page)
 {
 }
 
-#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
-static inline bool gigantic_page_supported(void) { return true; }
-#endif
-
 #endif /* _ASM_X86_HUGETLB_H */
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index 71d7b77eea50..822f433ac95c 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -126,4 +126,11 @@  static inline pte_t huge_ptep_get(pte_t *ptep)
 }
 #endif
 
+#ifndef __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED
+static inline bool gigantic_page_runtime_supported(void)
+{
+	return IS_ENABLED(CONFIG_ARCH_HAS_GIGANTIC_PAGE);
+}
+#endif /* __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED */
+
 #endif /* _ASM_GENERIC_HUGETLB_H */
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index e77ab30e9328..fb07b503dc45 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -589,8 +589,8 @@  static inline bool pm_suspended_storage(void)
 /* The below functions must be run on a range from a single zone. */
 extern int alloc_contig_range(unsigned long start, unsigned long end,
 			      unsigned migratetype, gfp_t gfp_mask);
-extern void free_contig_range(unsigned long pfn, unsigned nr_pages);
 #endif
+void free_contig_range(unsigned long pfn, unsigned int nr_pages);
 
 #ifdef CONFIG_CMA
 /* CMA stuff */
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 97b1e0290c66..f3e84c1bef11 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1059,6 +1059,7 @@  static void free_gigantic_page(struct page *page, unsigned int order)
 	free_contig_range(page_to_pfn(page), 1 << order);
 }
 
+#ifdef CONFIG_CONTIG_ALLOC
 static int __alloc_gigantic_page(unsigned long start_pfn,
 				unsigned long nr_pages, gfp_t gfp_mask)
 {
@@ -1143,11 +1144,20 @@  static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
 
 static void prep_new_huge_page(struct hstate *h, struct page *page, int nid);
 static void prep_compound_gigantic_page(struct page *page, unsigned int order);
+#else /* !CONFIG_CONTIG_ALLOC */
+static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
+					int nid, nodemask_t *nodemask)
+{
+	return NULL;
+}
+#endif /* CONFIG_CONTIG_ALLOC */
 
 #else /* !CONFIG_ARCH_HAS_GIGANTIC_PAGE */
-static inline bool gigantic_page_supported(void) { return false; }
 static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
-		int nid, nodemask_t *nodemask) { return NULL; }
+					int nid, nodemask_t *nodemask)
+{
+	return NULL;
+}
 static inline void free_gigantic_page(struct page *page, unsigned int order) { }
 static inline void destroy_compound_gigantic_page(struct page *page,
 						unsigned int order) { }
@@ -1157,7 +1167,7 @@  static void update_and_free_page(struct hstate *h, struct page *page)
 {
 	int i;
 
-	if (hstate_is_gigantic(h) && !gigantic_page_supported())
+	if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
 		return;
 
 	h->nr_huge_pages--;
@@ -2277,13 +2287,27 @@  static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed,
 }
 
 #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
-static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
-						nodemask_t *nodes_allowed)
+static int set_max_huge_pages(struct hstate *h, unsigned long count,
+			      nodemask_t *nodes_allowed)
 {
 	unsigned long min_count, ret;
 
-	if (hstate_is_gigantic(h) && !gigantic_page_supported())
-		return h->max_huge_pages;
+	spin_lock(&hugetlb_lock);
+
+	/*
+	 * Gigantic pages runtime allocation depend on the capability for large
+	 * page range allocation.
+	 * If the system does not provide this feature, return an error when
+	 * the user tries to allocate gigantic pages but let the user free the
+	 * boottime allocated gigantic pages.
+	 */
+	if (hstate_is_gigantic(h) && !IS_ENABLED(CONFIG_CONTIG_ALLOC)) {
+		if (count > persistent_huge_pages(h)) {
+			spin_unlock(&hugetlb_lock);
+			return -EINVAL;
+		}
+		/* Fall through to decrease pool */
+	}
 
 	/*
 	 * Increase the pool size
@@ -2296,7 +2320,6 @@  static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
 	 * pool might be one hugepage larger than it needs to be, but
 	 * within all the constraints specified by the sysctls.
 	 */
-	spin_lock(&hugetlb_lock);
 	while (h->surplus_huge_pages && count > persistent_huge_pages(h)) {
 		if (!adjust_pool_surplus(h, nodes_allowed, -1))
 			break;
@@ -2351,9 +2374,10 @@  static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
 			break;
 	}
 out:
-	ret = persistent_huge_pages(h);
+	h->max_huge_pages = persistent_huge_pages(h);
 	spin_unlock(&hugetlb_lock);
-	return ret;
+
+	return 0;
 }
 
 #define HSTATE_ATTR_RO(_name) \
@@ -2405,7 +2429,7 @@  static ssize_t __nr_hugepages_store_common(bool obey_mempolicy,
 	int err;
 	NODEMASK_ALLOC(nodemask_t, nodes_allowed, GFP_KERNEL | __GFP_NORETRY);
 
-	if (hstate_is_gigantic(h) && !gigantic_page_supported()) {
+	if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) {
 		err = -EINVAL;
 		goto out;
 	}
@@ -2429,15 +2453,13 @@  static ssize_t __nr_hugepages_store_common(bool obey_mempolicy,
 	} else
 		nodes_allowed = &node_states[N_MEMORY];
 
-	h->max_huge_pages = set_max_huge_pages(h, count, nodes_allowed);
+	err = set_max_huge_pages(h, count, nodes_allowed);
 
+out:
 	if (nodes_allowed != &node_states[N_MEMORY])
 		NODEMASK_FREE(nodes_allowed);
 
-	return len;
-out:
-	NODEMASK_FREE(nodes_allowed);
-	return err;
+	return err ? err : len;
 }
 
 static ssize_t nr_hugepages_store_common(bool obey_mempolicy,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ecb115a74a9d..cad000879f14 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -8318,8 +8318,9 @@  int alloc_contig_range(unsigned long start, unsigned long end,
 				pfn_max_align_up(end), migratetype);
 	return ret;
 }
+#endif /* CONFIG_CONTIG_ALLOC */
 
-void free_contig_range(unsigned long pfn, unsigned nr_pages)
+void free_contig_range(unsigned long pfn, unsigned int nr_pages)
 {
 	unsigned int count = 0;
 
@@ -8331,7 +8332,6 @@  void free_contig_range(unsigned long pfn, unsigned nr_pages)
 	}
 	WARN(count != 0, "%d pages are still in use!\n", count);
 }
-#endif
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 /*