diff mbox

[v3] KVM: PPC: Book3S HV: Migrate pinned pages out of CMA

Message ID 2e840fe0-40cf-abf0-4fe6-a621ce46ae13@gmail.com (mailing list archive)
State New, archived
Headers show

Commit Message

Education Directorate Sept. 6, 2016, 6:27 a.m. UTC
When PCI Device pass-through is enabled via VFIO, KVM-PPC will
pin pages using get_user_pages_fast(). One of the downsides of
the pinning is that the page could be in CMA region. The CMA
region is used for other allocations like the hash page table.
Ideally we want the pinned pages to be from non CMA region.

This patch (currently only for KVM PPC with VFIO) forcefully
migrates the pages out (huge pages are omitted for the moment).
There are more efficient ways of doing this, but that might
be elaborate and might impact a larger audience beyond just
the kvm ppc implementation.

The magic is in new_iommu_non_cma_page() which allocates the
new page from a non CMA region.

I've tested the patches lightly at my end. The full solution
requires migration of THP pages in the CMA region. That work
will be done incrementally on top of this.

Previous discussion was at
http://permalink.gmane.org/gmane.linux.kernel.mm/136738

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Alexey Kardashevskiy <aik@ozlabs.ru>

Signed-off-by: Balbir Singh <bsingharora@gmail.com>
Acked-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
 arch/powerpc/include/asm/mmu_context.h |  1 +
 arch/powerpc/mm/mmu_context_iommu.c    | 81 ++++++++++++++++++++++++++++++++--
 2 files changed, 78 insertions(+), 4 deletions(-)

Comments

Anshuman Khandual Sept. 6, 2016, 11:54 a.m. UTC | #1
On 09/06/2016 11:57 AM, Balbir Singh wrote:
> 
> When PCI Device pass-through is enabled via VFIO, KVM-PPC will
> pin pages using get_user_pages_fast(). One of the downsides of
> the pinning is that the page could be in CMA region. The CMA
> region is used for other allocations like the hash page table.
> Ideally we want the pinned pages to be from non CMA region.
> 
> This patch (currently only for KVM PPC with VFIO) forcefully
> migrates the pages out (huge pages are omitted for the moment).
> There are more efficient ways of doing this, but that might
> be elaborate and might impact a larger audience beyond just
> the kvm ppc implementation.
> 
> The magic is in new_iommu_non_cma_page() which allocates the
> new page from a non CMA region.
> 
> I've tested the patches lightly at my end. The full solution
> requires migration of THP pages in the CMA region. That work
> will be done incrementally on top of this.
> 
> Previous discussion was at
> http://permalink.gmane.org/gmane.linux.kernel.mm/136738
> 
> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
> Cc: Michael Ellerman <mpe@ellerman.id.au>
> Cc: Paul Mackerras <paulus@ozlabs.org>
> Cc: Alexey Kardashevskiy <aik@ozlabs.ru>
> 
> Signed-off-by: Balbir Singh <bsingharora@gmail.com>
> Acked-by: Alexey Kardashevskiy <aik@ozlabs.ru>
> ---
>  arch/powerpc/include/asm/mmu_context.h |  1 +
>  arch/powerpc/mm/mmu_context_iommu.c    | 81 ++++++++++++++++++++++++++++++++--
>  2 files changed, 78 insertions(+), 4 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
> index 9d2cd0c..475d1be 100644
> --- a/arch/powerpc/include/asm/mmu_context.h
> +++ b/arch/powerpc/include/asm/mmu_context.h
> @@ -18,6 +18,7 @@ extern void destroy_context(struct mm_struct *mm);
>  #ifdef CONFIG_SPAPR_TCE_IOMMU
>  struct mm_iommu_table_group_mem_t;
> 
> +extern int isolate_lru_page(struct page *page);	/* from internal.h */

Small nit, cant we just add "mm/internal.h" header here with full path ?

>  extern bool mm_iommu_preregistered(void);
>  extern long mm_iommu_get(unsigned long ua, unsigned long entries,
>  		struct mm_iommu_table_group_mem_t **pmem);
> diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
> index da6a216..e0f1c33 100644
> --- a/arch/powerpc/mm/mmu_context_iommu.c
> +++ b/arch/powerpc/mm/mmu_context_iommu.c
> @@ -15,6 +15,9 @@
>  #include <linux/rculist.h>
>  #include <linux/vmalloc.h>
>  #include <linux/mutex.h>
> +#include <linux/migrate.h>
> +#include <linux/hugetlb.h>
> +#include <linux/swap.h>
>  #include <asm/mmu_context.h>
> 
>  static DEFINE_MUTEX(mem_list_mutex);
> @@ -72,6 +75,55 @@ bool mm_iommu_preregistered(void)
>  }
>  EXPORT_SYMBOL_GPL(mm_iommu_preregistered);
> 
> +/*
> + * Taken from alloc_migrate_target with changes to remove CMA allocations
> + */
> +struct page *new_iommu_non_cma_page(struct page *page, unsigned long private,
> +					int **resultp)
> +{
> +	gfp_t gfp_mask = GFP_USER;
> +	struct page *new_page;
> +
> +	if (PageHuge(page) || PageTransHuge(page) || PageCompound(page))
> +		return NULL;
> +
> +	if (PageHighMem(page))
> +		gfp_mask |= __GFP_HIGHMEM;
> +
> +	/*
> +	 * We don't want the allocation to force an OOM if possibe
> +	 */
> +	new_page = alloc_page(gfp_mask | __GFP_NORETRY | __GFP_NOWARN);

So what guarantees that the new page too wont come from MIGRATE_CMA
page block ? Is absence of __GFP_MOVABLE flag enough. Also should not
we be checking that migrate type of the new allocated page is indeed
not MIGRATE_CMA ?

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Education Directorate Sept. 6, 2016, 11:53 p.m. UTC | #2
On 06/09/16 21:54, Anshuman Khandual wrote:
> On 09/06/2016 11:57 AM, Balbir Singh wrote:
>>
>> When PCI Device pass-through is enabled via VFIO, KVM-PPC will
>> pin pages using get_user_pages_fast(). One of the downsides of
>> the pinning is that the page could be in CMA region. The CMA
>> region is used for other allocations like the hash page table.
>> Ideally we want the pinned pages to be from non CMA region.
>>
>> This patch (currently only for KVM PPC with VFIO) forcefully
>> migrates the pages out (huge pages are omitted for the moment).
>> There are more efficient ways of doing this, but that might
>> be elaborate and might impact a larger audience beyond just
>> the kvm ppc implementation.
>>
>> The magic is in new_iommu_non_cma_page() which allocates the
>> new page from a non CMA region.
>>
>> I've tested the patches lightly at my end. The full solution
>> requires migration of THP pages in the CMA region. That work
>> will be done incrementally on top of this.
>>
>> Previous discussion was at
>> http://permalink.gmane.org/gmane.linux.kernel.mm/136738
>>
>> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
>> Cc: Michael Ellerman <mpe@ellerman.id.au>
>> Cc: Paul Mackerras <paulus@ozlabs.org>
>> Cc: Alexey Kardashevskiy <aik@ozlabs.ru>
>>
>> Signed-off-by: Balbir Singh <bsingharora@gmail.com>
>> Acked-by: Alexey Kardashevskiy <aik@ozlabs.ru>
>> ---
>>  arch/powerpc/include/asm/mmu_context.h |  1 +
>>  arch/powerpc/mm/mmu_context_iommu.c    | 81 ++++++++++++++++++++++++++++++++--
>>  2 files changed, 78 insertions(+), 4 deletions(-)
>>
>> diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
>> index 9d2cd0c..475d1be 100644
>> --- a/arch/powerpc/include/asm/mmu_context.h
>> +++ b/arch/powerpc/include/asm/mmu_context.h
>> @@ -18,6 +18,7 @@ extern void destroy_context(struct mm_struct *mm);
>>  #ifdef CONFIG_SPAPR_TCE_IOMMU
>>  struct mm_iommu_table_group_mem_t;
>>
>> +extern int isolate_lru_page(struct page *page);	/* from internal.h */
> 
> Small nit, cant we just add "mm/internal.h" header here with full path ?
> 

I did not think it was worth including it here

>>  extern bool mm_iommu_preregistered(void);
>>  extern long mm_iommu_get(unsigned long ua, unsigned long entries,
>>  		struct mm_iommu_table_group_mem_t **pmem);
>> diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
>> index da6a216..e0f1c33 100644
>> --- a/arch/powerpc/mm/mmu_context_iommu.c
>> +++ b/arch/powerpc/mm/mmu_context_iommu.c
>> @@ -15,6 +15,9 @@
>>  #include <linux/rculist.h>
>>  #include <linux/vmalloc.h>
>>  #include <linux/mutex.h>
>> +#include <linux/migrate.h>
>> +#include <linux/hugetlb.h>
>> +#include <linux/swap.h>
>>  #include <asm/mmu_context.h>
>>
>>  static DEFINE_MUTEX(mem_list_mutex);
>> @@ -72,6 +75,55 @@ bool mm_iommu_preregistered(void)
>>  }
>>  EXPORT_SYMBOL_GPL(mm_iommu_preregistered);
>>
>> +/*
>> + * Taken from alloc_migrate_target with changes to remove CMA allocations
>> + */
>> +struct page *new_iommu_non_cma_page(struct page *page, unsigned long private,
>> +					int **resultp)
>> +{
>> +	gfp_t gfp_mask = GFP_USER;
>> +	struct page *new_page;
>> +
>> +	if (PageHuge(page) || PageTransHuge(page) || PageCompound(page))
>> +		return NULL;
>> +
>> +	if (PageHighMem(page))
>> +		gfp_mask |= __GFP_HIGHMEM;
>> +
>> +	/*
>> +	 * We don't want the allocation to force an OOM if possibe
>> +	 */
>> +	new_page = alloc_page(gfp_mask | __GFP_NORETRY | __GFP_NOWARN);
> 
> So what guarantees that the new page too wont come from MIGRATE_CMA
> page block ? Is absence of __GFP_MOVABLE flag enough.

I think so, that is what I am relying on and checked for

 Also should not
> we be checking that migrate type of the new allocated page is indeed
> not MIGRATE_CMA ?
> 

I don't think that is required, may be I can do a VM_WARN_ON for debugging

Balbir Singh.
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Michael Ellerman Sept. 29, 2016, 1:13 p.m. UTC | #3
On Tue, 2016-06-09 at 06:27:31 UTC, Balbir Singh wrote:
> When PCI Device pass-through is enabled via VFIO, KVM-PPC will
> pin pages using get_user_pages_fast(). One of the downsides of
> the pinning is that the page could be in CMA region. The CMA
> region is used for other allocations like the hash page table.
> Ideally we want the pinned pages to be from non CMA region.
> 
> This patch (currently only for KVM PPC with VFIO) forcefully
> migrates the pages out (huge pages are omitted for the moment).
> There are more efficient ways of doing this, but that might
> be elaborate and might impact a larger audience beyond just
> the kvm ppc implementation.
> 
> The magic is in new_iommu_non_cma_page() which allocates the
> new page from a non CMA region.
> 
> I've tested the patches lightly at my end. The full solution
> requires migration of THP pages in the CMA region. That work
> will be done incrementally on top of this.
> 
> Signed-off-by: Balbir Singh <bsingharora@gmail.com>
> Acked-by: Alexey Kardashevskiy <aik@ozlabs.ru>

Applied to powerpc next, thanks.

https://git.kernel.org/powerpc/c/2e5bbb5461f138cac631fe21b4ad95

cheers
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 9d2cd0c..475d1be 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -18,6 +18,7 @@  extern void destroy_context(struct mm_struct *mm);
 #ifdef CONFIG_SPAPR_TCE_IOMMU
 struct mm_iommu_table_group_mem_t;
 
+extern int isolate_lru_page(struct page *page);	/* from internal.h */
 extern bool mm_iommu_preregistered(void);
 extern long mm_iommu_get(unsigned long ua, unsigned long entries,
 		struct mm_iommu_table_group_mem_t **pmem);
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index da6a216..e0f1c33 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -15,6 +15,9 @@ 
 #include <linux/rculist.h>
 #include <linux/vmalloc.h>
 #include <linux/mutex.h>
+#include <linux/migrate.h>
+#include <linux/hugetlb.h>
+#include <linux/swap.h>
 #include <asm/mmu_context.h>
 
 static DEFINE_MUTEX(mem_list_mutex);
@@ -72,6 +75,55 @@  bool mm_iommu_preregistered(void)
 }
 EXPORT_SYMBOL_GPL(mm_iommu_preregistered);
 
+/*
+ * Taken from alloc_migrate_target with changes to remove CMA allocations
+ */
+struct page *new_iommu_non_cma_page(struct page *page, unsigned long private,
+					int **resultp)
+{
+	gfp_t gfp_mask = GFP_USER;
+	struct page *new_page;
+
+	if (PageHuge(page) || PageTransHuge(page) || PageCompound(page))
+		return NULL;
+
+	if (PageHighMem(page))
+		gfp_mask |= __GFP_HIGHMEM;
+
+	/*
+	 * We don't want the allocation to force an OOM if possibe
+	 */
+	new_page = alloc_page(gfp_mask | __GFP_NORETRY | __GFP_NOWARN);
+	return new_page;
+}
+
+static int mm_iommu_move_page_from_cma(struct page *page)
+{
+	int ret = 0;
+	LIST_HEAD(cma_migrate_pages);
+
+	/* Ignore huge pages for now */
+	if (PageHuge(page) || PageTransHuge(page) || PageCompound(page))
+		return -EBUSY;
+
+	lru_add_drain();
+	ret = isolate_lru_page(page);
+	if (ret)
+		return ret;
+
+	list_add(&page->lru, &cma_migrate_pages);
+	put_page(page); /* Drop the gup reference */
+
+	ret = migrate_pages(&cma_migrate_pages, new_iommu_non_cma_page,
+				NULL, 0, MIGRATE_SYNC, MR_CMA);
+	if (ret) {
+		if (!list_empty(&cma_migrate_pages))
+			putback_movable_pages(&cma_migrate_pages);
+	}
+
+	return 0;
+}
+
 long mm_iommu_get(unsigned long ua, unsigned long entries,
 		struct mm_iommu_table_group_mem_t **pmem)
 {
@@ -124,15 +176,36 @@  long mm_iommu_get(unsigned long ua, unsigned long entries,
 	for (i = 0; i < entries; ++i) {
 		if (1 != get_user_pages_fast(ua + (i << PAGE_SHIFT),
 					1/* pages */, 1/* iswrite */, &page)) {
+			ret = -EFAULT;
 			for (j = 0; j < i; ++j)
-				put_page(pfn_to_page(
-						mem->hpas[j] >> PAGE_SHIFT));
+				put_page(pfn_to_page(mem->hpas[j] >>
+						PAGE_SHIFT));
 			vfree(mem->hpas);
 			kfree(mem);
-			ret = -EFAULT;
 			goto unlock_exit;
 		}
-
+		/*
+		 * If we get a page from the CMA zone, since we are going to
+		 * be pinning these entries, we might as well move them out
+		 * of the CMA zone if possible. NOTE: faulting in + migration
+		 * can be expensive. Batching can be considered later
+		 */
+		if (get_pageblock_migratetype(page) == MIGRATE_CMA) {
+			if (mm_iommu_move_page_from_cma(page))
+				goto populate;
+			if (1 != get_user_pages_fast(ua + (i << PAGE_SHIFT),
+						1/* pages */, 1/* iswrite */,
+						&page)) {
+				ret = -EFAULT;
+				for (j = 0; j < i; ++j)
+					put_page(pfn_to_page(mem->hpas[j] >>
+								PAGE_SHIFT));
+				vfree(mem->hpas);
+				kfree(mem);
+				goto unlock_exit;
+			}
+		}
+populate:
 		mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
 	}