Skip to contentSkip to conversation

Implement Eager Page Splitting for ARM

PATCH Applied Ricardo Koller 2 participants 14 messages Apr 26, 2023 – May 16, 2023

Subsystems (4)
lore
Share & tools
lore
#0 lore raw

v8 cover Implement Eager Page Splitting for ARM

Eager Page Splitting improves the performance of dirty-logging (used in live migrations) when guest memory is backed by huge-pages. It's an optimization used in Google Cloud since 2016 on x86, and for the last couple of months on ARM.

Background and motivation
=========================
Dirty logging is typically used for live-migration iterative copying. KVM implements dirty-logging at the PAGE_SIZE granularity (will refer to 4K pages from now on). It does it by faulting on write-protected 4K pages. Therefore, enabling dirty-logging on a huge-page requires breaking it into 4K pages in the first place. KVM does this breaking on fault, and because it's in the critical path it only maps the 4K page that faulted; every other 4K page is left unmapped. This is not great for performance on ARM for a couple of reasons:

- Splitting on fault can halt vcpus for milliseconds in some implementations. Splitting a block PTE requires using a broadcasted TLB invalidation (TLBI) for every huge-page (due to the break-before-make requirement). Note that x86 doesn't need this. We observed some implementations that take millliseconds to complete broadcasted TLBIs when done in parallel from multiple vcpus. And that's exactly what happens when doing it on fault: multiple vcpus fault at the same time triggering TLBIs in parallel.

- Read intensive guest workloads end up paying for dirty-logging. Only mapping the faulting 4K page means that all the other pages that were part of the huge-page will now be unmapped. The effect is that any access, including reads, now has to fault.

Eager Page Splitting (on ARM)
=============================
Eager Page Splitting fixes the above two issues by eagerly splitting huge-pages when enabling dirty logging. The goal is to avoid doing it while faulting on write-protected pages. This is what the TDP MMU does for x86 [0], except that x86 does it for different reasons: to avoid grabbing the MMU lock on fault. Note that taking care of write-protection faults still requires grabbing the MMU lock on ARM, but not on x86 (with the fast_page_fault path).

An additional benefit of eagerly splitting huge-pages is that it can be done in a controlled way (e.g., via an IOCTL). This series provides two knobs for doing it, just like its x86 counterpart: when enabling dirty logging, and when using the KVM_CLEAR_DIRTY_LOG ioctl. The benefit of doing it on KVM_CLEAR_DIRTY_LOG is that this ioctl takes ranges, and not complete memslots like when enabling dirty logging. This means that the cost of splitting (mainly broadcasted TLBIs) can be throttled: split a range, wait for a bit, split another range, etc. The benefits of this approach were presented by Oliver Upton at KVM Forum 2022 [1].

Implementation
==============
Patches 3-4 add a pgtable utility function for splitting huge block
PTEs: kvm_pgtable_stage2_split(). Patches 5-9 add support for eagerly splitting huge-pages when enabling dirty-logging and when using the KVM_CLEAR_DIRTY_LOG ioctl. Note that this is just like what x86 does, and the code is actually based on it. And finally, patch 9:

KVM: arm64: Use local TLBI on permission relaxation

adds support for using local TLBIs instead of broadcasts when doing permission relaxation. This last patch is key to achieving good performance during dirty-logging, as eagerly breaking huge-pages replaces mapping new pages with permission relaxation. Got this patch (indirectly) from Marc Z. and took the liberty of adding a commit message.

Note: this applies on top of 6.3-rc2.

Performance evaluation
======================
The performance benefits were tested using the dirty_log_perf_test selftest with 2M huge-pages.

The first test uses a write-only sequential workload where the stride is 2M instead of 4K [2]. The idea with this experiment is to emulate a random access pattern writing a different huge-page at every access. Observe that the benefit increases with the number of vcpus: up to 5.76x for 152 vcpus. This table shows the guest dirtying time when using the CLEAR ioctl (and KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2):

/dirty_log_perf_test_sparse -s anonymous_hugetlb_2mb -b 1G -v $i -i 3 -m 2

	+-------+----------+------------------+
	| vCPUs | 6.2-rc3  | 6.2-rc3 + series |
	|       |    (ms)  |             (ms) |
	+-------+----------+------------------+
	|    1  |    2.63  |          1.66    |
	|    2  |    2.95  |          1.70    |
	|    4  |    3.21  |          1.71    |
	|    8  |    4.97  |          1.78    |
	|   16  |    9.51  |          1.82    |
	|   32  |   20.15  |          3.03    |
	|   64  |   40.09  |          5.80    |
	|  128  |   80.08  |         12.24    |
	|  152  |  109.81  |         15.14    |
	+-------+----------+------------------+

This secondv test measures the benefit of eager page splitting on read intensive workloads (1 write for every 10 reads). As in the other test, the benefit increases with the number of vcpus, up to 8.82x for 152 vcpus. This table shows the guest dirtying time when using the CLEAR ioctl (and KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2):

./dirty_log_perf_test -s anonymous_hugetlb_2mb -b 1G -v $i -i 3 -m 2 -w 10

	+-------+----------+------------------+
	| vCPUs | 6.2-rc3  | 6.2-rc3 + series |
	|       |   (sec)  |            (sec) |
	+-------+----------+------------------+
	|    1  |    0.65  |          0.07    |
	|    2  |    0.70  |          0.08    |
	|    4  |    0.71  |          0.08    |
	|    8  |    0.72  |          0.08    |
	|   16  |    0.76  |          0.08    |
	|   32  |    1.61  |          0.14    |
	|   64  |    3.46  |          0.30    |
	|  128  |    5.49  |          0.64    |
	|  152  |    6.44  |          0.63    |
	+-------+----------+------------------+

Changes from v7:
https://lore.kernel.org/kvmarm/[email protected]/
- Fixed errors in comments: 64bit, EAGER_PAGE_SPLIT_CHUNK_SIZE. (Gavin)
- Extended some comments in: kvm_pgtable_stage2_create_unlinked(), kvm_arch_commit_memory_region(), kvm_init_stage2_mmu(). (Gavin)
- Added: EXPORT_SYMBOL_GPL(kvm_are_all_memslots_empty). (Gavin)
- Implemented is_power_of_two(s) as IS_ALIGNED(s, s). (Gavin)
- Removed lock(kvm->lock) from kvm_vm_ioctl_enable_cap(). (Reiji)
- kvm_supported_block_sizes() returns u32 instead of u64. (Gavin)
- Collected r-b's from Gavin.

Changes from v6. All based on Marc comments:
https://lore.kernel.org/kvmarm/[email protected]/
- Don't enable eager-splitting by default
- Only accept block sizes as valid CHUNK_SIZE's.
- Export the acceptable block sizes (as a bitmap) in a new capability.
- KVM_PGTABLE_WALK_SKIP_BBM to KVM_PGTABLE_WALK_SKIP_BBM_TLBI
- Moved kvm_pgtable_walk_skip_*() from kvm_pgtable.h to pgtable.c.
- Add unlikely() to kvm_pgtable_walk_skip_*().
- Add check for alignment in kvm_pgtable_stage2_create_unlinked().
- kvm_pgtable_stage2_split() does not take a void *mc anymore, and takes a kvm_mmu_memory_cache struct instead.
- kvm_pgtable_stage2_split() does not take an mc_capacity argument anymore.
- Renamed need_topup_split_page_cache_or_resched().
- Moved lockdep_assert_held_write() to the begginning of their respective functions in mmu.c.
- Removed the cache_capacity arg from need_split_memcache_topup_or_resched()
- Rewording for:
- Replaced all instances of PMD and PUD
- KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE description in api.rst
- multiple function descriptions and comments in mmu.c
- description of kvm_pgtable_stage2_split() and create_unlinked().
- removed "no functional change expected" from all commits.
- improved commit messages for the first 2 and last one (Marc's commit).

Changes from v5:
https://lore.kernel.org/kvmarm/[email protected]/
- fixed message in "Use local TLBI on permission relaxation". (Vladimir)
- s/removed/unlinked in first commit message. (Shaoqin)
- rebased series
- collected r-b's from Shaoqin

Changes from v4:
https://lore.kernel.org/kvmarm/[email protected]/
- nits on some comments (s/removed/unlinked and remove @new). (Shaoqin)

Changes from v3:
https://lore.kernel.org/kvmarm/[email protected]/
- KVM_PGTABLE_WALK_SKIP_CMO to use BIT(5). (Shaoqin)
- Rewritten commit message for "Rename free_unlinked to free_removed" using Oliver's suggestion. (Oliver)
- "un" -> "an" typo. (Shaoqin)
- kvm_pgtable_stage2_create_unlinked() to return a "kvm_pte_t *". (Oliver)
- refactored stage2_block_get_nr_page_tables(). (Oliver)
- /s/bock/block. (Shaoqin)

Changes from v2:
https://lore.kernel.org/kvmarm/[email protected]/
- removed redundant kvm_pte_table() check from split walker function. (Gavin)
- fix compilation of patch 8 by moving some definitions from path 9. (Gavin)
- add comment for kvm_mmu_split_nr_page_tables(). (Gavin)

Changes from v1:
https://lore.kernel.org/kvmarm/[email protected]/
- added a capability to set the eager splitting chunk size. This indirectly sets the number of pages in the cache. It also allows for opting out of this feature. (Oliver, Marc)
- changed kvm_pgtable_stage2_split() to split 1g huge-pages using either 513 or 1 at a time (with a cache of 1). (Oliver, Marc)
- added force_pte arg to kvm_pgtable_stage2_create_removed().
- renamed free_removed to free_unlinked. (Ben and Oliver)
- added KVM_PGTABLE_WALK ctx->flags for skipping BBM and CMO, instead of KVM_PGTABLE_WALK_REMOVED. (Oliver)

Changes from the RFC:
https://lore.kernel.org/kvmarm/[email protected]/
- dropped the changes to split on POST visits. No visible perf benefit.
- changed the kvm_pgtable_stage2_free_removed() implementation to reuse the stage2 mapper.
- dropped the FEAT_BBM changes and optimization. Will send this on a different series.

Thanks,
Ricardo

Marc Zyngier (1):
KVM: arm64: Use local TLBI on permission relaxation

Ricardo Koller (11):
KVM: arm64: Rename free_removed to free_unlinked
KVM: arm64: Add KVM_PGTABLE_WALK flags for skipping CMOs and BBM TLBIs
KVM: arm64: Add helper for creating unlinked stage2 subtrees
KVM: arm64: Export kvm_are_all_memslots_empty()
KVM: arm64: Add KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE
KVM: arm64: Add kvm_pgtable_stage2_split()
KVM: arm64: Refactor kvm_arch_commit_memory_region()
KVM: arm64: Add kvm_uninit_stage2_mmu()
KVM: arm64: Split huge pages when dirty logging is enabled
KVM: arm64: Open-code kvm_mmu_write_protect_pt_masked()
KVM: arm64: Split huge pages during KVM_CLEAR_DIRTY_LOG

 Documentation/virt/kvm/api.rst        |  27 ++++
 arch/arm64/include/asm/kvm_asm.h      |   4 +
 arch/arm64/include/asm/kvm_host.h     |  15 ++
 arch/arm64/include/asm/kvm_mmu.h      |   1 +
 arch/arm64/include/asm/kvm_pgtable.h  |  79 +++++++++-
 arch/arm64/kvm/arm.c                  |  28 ++++
 arch/arm64/kvm/hyp/nvhe/hyp-main.c    |  10 ++
 arch/arm64/kvm/hyp/nvhe/mem_protect.c |   6 +-
 arch/arm64/kvm/hyp/nvhe/tlb.c         |  52 +++++++
 arch/arm64/kvm/hyp/pgtable.c          | 201 +++++++++++++++++++++++--
 arch/arm64/kvm/hyp/vhe/tlb.c          |  32 ++++
 arch/arm64/kvm/mmu.c                  | 207 +++++++++++++++++++++-----
 include/linux/kvm_host.h              |   2 +
 include/uapi/linux/kvm.h              |   2 +
 virt/kvm/kvm_main.c                   |   3 +-
 15 files changed, 612 insertions(+), 57 deletions(-)
Signature · 1 line
2.40.1.495.gc816e09b53d-goog
#1 lore raw

PATCH v8 1/12 KVM: arm64: Rename free_removed to free_unlinked

Normalize on referring to tables outside of an active paging structure as 'unlinked'.

A subsequent change to KVM will add support for building page tables that are not part of an active paging structure. The existing 'removed_table' terminology is quite clunky when applied in this context.

---
 arch/arm64/include/asm/kvm_pgtable.h  |  8 ++++----
 arch/arm64/kvm/hyp/nvhe/mem_protect.c |  6 +++---
 arch/arm64/kvm/hyp/pgtable.c          |  6 +++---
 arch/arm64/kvm/mmu.c                  | 10 +++++-----
 4 files changed, 15 insertions(+), 15 deletions(-)
arch/arm64/include/asm/kvm_pgtable.h +4 -4
index dc3c072e862f1..965fddcd53b8b 100644
@@ -104,7 +104,7 @@ static inline bool kvm_level_supports_block_mapping(u32 level)
  *				allocation is physically contiguous.
  * @free_pages_exact:		Free an exact number of memory pages previously
  *				allocated by zalloc_pages_exact.
- * @free_removed_table:		Free a removed paging structure by unlinking and
+ * @free_unlinked_table:	Free an unlinked paging structure by unlinking and
  *				dropping references.
  * @get_page:			Increment the refcount on a page.
  * @put_page:			Decrement the refcount on a page. When the
@@ -124,7 +124,7 @@ struct kvm_pgtable_mm_ops {
 	void*		(*zalloc_page)(void *arg);
 	void*		(*zalloc_pages_exact)(size_t size);
 	void		(*free_pages_exact)(void *addr, size_t size);
-	void		(*free_removed_table)(void *addr, u32 level);
+	void		(*free_unlinked_table)(void *addr, u32 level);
 	void		(*get_page)(void *addr);
 	void		(*put_page)(void *addr);
 	int		(*page_count)(void *addr);
@@ -441,7 +441,7 @@ int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
 void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
 
 /**
- * kvm_pgtable_stage2_free_removed() - Free a removed stage-2 paging structure.
+ * kvm_pgtable_stage2_free_unlinked() - Free an unlinked stage-2 paging structure.
  * @mm_ops:	Memory management callbacks.
  * @pgtable:	Unlinked stage-2 paging structure to be freed.
  * @level:	Level of the stage-2 paging structure to be freed.
@@ -449,7 +449,7 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
  * The page-table is assumed to be unreachable by any hardware walkers prior to
  * freeing and therefore no TLB invalidation is performed.
  */
-void kvm_pgtable_stage2_free_removed(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level);
+void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level);
 
 /**
  * kvm_pgtable_stage2_map() - Install a mapping in a guest stage-2 page-table.
arch/arm64/kvm/hyp/nvhe/mem_protect.c +3 -3
index 2e9ec4a2a4a32..d35e75b13ffe1 100644
@@ -91,9 +91,9 @@ static void host_s2_put_page(void *addr)
 	hyp_put_page(&host_s2_pool, addr);
 }
 
-static void host_s2_free_removed_table(void *addr, u32 level)
+static void host_s2_free_unlinked_table(void *addr, u32 level)
 {
-	kvm_pgtable_stage2_free_removed(&host_mmu.mm_ops, addr, level);
+	kvm_pgtable_stage2_free_unlinked(&host_mmu.mm_ops, addr, level);
 }
 
 static int prepare_s2_pool(void *pgt_pool_base)
@@ -110,7 +110,7 @@ static int prepare_s2_pool(void *pgt_pool_base)
 	host_mmu.mm_ops = (struct kvm_pgtable_mm_ops) {
 		.zalloc_pages_exact = host_s2_zalloc_pages_exact,
 		.zalloc_page = host_s2_zalloc_page,
-		.free_removed_table = host_s2_free_removed_table,
+		.free_unlinked_table = host_s2_free_unlinked_table,
 		.phys_to_virt = hyp_phys_to_virt,
 		.virt_to_phys = hyp_virt_to_phys,
 		.page_count = hyp_page_count,
arch/arm64/kvm/hyp/pgtable.c +3 -3
index 5282cb9ca4cff..1dfbc4848ae52 100644
@@ -883,7 +883,7 @@ static int stage2_map_walk_table_pre(const struct kvm_pgtable_visit_ctx *ctx,
 	if (ret)
 		return ret;
 
-	mm_ops->free_removed_table(childp, ctx->level);
+	mm_ops->free_unlinked_table(childp, ctx->level);
 	return 0;
 }
 
@@ -928,7 +928,7 @@ static int stage2_map_walk_leaf(const struct kvm_pgtable_visit_ctx *ctx,
  * The TABLE_PRE callback runs for table entries on the way down, looking
  * for table entries which we could conceivably replace with a block entry
  * for this mapping. If it finds one it replaces the entry and calls
- * kvm_pgtable_mm_ops::free_removed_table() to tear down the detached table.
+ * kvm_pgtable_mm_ops::free_unlinked_table() to tear down the detached table.
  *
  * Otherwise, the LEAF callback performs the mapping at the existing leaves
  * instead.
@@ -1299,7 +1299,7 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
 	pgt->pgd = NULL;
 }
 
-void kvm_pgtable_stage2_free_removed(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level)
+void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level)
 {
 	kvm_pteref_t ptep = (kvm_pteref_t)pgtable;
 	struct kvm_pgtable_walker walker = {
arch/arm64/kvm/mmu.c +5 -5
index 7113587222ffe..efdaab3f154de 100644
@@ -131,21 +131,21 @@ static void kvm_s2_free_pages_exact(void *virt, size_t size)
 
 static struct kvm_pgtable_mm_ops kvm_s2_mm_ops;
 
-static void stage2_free_removed_table_rcu_cb(struct rcu_head *head)
+static void stage2_free_unlinked_table_rcu_cb(struct rcu_head *head)
 {
 	struct page *page = container_of(head, struct page, rcu_head);
 	void *pgtable = page_to_virt(page);
 	u32 level = page_private(page);
 
-	kvm_pgtable_stage2_free_removed(&kvm_s2_mm_ops, pgtable, level);
+	kvm_pgtable_stage2_free_unlinked(&kvm_s2_mm_ops, pgtable, level);
 }
 
-static void stage2_free_removed_table(void *addr, u32 level)
+static void stage2_free_unlinked_table(void *addr, u32 level)
 {
 	struct page *page = virt_to_page(addr);
 
 	set_page_private(page, (unsigned long)level);
-	call_rcu(&page->rcu_head, stage2_free_removed_table_rcu_cb);
+	call_rcu(&page->rcu_head, stage2_free_unlinked_table_rcu_cb);
 }
 
 static void kvm_host_get_page(void *addr)
@@ -682,7 +682,7 @@ static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = {
 	.zalloc_page		= stage2_memcache_zalloc_page,
 	.zalloc_pages_exact	= kvm_s2_zalloc_pages_exact,
 	.free_pages_exact	= kvm_s2_free_pages_exact,
-	.free_removed_table	= stage2_free_removed_table,
+	.free_unlinked_table	= stage2_free_unlinked_table,
 	.get_page		= kvm_host_get_page,
 	.put_page		= kvm_s2_put_page,
 	.page_count		= kvm_host_page_count,
Signature · 1 line
2.40.1.495.gc816e09b53d-goog
#2 lore raw

PATCH v8 2/12 KVM: arm64: Add KVM_PGTABLE_WALK flags for skipping CMOs and BBM TLBIs

In reply to Ricardo Koller

Add two flags to kvm_pgtable_visit_ctx, KVM_PGTABLE_WALK_SKIP_BBM_TLBI and KVM_PGTABLE_WALK_SKIP_CMO, to indicate that the walk should not perform TLB invalidations (TLBIs) in break-before-make (BBM) nor cache maintenance operations (CMO). This will be used by a future commit to create unlinked tables not accessible to the HW page-table walker.

---
 arch/arm64/include/asm/kvm_pgtable.h |  8 ++++++
 arch/arm64/kvm/hyp/pgtable.c         | 37 +++++++++++++++++++---------
 2 files changed, 34 insertions(+), 11 deletions(-)
arch/arm64/include/asm/kvm_pgtable.h +8 -0
index 965fddcd53b8b..7bbd77e9b7b47 100644
@@ -195,6 +195,12 @@ typedef bool (*kvm_pgtable_force_pte_cb_t)(u64 addr, u64 end,
  *					with other software walkers.
  * @KVM_PGTABLE_WALK_HANDLE_FAULT:	Indicates the page-table walk was
  *					invoked from a fault handler.
+ * @KVM_PGTABLE_WALK_SKIP_BBM_TLBI:	Visit and update table entries
+ *					without Break-before-make's
+ *					TLB invalidation.
+ * @KVM_PGTABLE_WALK_SKIP_CMO:		Visit and update table entries
+ *					without Cache maintenance
+ *					operations required.
  */
 enum kvm_pgtable_walk_flags {
 	KVM_PGTABLE_WALK_LEAF			= BIT(0),
@@ -202,6 +208,8 @@ enum kvm_pgtable_walk_flags {
 	KVM_PGTABLE_WALK_TABLE_POST		= BIT(2),
 	KVM_PGTABLE_WALK_SHARED			= BIT(3),
 	KVM_PGTABLE_WALK_HANDLE_FAULT		= BIT(4),
+	KVM_PGTABLE_WALK_SKIP_BBM_TLBI		= BIT(5),
+	KVM_PGTABLE_WALK_SKIP_CMO		= BIT(6),
 };
 
 struct kvm_pgtable_visit_ctx {
arch/arm64/kvm/hyp/pgtable.c +26 -11
index 1dfbc4848ae52..64c96f9116171 100644
@@ -63,6 +63,16 @@ struct kvm_pgtable_walk_data {
 	const u64			end;
 };
 
+static bool kvm_pgtable_walk_skip_bbm_tlbi(const struct kvm_pgtable_visit_ctx *ctx)
+{
+	return unlikely(ctx->flags & KVM_PGTABLE_WALK_SKIP_BBM_TLBI);
+}
+
+static bool kvm_pgtable_walk_skip_cmo(const struct kvm_pgtable_visit_ctx *ctx)
+{
+	return unlikely(ctx->flags & KVM_PGTABLE_WALK_SKIP_CMO);
+}
+
 static bool kvm_phys_is_valid(u64 phys)
 {
 	return phys < BIT(id_aa64mmfr0_parange_to_phys_shift(ID_AA64MMFR0_EL1_PARANGE_MAX));
@@ -743,14 +753,17 @@ static bool stage2_try_break_pte(const struct kvm_pgtable_visit_ctx *ctx,
 	if (!stage2_try_set_pte(ctx, KVM_INVALID_PTE_LOCKED))
 		return false;
 
-	/*
-	 * Perform the appropriate TLB invalidation based on the evicted pte
-	 * value (if any).
-	 */
-	if (kvm_pte_table(ctx->old, ctx->level))
-		kvm_call_hyp(__kvm_tlb_flush_vmid, mmu);
-	else if (kvm_pte_valid(ctx->old))
-		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, ctx->level);
+	if (!kvm_pgtable_walk_skip_bbm_tlbi(ctx)) {
+		/*
+		 * Perform the appropriate TLB invalidation based on the
+		 * evicted pte value (if any).
+		 */
+		if (kvm_pte_table(ctx->old, ctx->level))
+			kvm_call_hyp(__kvm_tlb_flush_vmid, mmu);
+		else if (kvm_pte_valid(ctx->old))
+			kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu,
+				     ctx->addr, ctx->level);
+	}
 
 	if (stage2_pte_is_counted(ctx->old))
 		mm_ops->put_page(ctx->ptep);
@@ -857,11 +870,13 @@ static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx,
 		return -EAGAIN;
 
 	/* Perform CMOs before installation of the guest stage-2 PTE */
-	if (mm_ops->dcache_clean_inval_poc && stage2_pte_cacheable(pgt, new))
+	if (!kvm_pgtable_walk_skip_cmo(ctx) && mm_ops->dcache_clean_inval_poc &&
+	    stage2_pte_cacheable(pgt, new))
 		mm_ops->dcache_clean_inval_poc(kvm_pte_follow(new, mm_ops),
-						granule);
+					       granule);
 
-	if (mm_ops->icache_inval_pou && stage2_pte_executable(new))
+	if (!kvm_pgtable_walk_skip_cmo(ctx) && mm_ops->icache_inval_pou &&
+	    stage2_pte_executable(new))
 		mm_ops->icache_inval_pou(kvm_pte_follow(new, mm_ops), granule);
 
 	stage2_make_pte(ctx, new);
Signature · 1 line
2.40.1.495.gc816e09b53d-goog
#3 lore raw

PATCH v8 3/12 KVM: arm64: Add helper for creating unlinked stage2 subtrees

In reply to Ricardo Koller

Add a stage2 helper, kvm_pgtable_stage2_create_unlinked(), for creating unlinked tables (which is the opposite of kvm_pgtable_stage2_free_unlinked()). Creating an unlinked table is useful for splitting level 1 and 2 entries into subtrees of PAGE_SIZE PTEs. For example, a level 1 entry can be split into PAGE_SIZE PTEs by first creating a fully populated tree, and then use it to replace the level 1 entry in a single step. This will be used in a subsequent commit for eager huge-page splitting (a dirty-logging optimization).

---
 arch/arm64/include/asm/kvm_pgtable.h | 26 ++++++++++++++
 arch/arm64/kvm/hyp/pgtable.c         | 53 ++++++++++++++++++++++++++++
 2 files changed, 79 insertions(+)
arch/arm64/include/asm/kvm_pgtable.h +26 -0
index 7bbd77e9b7b47..00c8bef4f3ca0 100644
@@ -459,6 +459,32 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
  */
 void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level);
 
+/**
+ * kvm_pgtable_stage2_create_unlinked() - Create an unlinked stage-2 paging structure.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
+ * @phys:	Physical address of the memory to map.
+ * @level:	Starting level of the stage-2 paging structure to be created.
+ * @prot:	Permissions and attributes for the mapping.
+ * @mc:		Cache of pre-allocated and zeroed memory from which to allocate
+ *		page-table pages.
+ * @force_pte:  Force mappings to PAGE_SIZE granularity.
+ *
+ * Returns an unlinked page-table tree.  This new page-table tree is
+ * not reachable (i.e., it is unlinked) from the root pgd and it's
+ * therefore unreachableby the hardware page-table walker. No TLB
+ * invalidation or CMOs are performed.
+ *
+ * If device attributes are not explicitly requested in @prot, then the
+ * mapping will be normal, cacheable.
+ *
+ * Return: The fully populated (unlinked) stage-2 paging structure, or
+ * an ERR_PTR(error) on failure.
+ */
+kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt,
+					      u64 phys, u32 level,
+					      enum kvm_pgtable_prot prot,
+					      void *mc, bool force_pte);
+
 /**
  * kvm_pgtable_stage2_map() - Install a mapping in a guest stage-2 page-table.
  * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
arch/arm64/kvm/hyp/pgtable.c +53 -0

59 lines not on this page · raw message

Signature · 1 line
2.40.1.495.gc816e09b53d-goog
#4 lore raw

PATCH v8 4/12 KVM: arm64: Export kvm_are_all_memslots_empty()

In reply to Ricardo Koller

Export kvm_are_all_memslots_empty(). This will be used by a future commit when checking before setting a capability.

---
 include/linux/kvm_host.h | 2 ++
 virt/kvm/kvm_main.c      | 3 ++-
 2 files changed, 4 insertions(+), 1 deletion(-)
include/linux/kvm_host.h +2 -0
index 8ada23756b0ec..c6fa634f236d9 100644
@@ -990,6 +990,8 @@ static inline bool kvm_memslots_empty(struct kvm_memslots *slots)
 	return RB_EMPTY_ROOT(&slots->gfn_tree);
 }
 
+bool kvm_are_all_memslots_empty(struct kvm *kvm);
+
 #define kvm_for_each_memslot(memslot, bkt, slots)			      \
 	hash_for_each(slots->id_hash, bkt, memslot, id_node[slots->node_idx]) \
 		if (WARN_ON_ONCE(!memslot->npages)) {			      \
virt/kvm/kvm_main.c +2 -1
index d255964ec331e..58074ecd346c9 100644
@@ -4596,7 +4596,7 @@ int __attribute__((weak)) kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 	return -EINVAL;
 }
 
-static bool kvm_are_all_memslots_empty(struct kvm *kvm)
+bool kvm_are_all_memslots_empty(struct kvm *kvm)
 {
 	int i;
 
@@ -4609,6 +4609,7 @@ static bool kvm_are_all_memslots_empty(struct kvm *kvm)
 
 	return true;
 }
+EXPORT_SYMBOL_GPL(kvm_are_all_memslots_empty);
 
 static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
 					   struct kvm_enable_cap *cap)
Signature · 1 line
2.40.1.495.gc816e09b53d-goog
#5 lore raw

PATCH v8 5/12 KVM: arm64: Add KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE

In reply to Ricardo Koller

Add a capability for userspace to specify the eager split chunk size. The chunk size specifies how many pages to break at a time, using a single allocation. Bigger the chunk size, more pages need to be allocated ahead of time.

---
 Documentation/virt/kvm/api.rst       | 27 +++++++++++++++++++++++++++
 arch/arm64/include/asm/kvm_host.h    | 15 +++++++++++++++
 arch/arm64/include/asm/kvm_pgtable.h | 18 ++++++++++++++++++
 arch/arm64/kvm/arm.c                 | 28 ++++++++++++++++++++++++++++
 arch/arm64/kvm/mmu.c                 |  4 ++++
 include/uapi/linux/kvm.h             |  2 ++
 6 files changed, 94 insertions(+)
Documentation/virt/kvm/api.rst +27 -0
index 42403dfe94969..7bf8227bce6b3 100644
@@ -8443,6 +8443,33 @@ structure.
 When getting the Modified Change Topology Report value, the attr->addr
 must point to a byte where the value will be stored or retrieved from.
 
+8.40 KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE
+---------------------------------------
+
+:Capability: KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE
+:Architectures: arm64
+:Type: vm
+:Parameters: arg[0] is the new split chunk size.
+:Returns: 0 on success, -EINVAL if any memslot was already created.
+
+This capability sets the chunk size used in Eager Page Splitting.
+
+Eager Page Splitting improves the performance of dirty-logging (used
+in live migrations) when guest memory is backed by huge-pages.  It
+avoids splitting huge-pages (into PAGE_SIZE pages) on fault, by doing
+it eagerly when enabling dirty logging (with the
+KVM_MEM_LOG_DIRTY_PAGES flag for a memory region), or when using
+KVM_CLEAR_DIRTY_LOG.
+
+The chunk size specifies how many pages to break at a time, using a
+single allocation for each chunk. Bigger the chunk size, more pages
+need to be allocated ahead of time.
+
+The chunk size needs to be a valid block size. The list of acceptable
+block sizes is exposed in KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES as a
+64-bit bitmap (each bit describing a block size). The default value is
+0, to disable the eager page splitting.
+
 9. Known KVM API problems
 =========================
 
arch/arm64/include/asm/kvm_host.h +15 -0
index ce7530968e39c..8d0a4c8a2d13b 100644
@@ -159,6 +159,21 @@ struct kvm_s2_mmu {
 	/* The last vcpu id that ran on each physical CPU */
 	int __percpu *last_vcpu_ran;
 
+#define KVM_ARM_EAGER_SPLIT_CHUNK_SIZE_DEFAULT 0
+	/*
+	 * Memory cache used to split
+	 * KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE worth of huge pages. It
+	 * is used to allocate stage2 page tables while splitting huge
+	 * pages. The choice of KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE
+	 * influences both the capacity of the split page cache, and
+	 * how often KVM reschedules. Be wary of raising CHUNK_SIZE
+	 * too high.
+	 *
+	 * Protected by kvm->slots_lock.
+	 */
+	struct kvm_mmu_memory_cache split_page_cache;
+	uint64_t split_page_chunk_size;
+
 	struct kvm_arch *arch;
 };
 
arch/arm64/include/asm/kvm_pgtable.h +18 -0
index 00c8bef4f3ca0..4182d5df70c93 100644
@@ -92,6 +92,24 @@ static inline bool kvm_level_supports_block_mapping(u32 level)
 	return level >= KVM_PGTABLE_MIN_BLOCK_LEVEL;
 }
 
+static inline u32 kvm_supported_block_sizes(void)
+{
+	u32 level = KVM_PGTABLE_MIN_BLOCK_LEVEL;
+	u32 r = 0;
+
+	for (; level < KVM_PGTABLE_MAX_LEVELS; level++)
+		r |= BIT(kvm_granule_shift(level));
+
+	return r;
+}
+
+static inline bool kvm_is_block_size_supported(u64 size)
+{
+	bool is_power_of_two = IS_ALIGNED(size, size);
+
+	return is_power_of_two && (size & kvm_supported_block_sizes());
+}
+
 /**
  * struct kvm_pgtable_mm_ops - Memory management callbacks.
  * @zalloc_page:		Allocate a single zeroed memory page.
arch/arm64/kvm/arm.c +28 -0
index bb21d0c25de75..c3056749338a6 100644
@@ -67,6 +67,7 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 			    struct kvm_enable_cap *cap)
 {
 	int r;
+	u64 new_cap;
 
 	if (cap->flags)
 		return -EINVAL;
@@ -91,6 +92,24 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 		r = 0;
 		set_bit(KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED, &kvm->arch.flags);
 		break;
+	case KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE:
+		new_cap = cap->args[0];
+
+		mutex_lock(&kvm->slots_lock);
+		/*
+		 * To keep things simple, allow changing the chunk
+		 * size only when no memory slots have been created.
+		 */
+		if (!kvm_are_all_memslots_empty(kvm)) {
+			r = -EINVAL;
+		} else if (new_cap && !kvm_is_block_size_supported(new_cap)) {
+			r = -EINVAL;
+		} else {
+			r = 0;
+			kvm->arch.mmu.split_page_chunk_size = new_cap;
+		}
+		mutex_unlock(&kvm->slots_lock);
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -303,6 +322,15 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ARM_PTRAUTH_GENERIC:
 		r = system_has_full_ptr_auth();
 		break;
+	case KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE:
+		if (kvm)
+			r = kvm->arch.mmu.split_page_chunk_size;
+		else
+			r = KVM_ARM_EAGER_SPLIT_CHUNK_SIZE_DEFAULT;
+		break;
+	case KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES:
+		r = kvm_supported_block_sizes();
+		break;
 	default:
 		r = 0;
 	}
arch/arm64/kvm/mmu.c +4 -0
index efdaab3f154de..7e1cb38d0fc97 100644
@@ -756,6 +756,10 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
 	for_each_possible_cpu(cpu)
 		*per_cpu_ptr(mmu->last_vcpu_ran, cpu) = -1;
 
+	 /* The eager page splitting is disabled by default */
+	mmu->split_page_chunk_size = KVM_ARM_EAGER_SPLIT_CHUNK_SIZE_DEFAULT;
+	mmu->split_page_cache.gfp_zero = __GFP_ZERO;
+
 	mmu->pgt = pgt;
 	mmu->pgd_phys = __pa(pgt->pgd);
 	return 0;
include/uapi/linux/kvm.h +2 -0
index 16287a996c324..94e09619b5a48 100644
@@ -1190,6 +1190,8 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225
 #define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226
 #define KVM_CAP_COUNTER_OFFSET 227
+#define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228
+#define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
Signature · 1 line
2.40.1.495.gc816e09b53d-goog
#6 lore raw

PATCH v8 6/12 KVM: arm64: Add kvm_pgtable_stage2_split()

In reply to Ricardo Koller

Add a new stage2 function, kvm_pgtable_stage2_split(), for splitting a range of huge pages. This will be used for eager-splitting huge pages into PAGE_SIZE pages. The goal is to avoid having to split huge pages on write-protection faults, and instead use this function to do it ahead of time for large ranges (e.g., all guest memory in 1G chunks at a time).

---
 arch/arm64/include/asm/kvm_pgtable.h |  19 +++++
 arch/arm64/kvm/hyp/pgtable.c         | 103 +++++++++++++++++++++++++++
 2 files changed, 122 insertions(+)
arch/arm64/include/asm/kvm_pgtable.h +19 -0
index 4182d5df70c93..a41581c985b78 100644
@@ -672,6 +672,25 @@ bool kvm_pgtable_stage2_is_young(struct kvm_pgtable *pgt, u64 addr);
  */
 int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size);
 
+/**
+ * kvm_pgtable_stage2_split() - Split a range of huge pages into leaf PTEs pointing
+ *				to PAGE_SIZE guest pages.
+ * @pgt:	 Page-table structure initialised by kvm_pgtable_stage2_init().
+ * @addr:	 Intermediate physical address from which to split.
+ * @size:	 Size of the range.
+ * @mc:		 Cache of pre-allocated and zeroed memory from which to allocate
+ *		 page-table pages.
+ *
+ * The function tries to split any level 1 or 2 entry that overlaps
+ * with the input range (given by @addr and @size).
+ *
+ * Return: 0 on success, negative error code on failure. Note that
+ * kvm_pgtable_stage2_split() is best effort: it tries to break as many
+ * blocks in the input range as allowed by @mc_capacity.
+ */
+int kvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size,
+			     struct kvm_mmu_memory_cache *mc);
+
 /**
  * kvm_pgtable_walk() - Walk a page-table.
  * @pgt:	Page-table structure initialised by kvm_pgtable_*_init().
arch/arm64/kvm/hyp/pgtable.c +103 -0

109 lines not on this page · raw message

Signature · 1 line
2.40.1.495.gc816e09b53d-goog
#7 lore raw

PATCH v8 7/12 KVM: arm64: Refactor kvm_arch_commit_memory_region()

In reply to Ricardo Koller

Refactor kvm_arch_commit_memory_region() as a preparation for a future commit to look cleaner and more understandable. Also, it looks more like its x86 counterpart (in kvm_mmu_slot_apply_flags()).

---
 arch/arm64/kvm/mmu.c | 26 +++++++++++++++++++-------
 1 file changed, 19 insertions(+), 7 deletions(-)
arch/arm64/kvm/mmu.c +19 -7
index 7e1cb38d0fc97..92f8872550f26 100644
@@ -1765,20 +1765,32 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 				   const struct kvm_memory_slot *new,
 				   enum kvm_mr_change change)
 {
+	bool log_dirty_pages = new && new->flags & KVM_MEM_LOG_DIRTY_PAGES;
+
 	/*
 	 * At this point memslot has been committed and there is an
 	 * allocated dirty_bitmap[], dirty pages will be tracked while the
 	 * memory slot is write protected.
 	 */
-	if (change != KVM_MR_DELETE && new->flags & KVM_MEM_LOG_DIRTY_PAGES) {
+	if (log_dirty_pages) {
+
+		if (change == KVM_MR_DELETE)
+			return;
+
 		/*
-		 * If we're with initial-all-set, we don't need to write
-		 * protect any pages because they're all reported as dirty.
-		 * Huge pages and normal pages will be write protect gradually.
+		 * Pages are write-protected on either of these two
+		 * cases:
+		 *
+		 * 1. with initial-all-set: gradually with CLEAR ioctls,
 		 */
-		if (!kvm_dirty_log_manual_protect_and_init_set(kvm)) {
-			kvm_mmu_wp_memory_region(kvm, new->id);
-		}
+		if (kvm_dirty_log_manual_protect_and_init_set(kvm))
+			return;
+		/*
+		 * or
+		 * 2. without initial-all-set: all in one shot when
+		 *    enabling dirty logging.
+		 */
+		kvm_mmu_wp_memory_region(kvm, new->id);
 	}
 }
 
Signature · 1 line
2.40.1.495.gc816e09b53d-goog
#8 lore raw

PATCH v8 8/12 KVM: arm64: Add kvm_uninit_stage2_mmu()

In reply to Ricardo Koller

Add kvm_uninit_stage2_mmu() and move kvm_free_stage2_pgd() into it. A future commit will add some more things to do inside of kvm_uninit_stage2_mmu().

---
 arch/arm64/include/asm/kvm_mmu.h | 1 +
 arch/arm64/kvm/mmu.c             | 7 ++++++-
 2 files changed, 7 insertions(+), 1 deletion(-)
arch/arm64/include/asm/kvm_mmu.h +1 -0
index 27e63c111f78a..20c50e00496d8 100644
@@ -172,6 +172,7 @@ void __init free_hyp_pgds(void);
 
 void stage2_unmap_vm(struct kvm *kvm);
 int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type);
+void kvm_uninit_stage2_mmu(struct kvm *kvm);
 void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu);
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 			  phys_addr_t pa, unsigned long size, bool writable);
arch/arm64/kvm/mmu.c +6 -1
index 92f8872550f26..46f005a894e57 100644
@@ -771,6 +771,11 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
 	return err;
 }
 
+void kvm_uninit_stage2_mmu(struct kvm *kvm)
+{
+	kvm_free_stage2_pgd(&kvm->arch.mmu);
+}
+
 static void stage2_unmap_memslot(struct kvm *kvm,
 				 struct kvm_memory_slot *memslot)
 {
@@ -1864,7 +1869,7 @@ void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
 
 void kvm_arch_flush_shadow_all(struct kvm *kvm)
 {
-	kvm_free_stage2_pgd(&kvm->arch.mmu);
+	kvm_uninit_stage2_mmu(kvm);
 }
 
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
Signature · 1 line
2.40.1.495.gc816e09b53d-goog
#9 lore raw

PATCH v8 9/12 KVM: arm64: Split huge pages when dirty logging is enabled

In reply to Ricardo Koller

Split huge pages eagerly when enabling dirty logging. The goal is to avoid doing it while faulting on write-protected pages, which negatively impacts guest performance.

A memslot marked for dirty logging is split in 1GB pieces at a time. This is in order to release the mmu_lock and give other kernel threads the opportunity to run, and also in order to allocate enough pages to split a 1GB range worth of huge pages (or a single 1GB huge page). Note that these page allocations can fail, so eager page splitting is best-effort. This is not a correctness issue though, as huge pages can still be split on write-faults.

Eager page splitting only takes effect when the huge page mapping has been existing in the stage-2 page table. Otherwise, the huge page will be mapped to multiple non-huge pages on page fault.

The benefits of eager page splitting are the same as in x86, added with commit a3fe5dbda0a4 ("KVM: x86/mmu: Split huge pages mapped by the TDP MMU when dirty logging is enabled"). For example, when running dirty_log_perf_test with 64 virtual CPUs (Ampere Altra), 1GB per vCPU, 50% reads, and 2MB HugeTLB memory, the time it takes vCPUs to access all of their memory after dirty logging is enabled decreased by 44% from 2.58s to 1.42s.

---
 arch/arm64/kvm/mmu.c | 127 +++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 123 insertions(+), 4 deletions(-)
arch/arm64/kvm/mmu.c +123 -4
index 46f005a894e57..4256c4a307531 100644
@@ -31,14 +31,21 @@ static phys_addr_t __ro_after_init hyp_idmap_vector;
 
 static unsigned long __ro_after_init io_map_base;
 
-static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end)
+static phys_addr_t __stage2_range_addr_end(phys_addr_t addr, phys_addr_t end,
+					   phys_addr_t size)
 {
-	phys_addr_t size = kvm_granule_size(KVM_PGTABLE_MIN_BLOCK_LEVEL);
 	phys_addr_t boundary = ALIGN_DOWN(addr + size, size);
 
 	return (boundary - 1 < end - 1) ? boundary : end;
 }
 
+static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t size = kvm_granule_size(KVM_PGTABLE_MIN_BLOCK_LEVEL);
+
+	return __stage2_range_addr_end(addr, end, size);
+}
+
 /*
  * Release kvm_mmu_lock periodically if the memory region is large. Otherwise,
  * we may see kernel panics with CONFIG_DETECT_HUNG_TASK,
@@ -75,6 +82,79 @@ static int stage2_apply_range(struct kvm_s2_mmu *mmu, phys_addr_t addr,
 #define stage2_apply_range_resched(mmu, addr, end, fn)			\
 	stage2_apply_range(mmu, addr, end, fn, true)
 
+/*
+ * Get the maximum number of page-tables pages needed to split a range
+ * of blocks into PAGE_SIZE PTEs. It assumes the range is already
+ * mapped at level 2, or at level 1 if allowed.
+ */
+static int kvm_mmu_split_nr_page_tables(u64 range)
+{
+	int n = 0;
+
+	if (KVM_PGTABLE_MIN_BLOCK_LEVEL < 2)
+		n += DIV_ROUND_UP_ULL(range, PUD_SIZE);
+	n += DIV_ROUND_UP_ULL(range, PMD_SIZE);
+	return n;
+}
+
+static bool need_split_memcache_topup_or_resched(struct kvm *kvm)
+{
+	struct kvm_mmu_memory_cache *cache;
+	u64 chunk_size, min;
+
+	if (need_resched() || rwlock_needbreak(&kvm->mmu_lock))
+		return true;
+
+	chunk_size = kvm->arch.mmu.split_page_chunk_size;
+	min = kvm_mmu_split_nr_page_tables(chunk_size);
+	cache = &kvm->arch.mmu.split_page_cache;
+	return kvm_mmu_memory_cache_nr_free_objects(cache) < min;
+}
+
+static int kvm_mmu_split_huge_pages(struct kvm *kvm, phys_addr_t addr,
+				    phys_addr_t end)
+{
+	struct kvm_mmu_memory_cache *cache;
+	struct kvm_pgtable *pgt;
+	int ret, cache_capacity;
+	u64 next, chunk_size;
+
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	chunk_size = kvm->arch.mmu.split_page_chunk_size;
+	cache_capacity = kvm_mmu_split_nr_page_tables(chunk_size);
+
+	if (chunk_size == 0)
+		return 0;
+
+	cache = &kvm->arch.mmu.split_page_cache;
+
+	do {
+		if (need_split_memcache_topup_or_resched(kvm)) {
+			write_unlock(&kvm->mmu_lock);
+			cond_resched();
+			/* Eager page splitting is best-effort. */
+			ret = __kvm_mmu_topup_memory_cache(cache,
+							   cache_capacity,
+							   cache_capacity);
+			write_lock(&kvm->mmu_lock);
+			if (ret)
+				break;
+		}
+
+		pgt = kvm->arch.mmu.pgt;
+		if (!pgt)
+			return -EINVAL;
+
+		next = __stage2_range_addr_end(addr, end, chunk_size);
+		ret = kvm_pgtable_stage2_split(pgt, addr, next - addr, cache);
+		if (ret)
+			break;
+	} while (addr = next, addr != end);
+
+	return ret;
+}
+
 static bool memslot_is_logging(struct kvm_memory_slot *memslot)
 {
 	return memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY);
@@ -774,6 +854,7 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
 void kvm_uninit_stage2_mmu(struct kvm *kvm)
 {
 	kvm_free_stage2_pgd(&kvm->arch.mmu);
+	kvm_mmu_free_memory_cache(&kvm->arch.mmu.split_page_cache);
 }
 
 static void stage2_unmap_memslot(struct kvm *kvm,
@@ -1000,6 +1081,34 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
 	stage2_wp_range(&kvm->arch.mmu, start, end);
 }
 
+/**
+ * kvm_mmu_split_memory_region() - split the stage 2 blocks into PAGE_SIZE
+ *				   pages for memory slot
+ * @kvm:	The KVM pointer
+ * @slot:	The memory slot to split
+ *
+ * Acquires kvm->mmu_lock. Called with kvm->slots_lock mutex acquired,
+ * serializing operations for VM memory regions.
+ */
+static void kvm_mmu_split_memory_region(struct kvm *kvm, int slot)
+{
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+	phys_addr_t start, end;
+
+	lockdep_assert_held(&kvm->slots_lock);
+
+	slots = kvm_memslots(kvm);
+	memslot = id_to_memslot(slots, slot);
+
+	start = memslot->base_gfn << PAGE_SHIFT;
+	end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
+
+	write_lock(&kvm->mmu_lock);
+	kvm_mmu_split_huge_pages(kvm, start, end);
+	write_unlock(&kvm->mmu_lock);
+}
+
 /*
  * kvm_arch_mmu_enable_log_dirty_pt_masked - enable dirty logging for selected
  * dirty pages.
@@ -1783,8 +1892,8 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 			return;
 
 		/*
-		 * Pages are write-protected on either of these two
-		 * cases:
+		 * Huge and normal pages are write-protected and split
+		 * on either of these two cases:
 		 *
 		 * 1. with initial-all-set: gradually with CLEAR ioctls,
 		 */
@@ -1796,6 +1905,16 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 		 *    enabling dirty logging.
 		 */
 		kvm_mmu_wp_memory_region(kvm, new->id);
+		kvm_mmu_split_memory_region(kvm, new->id);
+	} else {
+		/*
+		 * Free any leftovers from the eager page splitting cache. Do
+		 * this when deleting, moving, disabling dirty logging, or
+		 * creating the memslot (a nop). Doing it for deletes makes
+		 * sure we don't leak memory, and there's no need to keep the
+		 * cache around for any of the other cases.
+		 */
+		kvm_mmu_free_memory_cache(&kvm->arch.mmu.split_page_cache);
 	}
 }
 
Signature · 1 line
2.40.1.495.gc816e09b53d-goog
#10 lore raw

PATCH v8 10/12 KVM: arm64: Open-code kvm_mmu_write_protect_pt_masked()

In reply to Ricardo Koller

Move the functionality of kvm_mmu_write_protect_pt_masked() into its caller, kvm_arch_mmu_enable_log_dirty_pt_masked(). This will be used in a subsequent commit in order to share some of the code in kvm_arch_mmu_enable_log_dirty_pt_masked().

---
 arch/arm64/kvm/mmu.c | 42 +++++++++++++++---------------------------
 1 file changed, 15 insertions(+), 27 deletions(-)
arch/arm64/kvm/mmu.c +15 -27
index 4256c4a307531..835e4b8f4e5c3 100644
@@ -1059,28 +1059,6 @@ static void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot)
 	kvm_flush_remote_tlbs(kvm);
 }
 
-/**
- * kvm_mmu_write_protect_pt_masked() - write protect dirty pages
- * @kvm:	The KVM pointer
- * @slot:	The memory slot associated with mask
- * @gfn_offset:	The gfn offset in memory slot
- * @mask:	The mask of dirty pages at offset 'gfn_offset' in this memory
- *		slot to be write protected
- *
- * Walks bits set in mask write protects the associated pte's. Caller must
- * acquire kvm_mmu_lock.
- */
-static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
-		struct kvm_memory_slot *slot,
-		gfn_t gfn_offset, unsigned long mask)
-{
-	phys_addr_t base_gfn = slot->base_gfn + gfn_offset;
-	phys_addr_t start = (base_gfn +  __ffs(mask)) << PAGE_SHIFT;
-	phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT;
-
-	stage2_wp_range(&kvm->arch.mmu, start, end);
-}
-
 /**
  * kvm_mmu_split_memory_region() - split the stage 2 blocks into PAGE_SIZE
  *				   pages for memory slot
@@ -1110,17 +1088,27 @@ static void kvm_mmu_split_memory_region(struct kvm *kvm, int slot)
 }
 
 /*
- * kvm_arch_mmu_enable_log_dirty_pt_masked - enable dirty logging for selected
- * dirty pages.
+ * kvm_arch_mmu_enable_log_dirty_pt_masked() - enable dirty logging for selected pages.
+ * @kvm:	The KVM pointer
+ * @slot:	The memory slot associated with mask
+ * @gfn_offset:	The gfn offset in memory slot
+ * @mask:	The mask of pages at offset 'gfn_offset' in this memory
+ *		slot to enable dirty logging on
  *
- * It calls kvm_mmu_write_protect_pt_masked to write protect selected pages to
- * enable dirty logging for them.
+ * Writes protect selected pages to enable dirty logging for them. Caller must
+ * acquire kvm->mmu_lock.
  */
 void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 		struct kvm_memory_slot *slot,
 		gfn_t gfn_offset, unsigned long mask)
 {
-	kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
+	phys_addr_t base_gfn = slot->base_gfn + gfn_offset;
+	phys_addr_t start = (base_gfn +  __ffs(mask)) << PAGE_SHIFT;
+	phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT;
+
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	stage2_wp_range(&kvm->arch.mmu, start, end);
 }
 
 static void kvm_send_hwpoison_signal(unsigned long address, short lsb)
Signature · 1 line
2.40.1.495.gc816e09b53d-goog
#11 lore raw

PATCH v8 11/12 KVM: arm64: Split huge pages during KVM_CLEAR_DIRTY_LOG

In reply to Ricardo Koller

This is the arm64 counterpart of commit cb00a70bd4b7 ("KVM: x86/mmu:
Split huge pages mapped by the TDP MMU during KVM_CLEAR_DIRTY_LOG"), which has the benefit of splitting the cost of splitting a memslot across multiple ioctls.

Split huge pages on the range specified using KVM_CLEAR_DIRTY_LOG. And do not split when enabling dirty logging if KVM_DIRTY_LOG_INITIALLY_SET is set.

---
 arch/arm64/kvm/mmu.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)
arch/arm64/kvm/mmu.c +13 -2
index 835e4b8f4e5c3..7a68398517c95 100644
@@ -1095,8 +1095,8 @@ static void kvm_mmu_split_memory_region(struct kvm *kvm, int slot)
  * @mask:	The mask of pages at offset 'gfn_offset' in this memory
  *		slot to enable dirty logging on
  *
- * Writes protect selected pages to enable dirty logging for them. Caller must
- * acquire kvm->mmu_lock.
+ * Writes protect selected pages to enable dirty logging, and then
+ * splits them to PAGE_SIZE. Caller must acquire kvm->mmu_lock.
  */
 void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 		struct kvm_memory_slot *slot,
@@ -1109,6 +1109,17 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 	lockdep_assert_held_write(&kvm->mmu_lock);
 
 	stage2_wp_range(&kvm->arch.mmu, start, end);
+
+	/*
+	 * Eager-splitting is done when manual-protect is set.  We
+	 * also check for initially-all-set because we can avoid
+	 * eager-splitting if initially-all-set is false.
+	 * Initially-all-set equal false implies that huge-pages were
+	 * already split when enabling dirty logging: no need to do it
+	 * again.
+	 */
+	if (kvm_dirty_log_manual_protect_and_init_set(kvm))
+		kvm_mmu_split_huge_pages(kvm, start, end);
 }
 
 static void kvm_send_hwpoison_signal(unsigned long address, short lsb)
Signature · 1 line
2.40.1.495.gc816e09b53d-goog
#12 lore raw

PATCH v8 12/12 KVM: arm64: Use local TLBI on permission relaxation

In reply to Ricardo Koller

From: Marc Zyngier <[email protected]>

Broadcast TLB invalidations (TLBIs) targeting the Inner Shareable Domain are usually less performant than their non-shareable variant. In particular, we observed some implementations that take millliseconds to complete parallel broadcasted TLBIs.

It's safe to use non-shareable TLBIs when relaxing permissions on a PTE in the KVM case. According to the ARM ARM (0487I.a) section D8.13.1 "Using break-before-make when updating translation table entries", permission relaxation does not need break-before-make. Specifically, R_WHZWS states that these are the only changes that require a break-before-make sequence: changes of memory type (Shareability or Cacheability), address changes, or changing the block size.

---
 arch/arm64/include/asm/kvm_asm.h   |  4 +++
 arch/arm64/kvm/hyp/nvhe/hyp-main.c | 10 ++++++
 arch/arm64/kvm/hyp/nvhe/tlb.c      | 52 ++++++++++++++++++++++++++++++
 arch/arm64/kvm/hyp/pgtable.c       |  2 +-
 arch/arm64/kvm/hyp/vhe/tlb.c       | 32 ++++++++++++++++++
 5 files changed, 99 insertions(+), 1 deletion(-)
arch/arm64/include/asm/kvm_asm.h +4 -0
index 43c3bc0f9544d..bb17b2ead4c71 100644
@@ -68,6 +68,7 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___kvm_vcpu_run,
 	__KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context,
 	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa,
+	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa_nsh,
 	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid,
 	__KVM_HOST_SMCCC_FUNC___kvm_flush_cpu_context,
 	__KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff,
@@ -225,6 +226,9 @@ extern void __kvm_flush_vm_context(void);
 extern void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
 				     int level);
+extern void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu,
+					 phys_addr_t ipa,
+					 int level);
 extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu);
 
 extern void __kvm_timer_set_cntvoff(u64 cntvoff);
arch/arm64/kvm/hyp/nvhe/hyp-main.c +10 -0
index 728e01d4536b0..c6bf1e49ca934 100644
@@ -125,6 +125,15 @@ static void handle___kvm_tlb_flush_vmid_ipa(struct kvm_cpu_context *host_ctxt)
 	__kvm_tlb_flush_vmid_ipa(kern_hyp_va(mmu), ipa, level);
 }
 
+static void handle___kvm_tlb_flush_vmid_ipa_nsh(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
+	DECLARE_REG(phys_addr_t, ipa, host_ctxt, 2);
+	DECLARE_REG(int, level, host_ctxt, 3);
+
+	__kvm_tlb_flush_vmid_ipa_nsh(kern_hyp_va(mmu), ipa, level);
+}
+
 static void handle___kvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
@@ -315,6 +324,7 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__kvm_vcpu_run),
 	HANDLE_FUNC(__kvm_flush_vm_context),
 	HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa),
+	HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa_nsh),
 	HANDLE_FUNC(__kvm_tlb_flush_vmid),
 	HANDLE_FUNC(__kvm_flush_cpu_context),
 	HANDLE_FUNC(__kvm_timer_set_cntvoff),
arch/arm64/kvm/hyp/nvhe/tlb.c +52 -0

58 lines not on this page · raw message

arch/arm64/kvm/hyp/pgtable.c +1 -1
index 85f42fb2d0d75..8acab89080af9 100644
@@ -1212,7 +1212,7 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
 				       KVM_PGTABLE_WALK_HANDLE_FAULT |
 				       KVM_PGTABLE_WALK_SHARED);
 	if (!ret)
-		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, pgt->mmu, addr, level);
+		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa_nsh, pgt->mmu, addr, level);
 	return ret;
 }
 
arch/arm64/kvm/hyp/vhe/tlb.c +32 -0
index 24cef9b87f9e9..e69da550cdc5b 100644
@@ -111,6 +111,38 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
 	__tlb_switch_to_host(&cxt);
 }
 
+void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu,
+				  phys_addr_t ipa, int level)
+{
+	struct tlb_inv_context cxt;
+
+	dsb(nshst);
+
+	/* Switch to requested VMID */
+	__tlb_switch_to_guest(mmu, &cxt);
+
+	/*
+	 * We could do so much better if we had the VA as well.
+	 * Instead, we invalidate Stage-2 for this IPA, and the
+	 * whole of Stage-1. Weep...
+	 */
+	ipa >>= 12;
+	__tlbi_level(ipas2e1, ipa, level);
+
+	/*
+	 * We have to ensure completion of the invalidation at Stage-2,
+	 * since a table walk on another CPU could refill a TLB with a
+	 * complete (S1 + S2) walk based on the old Stage-2 mapping if
+	 * the Stage-1 invalidation happened first.
+	 */
+	dsb(nsh);
+	__tlbi(vmalle1);
+	dsb(nsh);
+	isb();
+
+	__tlb_switch_to_host(&cxt);
+}
+
 void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 {
 	struct tlb_inv_context cxt;
Signature · 1 line
2.40.1.495.gc816e09b53d-goog
Applied
#13 lore raw
In reply to Ricardo Koller
Quoted 16 lines · Ricardo Koller

Eager Page Splitting improves the performance of dirty-logging (used in live migrations) when guest memory is backed by huge-pages. It's an optimization used in Google Cloud since 2016 on x86, and for the last couple of months on ARM.

Background and motivation
=========================
Dirty logging is typically used for live-migration iterative copying. KVM implements dirty-logging at the PAGE_SIZE granularity (will refer to 4K pages from now on). It does it by faulting on write-protected 4K pages. Therefore, enabling dirty-logging on a huge-page requires breaking it into 4K pages in the first place. KVM does this breaking on fault, and because it's in the critical path it only maps the 4K page that faulted; every other 4K page is left unmapped. This is not great for performance on ARM for a couple of reasons:

Quoted 1 line

[...]

Picking these patches up early, as I'd like to get some mileage on the patches well in advance of 6.5.

Applied to kvmarm/next, thanks!

[01/12] KVM: arm64: Rename free_removed to free_unlinked

        https://git.kernel.org/kvmarm/kvmarm/c/c14d08c5adb2
[02/12] KVM: arm64: Add KVM_PGTABLE_WALK flags for skipping CMOs and BBM TLBIs
        https://git.kernel.org/kvmarm/kvmarm/c/02f10845f435
[03/12] KVM: arm64: Add helper for creating unlinked stage2 subtrees
        https://git.kernel.org/kvmarm/kvmarm/c/e7c05540c694
[04/12] KVM: arm64: Export kvm_are_all_memslots_empty()
        https://git.kernel.org/kvmarm/kvmarm/c/26f457142d7e
[05/12] KVM: arm64: Add KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE
        https://git.kernel.org/kvmarm/kvmarm/c/2f440b72e852
[06/12] KVM: arm64: Add kvm_pgtable_stage2_split()
        https://git.kernel.org/kvmarm/kvmarm/c/8f5a3eb7513f
[07/12] KVM: arm64: Refactor kvm_arch_commit_memory_region()
        https://git.kernel.org/kvmarm/kvmarm/c/6bd92b9d8b02
[08/12] KVM: arm64: Add kvm_uninit_stage2_mmu()
        https://git.kernel.org/kvmarm/kvmarm/c/ce2b60223800
[09/12] KVM: arm64: Split huge pages when dirty logging is enabled
        https://git.kernel.org/kvmarm/kvmarm/c/e7bf7a490c68
[10/12] KVM: arm64: Open-code kvm_mmu_write_protect_pt_masked()
        https://git.kernel.org/kvmarm/kvmarm/c/3005f6f29447
[11/12] KVM: arm64: Split huge pages during KVM_CLEAR_DIRTY_LOG
        https://git.kernel.org/kvmarm/kvmarm/c/6acf51666d03
[12/12] KVM: arm64: Use local TLBI on permission relaxation
        https://git.kernel.org/kvmarm/kvmarm/c/a12ab1378a88

--
Best,
Oliver