[PATCH v3 00/18] KVM: arm64: Non-protected guest stage-2 support for pKVM

[PATCH v3 00/18] KVM: arm64: Non-protected guest stage-2 support for pKVM

[Quentin Perret]

Hi all,

This is the v3 of the series adding support for non-protected guests
stage-2 to pKVM. Please refer to v1 for all the context:

  https://lore.kernel.org/kvmarm/20241104133204.85208-1-qperret@google.com/

The series is organized as follows:

 - Patches 01 to 04 move the host ownership state tracking from the
   host's stage-2 page-table to the hypervisor's vmemmap. This avoids
   fragmenting the host stage-2 for shared pages, which is only needed
   to store an annotation in the SW bits of the corresponding PTE. All
   pages mapped into non-protected guests are shared from pKVM's PoV,
   so the cost of stage-2 fragmentation will increase massively as we
   start tracking that at EL2. Note that these patches also help with
   the existing sharing for e.g. FF-A, so they could possibly be merged
   separately from the rest of the series.

 - Patches 05 to 07 implement a minor refactoring of the pgtable code to
   ease the integration of the pKVM MMU later on.

 - Patches 08 to 16 introduce all the infrastructure needed on the pKVM
   side for handling guest stage-2 page-tables at EL2.

 - Patches 17 and 18 plumb the newly introduced pKVM support into
   KVM/arm64.

Patches based on 6.13-rc3, tested on Pixel 6 and Qemu.

Changes in v3:
 - Rebased on 6.13-rc3
 - Applied Marc's rework of the for_each_mapping_in_range() macro mess
 - Removed mappings_lock in favor the mmu_lock
 - Dropped BUG_ON() from pkvm_mkstate()
 - Renamed range_is_allowed_memory() and clarified the comment inside it
 - Explicitly bail out when using host_stage2_set_owner_locked() on
   non-memory regions
 - Check PKVM_NOPAGE state as an equality rather than a bitwise
   operator
 - Reworked __pkvm_host_share_guest() to return -EPERM in case of
   illegal multi-sharing
 - Added get_np_pkvm_hyp_vm() to simplify HVC error handling in
   hyp-main.c
 - Cosmetic changes and improved coding consitency thoughout the series

Changes in v2:
 - Rebased on 6.13-rc1 (small conflicts with 2362506f7cff ("KVM: arm64:
   Don't mark "struct page" accessed when making SPTE young") in
   particular)
 - Fixed kerneldoc breakage for __unmap_stage2_range()
 - Fixed pkvm_pgtable_test_clear_young() to use correct HVC
 - Folded guest_get_valid_pte() into __check_host_unshare_guest() for
   clarity

Thanks,
Quentin

Marc Zyngier (1):
  KVM: arm64: Introduce __pkvm_vcpu_{load,put}()

Quentin Perret (17):
  KVM: arm64: Change the layout of enum pkvm_page_state
  KVM: arm64: Move enum pkvm_page_state to memory.h
  KVM: arm64: Make hyp_page::order a u8
  KVM: arm64: Move host page ownership tracking to the hyp vmemmap
  KVM: arm64: Pass walk flags to kvm_pgtable_stage2_mkyoung
  KVM: arm64: Pass walk flags to kvm_pgtable_stage2_relax_perms
  KVM: arm64: Make kvm_pgtable_stage2_init() a static inline function
  KVM: arm64: Add {get,put}_pkvm_hyp_vm() helpers
  KVM: arm64: Introduce __pkvm_host_share_guest()
  KVM: arm64: Introduce __pkvm_host_unshare_guest()
  KVM: arm64: Introduce __pkvm_host_relax_guest_perms()
  KVM: arm64: Introduce __pkvm_host_wrprotect_guest()
  KVM: arm64: Introduce __pkvm_host_test_clear_young_guest()
  KVM: arm64: Introduce __pkvm_host_mkyoung_guest()
  KVM: arm64: Introduce __pkvm_tlb_flush_vmid()
  KVM: arm64: Introduce the EL1 pKVM MMU
  KVM: arm64: Plumb the pKVM MMU in KVM

 arch/arm64/include/asm/kvm_asm.h              |   9 +
 arch/arm64/include/asm/kvm_host.h             |   4 +
 arch/arm64/include/asm/kvm_mmu.h              |  16 +
 arch/arm64/include/asm/kvm_pgtable.h          |  38 ++-
 arch/arm64/include/asm/kvm_pkvm.h             |  23 ++
 arch/arm64/kvm/arm.c                          |  23 +-
 arch/arm64/kvm/hyp/include/nvhe/gfp.h         |   6 +-
 arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |  38 +--
 arch/arm64/kvm/hyp/include/nvhe/memory.h      |  42 ++-
 arch/arm64/kvm/hyp/include/nvhe/pkvm.h        |  16 +
 arch/arm64/kvm/hyp/nvhe/hyp-main.c            | 201 ++++++++++-
 arch/arm64/kvm/hyp/nvhe/mem_protect.c         | 320 ++++++++++++++++--
 arch/arm64/kvm/hyp/nvhe/page_alloc.c          |  14 +-
 arch/arm64/kvm/hyp/nvhe/pkvm.c                |  68 ++++
 arch/arm64/kvm/hyp/nvhe/setup.c               |   7 +-
 arch/arm64/kvm/hyp/pgtable.c                  |  13 +-
 arch/arm64/kvm/mmu.c                          | 113 +++++--
 arch/arm64/kvm/pkvm.c                         | 198 +++++++++++
 arch/arm64/kvm/vgic/vgic-v3.c                 |   6 +-
 19 files changed, 1010 insertions(+), 145 deletions(-)

-- 
2.47.1.613.gc27f4b7a9f-goog

[PATCH v3 01/18] KVM: arm64: Change the layout of enum pkvm_page_state

[Quentin Perret]

The 'concrete' (a.k.a non-meta) page states are currently encoded using
software bits in PTEs. For performance reasons, the abstract
pkvm_page_state enum uses the same bits to encode these states as that
makes conversions from and to PTEs easy.

In order to prepare the ground for moving the 'concrete' state storage
to the hyp vmemmap, re-arrange the enum to use bits 0 and 1 for this
purpose.

No functional changes intended.

Signed-off-by: Quentin Perret <qperret@google.com>
---
 arch/arm64/kvm/hyp/include/nvhe/mem_protect.h | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
index 0972faccc2af..8c30362af2b9 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
@@ -24,25 +24,27 @@
  */
 enum pkvm_page_state {
 	PKVM_PAGE_OWNED			= 0ULL,
-	PKVM_PAGE_SHARED_OWNED		= KVM_PGTABLE_PROT_SW0,
-	PKVM_PAGE_SHARED_BORROWED	= KVM_PGTABLE_PROT_SW1,
-	__PKVM_PAGE_RESERVED		= KVM_PGTABLE_PROT_SW0 |
-					  KVM_PGTABLE_PROT_SW1,
+	PKVM_PAGE_SHARED_OWNED		= BIT(0),
+	PKVM_PAGE_SHARED_BORROWED	= BIT(1),
+	__PKVM_PAGE_RESERVED		= BIT(0) | BIT(1),
 
 	/* Meta-states which aren't encoded directly in the PTE's SW bits */
-	PKVM_NOPAGE,
+	PKVM_NOPAGE			= BIT(2),
 };
+#define PKVM_PAGE_META_STATES_MASK	(~(BIT(0) | BIT(1)))
 
 #define PKVM_PAGE_STATE_PROT_MASK	(KVM_PGTABLE_PROT_SW0 | KVM_PGTABLE_PROT_SW1)
 static inline enum kvm_pgtable_prot pkvm_mkstate(enum kvm_pgtable_prot prot,
 						 enum pkvm_page_state state)
 {
-	return (prot & ~PKVM_PAGE_STATE_PROT_MASK) | state;
+	prot &= ~PKVM_PAGE_STATE_PROT_MASK;
+	prot |= FIELD_PREP(PKVM_PAGE_STATE_PROT_MASK, state);
+	return prot;
 }
 
 static inline enum pkvm_page_state pkvm_getstate(enum kvm_pgtable_prot prot)
 {
-	return prot & PKVM_PAGE_STATE_PROT_MASK;
+	return FIELD_GET(PKVM_PAGE_STATE_PROT_MASK, prot);
 }
 
 struct host_mmu {
-- 
2.47.1.613.gc27f4b7a9f-goog

[PATCH v3 02/18] KVM: arm64: Move enum pkvm_page_state to memory.h

[Quentin Perret]

In order to prepare the way for storing page-tracking information in
pKVM's vmemmap, move the enum pkvm_page_state definition to
nvhe/memory.h.

No functional changes intended.

Signed-off-by: Quentin Perret <qperret@google.com>
---
 arch/arm64/kvm/hyp/include/nvhe/mem_protect.h | 34 +------------------
 arch/arm64/kvm/hyp/include/nvhe/memory.h      | 33 ++++++++++++++++++
 2 files changed, 34 insertions(+), 33 deletions(-)

diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
index 8c30362af2b9..25038ac705d8 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
@@ -11,42 +11,10 @@
 #include <asm/kvm_mmu.h>
 #include <asm/kvm_pgtable.h>
 #include <asm/virt.h>
+#include <nvhe/memory.h>
 #include <nvhe/pkvm.h>
 #include <nvhe/spinlock.h>
 
-/*
- * SW bits 0-1 are reserved to track the memory ownership state of each page:
- *   00: The page is owned exclusively by the page-table owner.
- *   01: The page is owned by the page-table owner, but is shared
- *       with another entity.
- *   10: The page is shared with, but not owned by the page-table owner.
- *   11: Reserved for future use (lending).
- */
-enum pkvm_page_state {
-	PKVM_PAGE_OWNED			= 0ULL,
-	PKVM_PAGE_SHARED_OWNED		= BIT(0),
-	PKVM_PAGE_SHARED_BORROWED	= BIT(1),
-	__PKVM_PAGE_RESERVED		= BIT(0) | BIT(1),
-
-	/* Meta-states which aren't encoded directly in the PTE's SW bits */
-	PKVM_NOPAGE			= BIT(2),
-};
-#define PKVM_PAGE_META_STATES_MASK	(~(BIT(0) | BIT(1)))
-
-#define PKVM_PAGE_STATE_PROT_MASK	(KVM_PGTABLE_PROT_SW0 | KVM_PGTABLE_PROT_SW1)
-static inline enum kvm_pgtable_prot pkvm_mkstate(enum kvm_pgtable_prot prot,
-						 enum pkvm_page_state state)
-{
-	prot &= ~PKVM_PAGE_STATE_PROT_MASK;
-	prot |= FIELD_PREP(PKVM_PAGE_STATE_PROT_MASK, state);
-	return prot;
-}
-
-static inline enum pkvm_page_state pkvm_getstate(enum kvm_pgtable_prot prot)
-{
-	return FIELD_GET(PKVM_PAGE_STATE_PROT_MASK, prot);
-}
-
 struct host_mmu {
 	struct kvm_arch arch;
 	struct kvm_pgtable pgt;
diff --git a/arch/arm64/kvm/hyp/include/nvhe/memory.h b/arch/arm64/kvm/hyp/include/nvhe/memory.h
index ab205c4d6774..c84b24234ac7 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/memory.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/memory.h
@@ -7,6 +7,39 @@
 
 #include <linux/types.h>
 
+/*
+ * SW bits 0-1 are reserved to track the memory ownership state of each page:
+ *   00: The page is owned exclusively by the page-table owner.
+ *   01: The page is owned by the page-table owner, but is shared
+ *       with another entity.
+ *   10: The page is shared with, but not owned by the page-table owner.
+ *   11: Reserved for future use (lending).
+ */
+enum pkvm_page_state {
+	PKVM_PAGE_OWNED			= 0ULL,
+	PKVM_PAGE_SHARED_OWNED		= BIT(0),
+	PKVM_PAGE_SHARED_BORROWED	= BIT(1),
+	__PKVM_PAGE_RESERVED		= BIT(0) | BIT(1),
+
+	/* Meta-states which aren't encoded directly in the PTE's SW bits */
+	PKVM_NOPAGE			= BIT(2),
+};
+#define PKVM_PAGE_META_STATES_MASK	(~(BIT(0) | BIT(1)))
+
+#define PKVM_PAGE_STATE_PROT_MASK	(KVM_PGTABLE_PROT_SW0 | KVM_PGTABLE_PROT_SW1)
+static inline enum kvm_pgtable_prot pkvm_mkstate(enum kvm_pgtable_prot prot,
+						 enum pkvm_page_state state)
+{
+	prot &= ~PKVM_PAGE_STATE_PROT_MASK;
+	prot |= FIELD_PREP(PKVM_PAGE_STATE_PROT_MASK, state);
+	return prot;
+}
+
+static inline enum pkvm_page_state pkvm_getstate(enum kvm_pgtable_prot prot)
+{
+	return FIELD_GET(PKVM_PAGE_STATE_PROT_MASK, prot);
+}
+
 struct hyp_page {
 	unsigned short refcount;
 	unsigned short order;
-- 
2.47.1.613.gc27f4b7a9f-goog

[PATCH v3 03/18] KVM: arm64: Make hyp_page::order a u8

[Quentin Perret]

We don't need 16 bits to store the hyp page order, and we'll need some
bits to store page ownership data soon, so let's reduce the order
member.

Signed-off-by: Quentin Perret <qperret@google.com>
---
 arch/arm64/kvm/hyp/include/nvhe/gfp.h    |  6 +++---
 arch/arm64/kvm/hyp/include/nvhe/memory.h |  5 +++--
 arch/arm64/kvm/hyp/nvhe/page_alloc.c     | 14 +++++++-------
 3 files changed, 13 insertions(+), 12 deletions(-)

diff --git a/arch/arm64/kvm/hyp/include/nvhe/gfp.h b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
index 97c527ef53c2..f1725bad6331 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/gfp.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
@@ -7,7 +7,7 @@
 #include <nvhe/memory.h>
 #include <nvhe/spinlock.h>
 
-#define HYP_NO_ORDER	USHRT_MAX
+#define HYP_NO_ORDER	0xff
 
 struct hyp_pool {
 	/*
@@ -19,11 +19,11 @@ struct hyp_pool {
 	struct list_head free_area[NR_PAGE_ORDERS];
 	phys_addr_t range_start;
 	phys_addr_t range_end;
-	unsigned short max_order;
+	u8 max_order;
 };
 
 /* Allocation */
-void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order);
+void *hyp_alloc_pages(struct hyp_pool *pool, u8 order);
 void hyp_split_page(struct hyp_page *page);
 void hyp_get_page(struct hyp_pool *pool, void *addr);
 void hyp_put_page(struct hyp_pool *pool, void *addr);
diff --git a/arch/arm64/kvm/hyp/include/nvhe/memory.h b/arch/arm64/kvm/hyp/include/nvhe/memory.h
index c84b24234ac7..45b8d1840aa4 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/memory.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/memory.h
@@ -41,8 +41,9 @@ static inline enum pkvm_page_state pkvm_getstate(enum kvm_pgtable_prot prot)
 }
 
 struct hyp_page {
-	unsigned short refcount;
-	unsigned short order;
+	u16 refcount;
+	u8 order;
+	u8 reserved;
 };
 
 extern u64 __hyp_vmemmap;
diff --git a/arch/arm64/kvm/hyp/nvhe/page_alloc.c b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
index e691290d3765..a1eb27a1a747 100644
--- a/arch/arm64/kvm/hyp/nvhe/page_alloc.c
+++ b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
@@ -32,7 +32,7 @@ u64 __hyp_vmemmap;
  */
 static struct hyp_page *__find_buddy_nocheck(struct hyp_pool *pool,
 					     struct hyp_page *p,
-					     unsigned short order)
+					     u8 order)
 {
 	phys_addr_t addr = hyp_page_to_phys(p);
 
@@ -51,7 +51,7 @@ static struct hyp_page *__find_buddy_nocheck(struct hyp_pool *pool,
 /* Find a buddy page currently available for allocation */
 static struct hyp_page *__find_buddy_avail(struct hyp_pool *pool,
 					   struct hyp_page *p,
-					   unsigned short order)
+					   u8 order)
 {
 	struct hyp_page *buddy = __find_buddy_nocheck(pool, p, order);
 
@@ -94,7 +94,7 @@ static void __hyp_attach_page(struct hyp_pool *pool,
 			      struct hyp_page *p)
 {
 	phys_addr_t phys = hyp_page_to_phys(p);
-	unsigned short order = p->order;
+	u8 order = p->order;
 	struct hyp_page *buddy;
 
 	memset(hyp_page_to_virt(p), 0, PAGE_SIZE << p->order);
@@ -129,7 +129,7 @@ static void __hyp_attach_page(struct hyp_pool *pool,
 
 static struct hyp_page *__hyp_extract_page(struct hyp_pool *pool,
 					   struct hyp_page *p,
-					   unsigned short order)
+					   u8 order)
 {
 	struct hyp_page *buddy;
 
@@ -183,7 +183,7 @@ void hyp_get_page(struct hyp_pool *pool, void *addr)
 
 void hyp_split_page(struct hyp_page *p)
 {
-	unsigned short order = p->order;
+	u8 order = p->order;
 	unsigned int i;
 
 	p->order = 0;
@@ -195,10 +195,10 @@ void hyp_split_page(struct hyp_page *p)
 	}
 }
 
-void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order)
+void *hyp_alloc_pages(struct hyp_pool *pool, u8 order)
 {
-	unsigned short i = order;
 	struct hyp_page *p;
+	u8 i = order;
 
 	hyp_spin_lock(&pool->lock);
 
-- 
2.47.1.613.gc27f4b7a9f-goog

[PATCH v3 04/18] KVM: arm64: Move host page ownership tracking to the hyp vmemmap

[Quentin Perret]

We currently store part of the page-tracking state in PTE software bits
for the host, guests and the hypervisor. This is sub-optimal when e.g.
sharing pages as this forces to break block mappings purely to support
this software tracking. This causes an unnecessarily fragmented stage-2
page-table for the host in particular when it shares pages with Secure,
which can lead to measurable regressions. Moreover, having this state
stored in the page-table forces us to do multiple costly walks on the
page transition path, hence causing overhead.

In order to work around these problems, move the host-side page-tracking
logic from SW bits in its stage-2 PTEs to the hypervisor's vmemmap.

Signed-off-by: Quentin Perret <qperret@google.com>
---
 arch/arm64/kvm/hyp/include/nvhe/memory.h |   6 +-
 arch/arm64/kvm/hyp/nvhe/mem_protect.c    | 100 ++++++++++++++++-------
 arch/arm64/kvm/hyp/nvhe/setup.c          |   7 +-
 3 files changed, 77 insertions(+), 36 deletions(-)

diff --git a/arch/arm64/kvm/hyp/include/nvhe/memory.h b/arch/arm64/kvm/hyp/include/nvhe/memory.h
index 45b8d1840aa4..8bd9a539f260 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/memory.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/memory.h
@@ -8,7 +8,7 @@
 #include <linux/types.h>
 
 /*
- * SW bits 0-1 are reserved to track the memory ownership state of each page:
+ * Bits 0-1 are reserved to track the memory ownership state of each page:
  *   00: The page is owned exclusively by the page-table owner.
  *   01: The page is owned by the page-table owner, but is shared
  *       with another entity.
@@ -43,7 +43,9 @@ static inline enum pkvm_page_state pkvm_getstate(enum kvm_pgtable_prot prot)
 struct hyp_page {
 	u16 refcount;
 	u8 order;
-	u8 reserved;
+
+	/* Host (non-meta) state. Guarded by the host stage-2 lock. */
+	enum pkvm_page_state host_state : 8;
 };
 
 extern u64 __hyp_vmemmap;
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index caba3e4bd09e..12bb5445fe47 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -201,8 +201,8 @@ static void *guest_s2_zalloc_page(void *mc)
 
 	memset(addr, 0, PAGE_SIZE);
 	p = hyp_virt_to_page(addr);
-	memset(p, 0, sizeof(*p));
 	p->refcount = 1;
+	p->order = 0;
 
 	return addr;
 }
@@ -268,6 +268,7 @@ int kvm_guest_prepare_stage2(struct pkvm_hyp_vm *vm, void *pgd)
 
 void reclaim_guest_pages(struct pkvm_hyp_vm *vm, struct kvm_hyp_memcache *mc)
 {
+	struct hyp_page *page;
 	void *addr;
 
 	/* Dump all pgtable pages in the hyp_pool */
@@ -279,7 +280,9 @@ void reclaim_guest_pages(struct pkvm_hyp_vm *vm, struct kvm_hyp_memcache *mc)
 	/* Drain the hyp_pool into the memcache */
 	addr = hyp_alloc_pages(&vm->pool, 0);
 	while (addr) {
-		memset(hyp_virt_to_page(addr), 0, sizeof(struct hyp_page));
+		page = hyp_virt_to_page(addr);
+		page->refcount = 0;
+		page->order = 0;
 		push_hyp_memcache(mc, addr, hyp_virt_to_phys);
 		WARN_ON(__pkvm_hyp_donate_host(hyp_virt_to_pfn(addr), 1));
 		addr = hyp_alloc_pages(&vm->pool, 0);
@@ -382,19 +385,28 @@ bool addr_is_memory(phys_addr_t phys)
 	return !!find_mem_range(phys, &range);
 }
 
-static bool addr_is_allowed_memory(phys_addr_t phys)
+static bool is_in_mem_range(u64 addr, struct kvm_mem_range *range)
+{
+	return range->start <= addr && addr < range->end;
+}
+
+static int check_range_allowed_memory(u64 start, u64 end)
 {
 	struct memblock_region *reg;
 	struct kvm_mem_range range;
 
-	reg = find_mem_range(phys, &range);
+	/*
+	 * Callers can't check the state of a range that overlaps memory and
+	 * MMIO regions, so ensure [start, end[ is in the same kvm_mem_range.
+	 */
+	reg = find_mem_range(start, &range);
+	if (!is_in_mem_range(end - 1, &range))
+		return -EINVAL;
 
-	return reg && !(reg->flags & MEMBLOCK_NOMAP);
-}
+	if (!reg || reg->flags & MEMBLOCK_NOMAP)
+		return -EPERM;
 
-static bool is_in_mem_range(u64 addr, struct kvm_mem_range *range)
-{
-	return range->start <= addr && addr < range->end;
+	return 0;
 }
 
 static bool range_is_memory(u64 start, u64 end)
@@ -454,8 +466,10 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
 	if (kvm_pte_valid(pte))
 		return -EAGAIN;
 
-	if (pte)
+	if (pte) {
+		WARN_ON(addr_is_memory(addr) && hyp_phys_to_page(addr)->host_state != PKVM_NOPAGE);
 		return -EPERM;
+	}
 
 	do {
 		u64 granule = kvm_granule_size(level);
@@ -477,10 +491,33 @@ int host_stage2_idmap_locked(phys_addr_t addr, u64 size,
 	return host_stage2_try(__host_stage2_idmap, addr, addr + size, prot);
 }
 
+static void __host_update_page_state(phys_addr_t addr, u64 size, enum pkvm_page_state state)
+{
+	phys_addr_t end = addr + size;
+
+	for (; addr < end; addr += PAGE_SIZE)
+		hyp_phys_to_page(addr)->host_state = state;
+}
+
 int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id)
 {
-	return host_stage2_try(kvm_pgtable_stage2_set_owner, &host_mmu.pgt,
-			       addr, size, &host_s2_pool, owner_id);
+	int ret;
+
+	if (!addr_is_memory(addr))
+		return -EPERM;
+
+	ret = host_stage2_try(kvm_pgtable_stage2_set_owner, &host_mmu.pgt,
+			      addr, size, &host_s2_pool, owner_id);
+	if (ret)
+		return ret;
+
+	/* Don't forget to update the vmemmap tracking for the host */
+	if (owner_id == PKVM_ID_HOST)
+		__host_update_page_state(addr, size, PKVM_PAGE_OWNED);
+	else
+		__host_update_page_state(addr, size, PKVM_NOPAGE);
+
+	return 0;
 }
 
 static bool host_stage2_force_pte_cb(u64 addr, u64 end, enum kvm_pgtable_prot prot)
@@ -604,35 +641,38 @@ static int check_page_state_range(struct kvm_pgtable *pgt, u64 addr, u64 size,
 	return kvm_pgtable_walk(pgt, addr, size, &walker);
 }
 
-static enum pkvm_page_state host_get_page_state(kvm_pte_t pte, u64 addr)
-{
-	if (!addr_is_allowed_memory(addr))
-		return PKVM_NOPAGE;
-
-	if (!kvm_pte_valid(pte) && pte)
-		return PKVM_NOPAGE;
-
-	return pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte));
-}
-
 static int __host_check_page_state_range(u64 addr, u64 size,
 					 enum pkvm_page_state state)
 {
-	struct check_walk_data d = {
-		.desired	= state,
-		.get_page_state	= host_get_page_state,
-	};
+	u64 end = addr + size;
+	int ret;
+
+	ret = check_range_allowed_memory(addr, end);
+	if (ret)
+		return ret;
 
 	hyp_assert_lock_held(&host_mmu.lock);
-	return check_page_state_range(&host_mmu.pgt, addr, size, &d);
+	for (; addr < end; addr += PAGE_SIZE) {
+		if (hyp_phys_to_page(addr)->host_state != state)
+			return -EPERM;
+	}
+
+	return 0;
 }
 
 static int __host_set_page_state_range(u64 addr, u64 size,
 				       enum pkvm_page_state state)
 {
-	enum kvm_pgtable_prot prot = pkvm_mkstate(PKVM_HOST_MEM_PROT, state);
+	if (hyp_phys_to_page(addr)->host_state == PKVM_NOPAGE) {
+		int ret = host_stage2_idmap_locked(addr, size, PKVM_HOST_MEM_PROT);
 
-	return host_stage2_idmap_locked(addr, size, prot);
+		if (ret)
+			return ret;
+	}
+
+	__host_update_page_state(addr, size, state);
+
+	return 0;
 }
 
 static int host_request_owned_transition(u64 *completer_addr,
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index cbdd18cd3f98..7e04d1c2a03d 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -180,7 +180,6 @@ static void hpool_put_page(void *addr)
 static int fix_host_ownership_walker(const struct kvm_pgtable_visit_ctx *ctx,
 				     enum kvm_pgtable_walk_flags visit)
 {
-	enum kvm_pgtable_prot prot;
 	enum pkvm_page_state state;
 	phys_addr_t phys;
 
@@ -203,16 +202,16 @@ static int fix_host_ownership_walker(const struct kvm_pgtable_visit_ctx *ctx,
 	case PKVM_PAGE_OWNED:
 		return host_stage2_set_owner_locked(phys, PAGE_SIZE, PKVM_ID_HYP);
 	case PKVM_PAGE_SHARED_OWNED:
-		prot = pkvm_mkstate(PKVM_HOST_MEM_PROT, PKVM_PAGE_SHARED_BORROWED);
+		hyp_phys_to_page(phys)->host_state = PKVM_PAGE_SHARED_BORROWED;
 		break;
 	case PKVM_PAGE_SHARED_BORROWED:
-		prot = pkvm_mkstate(PKVM_HOST_MEM_PROT, PKVM_PAGE_SHARED_OWNED);
+		hyp_phys_to_page(phys)->host_state = PKVM_PAGE_SHARED_OWNED;
 		break;
 	default:
 		return -EINVAL;
 	}
 
-	return host_stage2_idmap_locked(phys, PAGE_SIZE, prot);
+	return 0;
 }
 
 static int fix_hyp_pgtable_refcnt_walker(const struct kvm_pgtable_visit_ctx *ctx,
-- 
2.47.1.613.gc27f4b7a9f-goog

[PATCH v3 05/18] KVM: arm64: Pass walk flags to kvm_pgtable_stage2_mkyoung

[Quentin Perret]

kvm_pgtable_stage2_mkyoung currently assumes that it is being called
from a 'shared' walker, which will not be true once called from pKVM.
To allow for the re-use of that function, make the walk flags one of
its parameters.

Signed-off-by: Quentin Perret <qperret@google.com>
---
 arch/arm64/include/asm/kvm_pgtable.h | 4 +++-
 arch/arm64/kvm/hyp/pgtable.c         | 7 +++----
 arch/arm64/kvm/mmu.c                 | 3 ++-
 3 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index aab04097b505..38b7ec1c8614 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -669,13 +669,15 @@ int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size);
  * kvm_pgtable_stage2_mkyoung() - Set the access flag in a page-table entry.
  * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
  * @addr:	Intermediate physical address to identify the page-table entry.
+ * @flags:	Flags to control the page-table walk (ex. a shared walk)
  *
  * The offset of @addr within a page is ignored.
  *
  * If there is a valid, leaf page-table entry used to translate @addr, then
  * set the access flag in that entry.
  */
-void kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr);
+void kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr,
+				enum kvm_pgtable_walk_flags flags);
 
 /**
  * kvm_pgtable_stage2_test_clear_young() - Test and optionally clear the access
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 40bd55966540..0470aedb4bf4 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -1245,14 +1245,13 @@ int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
 					NULL, NULL, 0);
 }
 
-void kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr)
+void kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr,
+				enum kvm_pgtable_walk_flags flags)
 {
 	int ret;
 
 	ret = stage2_update_leaf_attrs(pgt, addr, 1, KVM_PTE_LEAF_ATTR_LO_S2_AF, 0,
-				       NULL, NULL,
-				       KVM_PGTABLE_WALK_HANDLE_FAULT |
-				       KVM_PGTABLE_WALK_SHARED);
+				       NULL, NULL, flags);
 	if (!ret)
 		dsb(ishst);
 }
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index c9d46ad57e52..a2339b76c826 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1718,13 +1718,14 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 /* Resolve the access fault by making the page young again. */
 static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 {
+	enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED;
 	struct kvm_s2_mmu *mmu;
 
 	trace_kvm_access_fault(fault_ipa);
 
 	read_lock(&vcpu->kvm->mmu_lock);
 	mmu = vcpu->arch.hw_mmu;
-	kvm_pgtable_stage2_mkyoung(mmu->pgt, fault_ipa);
+	kvm_pgtable_stage2_mkyoung(mmu->pgt, fault_ipa, flags);
 	read_unlock(&vcpu->kvm->mmu_lock);
 }
 
-- 
2.47.1.613.gc27f4b7a9f-goog

[PATCH v3 06/18] KVM: arm64: Pass walk flags to kvm_pgtable_stage2_relax_perms

[Quentin Perret]

kvm_pgtable_stage2_relax_perms currently assumes that it is being called
from a 'shared' walker, which will not be true once called from pKVM. To
allow for the re-use of that function, make the walk flags one of its
parameters.

Signed-off-by: Quentin Perret <qperret@google.com>
---
 arch/arm64/include/asm/kvm_pgtable.h | 4 +++-
 arch/arm64/kvm/hyp/pgtable.c         | 6 ++----
 arch/arm64/kvm/mmu.c                 | 7 +++----
 3 files changed, 8 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 38b7ec1c8614..c2f4149283ef 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -707,6 +707,7 @@ bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr,
  * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
  * @addr:	Intermediate physical address to identify the page-table entry.
  * @prot:	Additional permissions to grant for the mapping.
+ * @flags:	Flags to control the page-table walk (ex. a shared walk)
  *
  * The offset of @addr within a page is ignored.
  *
@@ -719,7 +720,8 @@ bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr,
  * Return: 0 on success, negative error code on failure.
  */
 int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
-				   enum kvm_pgtable_prot prot);
+				   enum kvm_pgtable_prot prot,
+				   enum kvm_pgtable_walk_flags flags);
 
 /**
  * kvm_pgtable_stage2_flush_range() - Clean and invalidate data cache to Point
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 0470aedb4bf4..b7a3b5363235 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -1307,7 +1307,7 @@ bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr,
 }
 
 int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
-				   enum kvm_pgtable_prot prot)
+				   enum kvm_pgtable_prot prot, enum kvm_pgtable_walk_flags flags)
 {
 	int ret;
 	s8 level;
@@ -1325,9 +1325,7 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
 	if (prot & KVM_PGTABLE_PROT_X)
 		clr |= KVM_PTE_LEAF_ATTR_HI_S2_XN;
 
-	ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level,
-				       KVM_PGTABLE_WALK_HANDLE_FAULT |
-				       KVM_PGTABLE_WALK_SHARED);
+	ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level, flags);
 	if (!ret || ret == -EAGAIN)
 		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa_nsh, pgt->mmu, addr, level);
 	return ret;
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index a2339b76c826..641e4fec1659 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1452,6 +1452,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
 	struct kvm_pgtable *pgt;
 	struct page *page;
+	enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED;
 
 	if (fault_is_perm)
 		fault_granule = kvm_vcpu_trap_get_perm_fault_granule(vcpu);
@@ -1695,13 +1696,11 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		 * PTE, which will be preserved.
 		 */
 		prot &= ~KVM_NV_GUEST_MAP_SZ;
-		ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot);
+		ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot, flags);
 	} else {
 		ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
 					     __pfn_to_phys(pfn), prot,
-					     memcache,
-					     KVM_PGTABLE_WALK_HANDLE_FAULT |
-					     KVM_PGTABLE_WALK_SHARED);
+					     memcache, flags);
 	}
 
 out_unlock:
-- 
2.47.1.613.gc27f4b7a9f-goog

[PATCH v3 07/18] KVM: arm64: Make kvm_pgtable_stage2_init() a static inline function

[Quentin Perret]

Turn kvm_pgtable_stage2_init() into a static inline function instead of
a macro. This will allow the usage of typeof() on it later on.

Signed-off-by: Quentin Perret <qperret@google.com>
---
 arch/arm64/include/asm/kvm_pgtable.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index c2f4149283ef..04418b5e3004 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -526,8 +526,11 @@ int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
 			      enum kvm_pgtable_stage2_flags flags,
 			      kvm_pgtable_force_pte_cb_t force_pte_cb);
 
-#define kvm_pgtable_stage2_init(pgt, mmu, mm_ops) \
-	__kvm_pgtable_stage2_init(pgt, mmu, mm_ops, 0, NULL)
+static inline int kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
+					  struct kvm_pgtable_mm_ops *mm_ops)
+{
+	return __kvm_pgtable_stage2_init(pgt, mmu, mm_ops, 0, NULL);
+}
 
 /**
  * kvm_pgtable_stage2_destroy() - Destroy an unused guest stage-2 page-table.
-- 
2.47.1.613.gc27f4b7a9f-goog

[PATCH v3 08/18] KVM: arm64: Add {get,put}_pkvm_hyp_vm() helpers

[Quentin Perret]

In preparation for accessing pkvm_hyp_vm structures at EL2 in a context
where we can't always expect a vCPU to be loaded (e.g. MMU notifiers),
introduce get/put helpers to get temporary references to hyp VMs from
any context.

Signed-off-by: Quentin Perret <qperret@google.com>
---
 arch/arm64/kvm/hyp/include/nvhe/pkvm.h |  3 +++
 arch/arm64/kvm/hyp/nvhe/pkvm.c         | 20 ++++++++++++++++++++
 2 files changed, 23 insertions(+)

diff --git a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
index 24a9a8330d19..f361d8b91930 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
@@ -70,4 +70,7 @@ struct pkvm_hyp_vcpu *pkvm_load_hyp_vcpu(pkvm_handle_t handle,
 					 unsigned int vcpu_idx);
 void pkvm_put_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu);
 
+struct pkvm_hyp_vm *get_pkvm_hyp_vm(pkvm_handle_t handle);
+void put_pkvm_hyp_vm(struct pkvm_hyp_vm *hyp_vm);
+
 #endif /* __ARM64_KVM_NVHE_PKVM_H__ */
diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index 071993c16de8..d46a02e24e4a 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -327,6 +327,26 @@ void pkvm_put_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 	hyp_spin_unlock(&vm_table_lock);
 }
 
+struct pkvm_hyp_vm *get_pkvm_hyp_vm(pkvm_handle_t handle)
+{
+	struct pkvm_hyp_vm *hyp_vm;
+
+	hyp_spin_lock(&vm_table_lock);
+	hyp_vm = get_vm_by_handle(handle);
+	if (hyp_vm)
+		hyp_page_ref_inc(hyp_virt_to_page(hyp_vm));
+	hyp_spin_unlock(&vm_table_lock);
+
+	return hyp_vm;
+}
+
+void put_pkvm_hyp_vm(struct pkvm_hyp_vm *hyp_vm)
+{
+	hyp_spin_lock(&vm_table_lock);
+	hyp_page_ref_dec(hyp_virt_to_page(hyp_vm));
+	hyp_spin_unlock(&vm_table_lock);
+}
+
 static void pkvm_init_features_from_host(struct pkvm_hyp_vm *hyp_vm, const struct kvm *host_kvm)
 {
 	struct kvm *kvm = &hyp_vm->kvm;
-- 
2.47.1.613.gc27f4b7a9f-goog

[PATCH v3 09/18] KVM: arm64: Introduce __pkvm_vcpu_{load,put}()

[Quentin Perret]

From: Marc Zyngier <maz@kernel.org>

Rather than look-up the hyp vCPU on every run hypercall at EL2,
introduce a per-CPU 'loaded_hyp_vcpu' tracking variable which is updated
by a pair of load/put hypercalls called directly from
kvm_arch_vcpu_{load,put}() when pKVM is enabled.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Quentin Perret <qperret@google.com>
---
 arch/arm64/include/asm/kvm_asm.h       |  2 ++
 arch/arm64/kvm/arm.c                   | 14 ++++++++
 arch/arm64/kvm/hyp/include/nvhe/pkvm.h |  7 ++++
 arch/arm64/kvm/hyp/nvhe/hyp-main.c     | 47 ++++++++++++++++++++------
 arch/arm64/kvm/hyp/nvhe/pkvm.c         | 29 ++++++++++++++++
 arch/arm64/kvm/vgic/vgic-v3.c          |  6 ++--
 6 files changed, 93 insertions(+), 12 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index ca2590344313..89c0fac69551 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -79,6 +79,8 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___pkvm_init_vm,
 	__KVM_HOST_SMCCC_FUNC___pkvm_init_vcpu,
 	__KVM_HOST_SMCCC_FUNC___pkvm_teardown_vm,
+	__KVM_HOST_SMCCC_FUNC___pkvm_vcpu_load,
+	__KVM_HOST_SMCCC_FUNC___pkvm_vcpu_put,
 };
 
 #define DECLARE_KVM_VHE_SYM(sym)	extern char sym[]
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index a102c3aebdbc..55cc62b2f469 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -619,12 +619,26 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	kvm_arch_vcpu_load_debug_state_flags(vcpu);
 
+	if (is_protected_kvm_enabled()) {
+		kvm_call_hyp_nvhe(__pkvm_vcpu_load,
+				  vcpu->kvm->arch.pkvm.handle,
+				  vcpu->vcpu_idx, vcpu->arch.hcr_el2);
+		kvm_call_hyp(__vgic_v3_restore_vmcr_aprs,
+			     &vcpu->arch.vgic_cpu.vgic_v3);
+	}
+
 	if (!cpumask_test_cpu(cpu, vcpu->kvm->arch.supported_cpus))
 		vcpu_set_on_unsupported_cpu(vcpu);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
+	if (is_protected_kvm_enabled()) {
+		kvm_call_hyp(__vgic_v3_save_vmcr_aprs,
+			     &vcpu->arch.vgic_cpu.vgic_v3);
+		kvm_call_hyp_nvhe(__pkvm_vcpu_put);
+	}
+
 	kvm_arch_vcpu_put_debug_state_flags(vcpu);
 	kvm_arch_vcpu_put_fp(vcpu);
 	if (has_vhe())
diff --git a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
index f361d8b91930..be52c5b15e21 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
@@ -20,6 +20,12 @@ struct pkvm_hyp_vcpu {
 
 	/* Backpointer to the host's (untrusted) vCPU instance. */
 	struct kvm_vcpu *host_vcpu;
+
+	/*
+	 * If this hyp vCPU is loaded, then this is a backpointer to the
+	 * per-cpu pointer tracking us. Otherwise, NULL if not loaded.
+	 */
+	struct pkvm_hyp_vcpu **loaded_hyp_vcpu;
 };
 
 /*
@@ -69,6 +75,7 @@ int __pkvm_teardown_vm(pkvm_handle_t handle);
 struct pkvm_hyp_vcpu *pkvm_load_hyp_vcpu(pkvm_handle_t handle,
 					 unsigned int vcpu_idx);
 void pkvm_put_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu);
+struct pkvm_hyp_vcpu *pkvm_get_loaded_hyp_vcpu(void);
 
 struct pkvm_hyp_vm *get_pkvm_hyp_vm(pkvm_handle_t handle);
 void put_pkvm_hyp_vm(struct pkvm_hyp_vm *hyp_vm);
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 6aa0b13d86e5..95d78db315b3 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -141,16 +141,46 @@ static void sync_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 		host_cpu_if->vgic_lr[i] = hyp_cpu_if->vgic_lr[i];
 }
 
+static void handle___pkvm_vcpu_load(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);
+	DECLARE_REG(unsigned int, vcpu_idx, host_ctxt, 2);
+	DECLARE_REG(u64, hcr_el2, host_ctxt, 3);
+	struct pkvm_hyp_vcpu *hyp_vcpu;
+
+	if (!is_protected_kvm_enabled())
+		return;
+
+	hyp_vcpu = pkvm_load_hyp_vcpu(handle, vcpu_idx);
+	if (!hyp_vcpu)
+		return;
+
+	if (pkvm_hyp_vcpu_is_protected(hyp_vcpu)) {
+		/* Propagate WFx trapping flags */
+		hyp_vcpu->vcpu.arch.hcr_el2 &= ~(HCR_TWE | HCR_TWI);
+		hyp_vcpu->vcpu.arch.hcr_el2 |= hcr_el2 & (HCR_TWE | HCR_TWI);
+	}
+}
+
+static void handle___pkvm_vcpu_put(struct kvm_cpu_context *host_ctxt)
+{
+	struct pkvm_hyp_vcpu *hyp_vcpu;
+
+	if (!is_protected_kvm_enabled())
+		return;
+
+	hyp_vcpu = pkvm_get_loaded_hyp_vcpu();
+	if (hyp_vcpu)
+		pkvm_put_hyp_vcpu(hyp_vcpu);
+}
+
 static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct kvm_vcpu *, host_vcpu, host_ctxt, 1);
 	int ret;
 
-	host_vcpu = kern_hyp_va(host_vcpu);
-
 	if (unlikely(is_protected_kvm_enabled())) {
-		struct pkvm_hyp_vcpu *hyp_vcpu;
-		struct kvm *host_kvm;
+		struct pkvm_hyp_vcpu *hyp_vcpu = pkvm_get_loaded_hyp_vcpu();
 
 		/*
 		 * KVM (and pKVM) doesn't support SME guests for now, and
@@ -163,9 +193,6 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
 			goto out;
 		}
 
-		host_kvm = kern_hyp_va(host_vcpu->kvm);
-		hyp_vcpu = pkvm_load_hyp_vcpu(host_kvm->arch.pkvm.handle,
-					      host_vcpu->vcpu_idx);
 		if (!hyp_vcpu) {
 			ret = -EINVAL;
 			goto out;
@@ -176,12 +203,10 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
 		ret = __kvm_vcpu_run(&hyp_vcpu->vcpu);
 
 		sync_hyp_vcpu(hyp_vcpu);
-		pkvm_put_hyp_vcpu(hyp_vcpu);
 	} else {
 		/* The host is fully trusted, run its vCPU directly. */
-		ret = __kvm_vcpu_run(host_vcpu);
+		ret = __kvm_vcpu_run(kern_hyp_va(host_vcpu));
 	}
-
 out:
 	cpu_reg(host_ctxt, 1) =  ret;
 }
@@ -409,6 +434,8 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__pkvm_init_vm),
 	HANDLE_FUNC(__pkvm_init_vcpu),
 	HANDLE_FUNC(__pkvm_teardown_vm),
+	HANDLE_FUNC(__pkvm_vcpu_load),
+	HANDLE_FUNC(__pkvm_vcpu_put),
 };
 
 static void handle_host_hcall(struct kvm_cpu_context *host_ctxt)
diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index d46a02e24e4a..496d186efb03 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -23,6 +23,12 @@ unsigned int kvm_arm_vmid_bits;
 
 unsigned int kvm_host_sve_max_vl;
 
+/*
+ * The currently loaded hyp vCPU for each physical CPU. Used only when
+ * protected KVM is enabled, but for both protected and non-protected VMs.
+ */
+static DEFINE_PER_CPU(struct pkvm_hyp_vcpu *, loaded_hyp_vcpu);
+
 /*
  * Set trap register values based on features in ID_AA64PFR0.
  */
@@ -306,15 +312,30 @@ struct pkvm_hyp_vcpu *pkvm_load_hyp_vcpu(pkvm_handle_t handle,
 	struct pkvm_hyp_vcpu *hyp_vcpu = NULL;
 	struct pkvm_hyp_vm *hyp_vm;
 
+	/* Cannot load a new vcpu without putting the old one first. */
+	if (__this_cpu_read(loaded_hyp_vcpu))
+		return NULL;
+
 	hyp_spin_lock(&vm_table_lock);
 	hyp_vm = get_vm_by_handle(handle);
 	if (!hyp_vm || hyp_vm->nr_vcpus <= vcpu_idx)
 		goto unlock;
 
 	hyp_vcpu = hyp_vm->vcpus[vcpu_idx];
+
+	/* Ensure vcpu isn't loaded on more than one cpu simultaneously. */
+	if (unlikely(hyp_vcpu->loaded_hyp_vcpu)) {
+		hyp_vcpu = NULL;
+		goto unlock;
+	}
+
+	hyp_vcpu->loaded_hyp_vcpu = this_cpu_ptr(&loaded_hyp_vcpu);
 	hyp_page_ref_inc(hyp_virt_to_page(hyp_vm));
 unlock:
 	hyp_spin_unlock(&vm_table_lock);
+
+	if (hyp_vcpu)
+		__this_cpu_write(loaded_hyp_vcpu, hyp_vcpu);
 	return hyp_vcpu;
 }
 
@@ -323,10 +344,18 @@ void pkvm_put_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 	struct pkvm_hyp_vm *hyp_vm = pkvm_hyp_vcpu_to_hyp_vm(hyp_vcpu);
 
 	hyp_spin_lock(&vm_table_lock);
+	hyp_vcpu->loaded_hyp_vcpu = NULL;
+	__this_cpu_write(loaded_hyp_vcpu, NULL);
 	hyp_page_ref_dec(hyp_virt_to_page(hyp_vm));
 	hyp_spin_unlock(&vm_table_lock);
 }
 
+struct pkvm_hyp_vcpu *pkvm_get_loaded_hyp_vcpu(void)
+{
+	return __this_cpu_read(loaded_hyp_vcpu);
+
+}
+
 struct pkvm_hyp_vm *get_pkvm_hyp_vm(pkvm_handle_t handle)
 {
 	struct pkvm_hyp_vm *hyp_vm;
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index f267bc2486a1..c2ef41fff079 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -734,7 +734,8 @@ void vgic_v3_load(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 
-	kvm_call_hyp(__vgic_v3_restore_vmcr_aprs, cpu_if);
+	if (likely(!is_protected_kvm_enabled()))
+		kvm_call_hyp(__vgic_v3_restore_vmcr_aprs, cpu_if);
 
 	if (has_vhe())
 		__vgic_v3_activate_traps(cpu_if);
@@ -746,7 +747,8 @@ void vgic_v3_put(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 
-	kvm_call_hyp(__vgic_v3_save_vmcr_aprs, cpu_if);
+	if (likely(!is_protected_kvm_enabled()))
+		kvm_call_hyp(__vgic_v3_save_vmcr_aprs, cpu_if);
 	WARN_ON(vgic_v4_put(vcpu));
 
 	if (has_vhe())
-- 
2.47.1.613.gc27f4b7a9f-goog

[PATCH v3 10/18] KVM: arm64: Introduce __pkvm_host_share_guest()

[Quentin Perret]

In preparation for handling guest stage-2 mappings at EL2, introduce a
new pKVM hypercall allowing to share pages with non-protected guests.

Signed-off-by: Quentin Perret <qperret@google.com>
---
 arch/arm64/include/asm/kvm_asm.h              |  1 +
 arch/arm64/include/asm/kvm_host.h             |  3 +
 arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |  1 +
 arch/arm64/kvm/hyp/include/nvhe/memory.h      |  2 +
 arch/arm64/kvm/hyp/nvhe/hyp-main.c            | 34 +++++++++
 arch/arm64/kvm/hyp/nvhe/mem_protect.c         | 72 +++++++++++++++++++
 arch/arm64/kvm/hyp/nvhe/pkvm.c                |  7 ++
 7 files changed, 120 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 89c0fac69551..449337f5b2a3 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -65,6 +65,7 @@ enum __kvm_host_smccc_func {
 	/* Hypercalls available after pKVM finalisation */
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp,
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_hyp,
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_share_guest,
 	__KVM_HOST_SMCCC_FUNC___kvm_adjust_pc,
 	__KVM_HOST_SMCCC_FUNC___kvm_vcpu_run,
 	__KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context,
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index e18e9244d17a..1246f1d01dbf 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -771,6 +771,9 @@ struct kvm_vcpu_arch {
 	/* Cache some mmu pages needed inside spinlock regions */
 	struct kvm_mmu_memory_cache mmu_page_cache;
 
+	/* Pages to top-up the pKVM/EL2 guest pool */
+	struct kvm_hyp_memcache pkvm_memcache;
+
 	/* Virtual SError ESR to restore when HCR_EL2.VSE is set */
 	u64 vsesr_el2;
 
diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
index 25038ac705d8..a7976e50f556 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
@@ -39,6 +39,7 @@ int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages);
 int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages);
 int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages);
 int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages);
+int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot);
 
 bool addr_is_memory(phys_addr_t phys);
 int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot);
diff --git a/arch/arm64/kvm/hyp/include/nvhe/memory.h b/arch/arm64/kvm/hyp/include/nvhe/memory.h
index 8bd9a539f260..cc431820c6ce 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/memory.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/memory.h
@@ -46,6 +46,8 @@ struct hyp_page {
 
 	/* Host (non-meta) state. Guarded by the host stage-2 lock. */
 	enum pkvm_page_state host_state : 8;
+
+	u32 host_share_guest_count;
 };
 
 extern u64 __hyp_vmemmap;
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 95d78db315b3..d659462fbf5d 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -211,6 +211,39 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
 	cpu_reg(host_ctxt, 1) =  ret;
 }
 
+static int pkvm_refill_memcache(struct pkvm_hyp_vcpu *hyp_vcpu)
+{
+	struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
+
+	return refill_memcache(&hyp_vcpu->vcpu.arch.pkvm_memcache,
+			       host_vcpu->arch.pkvm_memcache.nr_pages,
+			       &host_vcpu->arch.pkvm_memcache);
+}
+
+static void handle___pkvm_host_share_guest(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(u64, pfn, host_ctxt, 1);
+	DECLARE_REG(u64, gfn, host_ctxt, 2);
+	DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 3);
+	struct pkvm_hyp_vcpu *hyp_vcpu;
+	int ret = -EINVAL;
+
+	if (!is_protected_kvm_enabled())
+		goto out;
+
+	hyp_vcpu = pkvm_get_loaded_hyp_vcpu();
+	if (!hyp_vcpu || pkvm_hyp_vcpu_is_protected(hyp_vcpu))
+		goto out;
+
+	ret = pkvm_refill_memcache(hyp_vcpu);
+	if (ret)
+		goto out;
+
+	ret = __pkvm_host_share_guest(pfn, gfn, hyp_vcpu, prot);
+out:
+	cpu_reg(host_ctxt, 1) =  ret;
+}
+
 static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1);
@@ -420,6 +453,7 @@ static const hcall_t host_hcall[] = {
 
 	HANDLE_FUNC(__pkvm_host_share_hyp),
 	HANDLE_FUNC(__pkvm_host_unshare_hyp),
+	HANDLE_FUNC(__pkvm_host_share_guest),
 	HANDLE_FUNC(__kvm_adjust_pc),
 	HANDLE_FUNC(__kvm_vcpu_run),
 	HANDLE_FUNC(__kvm_flush_vm_context),
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 12bb5445fe47..fb9592e721cf 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -867,6 +867,27 @@ static int hyp_complete_donation(u64 addr,
 	return pkvm_create_mappings_locked(start, end, prot);
 }
 
+static enum pkvm_page_state guest_get_page_state(kvm_pte_t pte, u64 addr)
+{
+	if (!kvm_pte_valid(pte))
+		return PKVM_NOPAGE;
+
+	return pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte));
+}
+
+static int __guest_check_page_state_range(struct pkvm_hyp_vcpu *vcpu, u64 addr,
+					  u64 size, enum pkvm_page_state state)
+{
+	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
+	struct check_walk_data d = {
+		.desired	= state,
+		.get_page_state	= guest_get_page_state,
+	};
+
+	hyp_assert_lock_held(&vm->lock);
+	return check_page_state_range(&vm->pgt, addr, size, &d);
+}
+
 static int check_share(struct pkvm_mem_share *share)
 {
 	const struct pkvm_mem_transition *tx = &share->tx;
@@ -1349,3 +1370,54 @@ int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages)
 
 	return ret;
 }
+
+int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu,
+			    enum kvm_pgtable_prot prot)
+{
+	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
+	u64 phys = hyp_pfn_to_phys(pfn);
+	u64 ipa = hyp_pfn_to_phys(gfn);
+	struct hyp_page *page;
+	int ret;
+
+	if (prot & ~KVM_PGTABLE_PROT_RWX)
+		return -EINVAL;
+
+	ret = check_range_allowed_memory(phys, phys + PAGE_SIZE);
+	if (ret)
+		return ret;
+
+	host_lock_component();
+	guest_lock_component(vm);
+
+	ret = __guest_check_page_state_range(vcpu, ipa, PAGE_SIZE, PKVM_NOPAGE);
+	if (ret)
+		goto unlock;
+
+	page = hyp_phys_to_page(phys);
+	switch (page->host_state) {
+	case PKVM_PAGE_OWNED:
+		WARN_ON(__host_set_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_SHARED_OWNED));
+		break;
+	case PKVM_PAGE_SHARED_OWNED:
+		if (page->host_share_guest_count)
+			break;
+		/* Only host to np-guest multi-sharing is tolerated */
+		WARN_ON(1);
+		fallthrough;
+	default:
+		ret = -EPERM;
+		goto unlock;
+	}
+
+	WARN_ON(kvm_pgtable_stage2_map(&vm->pgt, ipa, PAGE_SIZE, phys,
+				       pkvm_mkstate(prot, PKVM_PAGE_SHARED_BORROWED),
+				       &vcpu->vcpu.arch.pkvm_memcache, 0));
+	page->host_share_guest_count++;
+
+unlock:
+	guest_unlock_component(vm);
+	host_unlock_component();
+
+	return ret;
+}
diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index 496d186efb03..f2e363fe6b84 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -795,6 +795,13 @@ int __pkvm_teardown_vm(pkvm_handle_t handle)
 	/* Push the metadata pages to the teardown memcache */
 	for (idx = 0; idx < hyp_vm->nr_vcpus; ++idx) {
 		struct pkvm_hyp_vcpu *hyp_vcpu = hyp_vm->vcpus[idx];
+		struct kvm_hyp_memcache *vcpu_mc = &hyp_vcpu->vcpu.arch.pkvm_memcache;
+
+		while (vcpu_mc->nr_pages) {
+			void *addr = pop_hyp_memcache(vcpu_mc, hyp_phys_to_virt);
+			push_hyp_memcache(mc, addr, hyp_virt_to_phys);
+			unmap_donated_memory_noclear(addr, PAGE_SIZE);
+		}
 
 		teardown_donated_memory(mc, hyp_vcpu, sizeof(*hyp_vcpu));
 	}
-- 
2.47.1.613.gc27f4b7a9f-goog

[PATCH v3 11/18] KVM: arm64: Introduce __pkvm_host_unshare_guest()

[Quentin Perret]

In preparation for letting the host unmap pages from non-protected
guests, introduce a new hypercall implementing the host-unshare-guest
transition.

Signed-off-by: Quentin Perret <qperret@google.com>
---
 arch/arm64/include/asm/kvm_asm.h              |  1 +
 arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |  1 +
 arch/arm64/kvm/hyp/include/nvhe/pkvm.h        |  6 ++
 arch/arm64/kvm/hyp/nvhe/hyp-main.c            | 21 ++++++
 arch/arm64/kvm/hyp/nvhe/mem_protect.c         | 67 +++++++++++++++++++
 arch/arm64/kvm/hyp/nvhe/pkvm.c                | 12 ++++
 6 files changed, 108 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 449337f5b2a3..0b6c4d325134 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -66,6 +66,7 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp,
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_hyp,
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_share_guest,
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_guest,
 	__KVM_HOST_SMCCC_FUNC___kvm_adjust_pc,
 	__KVM_HOST_SMCCC_FUNC___kvm_vcpu_run,
 	__KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context,
diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
index a7976e50f556..e528a42ed60e 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
@@ -40,6 +40,7 @@ int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages);
 int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages);
 int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages);
 int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot);
+int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm);
 
 bool addr_is_memory(phys_addr_t phys);
 int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot);
diff --git a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
index be52c5b15e21..0cc2a429f1fb 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
@@ -64,6 +64,11 @@ static inline bool pkvm_hyp_vcpu_is_protected(struct pkvm_hyp_vcpu *hyp_vcpu)
 	return vcpu_is_protected(&hyp_vcpu->vcpu);
 }
 
+static inline bool pkvm_hyp_vm_is_protected(struct pkvm_hyp_vm *hyp_vm)
+{
+	return kvm_vm_is_protected(&hyp_vm->kvm);
+}
+
 void pkvm_hyp_vm_table_init(void *tbl);
 
 int __pkvm_init_vm(struct kvm *host_kvm, unsigned long vm_hva,
@@ -78,6 +83,7 @@ void pkvm_put_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu);
 struct pkvm_hyp_vcpu *pkvm_get_loaded_hyp_vcpu(void);
 
 struct pkvm_hyp_vm *get_pkvm_hyp_vm(pkvm_handle_t handle);
+struct pkvm_hyp_vm *get_np_pkvm_hyp_vm(pkvm_handle_t handle);
 void put_pkvm_hyp_vm(struct pkvm_hyp_vm *hyp_vm);
 
 #endif /* __ARM64_KVM_NVHE_PKVM_H__ */
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index d659462fbf5d..3c3a27c985a2 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -244,6 +244,26 @@ static void handle___pkvm_host_share_guest(struct kvm_cpu_context *host_ctxt)
 	cpu_reg(host_ctxt, 1) =  ret;
 }
 
+static void handle___pkvm_host_unshare_guest(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);
+	DECLARE_REG(u64, gfn, host_ctxt, 2);
+	struct pkvm_hyp_vm *hyp_vm;
+	int ret = -EINVAL;
+
+	if (!is_protected_kvm_enabled())
+		goto out;
+
+	hyp_vm = get_np_pkvm_hyp_vm(handle);
+	if (!hyp_vm)
+		goto out;
+
+	ret = __pkvm_host_unshare_guest(gfn, hyp_vm);
+	put_pkvm_hyp_vm(hyp_vm);
+out:
+	cpu_reg(host_ctxt, 1) =  ret;
+}
+
 static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1);
@@ -454,6 +474,7 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__pkvm_host_share_hyp),
 	HANDLE_FUNC(__pkvm_host_unshare_hyp),
 	HANDLE_FUNC(__pkvm_host_share_guest),
+	HANDLE_FUNC(__pkvm_host_unshare_guest),
 	HANDLE_FUNC(__kvm_adjust_pc),
 	HANDLE_FUNC(__kvm_vcpu_run),
 	HANDLE_FUNC(__kvm_flush_vm_context),
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index fb9592e721cf..30243b7922f1 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -1421,3 +1421,70 @@ int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu,
 
 	return ret;
 }
+
+static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ipa)
+{
+	enum pkvm_page_state state;
+	struct hyp_page *page;
+	kvm_pte_t pte;
+	u64 phys;
+	s8 level;
+	int ret;
+
+	ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level);
+	if (ret)
+		return ret;
+	if (level != KVM_PGTABLE_LAST_LEVEL)
+		return -E2BIG;
+	if (!kvm_pte_valid(pte))
+		return -ENOENT;
+
+	state = guest_get_page_state(pte, ipa);
+	if (state != PKVM_PAGE_SHARED_BORROWED)
+		return -EPERM;
+
+	phys = kvm_pte_to_phys(pte);
+	ret = check_range_allowed_memory(phys, phys + PAGE_SIZE);
+	if (WARN_ON(ret))
+		return ret;
+
+	page = hyp_phys_to_page(phys);
+	if (page->host_state != PKVM_PAGE_SHARED_OWNED)
+		return -EPERM;
+	if (WARN_ON(!page->host_share_guest_count))
+		return -EINVAL;
+
+	*__phys = phys;
+
+	return 0;
+}
+
+int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *vm)
+{
+	u64 ipa = hyp_pfn_to_phys(gfn);
+	struct hyp_page *page;
+	u64 phys;
+	int ret;
+
+	host_lock_component();
+	guest_lock_component(vm);
+
+	ret = __check_host_shared_guest(vm, &phys, ipa);
+	if (ret)
+		goto unlock;
+
+	ret = kvm_pgtable_stage2_unmap(&vm->pgt, ipa, PAGE_SIZE);
+	if (ret)
+		goto unlock;
+
+	page = hyp_phys_to_page(phys);
+	page->host_share_guest_count--;
+	if (!page->host_share_guest_count)
+		WARN_ON(__host_set_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_OWNED));
+
+unlock:
+	guest_unlock_component(vm);
+	host_unlock_component();
+
+	return ret;
+}
diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index f2e363fe6b84..1b0982fa5ba8 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -376,6 +376,18 @@ void put_pkvm_hyp_vm(struct pkvm_hyp_vm *hyp_vm)
 	hyp_spin_unlock(&vm_table_lock);
 }
 
+struct pkvm_hyp_vm *get_np_pkvm_hyp_vm(pkvm_handle_t handle)
+{
+	struct pkvm_hyp_vm *hyp_vm = get_pkvm_hyp_vm(handle);
+
+	if (hyp_vm && pkvm_hyp_vm_is_protected(hyp_vm)) {
+		put_pkvm_hyp_vm(hyp_vm);
+		hyp_vm = NULL;
+	}
+
+	return hyp_vm;
+}
+
 static void pkvm_init_features_from_host(struct pkvm_hyp_vm *hyp_vm, const struct kvm *host_kvm)
 {
 	struct kvm *kvm = &hyp_vm->kvm;
-- 
2.47.1.613.gc27f4b7a9f-goog

[PATCH v3 12/18] KVM: arm64: Introduce __pkvm_host_relax_guest_perms()

[Quentin Perret]

Introduce a new hypercall allowing the host to relax the stage-2
permissions of mappings in a non-protected guest page-table. It will be
used later once we start allowing RO memslots and dirty logging.

Signed-off-by: Quentin Perret <qperret@google.com>
---
 arch/arm64/include/asm/kvm_asm.h              |  1 +
 arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |  1 +
 arch/arm64/kvm/hyp/nvhe/hyp-main.c            | 20 ++++++++++++++++
 arch/arm64/kvm/hyp/nvhe/mem_protect.c         | 23 +++++++++++++++++++
 4 files changed, 45 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 0b6c4d325134..66ee8542dcc9 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -67,6 +67,7 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_hyp,
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_share_guest,
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_guest,
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_relax_perms_guest,
 	__KVM_HOST_SMCCC_FUNC___kvm_adjust_pc,
 	__KVM_HOST_SMCCC_FUNC___kvm_vcpu_run,
 	__KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context,
diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
index e528a42ed60e..a308dcd3b5b8 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
@@ -41,6 +41,7 @@ int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages);
 int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages);
 int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot);
 int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm);
+int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot);
 
 bool addr_is_memory(phys_addr_t phys);
 int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot);
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 3c3a27c985a2..287e4ee93ef2 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -264,6 +264,25 @@ static void handle___pkvm_host_unshare_guest(struct kvm_cpu_context *host_ctxt)
 	cpu_reg(host_ctxt, 1) =  ret;
 }
 
+static void handle___pkvm_host_relax_perms_guest(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(u64, gfn, host_ctxt, 1);
+	DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 2);
+	struct pkvm_hyp_vcpu *hyp_vcpu;
+	int ret = -EINVAL;
+
+	if (!is_protected_kvm_enabled())
+		goto out;
+
+	hyp_vcpu = pkvm_get_loaded_hyp_vcpu();
+	if (!hyp_vcpu || pkvm_hyp_vcpu_is_protected(hyp_vcpu))
+		goto out;
+
+	ret = __pkvm_host_relax_perms_guest(gfn, hyp_vcpu, prot);
+out:
+	cpu_reg(host_ctxt, 1) = ret;
+}
+
 static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1);
@@ -475,6 +494,7 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__pkvm_host_unshare_hyp),
 	HANDLE_FUNC(__pkvm_host_share_guest),
 	HANDLE_FUNC(__pkvm_host_unshare_guest),
+	HANDLE_FUNC(__pkvm_host_relax_perms_guest),
 	HANDLE_FUNC(__kvm_adjust_pc),
 	HANDLE_FUNC(__kvm_vcpu_run),
 	HANDLE_FUNC(__kvm_flush_vm_context),
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 30243b7922f1..aa8e0408aebb 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -1488,3 +1488,26 @@ int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *vm)
 
 	return ret;
 }
+
+int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot)
+{
+	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
+	u64 ipa = hyp_pfn_to_phys(gfn);
+	u64 phys;
+	int ret;
+
+	if (prot & ~KVM_PGTABLE_PROT_RWX)
+		return -EINVAL;
+
+	host_lock_component();
+	guest_lock_component(vm);
+
+	ret = __check_host_shared_guest(vm, &phys, ipa);
+	if (!ret)
+		ret = kvm_pgtable_stage2_relax_perms(&vm->pgt, ipa, prot, 0);
+
+	guest_unlock_component(vm);
+	host_unlock_component();
+
+	return ret;
+}
-- 
2.47.1.613.gc27f4b7a9f-goog

[PATCH v3 13/18] KVM: arm64: Introduce __pkvm_host_wrprotect_guest()

[Quentin Perret]

Introduce a new hypercall to remove the write permission from a
non-protected guest stage-2 mapping. This will be used for e.g. enabling
dirty logging.

Signed-off-by: Quentin Perret <qperret@google.com>
---
 arch/arm64/include/asm/kvm_asm.h              |  1 +
 arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |  1 +
 arch/arm64/kvm/hyp/nvhe/hyp-main.c            | 21 +++++++++++++++++++
 arch/arm64/kvm/hyp/nvhe/mem_protect.c         | 19 +++++++++++++++++
 4 files changed, 42 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 66ee8542dcc9..8663a588cf34 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -68,6 +68,7 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_share_guest,
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_guest,
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_relax_perms_guest,
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_wrprotect_guest,
 	__KVM_HOST_SMCCC_FUNC___kvm_adjust_pc,
 	__KVM_HOST_SMCCC_FUNC___kvm_vcpu_run,
 	__KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context,
diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
index a308dcd3b5b8..fc9fdd5b0a52 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
@@ -42,6 +42,7 @@ int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages);
 int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot);
 int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm);
 int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot);
+int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm);
 
 bool addr_is_memory(phys_addr_t phys);
 int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot);
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 287e4ee93ef2..98d317735107 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -283,6 +283,26 @@ static void handle___pkvm_host_relax_perms_guest(struct kvm_cpu_context *host_ct
 	cpu_reg(host_ctxt, 1) = ret;
 }
 
+static void handle___pkvm_host_wrprotect_guest(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);
+	DECLARE_REG(u64, gfn, host_ctxt, 2);
+	struct pkvm_hyp_vm *hyp_vm;
+	int ret = -EINVAL;
+
+	if (!is_protected_kvm_enabled())
+		goto out;
+
+	hyp_vm = get_np_pkvm_hyp_vm(handle);
+	if (!hyp_vm)
+		goto out;
+
+	ret = __pkvm_host_wrprotect_guest(gfn, hyp_vm);
+	put_pkvm_hyp_vm(hyp_vm);
+out:
+	cpu_reg(host_ctxt, 1) = ret;
+}
+
 static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1);
@@ -495,6 +515,7 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__pkvm_host_share_guest),
 	HANDLE_FUNC(__pkvm_host_unshare_guest),
 	HANDLE_FUNC(__pkvm_host_relax_perms_guest),
+	HANDLE_FUNC(__pkvm_host_wrprotect_guest),
 	HANDLE_FUNC(__kvm_adjust_pc),
 	HANDLE_FUNC(__kvm_vcpu_run),
 	HANDLE_FUNC(__kvm_flush_vm_context),
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index aa8e0408aebb..94e4251b5077 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -1511,3 +1511,22 @@ int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_
 
 	return ret;
 }
+
+int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *vm)
+{
+	u64 ipa = hyp_pfn_to_phys(gfn);
+	u64 phys;
+	int ret;
+
+	host_lock_component();
+	guest_lock_component(vm);
+
+	ret = __check_host_shared_guest(vm, &phys, ipa);
+	if (!ret)
+		ret = kvm_pgtable_stage2_wrprotect(&vm->pgt, ipa, PAGE_SIZE);
+
+	guest_unlock_component(vm);
+	host_unlock_component();
+
+	return ret;
+}
-- 
2.47.1.613.gc27f4b7a9f-goog

[PATCH v3 14/18] KVM: arm64: Introduce __pkvm_host_test_clear_young_guest()

[Quentin Perret]

Plumb the kvm_stage2_test_clear_young() callback into pKVM for
non-protected guest. It will be later be called from MMU notifiers.

Signed-off-by: Quentin Perret <qperret@google.com>
---
 arch/arm64/include/asm/kvm_asm.h              |  1 +
 arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |  1 +
 arch/arm64/kvm/hyp/nvhe/hyp-main.c            | 22 +++++++++++++++++++
 arch/arm64/kvm/hyp/nvhe/mem_protect.c         | 19 ++++++++++++++++
 4 files changed, 43 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 8663a588cf34..4f97155d6323 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -69,6 +69,7 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_guest,
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_relax_perms_guest,
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_wrprotect_guest,
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_test_clear_young_guest,
 	__KVM_HOST_SMCCC_FUNC___kvm_adjust_pc,
 	__KVM_HOST_SMCCC_FUNC___kvm_vcpu_run,
 	__KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context,
diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
index fc9fdd5b0a52..b3aaad150b3e 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
@@ -43,6 +43,7 @@ int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum k
 int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm);
 int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot);
 int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm);
+int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *vm);
 
 bool addr_is_memory(phys_addr_t phys);
 int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot);
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 98d317735107..616e172a9c48 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -303,6 +303,27 @@ static void handle___pkvm_host_wrprotect_guest(struct kvm_cpu_context *host_ctxt
 	cpu_reg(host_ctxt, 1) = ret;
 }
 
+static void handle___pkvm_host_test_clear_young_guest(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);
+	DECLARE_REG(u64, gfn, host_ctxt, 2);
+	DECLARE_REG(bool, mkold, host_ctxt, 3);
+	struct pkvm_hyp_vm *hyp_vm;
+	int ret = -EINVAL;
+
+	if (!is_protected_kvm_enabled())
+		goto out;
+
+	hyp_vm = get_np_pkvm_hyp_vm(handle);
+	if (!hyp_vm)
+		goto out;
+
+	ret = __pkvm_host_test_clear_young_guest(gfn, mkold, hyp_vm);
+	put_pkvm_hyp_vm(hyp_vm);
+out:
+	cpu_reg(host_ctxt, 1) = ret;
+}
+
 static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1);
@@ -516,6 +537,7 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__pkvm_host_unshare_guest),
 	HANDLE_FUNC(__pkvm_host_relax_perms_guest),
 	HANDLE_FUNC(__pkvm_host_wrprotect_guest),
+	HANDLE_FUNC(__pkvm_host_test_clear_young_guest),
 	HANDLE_FUNC(__kvm_adjust_pc),
 	HANDLE_FUNC(__kvm_vcpu_run),
 	HANDLE_FUNC(__kvm_flush_vm_context),
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 94e4251b5077..0e42c3baaf4b 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -1530,3 +1530,22 @@ int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *vm)
 
 	return ret;
 }
+
+int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *vm)
+{
+	u64 ipa = hyp_pfn_to_phys(gfn);
+	u64 phys;
+	int ret;
+
+	host_lock_component();
+	guest_lock_component(vm);
+
+	ret = __check_host_shared_guest(vm, &phys, ipa);
+	if (!ret)
+		ret = kvm_pgtable_stage2_test_clear_young(&vm->pgt, ipa, PAGE_SIZE, mkold);
+
+	guest_unlock_component(vm);
+	host_unlock_component();
+
+	return ret;
+}
-- 
2.47.1.613.gc27f4b7a9f-goog

[PATCH v3 15/18] KVM: arm64: Introduce __pkvm_host_mkyoung_guest()

[Quentin Perret]

Plumb the kvm_pgtable_stage2_mkyoung() callback into pKVM for
non-protected guests. It will be called later from the fault handling
path.

Signed-off-by: Quentin Perret <qperret@google.com>
---
 arch/arm64/include/asm/kvm_asm.h              |  1 +
 arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |  1 +
 arch/arm64/kvm/hyp/nvhe/hyp-main.c            | 19 ++++++++++++++++++
 arch/arm64/kvm/hyp/nvhe/mem_protect.c         | 20 +++++++++++++++++++
 4 files changed, 41 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 4f97155d6323..a3b07db2776c 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -70,6 +70,7 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_relax_perms_guest,
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_wrprotect_guest,
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_test_clear_young_guest,
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_mkyoung_guest,
 	__KVM_HOST_SMCCC_FUNC___kvm_adjust_pc,
 	__KVM_HOST_SMCCC_FUNC___kvm_vcpu_run,
 	__KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context,
diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
index b3aaad150b3e..65c34753d86c 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
@@ -44,6 +44,7 @@ int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm);
 int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot);
 int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm);
 int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *vm);
+int __pkvm_host_mkyoung_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu);
 
 bool addr_is_memory(phys_addr_t phys);
 int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot);
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 616e172a9c48..32c4627b5b5b 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -324,6 +324,24 @@ static void handle___pkvm_host_test_clear_young_guest(struct kvm_cpu_context *ho
 	cpu_reg(host_ctxt, 1) = ret;
 }
 
+static void handle___pkvm_host_mkyoung_guest(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(u64, gfn, host_ctxt, 1);
+	struct pkvm_hyp_vcpu *hyp_vcpu;
+	int ret = -EINVAL;
+
+	if (!is_protected_kvm_enabled())
+		goto out;
+
+	hyp_vcpu = pkvm_get_loaded_hyp_vcpu();
+	if (!hyp_vcpu || pkvm_hyp_vcpu_is_protected(hyp_vcpu))
+		goto out;
+
+	ret = __pkvm_host_mkyoung_guest(gfn, hyp_vcpu);
+out:
+	cpu_reg(host_ctxt, 1) =  ret;
+}
+
 static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1);
@@ -538,6 +556,7 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__pkvm_host_relax_perms_guest),
 	HANDLE_FUNC(__pkvm_host_wrprotect_guest),
 	HANDLE_FUNC(__pkvm_host_test_clear_young_guest),
+	HANDLE_FUNC(__pkvm_host_mkyoung_guest),
 	HANDLE_FUNC(__kvm_adjust_pc),
 	HANDLE_FUNC(__kvm_vcpu_run),
 	HANDLE_FUNC(__kvm_flush_vm_context),
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 0e42c3baaf4b..eae03509d371 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -1549,3 +1549,23 @@ int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *
 
 	return ret;
 }
+
+int __pkvm_host_mkyoung_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu)
+{
+	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
+	u64 ipa = hyp_pfn_to_phys(gfn);
+	u64 phys;
+	int ret;
+
+	host_lock_component();
+	guest_lock_component(vm);
+
+	ret = __check_host_shared_guest(vm, &phys, ipa);
+	if (!ret)
+		kvm_pgtable_stage2_mkyoung(&vm->pgt, ipa, 0);
+
+	guest_unlock_component(vm);
+	host_unlock_component();
+
+	return ret;
+}
-- 
2.47.1.613.gc27f4b7a9f-goog

[PATCH v3 16/18] KVM: arm64: Introduce __pkvm_tlb_flush_vmid()

[Quentin Perret]

Introduce a new hypercall to flush the TLBs of non-protected guests. The
host kernel will be responsible for issuing this hypercall after changing
stage-2 permissions using the __pkvm_host_relax_guest_perms() or
__pkvm_host_wrprotect_guest() paths. This is left under the host's
responsibility for performance reasons.

Note however that the TLB maintenance for all *unmap* operations still
remains entirely under the hypervisor's responsibility for security
reasons -- an unmapped page may be donated to another entity, so a stale
TLB entry could be used to leak private data.

Signed-off-by: Quentin Perret <qperret@google.com>
---
 arch/arm64/include/asm/kvm_asm.h   |  1 +
 arch/arm64/kvm/hyp/nvhe/hyp-main.c | 17 +++++++++++++++++
 2 files changed, 18 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index a3b07db2776c..002088c6e297 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -87,6 +87,7 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___pkvm_teardown_vm,
 	__KVM_HOST_SMCCC_FUNC___pkvm_vcpu_load,
 	__KVM_HOST_SMCCC_FUNC___pkvm_vcpu_put,
+	__KVM_HOST_SMCCC_FUNC___pkvm_tlb_flush_vmid,
 };
 
 #define DECLARE_KVM_VHE_SYM(sym)	extern char sym[]
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 32c4627b5b5b..130f5f23bcb5 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -389,6 +389,22 @@ static void handle___kvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt)
 	__kvm_tlb_flush_vmid(kern_hyp_va(mmu));
 }
 
+static void handle___pkvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);
+	struct pkvm_hyp_vm *hyp_vm;
+
+	if (!is_protected_kvm_enabled())
+		return;
+
+	hyp_vm = get_np_pkvm_hyp_vm(handle);
+	if (!hyp_vm)
+		return;
+
+	__kvm_tlb_flush_vmid(&hyp_vm->kvm.arch.mmu);
+	put_pkvm_hyp_vm(hyp_vm);
+}
+
 static void handle___kvm_flush_cpu_context(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
@@ -573,6 +589,7 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__pkvm_teardown_vm),
 	HANDLE_FUNC(__pkvm_vcpu_load),
 	HANDLE_FUNC(__pkvm_vcpu_put),
+	HANDLE_FUNC(__pkvm_tlb_flush_vmid),
 };
 
 static void handle_host_hcall(struct kvm_cpu_context *host_ctxt)
-- 
2.47.1.613.gc27f4b7a9f-goog

[PATCH v3 17/18] KVM: arm64: Introduce the EL1 pKVM MMU

[Quentin Perret]

Introduce a set of helper functions allowing to manipulate the pKVM
guest stage-2 page-tables from EL1 using pKVM's HVC interface.

Each helper has an exact one-to-one correspondance with the traditional
kvm_pgtable_stage2_*() functions from pgtable.c, with a strictly
matching prototype. This will ease plumbing later on in mmu.c.

These callbacks track the gfn->pfn mappings in a simple rb_tree indexed
by IPA in lieu of a page-table. This rb-tree is kept in sync with pKVM's
state and is protected by a new rwlock -- the existing mmu_lock
protection does not suffice in the map() path where the tree must be
modified while user_mem_abort() only acquires a read_lock.

Signed-off-by: Quentin Perret <qperret@google.com>
---
 arch/arm64/include/asm/kvm_host.h    |   1 +
 arch/arm64/include/asm/kvm_pgtable.h |  23 ++--
 arch/arm64/include/asm/kvm_pkvm.h    |  23 ++++
 arch/arm64/kvm/pkvm.c                | 198 +++++++++++++++++++++++++++
 4 files changed, 236 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 1246f1d01dbf..f23f4ea9ec8b 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -85,6 +85,7 @@ void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu);
 struct kvm_hyp_memcache {
 	phys_addr_t head;
 	unsigned long nr_pages;
+	struct pkvm_mapping *mapping; /* only used from EL1 */
 };
 
 static inline void push_hyp_memcache(struct kvm_hyp_memcache *mc,
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 04418b5e3004..6b9d274052c7 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -412,15 +412,20 @@ static inline bool kvm_pgtable_walk_lock_held(void)
  *			be used instead of block mappings.
  */
 struct kvm_pgtable {
-	u32					ia_bits;
-	s8					start_level;
-	kvm_pteref_t				pgd;
-	struct kvm_pgtable_mm_ops		*mm_ops;
-
-	/* Stage-2 only */
-	struct kvm_s2_mmu			*mmu;
-	enum kvm_pgtable_stage2_flags		flags;
-	kvm_pgtable_force_pte_cb_t		force_pte_cb;
+	union {
+		struct rb_root					pkvm_mappings;
+		struct {
+			u32					ia_bits;
+			s8					start_level;
+			kvm_pteref_t				pgd;
+			struct kvm_pgtable_mm_ops		*mm_ops;
+
+			/* Stage-2 only */
+			enum kvm_pgtable_stage2_flags		flags;
+			kvm_pgtable_force_pte_cb_t		force_pte_cb;
+		};
+	};
+	struct kvm_s2_mmu					*mmu;
 };
 
 /**
diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h
index cd56acd9a842..76a8b70176a6 100644
--- a/arch/arm64/include/asm/kvm_pkvm.h
+++ b/arch/arm64/include/asm/kvm_pkvm.h
@@ -137,4 +137,27 @@ static inline size_t pkvm_host_sve_state_size(void)
 			SVE_SIG_REGS_SIZE(sve_vq_from_vl(kvm_host_sve_max_vl)));
 }
 
+struct pkvm_mapping {
+	struct rb_node node;
+	u64 gfn;
+	u64 pfn;
+};
+
+int pkvm_pgtable_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, struct kvm_pgtable_mm_ops *mm_ops);
+void pkvm_pgtable_destroy(struct kvm_pgtable *pgt);
+int pkvm_pgtable_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
+			   u64 phys, enum kvm_pgtable_prot prot,
+			   void *mc, enum kvm_pgtable_walk_flags flags);
+int pkvm_pgtable_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size);
+int pkvm_pgtable_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size);
+int pkvm_pgtable_flush(struct kvm_pgtable *pgt, u64 addr, u64 size);
+bool pkvm_pgtable_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64 size, bool mkold);
+int pkvm_pgtable_relax_perms(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_prot prot,
+			     enum kvm_pgtable_walk_flags flags);
+void pkvm_pgtable_mkyoung(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_walk_flags flags);
+int pkvm_pgtable_split(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_mmu_memory_cache *mc);
+void pkvm_pgtable_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level);
+kvm_pte_t *pkvm_pgtable_create_unlinked(struct kvm_pgtable *pgt, u64 phys, s8 level,
+					enum kvm_pgtable_prot prot, void *mc, bool force_pte);
+
 #endif	/* __ARM64_KVM_PKVM_H__ */
diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
index 85117ea8f351..9de9159afa5a 100644
--- a/arch/arm64/kvm/pkvm.c
+++ b/arch/arm64/kvm/pkvm.c
@@ -7,6 +7,7 @@
 #include <linux/init.h>
 #include <linux/kmemleak.h>
 #include <linux/kvm_host.h>
+#include <asm/kvm_mmu.h>
 #include <linux/memblock.h>
 #include <linux/mutex.h>
 #include <linux/sort.h>
@@ -268,3 +269,200 @@ static int __init finalize_pkvm(void)
 	return ret;
 }
 device_initcall_sync(finalize_pkvm);
+
+static int cmp_mappings(struct rb_node *node, const struct rb_node *parent)
+{
+	struct pkvm_mapping *a = rb_entry(node, struct pkvm_mapping, node);
+	struct pkvm_mapping *b = rb_entry(parent, struct pkvm_mapping, node);
+
+	if (a->gfn < b->gfn)
+		return -1;
+	if (a->gfn > b->gfn)
+		return 1;
+	return 0;
+}
+
+static struct rb_node *find_first_mapping_node(struct rb_root *root, u64 gfn)
+{
+	struct rb_node *node = root->rb_node, *prev = NULL;
+	struct pkvm_mapping *mapping;
+
+	while (node) {
+		mapping = rb_entry(node, struct pkvm_mapping, node);
+		if (mapping->gfn == gfn)
+			return node;
+		prev = node;
+		node = (gfn < mapping->gfn) ? node->rb_left : node->rb_right;
+	}
+
+	return prev;
+}
+
+/*
+ * __tmp is updated to rb_next(__tmp) *before* entering the body of the loop to allow freeing
+ * of __map inline.
+ */
+#define for_each_mapping_in_range_safe(__pgt, __start, __end, __map)					\
+	for (struct rb_node *__tmp = find_first_mapping_node(&(__pgt)->pkvm_mappings,			\
+							     ((__start) >> PAGE_SHIFT));		\
+	     __tmp && ({										\
+				__map = rb_entry(__tmp, struct pkvm_mapping, node);			\
+				__tmp = rb_next(__tmp);							\
+				true;									\
+		       });										\
+	    )												\
+		if (__map->gfn < ((__start) >> PAGE_SHIFT))						\
+			continue;									\
+		else if (__map->gfn >= ((__end) >> PAGE_SHIFT))						\
+			break;										\
+		else
+
+int pkvm_pgtable_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, struct kvm_pgtable_mm_ops *mm_ops)
+{
+	pgt->pkvm_mappings	= RB_ROOT;
+	pgt->mmu		= mmu;
+
+	return 0;
+}
+
+void pkvm_pgtable_destroy(struct kvm_pgtable *pgt)
+{
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
+	pkvm_handle_t handle = kvm->arch.pkvm.handle;
+	struct pkvm_mapping *mapping;
+	struct rb_node *node;
+
+	if (!handle)
+		return;
+
+	node = rb_first(&pgt->pkvm_mappings);
+	while (node) {
+		mapping = rb_entry(node, struct pkvm_mapping, node);
+		kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn);
+		node = rb_next(node);
+		rb_erase(&mapping->node, &pgt->pkvm_mappings);
+		kfree(mapping);
+	}
+}
+
+int pkvm_pgtable_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
+			   u64 phys, enum kvm_pgtable_prot prot,
+			   void *mc, enum kvm_pgtable_walk_flags flags)
+{
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
+	struct pkvm_mapping *mapping = NULL;
+	struct kvm_hyp_memcache *cache = mc;
+	u64 gfn = addr >> PAGE_SHIFT;
+	u64 pfn = phys >> PAGE_SHIFT;
+	int ret;
+
+	if (size != PAGE_SIZE)
+		return -EINVAL;
+
+	lockdep_assert_held_write(&kvm->mmu_lock);
+	ret = kvm_call_hyp_nvhe(__pkvm_host_share_guest, pfn, gfn, prot);
+	if (ret) {
+		/* Is the gfn already mapped due to a racing vCPU? */
+		if (ret == -EPERM)
+			return -EAGAIN;
+	}
+
+	swap(mapping, cache->mapping);
+	mapping->gfn = gfn;
+	mapping->pfn = pfn;
+	WARN_ON(rb_find_add(&mapping->node, &pgt->pkvm_mappings, cmp_mappings));
+
+	return ret;
+}
+
+int pkvm_pgtable_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
+{
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
+	pkvm_handle_t handle = kvm->arch.pkvm.handle;
+	struct pkvm_mapping *mapping;
+	int ret = 0;
+
+	lockdep_assert_held_write(&kvm->mmu_lock);
+	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) {
+		ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn);
+		if (WARN_ON(ret))
+			break;
+		rb_erase(&mapping->node, &pgt->pkvm_mappings);
+		kfree(mapping);
+	}
+
+	return ret;
+}
+
+int pkvm_pgtable_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
+{
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
+	pkvm_handle_t handle = kvm->arch.pkvm.handle;
+	struct pkvm_mapping *mapping;
+	int ret = 0;
+
+	lockdep_assert_held(&kvm->mmu_lock);
+	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) {
+		ret = kvm_call_hyp_nvhe(__pkvm_host_wrprotect_guest, handle, mapping->gfn);
+		if (WARN_ON(ret))
+			break;
+	}
+
+	return ret;
+}
+
+int pkvm_pgtable_flush(struct kvm_pgtable *pgt, u64 addr, u64 size)
+{
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
+	struct pkvm_mapping *mapping;
+
+	lockdep_assert_held(&kvm->mmu_lock);
+	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping)
+		__clean_dcache_guest_page(pfn_to_kaddr(mapping->pfn), PAGE_SIZE);
+
+	return 0;
+}
+
+bool pkvm_pgtable_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64 size, bool mkold)
+{
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
+	pkvm_handle_t handle = kvm->arch.pkvm.handle;
+	struct pkvm_mapping *mapping;
+	bool young = false;
+
+	lockdep_assert_held(&kvm->mmu_lock);
+	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping)
+		young |= kvm_call_hyp_nvhe(__pkvm_host_test_clear_young_guest, handle, mapping->gfn,
+					   mkold);
+
+	return young;
+}
+
+int pkvm_pgtable_relax_perms(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_prot prot,
+			     enum kvm_pgtable_walk_flags flags)
+{
+	return kvm_call_hyp_nvhe(__pkvm_host_relax_perms_guest, addr >> PAGE_SHIFT, prot);
+}
+
+void pkvm_pgtable_mkyoung(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_walk_flags flags)
+{
+	WARN_ON(kvm_call_hyp_nvhe(__pkvm_host_mkyoung_guest, addr >> PAGE_SHIFT));
+}
+
+void pkvm_pgtable_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level)
+{
+	WARN_ON_ONCE(1);
+}
+
+kvm_pte_t *pkvm_pgtable_create_unlinked(struct kvm_pgtable *pgt, u64 phys, s8 level,
+					enum kvm_pgtable_prot prot, void *mc, bool force_pte)
+{
+	WARN_ON_ONCE(1);
+	return NULL;
+}
+
+int pkvm_pgtable_split(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_mmu_memory_cache *mc)
+{
+	WARN_ON_ONCE(1);
+	return -EINVAL;
+}
-- 
2.47.1.613.gc27f4b7a9f-goog

[PATCH v3 18/18] KVM: arm64: Plumb the pKVM MMU in KVM

[Quentin Perret]

Introduce the KVM_PGT_S2() helper macro to allow switching from the
traditional pgtable code to the pKVM version easily in mmu.c. The cost
of this 'indirection' is expected to be very minimal due to
is_protected_kvm_enabled() being backed by a static key.

With this, everything is in place to allow the delegation of
non-protected guest stage-2 page-tables to pKVM, so let's stop using the
host's kvm_s2_mmu from EL2 and enjoy the ride.

Signed-off-by: Quentin Perret <qperret@google.com>
---
 arch/arm64/include/asm/kvm_mmu.h   |  16 +++++
 arch/arm64/kvm/arm.c               |   9 ++-
 arch/arm64/kvm/hyp/nvhe/hyp-main.c |   2 -
 arch/arm64/kvm/mmu.c               | 107 +++++++++++++++++++++--------
 4 files changed, 101 insertions(+), 33 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 66d93e320ec8..d116ab4230e8 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -353,6 +353,22 @@ static inline bool kvm_is_nested_s2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu)
 	return &kvm->arch.mmu != mmu;
 }
 
+static inline void kvm_fault_lock(struct kvm *kvm)
+{
+	if (is_protected_kvm_enabled())
+		write_lock(&kvm->mmu_lock);
+	else
+		read_lock(&kvm->mmu_lock);
+}
+
+static inline void kvm_fault_unlock(struct kvm *kvm)
+{
+	if (is_protected_kvm_enabled())
+		write_unlock(&kvm->mmu_lock);
+	else
+		read_unlock(&kvm->mmu_lock);
+}
+
 #ifdef CONFIG_PTDUMP_STAGE2_DEBUGFS
 void kvm_s2_ptdump_create_debugfs(struct kvm *kvm);
 #else
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 55cc62b2f469..9bcbc7b8ed38 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -502,7 +502,10 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
-	kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
+	if (!is_protected_kvm_enabled())
+		kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
+	else
+		free_hyp_memcache(&vcpu->arch.pkvm_memcache);
 	kvm_timer_vcpu_terminate(vcpu);
 	kvm_pmu_vcpu_destroy(vcpu);
 	kvm_vgic_vcpu_destroy(vcpu);
@@ -574,6 +577,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	struct kvm_s2_mmu *mmu;
 	int *last_ran;
 
+	if (is_protected_kvm_enabled())
+		goto nommu;
+
 	if (vcpu_has_nv(vcpu))
 		kvm_vcpu_load_hw_mmu(vcpu);
 
@@ -594,6 +600,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		*last_ran = vcpu->vcpu_idx;
 	}
 
+nommu:
 	vcpu->cpu = cpu;
 
 	kvm_vgic_load(vcpu);
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 130f5f23bcb5..258d572eed62 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -103,8 +103,6 @@ static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 	/* Limit guest vector length to the maximum supported by the host.  */
 	hyp_vcpu->vcpu.arch.sve_max_vl	= min(host_vcpu->arch.sve_max_vl, kvm_host_sve_max_vl);
 
-	hyp_vcpu->vcpu.arch.hw_mmu	= host_vcpu->arch.hw_mmu;
-
 	hyp_vcpu->vcpu.arch.mdcr_el2	= host_vcpu->arch.mdcr_el2;
 	hyp_vcpu->vcpu.arch.hcr_el2 &= ~(HCR_TWI | HCR_TWE);
 	hyp_vcpu->vcpu.arch.hcr_el2 |= READ_ONCE(host_vcpu->arch.hcr_el2) &
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 641e4fec1659..7c2995cb4577 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -15,6 +15,7 @@
 #include <asm/kvm_arm.h>
 #include <asm/kvm_mmu.h>
 #include <asm/kvm_pgtable.h>
+#include <asm/kvm_pkvm.h>
 #include <asm/kvm_ras.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
@@ -31,6 +32,14 @@ static phys_addr_t __ro_after_init hyp_idmap_vector;
 
 static unsigned long __ro_after_init io_map_base;
 
+#define KVM_PGT_S2(fn, ...)								\
+	({										\
+		typeof(kvm_pgtable_stage2_ ## fn) *__fn = kvm_pgtable_stage2_ ## fn;	\
+		if (is_protected_kvm_enabled())						\
+			__fn = pkvm_pgtable_ ## fn;					\
+		__fn(__VA_ARGS__);							\
+	})
+
 static phys_addr_t __stage2_range_addr_end(phys_addr_t addr, phys_addr_t end,
 					   phys_addr_t size)
 {
@@ -147,7 +156,7 @@ static int kvm_mmu_split_huge_pages(struct kvm *kvm, phys_addr_t addr,
 			return -EINVAL;
 
 		next = __stage2_range_addr_end(addr, end, chunk_size);
-		ret = kvm_pgtable_stage2_split(pgt, addr, next - addr, cache);
+		ret = KVM_PGT_S2(split, pgt, addr, next - addr, cache);
 		if (ret)
 			break;
 	} while (addr = next, addr != end);
@@ -168,15 +177,23 @@ static bool memslot_is_logging(struct kvm_memory_slot *memslot)
  */
 int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
 {
-	kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu);
+	if (is_protected_kvm_enabled())
+		kvm_call_hyp_nvhe(__pkvm_tlb_flush_vmid, kvm->arch.pkvm.handle);
+	else
+		kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu);
 	return 0;
 }
 
 int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm,
 				      gfn_t gfn, u64 nr_pages)
 {
-	kvm_tlb_flush_vmid_range(&kvm->arch.mmu,
-				gfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT);
+	u64 size = nr_pages << PAGE_SHIFT;
+	u64 addr = gfn << PAGE_SHIFT;
+
+	if (is_protected_kvm_enabled())
+		kvm_call_hyp_nvhe(__pkvm_tlb_flush_vmid, kvm->arch.pkvm.handle);
+	else
+		kvm_tlb_flush_vmid_range(&kvm->arch.mmu, addr, size);
 	return 0;
 }
 
@@ -225,7 +242,7 @@ static void stage2_free_unlinked_table_rcu_cb(struct rcu_head *head)
 	void *pgtable = page_to_virt(page);
 	s8 level = page_private(page);
 
-	kvm_pgtable_stage2_free_unlinked(&kvm_s2_mm_ops, pgtable, level);
+	KVM_PGT_S2(free_unlinked, &kvm_s2_mm_ops, pgtable, level);
 }
 
 static void stage2_free_unlinked_table(void *addr, s8 level)
@@ -280,6 +297,11 @@ static void invalidate_icache_guest_page(void *va, size_t size)
 	__invalidate_icache_guest_page(va, size);
 }
 
+static int kvm_s2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
+{
+	return KVM_PGT_S2(unmap, pgt, addr, size);
+}
+
 /*
  * Unmapping vs dcache management:
  *
@@ -324,8 +346,7 @@ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64
 
 	lockdep_assert_held_write(&kvm->mmu_lock);
 	WARN_ON(size & ~PAGE_MASK);
-	WARN_ON(stage2_apply_range(mmu, start, end, kvm_pgtable_stage2_unmap,
-				   may_block));
+	WARN_ON(stage2_apply_range(mmu, start, end, kvm_s2_unmap, may_block));
 }
 
 void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
@@ -334,9 +355,14 @@ void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
 	__unmap_stage2_range(mmu, start, size, may_block);
 }
 
+static int kvm_s2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size)
+{
+	return KVM_PGT_S2(flush, pgt, addr, size);
+}
+
 void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
 {
-	stage2_apply_range_resched(mmu, addr, end, kvm_pgtable_stage2_flush);
+	stage2_apply_range_resched(mmu, addr, end, kvm_s2_flush);
 }
 
 static void stage2_flush_memslot(struct kvm *kvm,
@@ -942,10 +968,14 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
 		return -ENOMEM;
 
 	mmu->arch = &kvm->arch;
-	err = kvm_pgtable_stage2_init(pgt, mmu, &kvm_s2_mm_ops);
+	err = KVM_PGT_S2(init, pgt, mmu, &kvm_s2_mm_ops);
 	if (err)
 		goto out_free_pgtable;
 
+	mmu->pgt = pgt;
+	if (is_protected_kvm_enabled())
+		return 0;
+
 	mmu->last_vcpu_ran = alloc_percpu(typeof(*mmu->last_vcpu_ran));
 	if (!mmu->last_vcpu_ran) {
 		err = -ENOMEM;
@@ -959,7 +989,6 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
 	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);
 
 	if (kvm_is_nested_s2_mmu(kvm, mmu))
@@ -968,7 +997,7 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
 	return 0;
 
 out_destroy_pgtable:
-	kvm_pgtable_stage2_destroy(pgt);
+	KVM_PGT_S2(destroy, pgt);
 out_free_pgtable:
 	kfree(pgt);
 	return err;
@@ -1065,7 +1094,7 @@ void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu)
 	write_unlock(&kvm->mmu_lock);
 
 	if (pgt) {
-		kvm_pgtable_stage2_destroy(pgt);
+		KVM_PGT_S2(destroy, pgt);
 		kfree(pgt);
 	}
 }
@@ -1082,9 +1111,11 @@ static void *hyp_mc_alloc_fn(void *unused)
 
 void free_hyp_memcache(struct kvm_hyp_memcache *mc)
 {
-	if (is_protected_kvm_enabled())
-		__free_hyp_memcache(mc, hyp_mc_free_fn,
-				    kvm_host_va, NULL);
+	if (!is_protected_kvm_enabled())
+		return;
+
+	kfree(mc->mapping);
+	__free_hyp_memcache(mc, hyp_mc_free_fn, kvm_host_va, NULL);
 }
 
 int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages)
@@ -1092,6 +1123,12 @@ int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages)
 	if (!is_protected_kvm_enabled())
 		return 0;
 
+	if (!mc->mapping) {
+		mc->mapping = kzalloc(sizeof(struct pkvm_mapping), GFP_KERNEL_ACCOUNT);
+		if (!mc->mapping)
+			return -ENOMEM;
+	}
+
 	return __topup_hyp_memcache(mc, min_pages, hyp_mc_alloc_fn,
 				    kvm_host_pa, NULL);
 }
@@ -1130,8 +1167,7 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 			break;
 
 		write_lock(&kvm->mmu_lock);
-		ret = kvm_pgtable_stage2_map(pgt, addr, PAGE_SIZE, pa, prot,
-					     &cache, 0);
+		ret = KVM_PGT_S2(map, pgt, addr, PAGE_SIZE, pa, prot, &cache, 0);
 		write_unlock(&kvm->mmu_lock);
 		if (ret)
 			break;
@@ -1143,6 +1179,10 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 	return ret;
 }
 
+static int kvm_s2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
+{
+	return KVM_PGT_S2(wrprotect, pgt, addr, size);
+}
 /**
  * kvm_stage2_wp_range() - write protect stage2 memory region range
  * @mmu:        The KVM stage-2 MMU pointer
@@ -1151,7 +1191,7 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
  */
 void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
 {
-	stage2_apply_range_resched(mmu, addr, end, kvm_pgtable_stage2_wrprotect);
+	stage2_apply_range_resched(mmu, addr, end, kvm_s2_wrprotect);
 }
 
 /**
@@ -1442,9 +1482,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	unsigned long mmu_seq;
 	phys_addr_t ipa = fault_ipa;
 	struct kvm *kvm = vcpu->kvm;
-	struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
 	struct vm_area_struct *vma;
 	short vma_shift;
+	void *memcache;
 	gfn_t gfn;
 	kvm_pfn_t pfn;
 	bool logging_active = memslot_is_logging(memslot);
@@ -1472,8 +1512,15 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * and a write fault needs to collapse a block entry into a table.
 	 */
 	if (!fault_is_perm || (logging_active && write_fault)) {
-		ret = kvm_mmu_topup_memory_cache(memcache,
-						 kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu));
+		int min_pages = kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu);
+
+		if (!is_protected_kvm_enabled()) {
+			memcache = &vcpu->arch.mmu_page_cache;
+			ret = kvm_mmu_topup_memory_cache(memcache, min_pages);
+		} else {
+			memcache = &vcpu->arch.pkvm_memcache;
+			ret = topup_hyp_memcache(memcache, min_pages);
+		}
 		if (ret)
 			return ret;
 	}
@@ -1494,7 +1541,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * logging_active is guaranteed to never be true for VM_PFNMAP
 	 * memslots.
 	 */
-	if (logging_active) {
+	if (logging_active || is_protected_kvm_enabled()) {
 		force_pte = true;
 		vma_shift = PAGE_SHIFT;
 	} else {
@@ -1634,7 +1681,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		prot |= kvm_encode_nested_level(nested);
 	}
 
-	read_lock(&kvm->mmu_lock);
+	kvm_fault_lock(kvm);
 	pgt = vcpu->arch.hw_mmu->pgt;
 	if (mmu_invalidate_retry(kvm, mmu_seq)) {
 		ret = -EAGAIN;
@@ -1696,16 +1743,16 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		 * PTE, which will be preserved.
 		 */
 		prot &= ~KVM_NV_GUEST_MAP_SZ;
-		ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot, flags);
+		ret = KVM_PGT_S2(relax_perms, pgt, fault_ipa, prot, flags);
 	} else {
-		ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
+		ret = KVM_PGT_S2(map, pgt, fault_ipa, vma_pagesize,
 					     __pfn_to_phys(pfn), prot,
 					     memcache, flags);
 	}
 
 out_unlock:
 	kvm_release_faultin_page(kvm, page, !!ret, writable);
-	read_unlock(&kvm->mmu_lock);
+	kvm_fault_unlock(kvm);
 
 	/* Mark the page dirty only if the fault is handled successfully */
 	if (writable && !ret)
@@ -1724,7 +1771,7 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 
 	read_lock(&vcpu->kvm->mmu_lock);
 	mmu = vcpu->arch.hw_mmu;
-	kvm_pgtable_stage2_mkyoung(mmu->pgt, fault_ipa, flags);
+	KVM_PGT_S2(mkyoung, mmu->pgt, fault_ipa, flags);
 	read_unlock(&vcpu->kvm->mmu_lock);
 }
 
@@ -1764,7 +1811,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 		}
 
 		/* Falls between the IPA range and the PARange? */
-		if (fault_ipa >= BIT_ULL(vcpu->arch.hw_mmu->pgt->ia_bits)) {
+		if (fault_ipa >= BIT_ULL(VTCR_EL2_IPA(vcpu->arch.hw_mmu->vtcr))) {
 			fault_ipa |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0);
 
 			if (is_iabt)
@@ -1930,7 +1977,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	if (!kvm->arch.mmu.pgt)
 		return false;
 
-	return kvm_pgtable_stage2_test_clear_young(kvm->arch.mmu.pgt,
+	return KVM_PGT_S2(test_clear_young, kvm->arch.mmu.pgt,
 						   range->start << PAGE_SHIFT,
 						   size, true);
 	/*
@@ -1946,7 +1993,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	if (!kvm->arch.mmu.pgt)
 		return false;
 
-	return kvm_pgtable_stage2_test_clear_young(kvm->arch.mmu.pgt,
+	return KVM_PGT_S2(test_clear_young, kvm->arch.mmu.pgt,
 						   range->start << PAGE_SHIFT,
 						   size, false);
 }
-- 
2.47.1.613.gc27f4b7a9f-goog

Re: [PATCH v3 01/18] KVM: arm64: Change the layout of enum pkvm_page_state

[Fuad Tabba]

On Mon, 16 Dec 2024 at 17:58, Quentin Perret <qperret@google.com> wrote:
>
> The 'concrete' (a.k.a non-meta) page states are currently encoded using
> software bits in PTEs. For performance reasons, the abstract
> pkvm_page_state enum uses the same bits to encode these states as that
> makes conversions from and to PTEs easy.
>
> In order to prepare the ground for moving the 'concrete' state storage
> to the hyp vmemmap, re-arrange the enum to use bits 0 and 1 for this
> purpose.
>
> No functional changes intended.
>
> Signed-off-by: Quentin Perret <qperret@google.com>

Reviewed-by: Fuad Tabba <tabba@google.com>

Cheers,
/fuad

> ---
>  arch/arm64/kvm/hyp/include/nvhe/mem_protect.h | 16 +++++++++-------
>  1 file changed, 9 insertions(+), 7 deletions(-)
>
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> index 0972faccc2af..8c30362af2b9 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> @@ -24,25 +24,27 @@
>   */
>  enum pkvm_page_state {
>         PKVM_PAGE_OWNED                 = 0ULL,
> -       PKVM_PAGE_SHARED_OWNED          = KVM_PGTABLE_PROT_SW0,
> -       PKVM_PAGE_SHARED_BORROWED       = KVM_PGTABLE_PROT_SW1,
> -       __PKVM_PAGE_RESERVED            = KVM_PGTABLE_PROT_SW0 |
> -                                         KVM_PGTABLE_PROT_SW1,
> +       PKVM_PAGE_SHARED_OWNED          = BIT(0),
> +       PKVM_PAGE_SHARED_BORROWED       = BIT(1),
> +       __PKVM_PAGE_RESERVED            = BIT(0) | BIT(1),
>
>         /* Meta-states which aren't encoded directly in the PTE's SW bits */
> -       PKVM_NOPAGE,
> +       PKVM_NOPAGE                     = BIT(2),
>  };
> +#define PKVM_PAGE_META_STATES_MASK     (~(BIT(0) | BIT(1)))
>
>  #define PKVM_PAGE_STATE_PROT_MASK      (KVM_PGTABLE_PROT_SW0 | KVM_PGTABLE_PROT_SW1)
>  static inline enum kvm_pgtable_prot pkvm_mkstate(enum kvm_pgtable_prot prot,
>                                                  enum pkvm_page_state state)
>  {
> -       return (prot & ~PKVM_PAGE_STATE_PROT_MASK) | state;
> +       prot &= ~PKVM_PAGE_STATE_PROT_MASK;
> +       prot |= FIELD_PREP(PKVM_PAGE_STATE_PROT_MASK, state);
> +       return prot;
>  }
>
>  static inline enum pkvm_page_state pkvm_getstate(enum kvm_pgtable_prot prot)
>  {
> -       return prot & PKVM_PAGE_STATE_PROT_MASK;
> +       return FIELD_GET(PKVM_PAGE_STATE_PROT_MASK, prot);
>  }
>
>  struct host_mmu {
> --
> 2.47.1.613.gc27f4b7a9f-goog
>

Re: [PATCH v3 02/18] KVM: arm64: Move enum pkvm_page_state to memory.h

[Fuad Tabba]

On Mon, 16 Dec 2024 at 17:58, Quentin Perret <qperret@google.com> wrote:
>
> In order to prepare the way for storing page-tracking information in
> pKVM's vmemmap, move the enum pkvm_page_state definition to
> nvhe/memory.h.
>
> No functional changes intended.
>
> Signed-off-by: Quentin Perret <qperret@google.com>

Reviewed-by: Fuad Tabba <tabba@google.com>

Cheers,
/fuad

> ---
>  arch/arm64/kvm/hyp/include/nvhe/mem_protect.h | 34 +------------------
>  arch/arm64/kvm/hyp/include/nvhe/memory.h      | 33 ++++++++++++++++++
>  2 files changed, 34 insertions(+), 33 deletions(-)
>
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> index 8c30362af2b9..25038ac705d8 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> @@ -11,42 +11,10 @@
>  #include <asm/kvm_mmu.h>
>  #include <asm/kvm_pgtable.h>
>  #include <asm/virt.h>
> +#include <nvhe/memory.h>
>  #include <nvhe/pkvm.h>
>  #include <nvhe/spinlock.h>
>
> -/*
> - * SW bits 0-1 are reserved to track the memory ownership state of each page:
> - *   00: The page is owned exclusively by the page-table owner.
> - *   01: The page is owned by the page-table owner, but is shared
> - *       with another entity.
> - *   10: The page is shared with, but not owned by the page-table owner.
> - *   11: Reserved for future use (lending).
> - */
> -enum pkvm_page_state {
> -       PKVM_PAGE_OWNED                 = 0ULL,
> -       PKVM_PAGE_SHARED_OWNED          = BIT(0),
> -       PKVM_PAGE_SHARED_BORROWED       = BIT(1),
> -       __PKVM_PAGE_RESERVED            = BIT(0) | BIT(1),
> -
> -       /* Meta-states which aren't encoded directly in the PTE's SW bits */
> -       PKVM_NOPAGE                     = BIT(2),
> -};
> -#define PKVM_PAGE_META_STATES_MASK     (~(BIT(0) | BIT(1)))
> -
> -#define PKVM_PAGE_STATE_PROT_MASK      (KVM_PGTABLE_PROT_SW0 | KVM_PGTABLE_PROT_SW1)
> -static inline enum kvm_pgtable_prot pkvm_mkstate(enum kvm_pgtable_prot prot,
> -                                                enum pkvm_page_state state)
> -{
> -       prot &= ~PKVM_PAGE_STATE_PROT_MASK;
> -       prot |= FIELD_PREP(PKVM_PAGE_STATE_PROT_MASK, state);
> -       return prot;
> -}
> -
> -static inline enum pkvm_page_state pkvm_getstate(enum kvm_pgtable_prot prot)
> -{
> -       return FIELD_GET(PKVM_PAGE_STATE_PROT_MASK, prot);
> -}
> -
>  struct host_mmu {
>         struct kvm_arch arch;
>         struct kvm_pgtable pgt;
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/memory.h b/arch/arm64/kvm/hyp/include/nvhe/memory.h
> index ab205c4d6774..c84b24234ac7 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/memory.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/memory.h
> @@ -7,6 +7,39 @@
>
>  #include <linux/types.h>
>
> +/*
> + * SW bits 0-1 are reserved to track the memory ownership state of each page:
> + *   00: The page is owned exclusively by the page-table owner.
> + *   01: The page is owned by the page-table owner, but is shared
> + *       with another entity.
> + *   10: The page is shared with, but not owned by the page-table owner.
> + *   11: Reserved for future use (lending).
> + */
> +enum pkvm_page_state {
> +       PKVM_PAGE_OWNED                 = 0ULL,
> +       PKVM_PAGE_SHARED_OWNED          = BIT(0),
> +       PKVM_PAGE_SHARED_BORROWED       = BIT(1),
> +       __PKVM_PAGE_RESERVED            = BIT(0) | BIT(1),
> +
> +       /* Meta-states which aren't encoded directly in the PTE's SW bits */
> +       PKVM_NOPAGE                     = BIT(2),
> +};
> +#define PKVM_PAGE_META_STATES_MASK     (~(BIT(0) | BIT(1)))
> +
> +#define PKVM_PAGE_STATE_PROT_MASK      (KVM_PGTABLE_PROT_SW0 | KVM_PGTABLE_PROT_SW1)
> +static inline enum kvm_pgtable_prot pkvm_mkstate(enum kvm_pgtable_prot prot,
> +                                                enum pkvm_page_state state)
> +{
> +       prot &= ~PKVM_PAGE_STATE_PROT_MASK;
> +       prot |= FIELD_PREP(PKVM_PAGE_STATE_PROT_MASK, state);
> +       return prot;
> +}
> +
> +static inline enum pkvm_page_state pkvm_getstate(enum kvm_pgtable_prot prot)
> +{
> +       return FIELD_GET(PKVM_PAGE_STATE_PROT_MASK, prot);
> +}
> +
>  struct hyp_page {
>         unsigned short refcount;
>         unsigned short order;
> --
> 2.47.1.613.gc27f4b7a9f-goog
>

Re: [PATCH v3 03/18] KVM: arm64: Make hyp_page::order a u8

[Fuad Tabba]

On Mon, 16 Dec 2024 at 17:58, Quentin Perret <qperret@google.com> wrote:
>
> We don't need 16 bits to store the hyp page order, and we'll need some
> bits to store page ownership data soon, so let's reduce the order
> member.
>
> Signed-off-by: Quentin Perret <qperret@google.com>

Reviewed-by: Fuad Tabba <tabba@google.com>

Cheers,
/fuad

> ---
>  arch/arm64/kvm/hyp/include/nvhe/gfp.h    |  6 +++---
>  arch/arm64/kvm/hyp/include/nvhe/memory.h |  5 +++--
>  arch/arm64/kvm/hyp/nvhe/page_alloc.c     | 14 +++++++-------
>  3 files changed, 13 insertions(+), 12 deletions(-)
>
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/gfp.h b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
> index 97c527ef53c2..f1725bad6331 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/gfp.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
> @@ -7,7 +7,7 @@
>  #include <nvhe/memory.h>
>  #include <nvhe/spinlock.h>
>
> -#define HYP_NO_ORDER   USHRT_MAX
> +#define HYP_NO_ORDER   0xff
>
>  struct hyp_pool {
>         /*
> @@ -19,11 +19,11 @@ struct hyp_pool {
>         struct list_head free_area[NR_PAGE_ORDERS];
>         phys_addr_t range_start;
>         phys_addr_t range_end;
> -       unsigned short max_order;
> +       u8 max_order;
>  };
>
>  /* Allocation */
> -void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order);
> +void *hyp_alloc_pages(struct hyp_pool *pool, u8 order);
>  void hyp_split_page(struct hyp_page *page);
>  void hyp_get_page(struct hyp_pool *pool, void *addr);
>  void hyp_put_page(struct hyp_pool *pool, void *addr);
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/memory.h b/arch/arm64/kvm/hyp/include/nvhe/memory.h
> index c84b24234ac7..45b8d1840aa4 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/memory.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/memory.h
> @@ -41,8 +41,9 @@ static inline enum pkvm_page_state pkvm_getstate(enum kvm_pgtable_prot prot)
>  }
>
>  struct hyp_page {
> -       unsigned short refcount;
> -       unsigned short order;
> +       u16 refcount;
> +       u8 order;
> +       u8 reserved;
>  };
>
>  extern u64 __hyp_vmemmap;
> diff --git a/arch/arm64/kvm/hyp/nvhe/page_alloc.c b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
> index e691290d3765..a1eb27a1a747 100644
> --- a/arch/arm64/kvm/hyp/nvhe/page_alloc.c
> +++ b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
> @@ -32,7 +32,7 @@ u64 __hyp_vmemmap;
>   */
>  static struct hyp_page *__find_buddy_nocheck(struct hyp_pool *pool,
>                                              struct hyp_page *p,
> -                                            unsigned short order)
> +                                            u8 order)
>  {
>         phys_addr_t addr = hyp_page_to_phys(p);
>
> @@ -51,7 +51,7 @@ static struct hyp_page *__find_buddy_nocheck(struct hyp_pool *pool,
>  /* Find a buddy page currently available for allocation */
>  static struct hyp_page *__find_buddy_avail(struct hyp_pool *pool,
>                                            struct hyp_page *p,
> -                                          unsigned short order)
> +                                          u8 order)
>  {
>         struct hyp_page *buddy = __find_buddy_nocheck(pool, p, order);
>
> @@ -94,7 +94,7 @@ static void __hyp_attach_page(struct hyp_pool *pool,
>                               struct hyp_page *p)
>  {
>         phys_addr_t phys = hyp_page_to_phys(p);
> -       unsigned short order = p->order;
> +       u8 order = p->order;
>         struct hyp_page *buddy;
>
>         memset(hyp_page_to_virt(p), 0, PAGE_SIZE << p->order);
> @@ -129,7 +129,7 @@ static void __hyp_attach_page(struct hyp_pool *pool,
>
>  static struct hyp_page *__hyp_extract_page(struct hyp_pool *pool,
>                                            struct hyp_page *p,
> -                                          unsigned short order)
> +                                          u8 order)
>  {
>         struct hyp_page *buddy;
>
> @@ -183,7 +183,7 @@ void hyp_get_page(struct hyp_pool *pool, void *addr)
>
>  void hyp_split_page(struct hyp_page *p)
>  {
> -       unsigned short order = p->order;
> +       u8 order = p->order;
>         unsigned int i;
>
>         p->order = 0;
> @@ -195,10 +195,10 @@ void hyp_split_page(struct hyp_page *p)
>         }
>  }
>
> -void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order)
> +void *hyp_alloc_pages(struct hyp_pool *pool, u8 order)
>  {
> -       unsigned short i = order;
>         struct hyp_page *p;
> +       u8 i = order;
>
>         hyp_spin_lock(&pool->lock);
>
> --
> 2.47.1.613.gc27f4b7a9f-goog
>

Re: [PATCH v3 04/18] KVM: arm64: Move host page ownership tracking to the hyp vmemmap

[Fuad Tabba]

On Mon, 16 Dec 2024 at 17:58, Quentin Perret <qperret@google.com> wrote:
>
> We currently store part of the page-tracking state in PTE software bits
> for the host, guests and the hypervisor. This is sub-optimal when e.g.
> sharing pages as this forces to break block mappings purely to support
> this software tracking. This causes an unnecessarily fragmented stage-2
> page-table for the host in particular when it shares pages with Secure,
> which can lead to measurable regressions. Moreover, having this state
> stored in the page-table forces us to do multiple costly walks on the
> page transition path, hence causing overhead.
>
> In order to work around these problems, move the host-side page-tracking
> logic from SW bits in its stage-2 PTEs to the hypervisor's vmemmap.
>
> Signed-off-by: Quentin Perret <qperret@google.com>

Reviewed-by: Fuad Tabba <tabba@google.com>

Cheers,
/fuad

> ---
>  arch/arm64/kvm/hyp/include/nvhe/memory.h |   6 +-
>  arch/arm64/kvm/hyp/nvhe/mem_protect.c    | 100 ++++++++++++++++-------
>  arch/arm64/kvm/hyp/nvhe/setup.c          |   7 +-
>  3 files changed, 77 insertions(+), 36 deletions(-)
>
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/memory.h b/arch/arm64/kvm/hyp/include/nvhe/memory.h
> index 45b8d1840aa4..8bd9a539f260 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/memory.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/memory.h
> @@ -8,7 +8,7 @@
>  #include <linux/types.h>
>
>  /*
> - * SW bits 0-1 are reserved to track the memory ownership state of each page:
> + * Bits 0-1 are reserved to track the memory ownership state of each page:
>   *   00: The page is owned exclusively by the page-table owner.
>   *   01: The page is owned by the page-table owner, but is shared
>   *       with another entity.
> @@ -43,7 +43,9 @@ static inline enum pkvm_page_state pkvm_getstate(enum kvm_pgtable_prot prot)
>  struct hyp_page {
>         u16 refcount;
>         u8 order;
> -       u8 reserved;
> +
> +       /* Host (non-meta) state. Guarded by the host stage-2 lock. */
> +       enum pkvm_page_state host_state : 8;
>  };
>
>  extern u64 __hyp_vmemmap;
> diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> index caba3e4bd09e..12bb5445fe47 100644
> --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> @@ -201,8 +201,8 @@ static void *guest_s2_zalloc_page(void *mc)
>
>         memset(addr, 0, PAGE_SIZE);
>         p = hyp_virt_to_page(addr);
> -       memset(p, 0, sizeof(*p));
>         p->refcount = 1;
> +       p->order = 0;
>
>         return addr;
>  }
> @@ -268,6 +268,7 @@ int kvm_guest_prepare_stage2(struct pkvm_hyp_vm *vm, void *pgd)
>
>  void reclaim_guest_pages(struct pkvm_hyp_vm *vm, struct kvm_hyp_memcache *mc)
>  {
> +       struct hyp_page *page;
>         void *addr;
>
>         /* Dump all pgtable pages in the hyp_pool */
> @@ -279,7 +280,9 @@ void reclaim_guest_pages(struct pkvm_hyp_vm *vm, struct kvm_hyp_memcache *mc)
>         /* Drain the hyp_pool into the memcache */
>         addr = hyp_alloc_pages(&vm->pool, 0);
>         while (addr) {
> -               memset(hyp_virt_to_page(addr), 0, sizeof(struct hyp_page));
> +               page = hyp_virt_to_page(addr);
> +               page->refcount = 0;
> +               page->order = 0;
>                 push_hyp_memcache(mc, addr, hyp_virt_to_phys);
>                 WARN_ON(__pkvm_hyp_donate_host(hyp_virt_to_pfn(addr), 1));
>                 addr = hyp_alloc_pages(&vm->pool, 0);
> @@ -382,19 +385,28 @@ bool addr_is_memory(phys_addr_t phys)
>         return !!find_mem_range(phys, &range);
>  }
>
> -static bool addr_is_allowed_memory(phys_addr_t phys)
> +static bool is_in_mem_range(u64 addr, struct kvm_mem_range *range)
> +{
> +       return range->start <= addr && addr < range->end;
> +}
> +
> +static int check_range_allowed_memory(u64 start, u64 end)
>  {
>         struct memblock_region *reg;
>         struct kvm_mem_range range;
>
> -       reg = find_mem_range(phys, &range);
> +       /*
> +        * Callers can't check the state of a range that overlaps memory and
> +        * MMIO regions, so ensure [start, end[ is in the same kvm_mem_range.
> +        */
> +       reg = find_mem_range(start, &range);
> +       if (!is_in_mem_range(end - 1, &range))
> +               return -EINVAL;
>
> -       return reg && !(reg->flags & MEMBLOCK_NOMAP);
> -}
> +       if (!reg || reg->flags & MEMBLOCK_NOMAP)
> +               return -EPERM;
>
> -static bool is_in_mem_range(u64 addr, struct kvm_mem_range *range)
> -{
> -       return range->start <= addr && addr < range->end;
> +       return 0;
>  }
>
>  static bool range_is_memory(u64 start, u64 end)
> @@ -454,8 +466,10 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
>         if (kvm_pte_valid(pte))
>                 return -EAGAIN;
>
> -       if (pte)
> +       if (pte) {
> +               WARN_ON(addr_is_memory(addr) && hyp_phys_to_page(addr)->host_state != PKVM_NOPAGE);
>                 return -EPERM;
> +       }
>
>         do {
>                 u64 granule = kvm_granule_size(level);
> @@ -477,10 +491,33 @@ int host_stage2_idmap_locked(phys_addr_t addr, u64 size,
>         return host_stage2_try(__host_stage2_idmap, addr, addr + size, prot);
>  }
>
> +static void __host_update_page_state(phys_addr_t addr, u64 size, enum pkvm_page_state state)
> +{
> +       phys_addr_t end = addr + size;
> +
> +       for (; addr < end; addr += PAGE_SIZE)
> +               hyp_phys_to_page(addr)->host_state = state;
> +}
> +
>  int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id)
>  {
> -       return host_stage2_try(kvm_pgtable_stage2_set_owner, &host_mmu.pgt,
> -                              addr, size, &host_s2_pool, owner_id);
> +       int ret;
> +
> +       if (!addr_is_memory(addr))
> +               return -EPERM;
> +
> +       ret = host_stage2_try(kvm_pgtable_stage2_set_owner, &host_mmu.pgt,
> +                             addr, size, &host_s2_pool, owner_id);
> +       if (ret)
> +               return ret;
> +
> +       /* Don't forget to update the vmemmap tracking for the host */
> +       if (owner_id == PKVM_ID_HOST)
> +               __host_update_page_state(addr, size, PKVM_PAGE_OWNED);
> +       else
> +               __host_update_page_state(addr, size, PKVM_NOPAGE);
> +
> +       return 0;
>  }
>
>  static bool host_stage2_force_pte_cb(u64 addr, u64 end, enum kvm_pgtable_prot prot)
> @@ -604,35 +641,38 @@ static int check_page_state_range(struct kvm_pgtable *pgt, u64 addr, u64 size,
>         return kvm_pgtable_walk(pgt, addr, size, &walker);
>  }
>
> -static enum pkvm_page_state host_get_page_state(kvm_pte_t pte, u64 addr)
> -{
> -       if (!addr_is_allowed_memory(addr))
> -               return PKVM_NOPAGE;
> -
> -       if (!kvm_pte_valid(pte) && pte)
> -               return PKVM_NOPAGE;
> -
> -       return pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte));
> -}
> -
>  static int __host_check_page_state_range(u64 addr, u64 size,
>                                          enum pkvm_page_state state)
>  {
> -       struct check_walk_data d = {
> -               .desired        = state,
> -               .get_page_state = host_get_page_state,
> -       };
> +       u64 end = addr + size;
> +       int ret;
> +
> +       ret = check_range_allowed_memory(addr, end);
> +       if (ret)
> +               return ret;
>
>         hyp_assert_lock_held(&host_mmu.lock);
> -       return check_page_state_range(&host_mmu.pgt, addr, size, &d);
> +       for (; addr < end; addr += PAGE_SIZE) {
> +               if (hyp_phys_to_page(addr)->host_state != state)
> +                       return -EPERM;
> +       }
> +
> +       return 0;
>  }
>
>  static int __host_set_page_state_range(u64 addr, u64 size,
>                                        enum pkvm_page_state state)
>  {
> -       enum kvm_pgtable_prot prot = pkvm_mkstate(PKVM_HOST_MEM_PROT, state);
> +       if (hyp_phys_to_page(addr)->host_state == PKVM_NOPAGE) {
> +               int ret = host_stage2_idmap_locked(addr, size, PKVM_HOST_MEM_PROT);
>
> -       return host_stage2_idmap_locked(addr, size, prot);
> +               if (ret)
> +                       return ret;
> +       }
> +
> +       __host_update_page_state(addr, size, state);
> +
> +       return 0;
>  }
>
>  static int host_request_owned_transition(u64 *completer_addr,
> diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
> index cbdd18cd3f98..7e04d1c2a03d 100644
> --- a/arch/arm64/kvm/hyp/nvhe/setup.c
> +++ b/arch/arm64/kvm/hyp/nvhe/setup.c
> @@ -180,7 +180,6 @@ static void hpool_put_page(void *addr)
>  static int fix_host_ownership_walker(const struct kvm_pgtable_visit_ctx *ctx,
>                                      enum kvm_pgtable_walk_flags visit)
>  {
> -       enum kvm_pgtable_prot prot;
>         enum pkvm_page_state state;
>         phys_addr_t phys;
>
> @@ -203,16 +202,16 @@ static int fix_host_ownership_walker(const struct kvm_pgtable_visit_ctx *ctx,
>         case PKVM_PAGE_OWNED:
>                 return host_stage2_set_owner_locked(phys, PAGE_SIZE, PKVM_ID_HYP);
>         case PKVM_PAGE_SHARED_OWNED:
> -               prot = pkvm_mkstate(PKVM_HOST_MEM_PROT, PKVM_PAGE_SHARED_BORROWED);
> +               hyp_phys_to_page(phys)->host_state = PKVM_PAGE_SHARED_BORROWED;
>                 break;
>         case PKVM_PAGE_SHARED_BORROWED:
> -               prot = pkvm_mkstate(PKVM_HOST_MEM_PROT, PKVM_PAGE_SHARED_OWNED);
> +               hyp_phys_to_page(phys)->host_state = PKVM_PAGE_SHARED_OWNED;
>                 break;
>         default:
>                 return -EINVAL;
>         }
>
> -       return host_stage2_idmap_locked(phys, PAGE_SIZE, prot);
> +       return 0;
>  }
>
>  static int fix_hyp_pgtable_refcnt_walker(const struct kvm_pgtable_visit_ctx *ctx,
> --
> 2.47.1.613.gc27f4b7a9f-goog
>

Re: [PATCH v3 05/18] KVM: arm64: Pass walk flags to kvm_pgtable_stage2_mkyoung

[Fuad Tabba]

On Mon, 16 Dec 2024 at 17:58, Quentin Perret <qperret@google.com> wrote:
>
> kvm_pgtable_stage2_mkyoung currently assumes that it is being called
> from a 'shared' walker, which will not be true once called from pKVM.
> To allow for the re-use of that function, make the walk flags one of
> its parameters.
>
> Signed-off-by: Quentin Perret <qperret@google.com>

Reviewed-by: Fuad Tabba <tabba@google.com>

Cheers,
/fuad

> ---
>  arch/arm64/include/asm/kvm_pgtable.h | 4 +++-
>  arch/arm64/kvm/hyp/pgtable.c         | 7 +++----
>  arch/arm64/kvm/mmu.c                 | 3 ++-
>  3 files changed, 8 insertions(+), 6 deletions(-)
>
> diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
> index aab04097b505..38b7ec1c8614 100644
> --- a/arch/arm64/include/asm/kvm_pgtable.h
> +++ b/arch/arm64/include/asm/kvm_pgtable.h
> @@ -669,13 +669,15 @@ int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size);
>   * kvm_pgtable_stage2_mkyoung() - Set the access flag in a page-table entry.
>   * @pgt:       Page-table structure initialised by kvm_pgtable_stage2_init*().
>   * @addr:      Intermediate physical address to identify the page-table entry.
> + * @flags:     Flags to control the page-table walk (ex. a shared walk)
>   *
>   * The offset of @addr within a page is ignored.
>   *
>   * If there is a valid, leaf page-table entry used to translate @addr, then
>   * set the access flag in that entry.
>   */
> -void kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr);
> +void kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr,
> +                               enum kvm_pgtable_walk_flags flags);
>
>  /**
>   * kvm_pgtable_stage2_test_clear_young() - Test and optionally clear the access
> diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
> index 40bd55966540..0470aedb4bf4 100644
> --- a/arch/arm64/kvm/hyp/pgtable.c
> +++ b/arch/arm64/kvm/hyp/pgtable.c
> @@ -1245,14 +1245,13 @@ int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
>                                         NULL, NULL, 0);
>  }
>
> -void kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr)
> +void kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr,
> +                               enum kvm_pgtable_walk_flags flags)
>  {
>         int ret;
>
>         ret = stage2_update_leaf_attrs(pgt, addr, 1, KVM_PTE_LEAF_ATTR_LO_S2_AF, 0,
> -                                      NULL, NULL,
> -                                      KVM_PGTABLE_WALK_HANDLE_FAULT |
> -                                      KVM_PGTABLE_WALK_SHARED);
> +                                      NULL, NULL, flags);
>         if (!ret)
>                 dsb(ishst);
>  }
> diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
> index c9d46ad57e52..a2339b76c826 100644
> --- a/arch/arm64/kvm/mmu.c
> +++ b/arch/arm64/kvm/mmu.c
> @@ -1718,13 +1718,14 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
>  /* Resolve the access fault by making the page young again. */
>  static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
>  {
> +       enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED;
>         struct kvm_s2_mmu *mmu;
>
>         trace_kvm_access_fault(fault_ipa);
>
>         read_lock(&vcpu->kvm->mmu_lock);
>         mmu = vcpu->arch.hw_mmu;
> -       kvm_pgtable_stage2_mkyoung(mmu->pgt, fault_ipa);
> +       kvm_pgtable_stage2_mkyoung(mmu->pgt, fault_ipa, flags);
>         read_unlock(&vcpu->kvm->mmu_lock);
>  }
>
> --
> 2.47.1.613.gc27f4b7a9f-goog
>

Re: [PATCH v3 06/18] KVM: arm64: Pass walk flags to kvm_pgtable_stage2_relax_perms

[Fuad Tabba]

On Mon, 16 Dec 2024 at 17:58, Quentin Perret <qperret@google.com> wrote:
>
> kvm_pgtable_stage2_relax_perms currently assumes that it is being called
> from a 'shared' walker, which will not be true once called from pKVM. To
> allow for the re-use of that function, make the walk flags one of its
> parameters.
>
> Signed-off-by: Quentin Perret <qperret@google.com>

Reviewed-by: Fuad Tabba <tabba@google.com>

Cheers,
/fuad

> ---
>  arch/arm64/include/asm/kvm_pgtable.h | 4 +++-
>  arch/arm64/kvm/hyp/pgtable.c         | 6 ++----
>  arch/arm64/kvm/mmu.c                 | 7 +++----
>  3 files changed, 8 insertions(+), 9 deletions(-)
>
> diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
> index 38b7ec1c8614..c2f4149283ef 100644
> --- a/arch/arm64/include/asm/kvm_pgtable.h
> +++ b/arch/arm64/include/asm/kvm_pgtable.h
> @@ -707,6 +707,7 @@ bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr,
>   * @pgt:       Page-table structure initialised by kvm_pgtable_stage2_init*().
>   * @addr:      Intermediate physical address to identify the page-table entry.
>   * @prot:      Additional permissions to grant for the mapping.
> + * @flags:     Flags to control the page-table walk (ex. a shared walk)
>   *
>   * The offset of @addr within a page is ignored.
>   *
> @@ -719,7 +720,8 @@ bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr,
>   * Return: 0 on success, negative error code on failure.
>   */
>  int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
> -                                  enum kvm_pgtable_prot prot);
> +                                  enum kvm_pgtable_prot prot,
> +                                  enum kvm_pgtable_walk_flags flags);
>
>  /**
>   * kvm_pgtable_stage2_flush_range() - Clean and invalidate data cache to Point
> diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
> index 0470aedb4bf4..b7a3b5363235 100644
> --- a/arch/arm64/kvm/hyp/pgtable.c
> +++ b/arch/arm64/kvm/hyp/pgtable.c
> @@ -1307,7 +1307,7 @@ bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr,
>  }
>
>  int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
> -                                  enum kvm_pgtable_prot prot)
> +                                  enum kvm_pgtable_prot prot, enum kvm_pgtable_walk_flags flags)
>  {
>         int ret;
>         s8 level;
> @@ -1325,9 +1325,7 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
>         if (prot & KVM_PGTABLE_PROT_X)
>                 clr |= KVM_PTE_LEAF_ATTR_HI_S2_XN;
>
> -       ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level,
> -                                      KVM_PGTABLE_WALK_HANDLE_FAULT |
> -                                      KVM_PGTABLE_WALK_SHARED);
> +       ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level, flags);
>         if (!ret || ret == -EAGAIN)
>                 kvm_call_hyp(__kvm_tlb_flush_vmid_ipa_nsh, pgt->mmu, addr, level);
>         return ret;
> diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
> index a2339b76c826..641e4fec1659 100644
> --- a/arch/arm64/kvm/mmu.c
> +++ b/arch/arm64/kvm/mmu.c
> @@ -1452,6 +1452,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
>         enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
>         struct kvm_pgtable *pgt;
>         struct page *page;
> +       enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED;
>
>         if (fault_is_perm)
>                 fault_granule = kvm_vcpu_trap_get_perm_fault_granule(vcpu);
> @@ -1695,13 +1696,11 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
>                  * PTE, which will be preserved.
>                  */
>                 prot &= ~KVM_NV_GUEST_MAP_SZ;
> -               ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot);
> +               ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot, flags);
>         } else {
>                 ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
>                                              __pfn_to_phys(pfn), prot,
> -                                            memcache,
> -                                            KVM_PGTABLE_WALK_HANDLE_FAULT |
> -                                            KVM_PGTABLE_WALK_SHARED);
> +                                            memcache, flags);
>         }
>
>  out_unlock:
> --
> 2.47.1.613.gc27f4b7a9f-goog
>

Re: [PATCH v3 08/18] KVM: arm64: Add {get,put}_pkvm_hyp_vm() helpers

[Fuad Tabba]

On Mon, 16 Dec 2024 at 17:58, Quentin Perret <qperret@google.com> wrote:
>
> In preparation for accessing pkvm_hyp_vm structures at EL2 in a context
> where we can't always expect a vCPU to be loaded (e.g. MMU notifiers),
> introduce get/put helpers to get temporary references to hyp VMs from
> any context.
>
> Signed-off-by: Quentin Perret <qperret@google.com>

Reviewed-by: Fuad Tabba <tabba@google.com>

Cheers,
/fuad

> ---
>  arch/arm64/kvm/hyp/include/nvhe/pkvm.h |  3 +++
>  arch/arm64/kvm/hyp/nvhe/pkvm.c         | 20 ++++++++++++++++++++
>  2 files changed, 23 insertions(+)
>
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
> index 24a9a8330d19..f361d8b91930 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
> @@ -70,4 +70,7 @@ struct pkvm_hyp_vcpu *pkvm_load_hyp_vcpu(pkvm_handle_t handle,
>                                          unsigned int vcpu_idx);
>  void pkvm_put_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu);
>
> +struct pkvm_hyp_vm *get_pkvm_hyp_vm(pkvm_handle_t handle);
> +void put_pkvm_hyp_vm(struct pkvm_hyp_vm *hyp_vm);
> +
>  #endif /* __ARM64_KVM_NVHE_PKVM_H__ */
> diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
> index 071993c16de8..d46a02e24e4a 100644
> --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
> +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
> @@ -327,6 +327,26 @@ void pkvm_put_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
>         hyp_spin_unlock(&vm_table_lock);
>  }
>
> +struct pkvm_hyp_vm *get_pkvm_hyp_vm(pkvm_handle_t handle)
> +{
> +       struct pkvm_hyp_vm *hyp_vm;
> +
> +       hyp_spin_lock(&vm_table_lock);
> +       hyp_vm = get_vm_by_handle(handle);
> +       if (hyp_vm)
> +               hyp_page_ref_inc(hyp_virt_to_page(hyp_vm));
> +       hyp_spin_unlock(&vm_table_lock);
> +
> +       return hyp_vm;
> +}
> +
> +void put_pkvm_hyp_vm(struct pkvm_hyp_vm *hyp_vm)
> +{
> +       hyp_spin_lock(&vm_table_lock);
> +       hyp_page_ref_dec(hyp_virt_to_page(hyp_vm));
> +       hyp_spin_unlock(&vm_table_lock);
> +}
> +
>  static void pkvm_init_features_from_host(struct pkvm_hyp_vm *hyp_vm, const struct kvm *host_kvm)
>  {
>         struct kvm *kvm = &hyp_vm->kvm;
> --
> 2.47.1.613.gc27f4b7a9f-goog
>

Re: [PATCH v3 07/18] KVM: arm64: Make kvm_pgtable_stage2_init() a static inline function

[Fuad Tabba]

On Mon, 16 Dec 2024 at 17:58, Quentin Perret <qperret@google.com> wrote:
>
> Turn kvm_pgtable_stage2_init() into a static inline function instead of
> a macro. This will allow the usage of typeof() on it later on.
>
> Signed-off-by: Quentin Perret <qperret@google.com>

Reviewed-by: Fuad Tabba <tabba@google.com>

Cheers,
/fuad

> ---
>  arch/arm64/include/asm/kvm_pgtable.h | 7 +++++--
>  1 file changed, 5 insertions(+), 2 deletions(-)
>
> diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
> index c2f4149283ef..04418b5e3004 100644
> --- a/arch/arm64/include/asm/kvm_pgtable.h
> +++ b/arch/arm64/include/asm/kvm_pgtable.h
> @@ -526,8 +526,11 @@ int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
>                               enum kvm_pgtable_stage2_flags flags,
>                               kvm_pgtable_force_pte_cb_t force_pte_cb);
>
> -#define kvm_pgtable_stage2_init(pgt, mmu, mm_ops) \
> -       __kvm_pgtable_stage2_init(pgt, mmu, mm_ops, 0, NULL)
> +static inline int kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
> +                                         struct kvm_pgtable_mm_ops *mm_ops)
> +{
> +       return __kvm_pgtable_stage2_init(pgt, mmu, mm_ops, 0, NULL);
> +}
>
>  /**
>   * kvm_pgtable_stage2_destroy() - Destroy an unused guest stage-2 page-table.
> --
> 2.47.1.613.gc27f4b7a9f-goog
>

Re: [PATCH v3 09/18] KVM: arm64: Introduce __pkvm_vcpu_{load,put}()

[Fuad Tabba]

On Mon, 16 Dec 2024 at 17:58, Quentin Perret <qperret@google.com> wrote:
>
> From: Marc Zyngier <maz@kernel.org>
>
> Rather than look-up the hyp vCPU on every run hypercall at EL2,
> introduce a per-CPU 'loaded_hyp_vcpu' tracking variable which is updated
> by a pair of load/put hypercalls called directly from
> kvm_arch_vcpu_{load,put}() when pKVM is enabled.
>
> Signed-off-by: Marc Zyngier <maz@kernel.org>
> Signed-off-by: Quentin Perret <qperret@google.com>

Reviewed-by: Fuad Tabba <tabba@google.com>

Cheers,
/fuad

> ---
>  arch/arm64/include/asm/kvm_asm.h       |  2 ++
>  arch/arm64/kvm/arm.c                   | 14 ++++++++
>  arch/arm64/kvm/hyp/include/nvhe/pkvm.h |  7 ++++
>  arch/arm64/kvm/hyp/nvhe/hyp-main.c     | 47 ++++++++++++++++++++------
>  arch/arm64/kvm/hyp/nvhe/pkvm.c         | 29 ++++++++++++++++
>  arch/arm64/kvm/vgic/vgic-v3.c          |  6 ++--
>  6 files changed, 93 insertions(+), 12 deletions(-)
>
> diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
> index ca2590344313..89c0fac69551 100644
> --- a/arch/arm64/include/asm/kvm_asm.h
> +++ b/arch/arm64/include/asm/kvm_asm.h
> @@ -79,6 +79,8 @@ enum __kvm_host_smccc_func {
>         __KVM_HOST_SMCCC_FUNC___pkvm_init_vm,
>         __KVM_HOST_SMCCC_FUNC___pkvm_init_vcpu,
>         __KVM_HOST_SMCCC_FUNC___pkvm_teardown_vm,
> +       __KVM_HOST_SMCCC_FUNC___pkvm_vcpu_load,
> +       __KVM_HOST_SMCCC_FUNC___pkvm_vcpu_put,
>  };
>
>  #define DECLARE_KVM_VHE_SYM(sym)       extern char sym[]
> diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
> index a102c3aebdbc..55cc62b2f469 100644
> --- a/arch/arm64/kvm/arm.c
> +++ b/arch/arm64/kvm/arm.c
> @@ -619,12 +619,26 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
>
>         kvm_arch_vcpu_load_debug_state_flags(vcpu);
>
> +       if (is_protected_kvm_enabled()) {
> +               kvm_call_hyp_nvhe(__pkvm_vcpu_load,
> +                                 vcpu->kvm->arch.pkvm.handle,
> +                                 vcpu->vcpu_idx, vcpu->arch.hcr_el2);
> +               kvm_call_hyp(__vgic_v3_restore_vmcr_aprs,
> +                            &vcpu->arch.vgic_cpu.vgic_v3);
> +       }
> +
>         if (!cpumask_test_cpu(cpu, vcpu->kvm->arch.supported_cpus))
>                 vcpu_set_on_unsupported_cpu(vcpu);
>  }
>
>  void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
>  {
> +       if (is_protected_kvm_enabled()) {
> +               kvm_call_hyp(__vgic_v3_save_vmcr_aprs,
> +                            &vcpu->arch.vgic_cpu.vgic_v3);
> +               kvm_call_hyp_nvhe(__pkvm_vcpu_put);
> +       }
> +
>         kvm_arch_vcpu_put_debug_state_flags(vcpu);
>         kvm_arch_vcpu_put_fp(vcpu);
>         if (has_vhe())
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
> index f361d8b91930..be52c5b15e21 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
> @@ -20,6 +20,12 @@ struct pkvm_hyp_vcpu {
>
>         /* Backpointer to the host's (untrusted) vCPU instance. */
>         struct kvm_vcpu *host_vcpu;
> +
> +       /*
> +        * If this hyp vCPU is loaded, then this is a backpointer to the
> +        * per-cpu pointer tracking us. Otherwise, NULL if not loaded.
> +        */
> +       struct pkvm_hyp_vcpu **loaded_hyp_vcpu;
>  };
>
>  /*
> @@ -69,6 +75,7 @@ int __pkvm_teardown_vm(pkvm_handle_t handle);
>  struct pkvm_hyp_vcpu *pkvm_load_hyp_vcpu(pkvm_handle_t handle,
>                                          unsigned int vcpu_idx);
>  void pkvm_put_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu);
> +struct pkvm_hyp_vcpu *pkvm_get_loaded_hyp_vcpu(void);
>
>  struct pkvm_hyp_vm *get_pkvm_hyp_vm(pkvm_handle_t handle);
>  void put_pkvm_hyp_vm(struct pkvm_hyp_vm *hyp_vm);
> diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> index 6aa0b13d86e5..95d78db315b3 100644
> --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> @@ -141,16 +141,46 @@ static void sync_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
>                 host_cpu_if->vgic_lr[i] = hyp_cpu_if->vgic_lr[i];
>  }
>
> +static void handle___pkvm_vcpu_load(struct kvm_cpu_context *host_ctxt)
> +{
> +       DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);
> +       DECLARE_REG(unsigned int, vcpu_idx, host_ctxt, 2);
> +       DECLARE_REG(u64, hcr_el2, host_ctxt, 3);
> +       struct pkvm_hyp_vcpu *hyp_vcpu;
> +
> +       if (!is_protected_kvm_enabled())
> +               return;
> +
> +       hyp_vcpu = pkvm_load_hyp_vcpu(handle, vcpu_idx);
> +       if (!hyp_vcpu)
> +               return;
> +
> +       if (pkvm_hyp_vcpu_is_protected(hyp_vcpu)) {
> +               /* Propagate WFx trapping flags */
> +               hyp_vcpu->vcpu.arch.hcr_el2 &= ~(HCR_TWE | HCR_TWI);
> +               hyp_vcpu->vcpu.arch.hcr_el2 |= hcr_el2 & (HCR_TWE | HCR_TWI);
> +       }
> +}
> +
> +static void handle___pkvm_vcpu_put(struct kvm_cpu_context *host_ctxt)
> +{
> +       struct pkvm_hyp_vcpu *hyp_vcpu;
> +
> +       if (!is_protected_kvm_enabled())
> +               return;
> +
> +       hyp_vcpu = pkvm_get_loaded_hyp_vcpu();
> +       if (hyp_vcpu)
> +               pkvm_put_hyp_vcpu(hyp_vcpu);
> +}
> +
>  static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
>  {
>         DECLARE_REG(struct kvm_vcpu *, host_vcpu, host_ctxt, 1);
>         int ret;
>
> -       host_vcpu = kern_hyp_va(host_vcpu);
> -
>         if (unlikely(is_protected_kvm_enabled())) {
> -               struct pkvm_hyp_vcpu *hyp_vcpu;
> -               struct kvm *host_kvm;
> +               struct pkvm_hyp_vcpu *hyp_vcpu = pkvm_get_loaded_hyp_vcpu();
>
>                 /*
>                  * KVM (and pKVM) doesn't support SME guests for now, and
> @@ -163,9 +193,6 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
>                         goto out;
>                 }
>
> -               host_kvm = kern_hyp_va(host_vcpu->kvm);
> -               hyp_vcpu = pkvm_load_hyp_vcpu(host_kvm->arch.pkvm.handle,
> -                                             host_vcpu->vcpu_idx);
>                 if (!hyp_vcpu) {
>                         ret = -EINVAL;
>                         goto out;
> @@ -176,12 +203,10 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
>                 ret = __kvm_vcpu_run(&hyp_vcpu->vcpu);
>
>                 sync_hyp_vcpu(hyp_vcpu);
> -               pkvm_put_hyp_vcpu(hyp_vcpu);
>         } else {
>                 /* The host is fully trusted, run its vCPU directly. */
> -               ret = __kvm_vcpu_run(host_vcpu);
> +               ret = __kvm_vcpu_run(kern_hyp_va(host_vcpu));
>         }
> -
>  out:
>         cpu_reg(host_ctxt, 1) =  ret;
>  }
> @@ -409,6 +434,8 @@ static const hcall_t host_hcall[] = {
>         HANDLE_FUNC(__pkvm_init_vm),
>         HANDLE_FUNC(__pkvm_init_vcpu),
>         HANDLE_FUNC(__pkvm_teardown_vm),
> +       HANDLE_FUNC(__pkvm_vcpu_load),
> +       HANDLE_FUNC(__pkvm_vcpu_put),
>  };
>
>  static void handle_host_hcall(struct kvm_cpu_context *host_ctxt)
> diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
> index d46a02e24e4a..496d186efb03 100644
> --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
> +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
> @@ -23,6 +23,12 @@ unsigned int kvm_arm_vmid_bits;
>
>  unsigned int kvm_host_sve_max_vl;
>
> +/*
> + * The currently loaded hyp vCPU for each physical CPU. Used only when
> + * protected KVM is enabled, but for both protected and non-protected VMs.
> + */
> +static DEFINE_PER_CPU(struct pkvm_hyp_vcpu *, loaded_hyp_vcpu);
> +
>  /*
>   * Set trap register values based on features in ID_AA64PFR0.
>   */
> @@ -306,15 +312,30 @@ struct pkvm_hyp_vcpu *pkvm_load_hyp_vcpu(pkvm_handle_t handle,
>         struct pkvm_hyp_vcpu *hyp_vcpu = NULL;
>         struct pkvm_hyp_vm *hyp_vm;
>
> +       /* Cannot load a new vcpu without putting the old one first. */
> +       if (__this_cpu_read(loaded_hyp_vcpu))
> +               return NULL;
> +
>         hyp_spin_lock(&vm_table_lock);
>         hyp_vm = get_vm_by_handle(handle);
>         if (!hyp_vm || hyp_vm->nr_vcpus <= vcpu_idx)
>                 goto unlock;
>
>         hyp_vcpu = hyp_vm->vcpus[vcpu_idx];
> +
> +       /* Ensure vcpu isn't loaded on more than one cpu simultaneously. */
> +       if (unlikely(hyp_vcpu->loaded_hyp_vcpu)) {
> +               hyp_vcpu = NULL;
> +               goto unlock;
> +       }
> +
> +       hyp_vcpu->loaded_hyp_vcpu = this_cpu_ptr(&loaded_hyp_vcpu);
>         hyp_page_ref_inc(hyp_virt_to_page(hyp_vm));
>  unlock:
>         hyp_spin_unlock(&vm_table_lock);
> +
> +       if (hyp_vcpu)
> +               __this_cpu_write(loaded_hyp_vcpu, hyp_vcpu);
>         return hyp_vcpu;
>  }
>
> @@ -323,10 +344,18 @@ void pkvm_put_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
>         struct pkvm_hyp_vm *hyp_vm = pkvm_hyp_vcpu_to_hyp_vm(hyp_vcpu);
>
>         hyp_spin_lock(&vm_table_lock);
> +       hyp_vcpu->loaded_hyp_vcpu = NULL;
> +       __this_cpu_write(loaded_hyp_vcpu, NULL);
>         hyp_page_ref_dec(hyp_virt_to_page(hyp_vm));
>         hyp_spin_unlock(&vm_table_lock);
>  }
>
> +struct pkvm_hyp_vcpu *pkvm_get_loaded_hyp_vcpu(void)
> +{
> +       return __this_cpu_read(loaded_hyp_vcpu);
> +
> +}
> +
>  struct pkvm_hyp_vm *get_pkvm_hyp_vm(pkvm_handle_t handle)
>  {
>         struct pkvm_hyp_vm *hyp_vm;
> diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
> index f267bc2486a1..c2ef41fff079 100644
> --- a/arch/arm64/kvm/vgic/vgic-v3.c
> +++ b/arch/arm64/kvm/vgic/vgic-v3.c
> @@ -734,7 +734,8 @@ void vgic_v3_load(struct kvm_vcpu *vcpu)
>  {
>         struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
>
> -       kvm_call_hyp(__vgic_v3_restore_vmcr_aprs, cpu_if);
> +       if (likely(!is_protected_kvm_enabled()))
> +               kvm_call_hyp(__vgic_v3_restore_vmcr_aprs, cpu_if);
>
>         if (has_vhe())
>                 __vgic_v3_activate_traps(cpu_if);
> @@ -746,7 +747,8 @@ void vgic_v3_put(struct kvm_vcpu *vcpu)
>  {
>         struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
>
> -       kvm_call_hyp(__vgic_v3_save_vmcr_aprs, cpu_if);
> +       if (likely(!is_protected_kvm_enabled()))
> +               kvm_call_hyp(__vgic_v3_save_vmcr_aprs, cpu_if);
>         WARN_ON(vgic_v4_put(vcpu));
>
>         if (has_vhe())
> --
> 2.47.1.613.gc27f4b7a9f-goog
>

Re: [PATCH v3 10/18] KVM: arm64: Introduce __pkvm_host_share_guest()

[Fuad Tabba]

On Mon, 16 Dec 2024 at 17:58, Quentin Perret <qperret@google.com> wrote:
>
> In preparation for handling guest stage-2 mappings at EL2, introduce a
> new pKVM hypercall allowing to share pages with non-protected guests.
>
> Signed-off-by: Quentin Perret <qperret@google.com>

(Apart from a nit below)

Reviewed-by: Fuad Tabba <tabba@google.com>

Cheers,
/fuad


> ---
>  arch/arm64/include/asm/kvm_asm.h              |  1 +
>  arch/arm64/include/asm/kvm_host.h             |  3 +
>  arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |  1 +
>  arch/arm64/kvm/hyp/include/nvhe/memory.h      |  2 +
>  arch/arm64/kvm/hyp/nvhe/hyp-main.c            | 34 +++++++++
>  arch/arm64/kvm/hyp/nvhe/mem_protect.c         | 72 +++++++++++++++++++
>  arch/arm64/kvm/hyp/nvhe/pkvm.c                |  7 ++
>  7 files changed, 120 insertions(+)
>
> diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
> index 89c0fac69551..449337f5b2a3 100644
> --- a/arch/arm64/include/asm/kvm_asm.h
> +++ b/arch/arm64/include/asm/kvm_asm.h
> @@ -65,6 +65,7 @@ enum __kvm_host_smccc_func {
>         /* Hypercalls available after pKVM finalisation */
>         __KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp,
>         __KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_hyp,
> +       __KVM_HOST_SMCCC_FUNC___pkvm_host_share_guest,
>         __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc,
>         __KVM_HOST_SMCCC_FUNC___kvm_vcpu_run,
>         __KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context,
> diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
> index e18e9244d17a..1246f1d01dbf 100644
> --- a/arch/arm64/include/asm/kvm_host.h
> +++ b/arch/arm64/include/asm/kvm_host.h
> @@ -771,6 +771,9 @@ struct kvm_vcpu_arch {
>         /* Cache some mmu pages needed inside spinlock regions */
>         struct kvm_mmu_memory_cache mmu_page_cache;
>
> +       /* Pages to top-up the pKVM/EL2 guest pool */
> +       struct kvm_hyp_memcache pkvm_memcache;
> +
>         /* Virtual SError ESR to restore when HCR_EL2.VSE is set */
>         u64 vsesr_el2;
>
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> index 25038ac705d8..a7976e50f556 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> @@ -39,6 +39,7 @@ int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages);
>  int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages);
>  int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages);
>  int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages);
> +int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot);
>
>  bool addr_is_memory(phys_addr_t phys);
>  int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot);
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/memory.h b/arch/arm64/kvm/hyp/include/nvhe/memory.h
> index 8bd9a539f260..cc431820c6ce 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/memory.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/memory.h
> @@ -46,6 +46,8 @@ struct hyp_page {
>
>         /* Host (non-meta) state. Guarded by the host stage-2 lock. */
>         enum pkvm_page_state host_state : 8;
> +
> +       u32 host_share_guest_count;
>  };
>
>  extern u64 __hyp_vmemmap;
> diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> index 95d78db315b3..d659462fbf5d 100644
> --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> @@ -211,6 +211,39 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
>         cpu_reg(host_ctxt, 1) =  ret;
>  }
>
> +static int pkvm_refill_memcache(struct pkvm_hyp_vcpu *hyp_vcpu)
> +{
> +       struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
> +
> +       return refill_memcache(&hyp_vcpu->vcpu.arch.pkvm_memcache,
> +                              host_vcpu->arch.pkvm_memcache.nr_pages,
> +                              &host_vcpu->arch.pkvm_memcache);
> +}
> +
> +static void handle___pkvm_host_share_guest(struct kvm_cpu_context *host_ctxt)
> +{
> +       DECLARE_REG(u64, pfn, host_ctxt, 1);
> +       DECLARE_REG(u64, gfn, host_ctxt, 2);
> +       DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 3);
> +       struct pkvm_hyp_vcpu *hyp_vcpu;
> +       int ret = -EINVAL;
> +
> +       if (!is_protected_kvm_enabled())
> +               goto out;
> +
> +       hyp_vcpu = pkvm_get_loaded_hyp_vcpu();
> +       if (!hyp_vcpu || pkvm_hyp_vcpu_is_protected(hyp_vcpu))
> +               goto out;
> +
> +       ret = pkvm_refill_memcache(hyp_vcpu);
> +       if (ret)
> +               goto out;
> +
> +       ret = __pkvm_host_share_guest(pfn, gfn, hyp_vcpu, prot);
> +out:
> +       cpu_reg(host_ctxt, 1) =  ret;
> +}
> +
>  static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt)
>  {
>         DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1);
> @@ -420,6 +453,7 @@ static const hcall_t host_hcall[] = {
>
>         HANDLE_FUNC(__pkvm_host_share_hyp),
>         HANDLE_FUNC(__pkvm_host_unshare_hyp),
> +       HANDLE_FUNC(__pkvm_host_share_guest),
>         HANDLE_FUNC(__kvm_adjust_pc),
>         HANDLE_FUNC(__kvm_vcpu_run),
>         HANDLE_FUNC(__kvm_flush_vm_context),
> diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> index 12bb5445fe47..fb9592e721cf 100644
> --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> @@ -867,6 +867,27 @@ static int hyp_complete_donation(u64 addr,
>         return pkvm_create_mappings_locked(start, end, prot);
>  }
>
> +static enum pkvm_page_state guest_get_page_state(kvm_pte_t pte, u64 addr)
> +{
> +       if (!kvm_pte_valid(pte))
> +               return PKVM_NOPAGE;
> +
> +       return pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte));
> +}
> +
> +static int __guest_check_page_state_range(struct pkvm_hyp_vcpu *vcpu, u64 addr,
> +                                         u64 size, enum pkvm_page_state state)
> +{
> +       struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
> +       struct check_walk_data d = {
> +               .desired        = state,
> +               .get_page_state = guest_get_page_state,
> +       };
> +
> +       hyp_assert_lock_held(&vm->lock);
> +       return check_page_state_range(&vm->pgt, addr, size, &d);
> +}
> +
>  static int check_share(struct pkvm_mem_share *share)
>  {
>         const struct pkvm_mem_transition *tx = &share->tx;
> @@ -1349,3 +1370,54 @@ int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages)
>
>         return ret;
>  }
> +
> +int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu,
> +                           enum kvm_pgtable_prot prot)
> +{
> +       struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
> +       u64 phys = hyp_pfn_to_phys(pfn);
> +       u64 ipa = hyp_pfn_to_phys(gfn);
> +       struct hyp_page *page;
> +       int ret;
> +
> +       if (prot & ~KVM_PGTABLE_PROT_RWX)
> +               return -EINVAL;
> +
> +       ret = check_range_allowed_memory(phys, phys + PAGE_SIZE);
> +       if (ret)
> +               return ret;
> +
> +       host_lock_component();
> +       guest_lock_component(vm);
> +
> +       ret = __guest_check_page_state_range(vcpu, ipa, PAGE_SIZE, PKVM_NOPAGE);
> +       if (ret)
> +               goto unlock;
> +
> +       page = hyp_phys_to_page(phys);
> +       switch (page->host_state) {
> +       case PKVM_PAGE_OWNED:
> +               WARN_ON(__host_set_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_SHARED_OWNED));
> +               break;
> +       case PKVM_PAGE_SHARED_OWNED:
> +               if (page->host_share_guest_count)
> +                       break;
> +               /* Only host to np-guest multi-sharing is tolerated */
> +               WARN_ON(1);
> +               fallthrough;
> +       default:
> +               ret = -EPERM;
> +               goto unlock;
> +       }
> +
> +       WARN_ON(kvm_pgtable_stage2_map(&vm->pgt, ipa, PAGE_SIZE, phys,
> +                                      pkvm_mkstate(prot, PKVM_PAGE_SHARED_BORROWED),
> +                                      &vcpu->vcpu.arch.pkvm_memcache, 0));
> +       page->host_share_guest_count++;
> +
> +unlock:
> +       guest_unlock_component(vm);
> +       host_unlock_component();
> +
> +       return ret;
> +}
> diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
> index 496d186efb03..f2e363fe6b84 100644
> --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
> +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
> @@ -795,6 +795,13 @@ int __pkvm_teardown_vm(pkvm_handle_t handle)
>         /* Push the metadata pages to the teardown memcache */
>         for (idx = 0; idx < hyp_vm->nr_vcpus; ++idx) {
>                 struct pkvm_hyp_vcpu *hyp_vcpu = hyp_vm->vcpus[idx];
> +               struct kvm_hyp_memcache *vcpu_mc = &hyp_vcpu->vcpu.arch.pkvm_memcache;
> +
> +               while (vcpu_mc->nr_pages) {
> +                       void *addr = pop_hyp_memcache(vcpu_mc, hyp_phys_to_virt);

nit: newline

> +                       push_hyp_memcache(mc, addr, hyp_virt_to_phys);
> +                       unmap_donated_memory_noclear(addr, PAGE_SIZE);
> +               }
>
>                 teardown_donated_memory(mc, hyp_vcpu, sizeof(*hyp_vcpu));
>         }
> --
> 2.47.1.613.gc27f4b7a9f-goog
>

Re: [PATCH v3 11/18] KVM: arm64: Introduce __pkvm_host_unshare_guest()

[Fuad Tabba]

On Mon, 16 Dec 2024 at 17:58, Quentin Perret <qperret@google.com> wrote:
>
> In preparation for letting the host unmap pages from non-protected
> guests, introduce a new hypercall implementing the host-unshare-guest
> transition.
>
> Signed-off-by: Quentin Perret <qperret@google.com>

Apart from nit below.
Reviewed-by: Fuad Tabba <tabba@google.com>

Cheers,
/fuad


> ---
>  arch/arm64/include/asm/kvm_asm.h              |  1 +
>  arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |  1 +
>  arch/arm64/kvm/hyp/include/nvhe/pkvm.h        |  6 ++
>  arch/arm64/kvm/hyp/nvhe/hyp-main.c            | 21 ++++++
>  arch/arm64/kvm/hyp/nvhe/mem_protect.c         | 67 +++++++++++++++++++
>  arch/arm64/kvm/hyp/nvhe/pkvm.c                | 12 ++++
>  6 files changed, 108 insertions(+)
>
> diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
> index 449337f5b2a3..0b6c4d325134 100644
> --- a/arch/arm64/include/asm/kvm_asm.h
> +++ b/arch/arm64/include/asm/kvm_asm.h
> @@ -66,6 +66,7 @@ enum __kvm_host_smccc_func {
>         __KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp,
>         __KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_hyp,
>         __KVM_HOST_SMCCC_FUNC___pkvm_host_share_guest,
> +       __KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_guest,
>         __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc,
>         __KVM_HOST_SMCCC_FUNC___kvm_vcpu_run,
>         __KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context,
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> index a7976e50f556..e528a42ed60e 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> @@ -40,6 +40,7 @@ int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages);
>  int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages);
>  int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages);
>  int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot);
> +int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm);
>
>  bool addr_is_memory(phys_addr_t phys);
>  int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot);
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
> index be52c5b15e21..0cc2a429f1fb 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
> @@ -64,6 +64,11 @@ static inline bool pkvm_hyp_vcpu_is_protected(struct pkvm_hyp_vcpu *hyp_vcpu)
>         return vcpu_is_protected(&hyp_vcpu->vcpu);
>  }
>
> +static inline bool pkvm_hyp_vm_is_protected(struct pkvm_hyp_vm *hyp_vm)
> +{
> +       return kvm_vm_is_protected(&hyp_vm->kvm);
> +}
> +
>  void pkvm_hyp_vm_table_init(void *tbl);
>
>  int __pkvm_init_vm(struct kvm *host_kvm, unsigned long vm_hva,
> @@ -78,6 +83,7 @@ void pkvm_put_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu);
>  struct pkvm_hyp_vcpu *pkvm_get_loaded_hyp_vcpu(void);
>
>  struct pkvm_hyp_vm *get_pkvm_hyp_vm(pkvm_handle_t handle);
> +struct pkvm_hyp_vm *get_np_pkvm_hyp_vm(pkvm_handle_t handle);
>  void put_pkvm_hyp_vm(struct pkvm_hyp_vm *hyp_vm);
>
>  #endif /* __ARM64_KVM_NVHE_PKVM_H__ */
> diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> index d659462fbf5d..3c3a27c985a2 100644
> --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> @@ -244,6 +244,26 @@ static void handle___pkvm_host_share_guest(struct kvm_cpu_context *host_ctxt)
>         cpu_reg(host_ctxt, 1) =  ret;
>  }
>
> +static void handle___pkvm_host_unshare_guest(struct kvm_cpu_context *host_ctxt)
> +{
> +       DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);
> +       DECLARE_REG(u64, gfn, host_ctxt, 2);
> +       struct pkvm_hyp_vm *hyp_vm;
> +       int ret = -EINVAL;
> +
> +       if (!is_protected_kvm_enabled())
> +               goto out;
> +
> +       hyp_vm = get_np_pkvm_hyp_vm(handle);
> +       if (!hyp_vm)
> +               goto out;
> +
> +       ret = __pkvm_host_unshare_guest(gfn, hyp_vm);
> +       put_pkvm_hyp_vm(hyp_vm);
> +out:
> +       cpu_reg(host_ctxt, 1) =  ret;
> +}
> +
>  static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt)
>  {
>         DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1);
> @@ -454,6 +474,7 @@ static const hcall_t host_hcall[] = {
>         HANDLE_FUNC(__pkvm_host_share_hyp),
>         HANDLE_FUNC(__pkvm_host_unshare_hyp),
>         HANDLE_FUNC(__pkvm_host_share_guest),
> +       HANDLE_FUNC(__pkvm_host_unshare_guest),
>         HANDLE_FUNC(__kvm_adjust_pc),
>         HANDLE_FUNC(__kvm_vcpu_run),
>         HANDLE_FUNC(__kvm_flush_vm_context),
> diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> index fb9592e721cf..30243b7922f1 100644
> --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> @@ -1421,3 +1421,70 @@ int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu,
>
>         return ret;
>  }
> +
> +static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ipa)

nit: This parameter in this patch, and others, is sometimes hyp_vm, at
others just vm. It would be nicer if it was always the same.


> +{
> +       enum pkvm_page_state state;
> +       struct hyp_page *page;
> +       kvm_pte_t pte;
> +       u64 phys;
> +       s8 level;
> +       int ret;
> +
> +       ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level);
> +       if (ret)
> +               return ret;
> +       if (level != KVM_PGTABLE_LAST_LEVEL)
> +               return -E2BIG;
> +       if (!kvm_pte_valid(pte))
> +               return -ENOENT;
> +
> +       state = guest_get_page_state(pte, ipa);
> +       if (state != PKVM_PAGE_SHARED_BORROWED)
> +               return -EPERM;
> +
> +       phys = kvm_pte_to_phys(pte);
> +       ret = check_range_allowed_memory(phys, phys + PAGE_SIZE);
> +       if (WARN_ON(ret))
> +               return ret;
> +
> +       page = hyp_phys_to_page(phys);
> +       if (page->host_state != PKVM_PAGE_SHARED_OWNED)
> +               return -EPERM;
> +       if (WARN_ON(!page->host_share_guest_count))
> +               return -EINVAL;
> +
> +       *__phys = phys;
> +
> +       return 0;
> +}
> +
> +int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *vm)
> +{
> +       u64 ipa = hyp_pfn_to_phys(gfn);
> +       struct hyp_page *page;
> +       u64 phys;
> +       int ret;
> +
> +       host_lock_component();
> +       guest_lock_component(vm);
> +
> +       ret = __check_host_shared_guest(vm, &phys, ipa);
> +       if (ret)
> +               goto unlock;
> +
> +       ret = kvm_pgtable_stage2_unmap(&vm->pgt, ipa, PAGE_SIZE);
> +       if (ret)
> +               goto unlock;
> +
> +       page = hyp_phys_to_page(phys);
> +       page->host_share_guest_count--;
> +       if (!page->host_share_guest_count)
> +               WARN_ON(__host_set_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_OWNED));
> +
> +unlock:
> +       guest_unlock_component(vm);
> +       host_unlock_component();
> +
> +       return ret;
> +}
> diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
> index f2e363fe6b84..1b0982fa5ba8 100644
> --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
> +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
> @@ -376,6 +376,18 @@ void put_pkvm_hyp_vm(struct pkvm_hyp_vm *hyp_vm)
>         hyp_spin_unlock(&vm_table_lock);
>  }
>
> +struct pkvm_hyp_vm *get_np_pkvm_hyp_vm(pkvm_handle_t handle)
> +{
> +       struct pkvm_hyp_vm *hyp_vm = get_pkvm_hyp_vm(handle);
> +
> +       if (hyp_vm && pkvm_hyp_vm_is_protected(hyp_vm)) {
> +               put_pkvm_hyp_vm(hyp_vm);
> +               hyp_vm = NULL;
> +       }
> +
> +       return hyp_vm;
> +}
> +
>  static void pkvm_init_features_from_host(struct pkvm_hyp_vm *hyp_vm, const struct kvm *host_kvm)
>  {
>         struct kvm *kvm = &hyp_vm->kvm;
> --
> 2.47.1.613.gc27f4b7a9f-goog
>

Re: [PATCH v3 13/18] KVM: arm64: Introduce __pkvm_host_wrprotect_guest()

[Fuad Tabba]

On Mon, 16 Dec 2024 at 17:58, Quentin Perret <qperret@google.com> wrote:
>
> Introduce a new hypercall to remove the write permission from a
> non-protected guest stage-2 mapping. This will be used for e.g. enabling
> dirty logging.
>
> Signed-off-by: Quentin Perret <qperret@google.com>

Reviewed-by: Fuad Tabba <tabba@google.com>

Cheers,
/fuad


> ---
>  arch/arm64/include/asm/kvm_asm.h              |  1 +
>  arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |  1 +
>  arch/arm64/kvm/hyp/nvhe/hyp-main.c            | 21 +++++++++++++++++++
>  arch/arm64/kvm/hyp/nvhe/mem_protect.c         | 19 +++++++++++++++++
>  4 files changed, 42 insertions(+)
>
> diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
> index 66ee8542dcc9..8663a588cf34 100644
> --- a/arch/arm64/include/asm/kvm_asm.h
> +++ b/arch/arm64/include/asm/kvm_asm.h
> @@ -68,6 +68,7 @@ enum __kvm_host_smccc_func {
>         __KVM_HOST_SMCCC_FUNC___pkvm_host_share_guest,
>         __KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_guest,
>         __KVM_HOST_SMCCC_FUNC___pkvm_host_relax_perms_guest,
> +       __KVM_HOST_SMCCC_FUNC___pkvm_host_wrprotect_guest,
>         __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc,
>         __KVM_HOST_SMCCC_FUNC___kvm_vcpu_run,
>         __KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context,
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> index a308dcd3b5b8..fc9fdd5b0a52 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> @@ -42,6 +42,7 @@ int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages);
>  int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot);
>  int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm);
>  int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot);
> +int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm);
>
>  bool addr_is_memory(phys_addr_t phys);
>  int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot);
> diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> index 287e4ee93ef2..98d317735107 100644
> --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> @@ -283,6 +283,26 @@ static void handle___pkvm_host_relax_perms_guest(struct kvm_cpu_context *host_ct
>         cpu_reg(host_ctxt, 1) = ret;
>  }
>
> +static void handle___pkvm_host_wrprotect_guest(struct kvm_cpu_context *host_ctxt)
> +{
> +       DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);
> +       DECLARE_REG(u64, gfn, host_ctxt, 2);
> +       struct pkvm_hyp_vm *hyp_vm;
> +       int ret = -EINVAL;
> +
> +       if (!is_protected_kvm_enabled())
> +               goto out;
> +
> +       hyp_vm = get_np_pkvm_hyp_vm(handle);
> +       if (!hyp_vm)
> +               goto out;
> +
> +       ret = __pkvm_host_wrprotect_guest(gfn, hyp_vm);
> +       put_pkvm_hyp_vm(hyp_vm);
> +out:
> +       cpu_reg(host_ctxt, 1) = ret;
> +}
> +
>  static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt)
>  {
>         DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1);
> @@ -495,6 +515,7 @@ static const hcall_t host_hcall[] = {
>         HANDLE_FUNC(__pkvm_host_share_guest),
>         HANDLE_FUNC(__pkvm_host_unshare_guest),
>         HANDLE_FUNC(__pkvm_host_relax_perms_guest),
> +       HANDLE_FUNC(__pkvm_host_wrprotect_guest),
>         HANDLE_FUNC(__kvm_adjust_pc),
>         HANDLE_FUNC(__kvm_vcpu_run),
>         HANDLE_FUNC(__kvm_flush_vm_context),
> diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> index aa8e0408aebb..94e4251b5077 100644
> --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> @@ -1511,3 +1511,22 @@ int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_
>
>         return ret;
>  }
> +
> +int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *vm)
> +{
> +       u64 ipa = hyp_pfn_to_phys(gfn);
> +       u64 phys;
> +       int ret;
> +
> +       host_lock_component();
> +       guest_lock_component(vm);
> +
> +       ret = __check_host_shared_guest(vm, &phys, ipa);
> +       if (!ret)
> +               ret = kvm_pgtable_stage2_wrprotect(&vm->pgt, ipa, PAGE_SIZE);
> +
> +       guest_unlock_component(vm);
> +       host_unlock_component();
> +
> +       return ret;
> +}
> --
> 2.47.1.613.gc27f4b7a9f-goog
>

Re: [PATCH v3 12/18] KVM: arm64: Introduce __pkvm_host_relax_guest_perms()

[Fuad Tabba]

On Mon, 16 Dec 2024 at 17:58, Quentin Perret <qperret@google.com> wrote:
>
> Introduce a new hypercall allowing the host to relax the stage-2
> permissions of mappings in a non-protected guest page-table. It will be
> used later once we start allowing RO memslots and dirty logging.
>
> Signed-off-by: Quentin Perret <qperret@google.com>

Reviewed-by: Fuad Tabba <tabba@google.com>

Cheers,
/fuad

> ---
>  arch/arm64/include/asm/kvm_asm.h              |  1 +
>  arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |  1 +
>  arch/arm64/kvm/hyp/nvhe/hyp-main.c            | 20 ++++++++++++++++
>  arch/arm64/kvm/hyp/nvhe/mem_protect.c         | 23 +++++++++++++++++++
>  4 files changed, 45 insertions(+)
>
> diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
> index 0b6c4d325134..66ee8542dcc9 100644
> --- a/arch/arm64/include/asm/kvm_asm.h
> +++ b/arch/arm64/include/asm/kvm_asm.h
> @@ -67,6 +67,7 @@ enum __kvm_host_smccc_func {
>         __KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_hyp,
>         __KVM_HOST_SMCCC_FUNC___pkvm_host_share_guest,
>         __KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_guest,
> +       __KVM_HOST_SMCCC_FUNC___pkvm_host_relax_perms_guest,
>         __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc,
>         __KVM_HOST_SMCCC_FUNC___kvm_vcpu_run,
>         __KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context,
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> index e528a42ed60e..a308dcd3b5b8 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> @@ -41,6 +41,7 @@ int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages);
>  int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages);
>  int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot);
>  int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm);
> +int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot);
>
>  bool addr_is_memory(phys_addr_t phys);
>  int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot);
> diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> index 3c3a27c985a2..287e4ee93ef2 100644
> --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> @@ -264,6 +264,25 @@ static void handle___pkvm_host_unshare_guest(struct kvm_cpu_context *host_ctxt)
>         cpu_reg(host_ctxt, 1) =  ret;
>  }
>
> +static void handle___pkvm_host_relax_perms_guest(struct kvm_cpu_context *host_ctxt)
> +{
> +       DECLARE_REG(u64, gfn, host_ctxt, 1);
> +       DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 2);
> +       struct pkvm_hyp_vcpu *hyp_vcpu;
> +       int ret = -EINVAL;
> +
> +       if (!is_protected_kvm_enabled())
> +               goto out;
> +
> +       hyp_vcpu = pkvm_get_loaded_hyp_vcpu();
> +       if (!hyp_vcpu || pkvm_hyp_vcpu_is_protected(hyp_vcpu))
> +               goto out;
> +
> +       ret = __pkvm_host_relax_perms_guest(gfn, hyp_vcpu, prot);
> +out:
> +       cpu_reg(host_ctxt, 1) = ret;
> +}
> +
>  static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt)
>  {
>         DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1);
> @@ -475,6 +494,7 @@ static const hcall_t host_hcall[] = {
>         HANDLE_FUNC(__pkvm_host_unshare_hyp),
>         HANDLE_FUNC(__pkvm_host_share_guest),
>         HANDLE_FUNC(__pkvm_host_unshare_guest),
> +       HANDLE_FUNC(__pkvm_host_relax_perms_guest),
>         HANDLE_FUNC(__kvm_adjust_pc),
>         HANDLE_FUNC(__kvm_vcpu_run),
>         HANDLE_FUNC(__kvm_flush_vm_context),
> diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> index 30243b7922f1..aa8e0408aebb 100644
> --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> @@ -1488,3 +1488,26 @@ int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *vm)
>
>         return ret;
>  }
> +
> +int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot)
> +{
> +       struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
> +       u64 ipa = hyp_pfn_to_phys(gfn);
> +       u64 phys;
> +       int ret;
> +
> +       if (prot & ~KVM_PGTABLE_PROT_RWX)
> +               return -EINVAL;
> +
> +       host_lock_component();
> +       guest_lock_component(vm);
> +
> +       ret = __check_host_shared_guest(vm, &phys, ipa);
> +       if (!ret)
> +               ret = kvm_pgtable_stage2_relax_perms(&vm->pgt, ipa, prot, 0);
> +
> +       guest_unlock_component(vm);
> +       host_unlock_component();
> +
> +       return ret;
> +}
> --
> 2.47.1.613.gc27f4b7a9f-goog
>

Re: [PATCH v3 14/18] KVM: arm64: Introduce __pkvm_host_test_clear_young_guest()

[Fuad Tabba]

On Mon, 16 Dec 2024 at 17:58, Quentin Perret <qperret@google.com> wrote:
>
> Plumb the kvm_stage2_test_clear_young() callback into pKVM for
> non-protected guest. It will be later be called from MMU notifiers.
>
> Signed-off-by: Quentin Perret <qperret@google.com>

Reviewed-by: Fuad Tabba <tabba@google.com>

Cheers,
/fuad

> ---
>  arch/arm64/include/asm/kvm_asm.h              |  1 +
>  arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |  1 +
>  arch/arm64/kvm/hyp/nvhe/hyp-main.c            | 22 +++++++++++++++++++
>  arch/arm64/kvm/hyp/nvhe/mem_protect.c         | 19 ++++++++++++++++
>  4 files changed, 43 insertions(+)
>
> diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
> index 8663a588cf34..4f97155d6323 100644
> --- a/arch/arm64/include/asm/kvm_asm.h
> +++ b/arch/arm64/include/asm/kvm_asm.h
> @@ -69,6 +69,7 @@ enum __kvm_host_smccc_func {
>         __KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_guest,
>         __KVM_HOST_SMCCC_FUNC___pkvm_host_relax_perms_guest,
>         __KVM_HOST_SMCCC_FUNC___pkvm_host_wrprotect_guest,
> +       __KVM_HOST_SMCCC_FUNC___pkvm_host_test_clear_young_guest,
>         __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc,
>         __KVM_HOST_SMCCC_FUNC___kvm_vcpu_run,
>         __KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context,
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> index fc9fdd5b0a52..b3aaad150b3e 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> @@ -43,6 +43,7 @@ int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum k
>  int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm);
>  int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot);
>  int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm);
> +int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *vm);
>
>  bool addr_is_memory(phys_addr_t phys);
>  int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot);
> diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> index 98d317735107..616e172a9c48 100644
> --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> @@ -303,6 +303,27 @@ static void handle___pkvm_host_wrprotect_guest(struct kvm_cpu_context *host_ctxt
>         cpu_reg(host_ctxt, 1) = ret;
>  }
>
> +static void handle___pkvm_host_test_clear_young_guest(struct kvm_cpu_context *host_ctxt)
> +{
> +       DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);
> +       DECLARE_REG(u64, gfn, host_ctxt, 2);
> +       DECLARE_REG(bool, mkold, host_ctxt, 3);
> +       struct pkvm_hyp_vm *hyp_vm;
> +       int ret = -EINVAL;
> +
> +       if (!is_protected_kvm_enabled())
> +               goto out;
> +
> +       hyp_vm = get_np_pkvm_hyp_vm(handle);
> +       if (!hyp_vm)
> +               goto out;
> +
> +       ret = __pkvm_host_test_clear_young_guest(gfn, mkold, hyp_vm);
> +       put_pkvm_hyp_vm(hyp_vm);
> +out:
> +       cpu_reg(host_ctxt, 1) = ret;
> +}
> +
>  static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt)
>  {
>         DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1);
> @@ -516,6 +537,7 @@ static const hcall_t host_hcall[] = {
>         HANDLE_FUNC(__pkvm_host_unshare_guest),
>         HANDLE_FUNC(__pkvm_host_relax_perms_guest),
>         HANDLE_FUNC(__pkvm_host_wrprotect_guest),
> +       HANDLE_FUNC(__pkvm_host_test_clear_young_guest),
>         HANDLE_FUNC(__kvm_adjust_pc),
>         HANDLE_FUNC(__kvm_vcpu_run),
>         HANDLE_FUNC(__kvm_flush_vm_context),
> diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> index 94e4251b5077..0e42c3baaf4b 100644
> --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> @@ -1530,3 +1530,22 @@ int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *vm)
>
>         return ret;
>  }
> +
> +int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *vm)
> +{
> +       u64 ipa = hyp_pfn_to_phys(gfn);
> +       u64 phys;
> +       int ret;
> +
> +       host_lock_component();
> +       guest_lock_component(vm);
> +
> +       ret = __check_host_shared_guest(vm, &phys, ipa);
> +       if (!ret)
> +               ret = kvm_pgtable_stage2_test_clear_young(&vm->pgt, ipa, PAGE_SIZE, mkold);
> +
> +       guest_unlock_component(vm);
> +       host_unlock_component();
> +
> +       return ret;
> +}
> --
> 2.47.1.613.gc27f4b7a9f-goog
>

Re: [PATCH v3 15/18] KVM: arm64: Introduce __pkvm_host_mkyoung_guest()

[Fuad Tabba]

On Mon, 16 Dec 2024 at 17:58, Quentin Perret <qperret@google.com> wrote:
>
> Plumb the kvm_pgtable_stage2_mkyoung() callback into pKVM for
> non-protected guests. It will be called later from the fault handling
> path.
>
> Signed-off-by: Quentin Perret <qperret@google.com>

Reviewed-by: Fuad Tabba <tabba@google.com>

Cheers,
/fuad

> ---
>  arch/arm64/include/asm/kvm_asm.h              |  1 +
>  arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |  1 +
>  arch/arm64/kvm/hyp/nvhe/hyp-main.c            | 19 ++++++++++++++++++
>  arch/arm64/kvm/hyp/nvhe/mem_protect.c         | 20 +++++++++++++++++++
>  4 files changed, 41 insertions(+)
>
> diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
> index 4f97155d6323..a3b07db2776c 100644
> --- a/arch/arm64/include/asm/kvm_asm.h
> +++ b/arch/arm64/include/asm/kvm_asm.h
> @@ -70,6 +70,7 @@ enum __kvm_host_smccc_func {
>         __KVM_HOST_SMCCC_FUNC___pkvm_host_relax_perms_guest,
>         __KVM_HOST_SMCCC_FUNC___pkvm_host_wrprotect_guest,
>         __KVM_HOST_SMCCC_FUNC___pkvm_host_test_clear_young_guest,
> +       __KVM_HOST_SMCCC_FUNC___pkvm_host_mkyoung_guest,
>         __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc,
>         __KVM_HOST_SMCCC_FUNC___kvm_vcpu_run,
>         __KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context,
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> index b3aaad150b3e..65c34753d86c 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> @@ -44,6 +44,7 @@ int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm);
>  int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot);
>  int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm);
>  int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *vm);
> +int __pkvm_host_mkyoung_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu);
>
>  bool addr_is_memory(phys_addr_t phys);
>  int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot);
> diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> index 616e172a9c48..32c4627b5b5b 100644
> --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> @@ -324,6 +324,24 @@ static void handle___pkvm_host_test_clear_young_guest(struct kvm_cpu_context *ho
>         cpu_reg(host_ctxt, 1) = ret;
>  }
>
> +static void handle___pkvm_host_mkyoung_guest(struct kvm_cpu_context *host_ctxt)
> +{
> +       DECLARE_REG(u64, gfn, host_ctxt, 1);
> +       struct pkvm_hyp_vcpu *hyp_vcpu;
> +       int ret = -EINVAL;
> +
> +       if (!is_protected_kvm_enabled())
> +               goto out;
> +
> +       hyp_vcpu = pkvm_get_loaded_hyp_vcpu();
> +       if (!hyp_vcpu || pkvm_hyp_vcpu_is_protected(hyp_vcpu))
> +               goto out;
> +
> +       ret = __pkvm_host_mkyoung_guest(gfn, hyp_vcpu);
> +out:
> +       cpu_reg(host_ctxt, 1) =  ret;
> +}
> +
>  static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt)
>  {
>         DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1);
> @@ -538,6 +556,7 @@ static const hcall_t host_hcall[] = {
>         HANDLE_FUNC(__pkvm_host_relax_perms_guest),
>         HANDLE_FUNC(__pkvm_host_wrprotect_guest),
>         HANDLE_FUNC(__pkvm_host_test_clear_young_guest),
> +       HANDLE_FUNC(__pkvm_host_mkyoung_guest),
>         HANDLE_FUNC(__kvm_adjust_pc),
>         HANDLE_FUNC(__kvm_vcpu_run),
>         HANDLE_FUNC(__kvm_flush_vm_context),
> diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> index 0e42c3baaf4b..eae03509d371 100644
> --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> @@ -1549,3 +1549,23 @@ int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *
>
>         return ret;
>  }
> +
> +int __pkvm_host_mkyoung_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu)
> +{
> +       struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
> +       u64 ipa = hyp_pfn_to_phys(gfn);
> +       u64 phys;
> +       int ret;
> +
> +       host_lock_component();
> +       guest_lock_component(vm);
> +
> +       ret = __check_host_shared_guest(vm, &phys, ipa);
> +       if (!ret)
> +               kvm_pgtable_stage2_mkyoung(&vm->pgt, ipa, 0);
> +
> +       guest_unlock_component(vm);
> +       host_unlock_component();
> +
> +       return ret;
> +}
> --
> 2.47.1.613.gc27f4b7a9f-goog
>

Re: [PATCH v3 16/18] KVM: arm64: Introduce __pkvm_tlb_flush_vmid()

[Fuad Tabba]

On Mon, 16 Dec 2024 at 17:58, Quentin Perret <qperret@google.com> wrote:
>
> Introduce a new hypercall to flush the TLBs of non-protected guests. The
> host kernel will be responsible for issuing this hypercall after changing
> stage-2 permissions using the __pkvm_host_relax_guest_perms() or
> __pkvm_host_wrprotect_guest() paths. This is left under the host's
> responsibility for performance reasons.
>
> Note however that the TLB maintenance for all *unmap* operations still
> remains entirely under the hypervisor's responsibility for security
> reasons -- an unmapped page may be donated to another entity, so a stale
> TLB entry could be used to leak private data.
>
> Signed-off-by: Quentin Perret <qperret@google.com>

Reviewed-by: Fuad Tabba <tabba@google.com>

Cheers,
/fuad

> ---
>  arch/arm64/include/asm/kvm_asm.h   |  1 +
>  arch/arm64/kvm/hyp/nvhe/hyp-main.c | 17 +++++++++++++++++
>  2 files changed, 18 insertions(+)
>
> diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
> index a3b07db2776c..002088c6e297 100644
> --- a/arch/arm64/include/asm/kvm_asm.h
> +++ b/arch/arm64/include/asm/kvm_asm.h
> @@ -87,6 +87,7 @@ enum __kvm_host_smccc_func {
>         __KVM_HOST_SMCCC_FUNC___pkvm_teardown_vm,
>         __KVM_HOST_SMCCC_FUNC___pkvm_vcpu_load,
>         __KVM_HOST_SMCCC_FUNC___pkvm_vcpu_put,
> +       __KVM_HOST_SMCCC_FUNC___pkvm_tlb_flush_vmid,
>  };
>
>  #define DECLARE_KVM_VHE_SYM(sym)       extern char sym[]
> diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> index 32c4627b5b5b..130f5f23bcb5 100644
> --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> @@ -389,6 +389,22 @@ static void handle___kvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt)
>         __kvm_tlb_flush_vmid(kern_hyp_va(mmu));
>  }
>
> +static void handle___pkvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt)
> +{
> +       DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);
> +       struct pkvm_hyp_vm *hyp_vm;
> +
> +       if (!is_protected_kvm_enabled())
> +               return;
> +
> +       hyp_vm = get_np_pkvm_hyp_vm(handle);
> +       if (!hyp_vm)
> +               return;
> +
> +       __kvm_tlb_flush_vmid(&hyp_vm->kvm.arch.mmu);
> +       put_pkvm_hyp_vm(hyp_vm);
> +}
> +
>  static void handle___kvm_flush_cpu_context(struct kvm_cpu_context *host_ctxt)
>  {
>         DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
> @@ -573,6 +589,7 @@ static const hcall_t host_hcall[] = {
>         HANDLE_FUNC(__pkvm_teardown_vm),
>         HANDLE_FUNC(__pkvm_vcpu_load),
>         HANDLE_FUNC(__pkvm_vcpu_put),
> +       HANDLE_FUNC(__pkvm_tlb_flush_vmid),
>  };
>
>  static void handle_host_hcall(struct kvm_cpu_context *host_ctxt)
> --
> 2.47.1.613.gc27f4b7a9f-goog
>

Re: [PATCH v3 00/18] KVM: arm64: Non-protected guest stage-2 support for pKVM

[Fuad Tabba]

On Mon, 16 Dec 2024 at 17:58, Quentin Perret <qperret@google.com> wrote:
>
> Hi all,
>
> This is the v3 of the series adding support for non-protected guests
> stage-2 to pKVM. Please refer to v1 for all the context:

For the series:

Tested-by: Fuad Tabba <tabba@google.com>

Cheers,
/fuad



>
>   https://lore.kernel.org/kvmarm/20241104133204.85208-1-qperret@google.com/
>
> The series is organized as follows:
>
>  - Patches 01 to 04 move the host ownership state tracking from the
>    host's stage-2 page-table to the hypervisor's vmemmap. This avoids
>    fragmenting the host stage-2 for shared pages, which is only needed
>    to store an annotation in the SW bits of the corresponding PTE. All
>    pages mapped into non-protected guests are shared from pKVM's PoV,
>    so the cost of stage-2 fragmentation will increase massively as we
>    start tracking that at EL2. Note that these patches also help with
>    the existing sharing for e.g. FF-A, so they could possibly be merged
>    separately from the rest of the series.
>
>  - Patches 05 to 07 implement a minor refactoring of the pgtable code to
>    ease the integration of the pKVM MMU later on.
>
>  - Patches 08 to 16 introduce all the infrastructure needed on the pKVM
>    side for handling guest stage-2 page-tables at EL2.
>
>  - Patches 17 and 18 plumb the newly introduced pKVM support into
>    KVM/arm64.
>
> Patches based on 6.13-rc3, tested on Pixel 6 and Qemu.
>
> Changes in v3:
>  - Rebased on 6.13-rc3
>  - Applied Marc's rework of the for_each_mapping_in_range() macro mess
>  - Removed mappings_lock in favor the mmu_lock
>  - Dropped BUG_ON() from pkvm_mkstate()
>  - Renamed range_is_allowed_memory() and clarified the comment inside it
>  - Explicitly bail out when using host_stage2_set_owner_locked() on
>    non-memory regions
>  - Check PKVM_NOPAGE state as an equality rather than a bitwise
>    operator
>  - Reworked __pkvm_host_share_guest() to return -EPERM in case of
>    illegal multi-sharing
>  - Added get_np_pkvm_hyp_vm() to simplify HVC error handling in
>    hyp-main.c
>  - Cosmetic changes and improved coding consitency thoughout the series
>
> Changes in v2:
>  - Rebased on 6.13-rc1 (small conflicts with 2362506f7cff ("KVM: arm64:
>    Don't mark "struct page" accessed when making SPTE young") in
>    particular)
>  - Fixed kerneldoc breakage for __unmap_stage2_range()
>  - Fixed pkvm_pgtable_test_clear_young() to use correct HVC
>  - Folded guest_get_valid_pte() into __check_host_unshare_guest() for
>    clarity
>
> Thanks,
> Quentin
>
> Marc Zyngier (1):
>   KVM: arm64: Introduce __pkvm_vcpu_{load,put}()
>
> Quentin Perret (17):
>   KVM: arm64: Change the layout of enum pkvm_page_state
>   KVM: arm64: Move enum pkvm_page_state to memory.h
>   KVM: arm64: Make hyp_page::order a u8
>   KVM: arm64: Move host page ownership tracking to the hyp vmemmap
>   KVM: arm64: Pass walk flags to kvm_pgtable_stage2_mkyoung
>   KVM: arm64: Pass walk flags to kvm_pgtable_stage2_relax_perms
>   KVM: arm64: Make kvm_pgtable_stage2_init() a static inline function
>   KVM: arm64: Add {get,put}_pkvm_hyp_vm() helpers
>   KVM: arm64: Introduce __pkvm_host_share_guest()
>   KVM: arm64: Introduce __pkvm_host_unshare_guest()
>   KVM: arm64: Introduce __pkvm_host_relax_guest_perms()
>   KVM: arm64: Introduce __pkvm_host_wrprotect_guest()
>   KVM: arm64: Introduce __pkvm_host_test_clear_young_guest()
>   KVM: arm64: Introduce __pkvm_host_mkyoung_guest()
>   KVM: arm64: Introduce __pkvm_tlb_flush_vmid()
>   KVM: arm64: Introduce the EL1 pKVM MMU
>   KVM: arm64: Plumb the pKVM MMU in KVM
>
>  arch/arm64/include/asm/kvm_asm.h              |   9 +
>  arch/arm64/include/asm/kvm_host.h             |   4 +
>  arch/arm64/include/asm/kvm_mmu.h              |  16 +
>  arch/arm64/include/asm/kvm_pgtable.h          |  38 ++-
>  arch/arm64/include/asm/kvm_pkvm.h             |  23 ++
>  arch/arm64/kvm/arm.c                          |  23 +-
>  arch/arm64/kvm/hyp/include/nvhe/gfp.h         |   6 +-
>  arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |  38 +--
>  arch/arm64/kvm/hyp/include/nvhe/memory.h      |  42 ++-
>  arch/arm64/kvm/hyp/include/nvhe/pkvm.h        |  16 +
>  arch/arm64/kvm/hyp/nvhe/hyp-main.c            | 201 ++++++++++-
>  arch/arm64/kvm/hyp/nvhe/mem_protect.c         | 320 ++++++++++++++++--
>  arch/arm64/kvm/hyp/nvhe/page_alloc.c          |  14 +-
>  arch/arm64/kvm/hyp/nvhe/pkvm.c                |  68 ++++
>  arch/arm64/kvm/hyp/nvhe/setup.c               |   7 +-
>  arch/arm64/kvm/hyp/pgtable.c                  |  13 +-
>  arch/arm64/kvm/mmu.c                          | 113 +++++--
>  arch/arm64/kvm/pkvm.c                         | 198 +++++++++++
>  arch/arm64/kvm/vgic/vgic-v3.c                 |   6 +-
>  19 files changed, 1010 insertions(+), 145 deletions(-)
>
> --
> 2.47.1.613.gc27f4b7a9f-goog
>

Re: [PATCH v3 18/18] KVM: arm64: Plumb the pKVM MMU in KVM

[Fuad Tabba]

On Mon, 16 Dec 2024 at 17:58, Quentin Perret <qperret@google.com> wrote:
>
> Introduce the KVM_PGT_S2() helper macro to allow switching from the
> traditional pgtable code to the pKVM version easily in mmu.c. The cost
> of this 'indirection' is expected to be very minimal due to
> is_protected_kvm_enabled() being backed by a static key.
>
> With this, everything is in place to allow the delegation of
> non-protected guest stage-2 page-tables to pKVM, so let's stop using the
> host's kvm_s2_mmu from EL2 and enjoy the ride.
>
> Signed-off-by: Quentin Perret <qperret@google.com>

Reviewed-by: Fuad Tabba <tabba@google.com>

Cheers,
/fuad

> ---
>  arch/arm64/include/asm/kvm_mmu.h   |  16 +++++
>  arch/arm64/kvm/arm.c               |   9 ++-
>  arch/arm64/kvm/hyp/nvhe/hyp-main.c |   2 -
>  arch/arm64/kvm/mmu.c               | 107 +++++++++++++++++++++--------
>  4 files changed, 101 insertions(+), 33 deletions(-)
>
> diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
> index 66d93e320ec8..d116ab4230e8 100644
> --- a/arch/arm64/include/asm/kvm_mmu.h
> +++ b/arch/arm64/include/asm/kvm_mmu.h
> @@ -353,6 +353,22 @@ static inline bool kvm_is_nested_s2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu)
>         return &kvm->arch.mmu != mmu;
>  }
>
> +static inline void kvm_fault_lock(struct kvm *kvm)
> +{
> +       if (is_protected_kvm_enabled())
> +               write_lock(&kvm->mmu_lock);
> +       else
> +               read_lock(&kvm->mmu_lock);
> +}
> +
> +static inline void kvm_fault_unlock(struct kvm *kvm)
> +{
> +       if (is_protected_kvm_enabled())
> +               write_unlock(&kvm->mmu_lock);
> +       else
> +               read_unlock(&kvm->mmu_lock);
> +}
> +
>  #ifdef CONFIG_PTDUMP_STAGE2_DEBUGFS
>  void kvm_s2_ptdump_create_debugfs(struct kvm *kvm);
>  #else
> diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
> index 55cc62b2f469..9bcbc7b8ed38 100644
> --- a/arch/arm64/kvm/arm.c
> +++ b/arch/arm64/kvm/arm.c
> @@ -502,7 +502,10 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
>
>  void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
>  {
> -       kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
> +       if (!is_protected_kvm_enabled())
> +               kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
> +       else
> +               free_hyp_memcache(&vcpu->arch.pkvm_memcache);
>         kvm_timer_vcpu_terminate(vcpu);
>         kvm_pmu_vcpu_destroy(vcpu);
>         kvm_vgic_vcpu_destroy(vcpu);
> @@ -574,6 +577,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
>         struct kvm_s2_mmu *mmu;
>         int *last_ran;
>
> +       if (is_protected_kvm_enabled())
> +               goto nommu;
> +
>         if (vcpu_has_nv(vcpu))
>                 kvm_vcpu_load_hw_mmu(vcpu);
>
> @@ -594,6 +600,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
>                 *last_ran = vcpu->vcpu_idx;
>         }
>
> +nommu:
>         vcpu->cpu = cpu;
>
>         kvm_vgic_load(vcpu);
> diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> index 130f5f23bcb5..258d572eed62 100644
> --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> @@ -103,8 +103,6 @@ static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
>         /* Limit guest vector length to the maximum supported by the host.  */
>         hyp_vcpu->vcpu.arch.sve_max_vl  = min(host_vcpu->arch.sve_max_vl, kvm_host_sve_max_vl);
>
> -       hyp_vcpu->vcpu.arch.hw_mmu      = host_vcpu->arch.hw_mmu;
> -
>         hyp_vcpu->vcpu.arch.mdcr_el2    = host_vcpu->arch.mdcr_el2;
>         hyp_vcpu->vcpu.arch.hcr_el2 &= ~(HCR_TWI | HCR_TWE);
>         hyp_vcpu->vcpu.arch.hcr_el2 |= READ_ONCE(host_vcpu->arch.hcr_el2) &
> diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
> index 641e4fec1659..7c2995cb4577 100644
> --- a/arch/arm64/kvm/mmu.c
> +++ b/arch/arm64/kvm/mmu.c
> @@ -15,6 +15,7 @@
>  #include <asm/kvm_arm.h>
>  #include <asm/kvm_mmu.h>
>  #include <asm/kvm_pgtable.h>
> +#include <asm/kvm_pkvm.h>
>  #include <asm/kvm_ras.h>
>  #include <asm/kvm_asm.h>
>  #include <asm/kvm_emulate.h>
> @@ -31,6 +32,14 @@ static phys_addr_t __ro_after_init hyp_idmap_vector;
>
>  static unsigned long __ro_after_init io_map_base;
>
> +#define KVM_PGT_S2(fn, ...)                                                            \
> +       ({                                                                              \
> +               typeof(kvm_pgtable_stage2_ ## fn) *__fn = kvm_pgtable_stage2_ ## fn;    \
> +               if (is_protected_kvm_enabled())                                         \
> +                       __fn = pkvm_pgtable_ ## fn;                                     \
> +               __fn(__VA_ARGS__);                                                      \
> +       })
> +
>  static phys_addr_t __stage2_range_addr_end(phys_addr_t addr, phys_addr_t end,
>                                            phys_addr_t size)
>  {
> @@ -147,7 +156,7 @@ static int kvm_mmu_split_huge_pages(struct kvm *kvm, phys_addr_t addr,
>                         return -EINVAL;
>
>                 next = __stage2_range_addr_end(addr, end, chunk_size);
> -               ret = kvm_pgtable_stage2_split(pgt, addr, next - addr, cache);
> +               ret = KVM_PGT_S2(split, pgt, addr, next - addr, cache);
>                 if (ret)
>                         break;
>         } while (addr = next, addr != end);
> @@ -168,15 +177,23 @@ static bool memslot_is_logging(struct kvm_memory_slot *memslot)
>   */
>  int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
>  {
> -       kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu);
> +       if (is_protected_kvm_enabled())
> +               kvm_call_hyp_nvhe(__pkvm_tlb_flush_vmid, kvm->arch.pkvm.handle);
> +       else
> +               kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu);
>         return 0;
>  }
>
>  int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm,
>                                       gfn_t gfn, u64 nr_pages)
>  {
> -       kvm_tlb_flush_vmid_range(&kvm->arch.mmu,
> -                               gfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT);
> +       u64 size = nr_pages << PAGE_SHIFT;
> +       u64 addr = gfn << PAGE_SHIFT;
> +
> +       if (is_protected_kvm_enabled())
> +               kvm_call_hyp_nvhe(__pkvm_tlb_flush_vmid, kvm->arch.pkvm.handle);
> +       else
> +               kvm_tlb_flush_vmid_range(&kvm->arch.mmu, addr, size);
>         return 0;
>  }
>
> @@ -225,7 +242,7 @@ static void stage2_free_unlinked_table_rcu_cb(struct rcu_head *head)
>         void *pgtable = page_to_virt(page);
>         s8 level = page_private(page);
>
> -       kvm_pgtable_stage2_free_unlinked(&kvm_s2_mm_ops, pgtable, level);
> +       KVM_PGT_S2(free_unlinked, &kvm_s2_mm_ops, pgtable, level);
>  }
>
>  static void stage2_free_unlinked_table(void *addr, s8 level)
> @@ -280,6 +297,11 @@ static void invalidate_icache_guest_page(void *va, size_t size)
>         __invalidate_icache_guest_page(va, size);
>  }
>
> +static int kvm_s2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
> +{
> +       return KVM_PGT_S2(unmap, pgt, addr, size);
> +}
> +
>  /*
>   * Unmapping vs dcache management:
>   *
> @@ -324,8 +346,7 @@ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64
>
>         lockdep_assert_held_write(&kvm->mmu_lock);
>         WARN_ON(size & ~PAGE_MASK);
> -       WARN_ON(stage2_apply_range(mmu, start, end, kvm_pgtable_stage2_unmap,
> -                                  may_block));
> +       WARN_ON(stage2_apply_range(mmu, start, end, kvm_s2_unmap, may_block));
>  }
>
>  void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
> @@ -334,9 +355,14 @@ void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
>         __unmap_stage2_range(mmu, start, size, may_block);
>  }
>
> +static int kvm_s2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size)
> +{
> +       return KVM_PGT_S2(flush, pgt, addr, size);
> +}
> +
>  void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
>  {
> -       stage2_apply_range_resched(mmu, addr, end, kvm_pgtable_stage2_flush);
> +       stage2_apply_range_resched(mmu, addr, end, kvm_s2_flush);
>  }
>
>  static void stage2_flush_memslot(struct kvm *kvm,
> @@ -942,10 +968,14 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
>                 return -ENOMEM;
>
>         mmu->arch = &kvm->arch;
> -       err = kvm_pgtable_stage2_init(pgt, mmu, &kvm_s2_mm_ops);
> +       err = KVM_PGT_S2(init, pgt, mmu, &kvm_s2_mm_ops);
>         if (err)
>                 goto out_free_pgtable;
>
> +       mmu->pgt = pgt;
> +       if (is_protected_kvm_enabled())
> +               return 0;
> +
>         mmu->last_vcpu_ran = alloc_percpu(typeof(*mmu->last_vcpu_ran));
>         if (!mmu->last_vcpu_ran) {
>                 err = -ENOMEM;
> @@ -959,7 +989,6 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
>         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);
>
>         if (kvm_is_nested_s2_mmu(kvm, mmu))
> @@ -968,7 +997,7 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
>         return 0;
>
>  out_destroy_pgtable:
> -       kvm_pgtable_stage2_destroy(pgt);
> +       KVM_PGT_S2(destroy, pgt);
>  out_free_pgtable:
>         kfree(pgt);
>         return err;
> @@ -1065,7 +1094,7 @@ void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu)
>         write_unlock(&kvm->mmu_lock);
>
>         if (pgt) {
> -               kvm_pgtable_stage2_destroy(pgt);
> +               KVM_PGT_S2(destroy, pgt);
>                 kfree(pgt);
>         }
>  }
> @@ -1082,9 +1111,11 @@ static void *hyp_mc_alloc_fn(void *unused)
>
>  void free_hyp_memcache(struct kvm_hyp_memcache *mc)
>  {
> -       if (is_protected_kvm_enabled())
> -               __free_hyp_memcache(mc, hyp_mc_free_fn,
> -                                   kvm_host_va, NULL);
> +       if (!is_protected_kvm_enabled())
> +               return;
> +
> +       kfree(mc->mapping);
> +       __free_hyp_memcache(mc, hyp_mc_free_fn, kvm_host_va, NULL);
>  }
>
>  int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages)
> @@ -1092,6 +1123,12 @@ int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages)
>         if (!is_protected_kvm_enabled())
>                 return 0;
>
> +       if (!mc->mapping) {
> +               mc->mapping = kzalloc(sizeof(struct pkvm_mapping), GFP_KERNEL_ACCOUNT);
> +               if (!mc->mapping)
> +                       return -ENOMEM;
> +       }
> +
>         return __topup_hyp_memcache(mc, min_pages, hyp_mc_alloc_fn,
>                                     kvm_host_pa, NULL);
>  }
> @@ -1130,8 +1167,7 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
>                         break;
>
>                 write_lock(&kvm->mmu_lock);
> -               ret = kvm_pgtable_stage2_map(pgt, addr, PAGE_SIZE, pa, prot,
> -                                            &cache, 0);
> +               ret = KVM_PGT_S2(map, pgt, addr, PAGE_SIZE, pa, prot, &cache, 0);
>                 write_unlock(&kvm->mmu_lock);
>                 if (ret)
>                         break;
> @@ -1143,6 +1179,10 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
>         return ret;
>  }
>
> +static int kvm_s2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
> +{
> +       return KVM_PGT_S2(wrprotect, pgt, addr, size);
> +}
>  /**
>   * kvm_stage2_wp_range() - write protect stage2 memory region range
>   * @mmu:        The KVM stage-2 MMU pointer
> @@ -1151,7 +1191,7 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
>   */
>  void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
>  {
> -       stage2_apply_range_resched(mmu, addr, end, kvm_pgtable_stage2_wrprotect);
> +       stage2_apply_range_resched(mmu, addr, end, kvm_s2_wrprotect);
>  }
>
>  /**
> @@ -1442,9 +1482,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
>         unsigned long mmu_seq;
>         phys_addr_t ipa = fault_ipa;
>         struct kvm *kvm = vcpu->kvm;
> -       struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
>         struct vm_area_struct *vma;
>         short vma_shift;
> +       void *memcache;
>         gfn_t gfn;
>         kvm_pfn_t pfn;
>         bool logging_active = memslot_is_logging(memslot);
> @@ -1472,8 +1512,15 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
>          * and a write fault needs to collapse a block entry into a table.
>          */
>         if (!fault_is_perm || (logging_active && write_fault)) {
> -               ret = kvm_mmu_topup_memory_cache(memcache,
> -                                                kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu));
> +               int min_pages = kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu);
> +
> +               if (!is_protected_kvm_enabled()) {
> +                       memcache = &vcpu->arch.mmu_page_cache;
> +                       ret = kvm_mmu_topup_memory_cache(memcache, min_pages);
> +               } else {
> +                       memcache = &vcpu->arch.pkvm_memcache;
> +                       ret = topup_hyp_memcache(memcache, min_pages);
> +               }
>                 if (ret)
>                         return ret;
>         }
> @@ -1494,7 +1541,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
>          * logging_active is guaranteed to never be true for VM_PFNMAP
>          * memslots.
>          */
> -       if (logging_active) {
> +       if (logging_active || is_protected_kvm_enabled()) {
>                 force_pte = true;
>                 vma_shift = PAGE_SHIFT;
>         } else {
> @@ -1634,7 +1681,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
>                 prot |= kvm_encode_nested_level(nested);
>         }
>
> -       read_lock(&kvm->mmu_lock);
> +       kvm_fault_lock(kvm);
>         pgt = vcpu->arch.hw_mmu->pgt;
>         if (mmu_invalidate_retry(kvm, mmu_seq)) {
>                 ret = -EAGAIN;
> @@ -1696,16 +1743,16 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
>                  * PTE, which will be preserved.
>                  */
>                 prot &= ~KVM_NV_GUEST_MAP_SZ;
> -               ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot, flags);
> +               ret = KVM_PGT_S2(relax_perms, pgt, fault_ipa, prot, flags);
>         } else {
> -               ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
> +               ret = KVM_PGT_S2(map, pgt, fault_ipa, vma_pagesize,
>                                              __pfn_to_phys(pfn), prot,
>                                              memcache, flags);
>         }
>
>  out_unlock:
>         kvm_release_faultin_page(kvm, page, !!ret, writable);
> -       read_unlock(&kvm->mmu_lock);
> +       kvm_fault_unlock(kvm);
>
>         /* Mark the page dirty only if the fault is handled successfully */
>         if (writable && !ret)
> @@ -1724,7 +1771,7 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
>
>         read_lock(&vcpu->kvm->mmu_lock);
>         mmu = vcpu->arch.hw_mmu;
> -       kvm_pgtable_stage2_mkyoung(mmu->pgt, fault_ipa, flags);
> +       KVM_PGT_S2(mkyoung, mmu->pgt, fault_ipa, flags);
>         read_unlock(&vcpu->kvm->mmu_lock);
>  }
>
> @@ -1764,7 +1811,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
>                 }
>
>                 /* Falls between the IPA range and the PARange? */
> -               if (fault_ipa >= BIT_ULL(vcpu->arch.hw_mmu->pgt->ia_bits)) {
> +               if (fault_ipa >= BIT_ULL(VTCR_EL2_IPA(vcpu->arch.hw_mmu->vtcr))) {
>                         fault_ipa |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0);
>
>                         if (is_iabt)
> @@ -1930,7 +1977,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
>         if (!kvm->arch.mmu.pgt)
>                 return false;
>
> -       return kvm_pgtable_stage2_test_clear_young(kvm->arch.mmu.pgt,
> +       return KVM_PGT_S2(test_clear_young, kvm->arch.mmu.pgt,
>                                                    range->start << PAGE_SHIFT,
>                                                    size, true);
>         /*
> @@ -1946,7 +1993,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
>         if (!kvm->arch.mmu.pgt)
>                 return false;
>
> -       return kvm_pgtable_stage2_test_clear_young(kvm->arch.mmu.pgt,
> +       return KVM_PGT_S2(test_clear_young, kvm->arch.mmu.pgt,
>                                                    range->start << PAGE_SHIFT,
>                                                    size, false);
>  }
> --
> 2.47.1.613.gc27f4b7a9f-goog
>

Re: [PATCH v3 01/18] KVM: arm64: Change the layout of enum pkvm_page_state

[Marc Zyngier]

On Mon, 16 Dec 2024 17:57:46 +0000,
Quentin Perret <qperret@google.com> wrote:
> 
> The 'concrete' (a.k.a non-meta) page states are currently encoded using
> software bits in PTEs. For performance reasons, the abstract
> pkvm_page_state enum uses the same bits to encode these states as that
> makes conversions from and to PTEs easy.
> 
> In order to prepare the ground for moving the 'concrete' state storage
> to the hyp vmemmap, re-arrange the enum to use bits 0 and 1 for this
> purpose.
> 
> No functional changes intended.
> 
> Signed-off-by: Quentin Perret <qperret@google.com>
> ---
>  arch/arm64/kvm/hyp/include/nvhe/mem_protect.h | 16 +++++++++-------
>  1 file changed, 9 insertions(+), 7 deletions(-)
> 
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> index 0972faccc2af..8c30362af2b9 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> @@ -24,25 +24,27 @@
>   */
>  enum pkvm_page_state {
>  	PKVM_PAGE_OWNED			= 0ULL,
> -	PKVM_PAGE_SHARED_OWNED		= KVM_PGTABLE_PROT_SW0,
> -	PKVM_PAGE_SHARED_BORROWED	= KVM_PGTABLE_PROT_SW1,
> -	__PKVM_PAGE_RESERVED		= KVM_PGTABLE_PROT_SW0 |
> -					  KVM_PGTABLE_PROT_SW1,
> +	PKVM_PAGE_SHARED_OWNED		= BIT(0),
> +	PKVM_PAGE_SHARED_BORROWED	= BIT(1),
> +	__PKVM_PAGE_RESERVED		= BIT(0) | BIT(1),
>  
>  	/* Meta-states which aren't encoded directly in the PTE's SW bits */
> -	PKVM_NOPAGE,
> +	PKVM_NOPAGE			= BIT(2),
>  };
> +#define PKVM_PAGE_META_STATES_MASK	(~(BIT(0) | BIT(1)))

Shouldn't that be ~__PKVM_PAGE_RESERVED, given that you just defined it?

>  
>  #define PKVM_PAGE_STATE_PROT_MASK	(KVM_PGTABLE_PROT_SW0 | KVM_PGTABLE_PROT_SW1)
>  static inline enum kvm_pgtable_prot pkvm_mkstate(enum kvm_pgtable_prot prot,
>  						 enum pkvm_page_state state)
>  {
> -	return (prot & ~PKVM_PAGE_STATE_PROT_MASK) | state;
> +	prot &= ~PKVM_PAGE_STATE_PROT_MASK;
> +	prot |= FIELD_PREP(PKVM_PAGE_STATE_PROT_MASK, state);
> +	return prot;
>  }
>  
>  static inline enum pkvm_page_state pkvm_getstate(enum kvm_pgtable_prot prot)
>  {
> -	return prot & PKVM_PAGE_STATE_PROT_MASK;
> +	return FIELD_GET(PKVM_PAGE_STATE_PROT_MASK, prot);
>  }
>  
>  struct host_mmu {

Thanks,

	M.

-- 
Without deviation from the norm, progress is not possible.

Re: [PATCH v3 03/18] KVM: arm64: Make hyp_page::order a u8

[Marc Zyngier]

On Mon, 16 Dec 2024 17:57:48 +0000,
Quentin Perret <qperret@google.com> wrote:
> 
> We don't need 16 bits to store the hyp page order, and we'll need some
> bits to store page ownership data soon, so let's reduce the order
> member.
> 
> Signed-off-by: Quentin Perret <qperret@google.com>
> ---
>  arch/arm64/kvm/hyp/include/nvhe/gfp.h    |  6 +++---
>  arch/arm64/kvm/hyp/include/nvhe/memory.h |  5 +++--
>  arch/arm64/kvm/hyp/nvhe/page_alloc.c     | 14 +++++++-------
>  3 files changed, 13 insertions(+), 12 deletions(-)
> 
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/gfp.h b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
> index 97c527ef53c2..f1725bad6331 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/gfp.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
> @@ -7,7 +7,7 @@
>  #include <nvhe/memory.h>
>  #include <nvhe/spinlock.h>
>  
> -#define HYP_NO_ORDER	USHRT_MAX
> +#define HYP_NO_ORDER	0xff

nit: (u8)(~0)?

	M.

-- 
Without deviation from the norm, progress is not possible.

Re: [PATCH v3 04/18] KVM: arm64: Move host page ownership tracking to the hyp vmemmap

[Marc Zyngier]

On Mon, 16 Dec 2024 17:57:49 +0000,
Quentin Perret <qperret@google.com> wrote:
> 
> We currently store part of the page-tracking state in PTE software bits
> for the host, guests and the hypervisor. This is sub-optimal when e.g.
> sharing pages as this forces to break block mappings purely to support
> this software tracking. This causes an unnecessarily fragmented stage-2
> page-table for the host in particular when it shares pages with Secure,
> which can lead to measurable regressions. Moreover, having this state
> stored in the page-table forces us to do multiple costly walks on the
> page transition path, hence causing overhead.
> 
> In order to work around these problems, move the host-side page-tracking
> logic from SW bits in its stage-2 PTEs to the hypervisor's vmemmap.
> 
> Signed-off-by: Quentin Perret <qperret@google.com>
> ---
>  arch/arm64/kvm/hyp/include/nvhe/memory.h |   6 +-
>  arch/arm64/kvm/hyp/nvhe/mem_protect.c    | 100 ++++++++++++++++-------
>  arch/arm64/kvm/hyp/nvhe/setup.c          |   7 +-
>  3 files changed, 77 insertions(+), 36 deletions(-)
> 
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/memory.h b/arch/arm64/kvm/hyp/include/nvhe/memory.h
> index 45b8d1840aa4..8bd9a539f260 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/memory.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/memory.h
> @@ -8,7 +8,7 @@
>  #include <linux/types.h>
>  
>  /*
> - * SW bits 0-1 are reserved to track the memory ownership state of each page:
> + * Bits 0-1 are reserved to track the memory ownership state of each page:
>   *   00: The page is owned exclusively by the page-table owner.
>   *   01: The page is owned by the page-table owner, but is shared
>   *       with another entity.
> @@ -43,7 +43,9 @@ static inline enum pkvm_page_state pkvm_getstate(enum kvm_pgtable_prot prot)
>  struct hyp_page {
>  	u16 refcount;
>  	u8 order;
> -	u8 reserved;
> +
> +	/* Host (non-meta) state. Guarded by the host stage-2 lock. */
> +	enum pkvm_page_state host_state : 8;

An enum as a bitfield? Crazy! :)

You probably want an assert somewhere that ensures that hyp_page is a
32bit quantity, just to make sure (and avoid hard to track bugs).

Thanks,

	M.

-- 
Without deviation from the norm, progress is not possible.

Re: [PATCH v3 11/18] KVM: arm64: Introduce __pkvm_host_unshare_guest()

[Marc Zyngier]

On Mon, 16 Dec 2024 17:57:56 +0000,
Quentin Perret <qperret@google.com> wrote:
> 
> In preparation for letting the host unmap pages from non-protected
> guests, introduce a new hypercall implementing the host-unshare-guest
> transition.
> 
> Signed-off-by: Quentin Perret <qperret@google.com>
> ---
>  arch/arm64/include/asm/kvm_asm.h              |  1 +
>  arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |  1 +
>  arch/arm64/kvm/hyp/include/nvhe/pkvm.h        |  6 ++
>  arch/arm64/kvm/hyp/nvhe/hyp-main.c            | 21 ++++++
>  arch/arm64/kvm/hyp/nvhe/mem_protect.c         | 67 +++++++++++++++++++
>  arch/arm64/kvm/hyp/nvhe/pkvm.c                | 12 ++++
>  6 files changed, 108 insertions(+)
> 
> diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
> index 449337f5b2a3..0b6c4d325134 100644
> --- a/arch/arm64/include/asm/kvm_asm.h
> +++ b/arch/arm64/include/asm/kvm_asm.h
> @@ -66,6 +66,7 @@ enum __kvm_host_smccc_func {
>  	__KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp,
>  	__KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_hyp,
>  	__KVM_HOST_SMCCC_FUNC___pkvm_host_share_guest,
> +	__KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_guest,
>  	__KVM_HOST_SMCCC_FUNC___kvm_adjust_pc,
>  	__KVM_HOST_SMCCC_FUNC___kvm_vcpu_run,
>  	__KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context,
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> index a7976e50f556..e528a42ed60e 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> @@ -40,6 +40,7 @@ int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages);
>  int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages);
>  int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages);
>  int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot);
> +int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm);
>  
>  bool addr_is_memory(phys_addr_t phys);
>  int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot);
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
> index be52c5b15e21..0cc2a429f1fb 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
> @@ -64,6 +64,11 @@ static inline bool pkvm_hyp_vcpu_is_protected(struct pkvm_hyp_vcpu *hyp_vcpu)
>  	return vcpu_is_protected(&hyp_vcpu->vcpu);
>  }
>  
> +static inline bool pkvm_hyp_vm_is_protected(struct pkvm_hyp_vm *hyp_vm)
> +{
> +	return kvm_vm_is_protected(&hyp_vm->kvm);
> +}
> +
>  void pkvm_hyp_vm_table_init(void *tbl);
>  
>  int __pkvm_init_vm(struct kvm *host_kvm, unsigned long vm_hva,
> @@ -78,6 +83,7 @@ void pkvm_put_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu);
>  struct pkvm_hyp_vcpu *pkvm_get_loaded_hyp_vcpu(void);
>  
>  struct pkvm_hyp_vm *get_pkvm_hyp_vm(pkvm_handle_t handle);
> +struct pkvm_hyp_vm *get_np_pkvm_hyp_vm(pkvm_handle_t handle);
>  void put_pkvm_hyp_vm(struct pkvm_hyp_vm *hyp_vm);
>  
>  #endif /* __ARM64_KVM_NVHE_PKVM_H__ */
> diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> index d659462fbf5d..3c3a27c985a2 100644
> --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> @@ -244,6 +244,26 @@ static void handle___pkvm_host_share_guest(struct kvm_cpu_context *host_ctxt)
>  	cpu_reg(host_ctxt, 1) =  ret;
>  }
>  
> +static void handle___pkvm_host_unshare_guest(struct kvm_cpu_context *host_ctxt)
> +{
> +	DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);
> +	DECLARE_REG(u64, gfn, host_ctxt, 2);
> +	struct pkvm_hyp_vm *hyp_vm;
> +	int ret = -EINVAL;
> +
> +	if (!is_protected_kvm_enabled())
> +		goto out;
> +
> +	hyp_vm = get_np_pkvm_hyp_vm(handle);
> +	if (!hyp_vm)
> +		goto out;
> +
> +	ret = __pkvm_host_unshare_guest(gfn, hyp_vm);
> +	put_pkvm_hyp_vm(hyp_vm);
> +out:
> +	cpu_reg(host_ctxt, 1) =  ret;
> +}
> +
>  static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt)
>  {
>  	DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1);
> @@ -454,6 +474,7 @@ static const hcall_t host_hcall[] = {
>  	HANDLE_FUNC(__pkvm_host_share_hyp),
>  	HANDLE_FUNC(__pkvm_host_unshare_hyp),
>  	HANDLE_FUNC(__pkvm_host_share_guest),
> +	HANDLE_FUNC(__pkvm_host_unshare_guest),
>  	HANDLE_FUNC(__kvm_adjust_pc),
>  	HANDLE_FUNC(__kvm_vcpu_run),
>  	HANDLE_FUNC(__kvm_flush_vm_context),
> diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> index fb9592e721cf..30243b7922f1 100644
> --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> @@ -1421,3 +1421,70 @@ int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu,
>  
>  	return ret;
>  }
> +
> +static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ipa)
> +{
> +	enum pkvm_page_state state;
> +	struct hyp_page *page;
> +	kvm_pte_t pte;
> +	u64 phys;
> +	s8 level;
> +	int ret;
> +
> +	ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level);
> +	if (ret)
> +		return ret;
> +	if (level != KVM_PGTABLE_LAST_LEVEL)

So there is still a very strong assumption that a guest is only
provided page mappings, and no blocks?

Thanks,

	M.

-- 
Without deviation from the norm, progress is not possible.

Re: [PATCH v3 00/18] KVM: arm64: Non-protected guest stage-2 support for pKVM

[Quentin Perret]

On Tuesday 17 Dec 2024 at 09:25:52 (+0000), Fuad Tabba wrote:
> On Mon, 16 Dec 2024 at 17:58, Quentin Perret <qperret@google.com> wrote:
> >
> > Hi all,
> >
> > This is the v3 of the series adding support for non-protected guests
> > stage-2 to pKVM. Please refer to v1 for all the context:
> 
> For the series:
> 
> Tested-by: Fuad Tabba <tabba@google.com>

Thank you!
Quentin

Re: [PATCH v3 01/18] KVM: arm64: Change the layout of enum pkvm_page_state

[Quentin Perret]

On Tuesday 17 Dec 2024 at 10:52:08 (+0000), Marc Zyngier wrote:
> On Mon, 16 Dec 2024 17:57:46 +0000,
> Quentin Perret <qperret@google.com> wrote:
> > 
> > The 'concrete' (a.k.a non-meta) page states are currently encoded using
> > software bits in PTEs. For performance reasons, the abstract
> > pkvm_page_state enum uses the same bits to encode these states as that
> > makes conversions from and to PTEs easy.
> > 
> > In order to prepare the ground for moving the 'concrete' state storage
> > to the hyp vmemmap, re-arrange the enum to use bits 0 and 1 for this
> > purpose.
> > 
> > No functional changes intended.
> > 
> > Signed-off-by: Quentin Perret <qperret@google.com>
> > ---
> >  arch/arm64/kvm/hyp/include/nvhe/mem_protect.h | 16 +++++++++-------
> >  1 file changed, 9 insertions(+), 7 deletions(-)
> > 
> > diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> > index 0972faccc2af..8c30362af2b9 100644
> > --- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> > +++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> > @@ -24,25 +24,27 @@
> >   */
> >  enum pkvm_page_state {
> >  	PKVM_PAGE_OWNED			= 0ULL,
> > -	PKVM_PAGE_SHARED_OWNED		= KVM_PGTABLE_PROT_SW0,
> > -	PKVM_PAGE_SHARED_BORROWED	= KVM_PGTABLE_PROT_SW1,
> > -	__PKVM_PAGE_RESERVED		= KVM_PGTABLE_PROT_SW0 |
> > -					  KVM_PGTABLE_PROT_SW1,
> > +	PKVM_PAGE_SHARED_OWNED		= BIT(0),
> > +	PKVM_PAGE_SHARED_BORROWED	= BIT(1),
> > +	__PKVM_PAGE_RESERVED		= BIT(0) | BIT(1),
> >  
> >  	/* Meta-states which aren't encoded directly in the PTE's SW bits */
> > -	PKVM_NOPAGE,
> > +	PKVM_NOPAGE			= BIT(2),
> >  };
> > +#define PKVM_PAGE_META_STATES_MASK	(~(BIT(0) | BIT(1)))
> 
> Shouldn't that be ~__PKVM_PAGE_RESERVED, given that you just defined it?

Sure thing, I followed the same pattern as PKVM_PAGE_STATE_PROT_MASK
which was explicit in which bits it sets, but very happy to change.

> >  
> >  #define PKVM_PAGE_STATE_PROT_MASK	(KVM_PGTABLE_PROT_SW0 | KVM_PGTABLE_PROT_SW1)
> >  static inline enum kvm_pgtable_prot pkvm_mkstate(enum kvm_pgtable_prot prot,
> >  						 enum pkvm_page_state state)
> >  {
> > -	return (prot & ~PKVM_PAGE_STATE_PROT_MASK) | state;
> > +	prot &= ~PKVM_PAGE_STATE_PROT_MASK;
> > +	prot |= FIELD_PREP(PKVM_PAGE_STATE_PROT_MASK, state);
> > +	return prot;
> >  }
> >  
> >  static inline enum pkvm_page_state pkvm_getstate(enum kvm_pgtable_prot prot)
> >  {
> > -	return prot & PKVM_PAGE_STATE_PROT_MASK;
> > +	return FIELD_GET(PKVM_PAGE_STATE_PROT_MASK, prot);
> >  }
> >  
> >  struct host_mmu {
> 
> Thanks,
> 
> 	M.
> 
> -- 
> Without deviation from the norm, progress is not possible.

Re: [PATCH v3 03/18] KVM: arm64: Make hyp_page::order a u8

[Quentin Perret]

On Tuesday 17 Dec 2024 at 10:55:58 (+0000), Marc Zyngier wrote:
> On Mon, 16 Dec 2024 17:57:48 +0000,
> Quentin Perret <qperret@google.com> wrote:
> > 
> > We don't need 16 bits to store the hyp page order, and we'll need some
> > bits to store page ownership data soon, so let's reduce the order
> > member.
> > 
> > Signed-off-by: Quentin Perret <qperret@google.com>
> > ---
> >  arch/arm64/kvm/hyp/include/nvhe/gfp.h    |  6 +++---
> >  arch/arm64/kvm/hyp/include/nvhe/memory.h |  5 +++--
> >  arch/arm64/kvm/hyp/nvhe/page_alloc.c     | 14 +++++++-------
> >  3 files changed, 13 insertions(+), 12 deletions(-)
> > 
> > diff --git a/arch/arm64/kvm/hyp/include/nvhe/gfp.h b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
> > index 97c527ef53c2..f1725bad6331 100644
> > --- a/arch/arm64/kvm/hyp/include/nvhe/gfp.h
> > +++ b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
> > @@ -7,7 +7,7 @@
> >  #include <nvhe/memory.h>
> >  #include <nvhe/spinlock.h>
> >  
> > -#define HYP_NO_ORDER	USHRT_MAX
> > +#define HYP_NO_ORDER	0xff
> 
> nit: (u8)(~0)?

SGTM.

Thanks,
Quentin

Re: [PATCH v3 04/18] KVM: arm64: Move host page ownership tracking to the hyp vmemmap

[Quentin Perret]

On Tuesday 17 Dec 2024 at 11:03:08 (+0000), Marc Zyngier wrote:
> On Mon, 16 Dec 2024 17:57:49 +0000,
> Quentin Perret <qperret@google.com> wrote:
> > 
> > We currently store part of the page-tracking state in PTE software bits
> > for the host, guests and the hypervisor. This is sub-optimal when e.g.
> > sharing pages as this forces to break block mappings purely to support
> > this software tracking. This causes an unnecessarily fragmented stage-2
> > page-table for the host in particular when it shares pages with Secure,
> > which can lead to measurable regressions. Moreover, having this state
> > stored in the page-table forces us to do multiple costly walks on the
> > page transition path, hence causing overhead.
> > 
> > In order to work around these problems, move the host-side page-tracking
> > logic from SW bits in its stage-2 PTEs to the hypervisor's vmemmap.
> > 
> > Signed-off-by: Quentin Perret <qperret@google.com>
> > ---
> >  arch/arm64/kvm/hyp/include/nvhe/memory.h |   6 +-
> >  arch/arm64/kvm/hyp/nvhe/mem_protect.c    | 100 ++++++++++++++++-------
> >  arch/arm64/kvm/hyp/nvhe/setup.c          |   7 +-
> >  3 files changed, 77 insertions(+), 36 deletions(-)
> > 
> > diff --git a/arch/arm64/kvm/hyp/include/nvhe/memory.h b/arch/arm64/kvm/hyp/include/nvhe/memory.h
> > index 45b8d1840aa4..8bd9a539f260 100644
> > --- a/arch/arm64/kvm/hyp/include/nvhe/memory.h
> > +++ b/arch/arm64/kvm/hyp/include/nvhe/memory.h
> > @@ -8,7 +8,7 @@
> >  #include <linux/types.h>
> >  
> >  /*
> > - * SW bits 0-1 are reserved to track the memory ownership state of each page:
> > + * Bits 0-1 are reserved to track the memory ownership state of each page:
> >   *   00: The page is owned exclusively by the page-table owner.
> >   *   01: The page is owned by the page-table owner, but is shared
> >   *       with another entity.
> > @@ -43,7 +43,9 @@ static inline enum pkvm_page_state pkvm_getstate(enum kvm_pgtable_prot prot)
> >  struct hyp_page {
> >  	u16 refcount;
> >  	u8 order;
> > -	u8 reserved;
> > +
> > +	/* Host (non-meta) state. Guarded by the host stage-2 lock. */
> > +	enum pkvm_page_state host_state : 8;
> 
> An enum as a bitfield? Crazy! :)

Hehe, it works so why not :)

> You probably want an assert somewhere that ensures that hyp_page is a
> 32bit quantity, just to make sure (and avoid hard to track bugs).

Sounds like a good idea, I'll stick a BUILD_BUG_ON() somewhere.

Re: [PATCH v3 11/18] KVM: arm64: Introduce __pkvm_host_unshare_guest()

[Quentin Perret]

On Tuesday 17 Dec 2024 at 08:53:34 (+0000), Fuad Tabba wrote:
> nit: This parameter in this patch, and others, is sometimes hyp_vm, at
> others just vm. It would be nicer if it was always the same.

Argh, where specifically do you see inconsistencies? All changes to
mem_protect.c should use 'vm' consistently in this series now.

The code in hyp-main.c does use 'hyp_vm' consistently however, but
perhaps that is what you meant? I did that to follow the pattern of the
existing code that uses 'hyp_vcpu' in that file.

Thanks!
Quentin

Re: [PATCH v3 11/18] KVM: arm64: Introduce __pkvm_host_unshare_guest()

[Fuad Tabba]

On Tue, 17 Dec 2024 at 13:14, Quentin Perret <qperret@google.com> wrote:
>
> On Tuesday 17 Dec 2024 at 08:53:34 (+0000), Fuad Tabba wrote:
> > nit: This parameter in this patch, and others, is sometimes hyp_vm, at
> > others just vm. It would be nicer if it was always the same.
>
> Argh, where specifically do you see inconsistencies? All changes to
> mem_protect.c should use 'vm' consistently in this series now.
>
> The code in hyp-main.c does use 'hyp_vm' consistently however, but
> perhaps that is what you meant? I did that to follow the pattern of the
> existing code that uses 'hyp_vcpu' in that file.

You're right, my bad. I was looking at the code in the patch, not in
the files. Sorry for the noise.
/fuad

> Thanks!
> Quentin

Re: [PATCH v3 11/18] KVM: arm64: Introduce __pkvm_host_unshare_guest()

[Quentin Perret]

On Tuesday 17 Dec 2024 at 11:29:03 (+0000), Marc Zyngier wrote:
> > +static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ipa)
> > +{
> > +	enum pkvm_page_state state;
> > +	struct hyp_page *page;
> > +	kvm_pte_t pte;
> > +	u64 phys;
> > +	s8 level;
> > +	int ret;
> > +
> > +	ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level);
> > +	if (ret)
> > +		return ret;
> > +	if (level != KVM_PGTABLE_LAST_LEVEL)
> 
> So there is still a very strong assumption that a guest is only
> provided page mappings, and no blocks?

Yep, very much so. It's one of the main limitations of the series as-is
(with the absence of support for mapping anything else than memory in
guests). Those limitations were mentioned in the cover letter of v1, but
I should have kept that mention in later versions, sorry!

The last patch of the series has a tweak to user_mem_abort() to force
mappings to PTE level which is trivial to do as we already need to do
similar things for dirty logging. And __pkvm_host_share_guest() doesn't
take a 'size' parameter in its current form, it assumes it is being
passed a single pfn. So all in all this works well, and simplifies the
series a lot.

Huge-page support should come as a natural extension to this series, but
I was hoping it could be done separately as that should have no
*functional* impact observable from userspace. I'm slightly more
concerned about the lack of support for mapping MMIO, but that too is
going to be some work, and I guess you should just turn pKVM off if
you want that for now...

Happy to address either or both of these limitations as part of this
series if we think they're strictly required to land this stuff
upstream, this is obviously up for debate. But that's going to be quite
a few patches on top :-)

Thanks,
Quentin

Re: [PATCH v3 18/18] KVM: arm64: Plumb the pKVM MMU in KVM

[Marc Zyngier]

On Mon, 16 Dec 2024 17:58:03 +0000,
Quentin Perret <qperret@google.com> wrote:
> 
> Introduce the KVM_PGT_S2() helper macro to allow switching from the
> traditional pgtable code to the pKVM version easily in mmu.c. The cost
> of this 'indirection' is expected to be very minimal due to
> is_protected_kvm_enabled() being backed by a static key.
> 
> With this, everything is in place to allow the delegation of
> non-protected guest stage-2 page-tables to pKVM, so let's stop using the
> host's kvm_s2_mmu from EL2 and enjoy the ride.
> 
> Signed-off-by: Quentin Perret <qperret@google.com>
> ---
>  arch/arm64/include/asm/kvm_mmu.h   |  16 +++++
>  arch/arm64/kvm/arm.c               |   9 ++-
>  arch/arm64/kvm/hyp/nvhe/hyp-main.c |   2 -
>  arch/arm64/kvm/mmu.c               | 107 +++++++++++++++++++++--------
>  4 files changed, 101 insertions(+), 33 deletions(-)
> 
> diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
> index 66d93e320ec8..d116ab4230e8 100644
> --- a/arch/arm64/include/asm/kvm_mmu.h
> +++ b/arch/arm64/include/asm/kvm_mmu.h
> @@ -353,6 +353,22 @@ static inline bool kvm_is_nested_s2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu)
>  	return &kvm->arch.mmu != mmu;
>  }
>  
> +static inline void kvm_fault_lock(struct kvm *kvm)
> +{
> +	if (is_protected_kvm_enabled())
> +		write_lock(&kvm->mmu_lock);
> +	else
> +		read_lock(&kvm->mmu_lock);
> +}
> +
> +static inline void kvm_fault_unlock(struct kvm *kvm)
> +{
> +	if (is_protected_kvm_enabled())
> +		write_unlock(&kvm->mmu_lock);
> +	else
> +		read_unlock(&kvm->mmu_lock);
> +}
> +
>  #ifdef CONFIG_PTDUMP_STAGE2_DEBUGFS
>  void kvm_s2_ptdump_create_debugfs(struct kvm *kvm);
>  #else
> diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
> index 55cc62b2f469..9bcbc7b8ed38 100644
> --- a/arch/arm64/kvm/arm.c
> +++ b/arch/arm64/kvm/arm.c
> @@ -502,7 +502,10 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
>  
>  void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
>  {
> -	kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
> +	if (!is_protected_kvm_enabled())
> +		kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
> +	else
> +		free_hyp_memcache(&vcpu->arch.pkvm_memcache);
>  	kvm_timer_vcpu_terminate(vcpu);
>  	kvm_pmu_vcpu_destroy(vcpu);
>  	kvm_vgic_vcpu_destroy(vcpu);
> @@ -574,6 +577,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
>  	struct kvm_s2_mmu *mmu;
>  	int *last_ran;
>  
> +	if (is_protected_kvm_enabled())
> +		goto nommu;
> +
>  	if (vcpu_has_nv(vcpu))
>  		kvm_vcpu_load_hw_mmu(vcpu);
>  
> @@ -594,6 +600,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
>  		*last_ran = vcpu->vcpu_idx;
>  	}
>  
> +nommu:
>  	vcpu->cpu = cpu;
>  
>  	kvm_vgic_load(vcpu);
> diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> index 130f5f23bcb5..258d572eed62 100644
> --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
> @@ -103,8 +103,6 @@ static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
>  	/* Limit guest vector length to the maximum supported by the host.  */
>  	hyp_vcpu->vcpu.arch.sve_max_vl	= min(host_vcpu->arch.sve_max_vl, kvm_host_sve_max_vl);
>  
> -	hyp_vcpu->vcpu.arch.hw_mmu	= host_vcpu->arch.hw_mmu;
> -
>  	hyp_vcpu->vcpu.arch.mdcr_el2	= host_vcpu->arch.mdcr_el2;
>  	hyp_vcpu->vcpu.arch.hcr_el2 &= ~(HCR_TWI | HCR_TWE);
>  	hyp_vcpu->vcpu.arch.hcr_el2 |= READ_ONCE(host_vcpu->arch.hcr_el2) &
> diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
> index 641e4fec1659..7c2995cb4577 100644
> --- a/arch/arm64/kvm/mmu.c
> +++ b/arch/arm64/kvm/mmu.c
> @@ -15,6 +15,7 @@
>  #include <asm/kvm_arm.h>
>  #include <asm/kvm_mmu.h>
>  #include <asm/kvm_pgtable.h>
> +#include <asm/kvm_pkvm.h>
>  #include <asm/kvm_ras.h>
>  #include <asm/kvm_asm.h>
>  #include <asm/kvm_emulate.h>
> @@ -31,6 +32,14 @@ static phys_addr_t __ro_after_init hyp_idmap_vector;
>  
>  static unsigned long __ro_after_init io_map_base;
>  
> +#define KVM_PGT_S2(fn, ...)								\
> +	({										\
> +		typeof(kvm_pgtable_stage2_ ## fn) *__fn = kvm_pgtable_stage2_ ## fn;	\
> +		if (is_protected_kvm_enabled())						\
> +			__fn = pkvm_pgtable_ ## fn;					\
> +		__fn(__VA_ARGS__);							\
> +	})
> +

My gripe with this is that it makes it much harder to follow what is
happening by using tags (ctags, etags, whatever). I ended up with the
hack below, which is super ugly, but preserves the tagging
functionality for non-pKVM.

I'll scratch my head to find something more elegant...

	M.

diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h
index 76a8b70176a6c..b9b9acb685d8f 100644
--- a/arch/arm64/include/asm/kvm_pkvm.h
+++ b/arch/arm64/include/asm/kvm_pkvm.h
@@ -143,21 +143,21 @@ struct pkvm_mapping {
 	u64 pfn;
 };
 
-int pkvm_pgtable_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, struct kvm_pgtable_mm_ops *mm_ops);
-void pkvm_pgtable_destroy(struct kvm_pgtable *pgt);
-int pkvm_pgtable_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
+int pkvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, struct kvm_pgtable_mm_ops *mm_ops);
+void pkvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
+int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
 			   u64 phys, enum kvm_pgtable_prot prot,
 			   void *mc, enum kvm_pgtable_walk_flags flags);
-int pkvm_pgtable_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size);
-int pkvm_pgtable_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size);
-int pkvm_pgtable_flush(struct kvm_pgtable *pgt, u64 addr, u64 size);
-bool pkvm_pgtable_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64 size, bool mkold);
-int pkvm_pgtable_relax_perms(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_prot prot,
+int pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size);
+int pkvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size);
+int pkvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size);
+bool pkvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64 size, bool mkold);
+int pkvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_prot prot,
 			     enum kvm_pgtable_walk_flags flags);
-void pkvm_pgtable_mkyoung(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_walk_flags flags);
-int pkvm_pgtable_split(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_mmu_memory_cache *mc);
-void pkvm_pgtable_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level);
-kvm_pte_t *pkvm_pgtable_create_unlinked(struct kvm_pgtable *pgt, u64 phys, s8 level,
+void pkvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_walk_flags flags);
+int pkvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_mmu_memory_cache *mc);
+void pkvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level);
+kvm_pte_t *pkvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt, u64 phys, s8 level,
 					enum kvm_pgtable_prot prot, void *mc, bool force_pte);
 
 #endif	/* __ARM64_KVM_PKVM_H__ */
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 7c2995cb45773..4b9153468a327 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -32,12 +32,13 @@ static phys_addr_t __ro_after_init hyp_idmap_vector;
 
 static unsigned long __ro_after_init io_map_base;
 
-#define KVM_PGT_S2(fn, ...)								\
-	({										\
-		typeof(kvm_pgtable_stage2_ ## fn) *__fn = kvm_pgtable_stage2_ ## fn;	\
-		if (is_protected_kvm_enabled())						\
-			__fn = pkvm_pgtable_ ## fn;					\
-		__fn(__VA_ARGS__);							\
+#define __S2(fn, ...)							\
+	({								\
+		typeof(fn) *__fn = fn;					\
+		/* upgrade the function name from kvm_* to pkvm_* */	\
+		if (is_protected_kvm_enabled())				\
+			__fn = p ## fn;					\
+		__fn(__VA_ARGS__);					\
 	})
 
 static phys_addr_t __stage2_range_addr_end(phys_addr_t addr, phys_addr_t end,
@@ -156,7 +157,7 @@ static int kvm_mmu_split_huge_pages(struct kvm *kvm, phys_addr_t addr,
 			return -EINVAL;
 
 		next = __stage2_range_addr_end(addr, end, chunk_size);
-		ret = KVM_PGT_S2(split, pgt, addr, next - addr, cache);
+		ret = __S2(kvm_pgtable_stage2_split, pgt, addr, next - addr, cache);
 		if (ret)
 			break;
 	} while (addr = next, addr != end);
@@ -242,7 +243,7 @@ static void stage2_free_unlinked_table_rcu_cb(struct rcu_head *head)
 	void *pgtable = page_to_virt(page);
 	s8 level = page_private(page);
 
-	KVM_PGT_S2(free_unlinked, &kvm_s2_mm_ops, pgtable, level);
+	__S2(kvm_pgtable_stage2_free_unlinked, &kvm_s2_mm_ops, pgtable, level);
 }
 
 static void stage2_free_unlinked_table(void *addr, s8 level)
@@ -299,7 +300,7 @@ static void invalidate_icache_guest_page(void *va, size_t size)
 
 static int kvm_s2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
 {
-	return KVM_PGT_S2(unmap, pgt, addr, size);
+	return __S2(kvm_pgtable_stage2_unmap, pgt, addr, size);
 }
 
 /*
@@ -357,7 +358,7 @@ void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
 
 static int kvm_s2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size)
 {
-	return KVM_PGT_S2(flush, pgt, addr, size);
+	return __S2(kvm_pgtable_stage2_flush, pgt, addr, size);
 }
 
 void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
@@ -968,7 +969,7 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
 		return -ENOMEM;
 
 	mmu->arch = &kvm->arch;
-	err = KVM_PGT_S2(init, pgt, mmu, &kvm_s2_mm_ops);
+	err = __S2(kvm_pgtable_stage2_init, pgt, mmu, &kvm_s2_mm_ops);
 	if (err)
 		goto out_free_pgtable;
 
@@ -997,7 +998,7 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
 	return 0;
 
 out_destroy_pgtable:
-	KVM_PGT_S2(destroy, pgt);
+	__S2(kvm_pgtable_stage2_destroy, pgt);
 out_free_pgtable:
 	kfree(pgt);
 	return err;
@@ -1094,7 +1095,7 @@ void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu)
 	write_unlock(&kvm->mmu_lock);
 
 	if (pgt) {
-		KVM_PGT_S2(destroy, pgt);
+		__S2(kvm_pgtable_stage2_destroy, pgt);
 		kfree(pgt);
 	}
 }
@@ -1167,7 +1168,7 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 			break;
 
 		write_lock(&kvm->mmu_lock);
-		ret = KVM_PGT_S2(map, pgt, addr, PAGE_SIZE, pa, prot, &cache, 0);
+		ret = __S2(kvm_pgtable_stage2_map, pgt, addr, PAGE_SIZE, pa, prot, &cache, 0);
 		write_unlock(&kvm->mmu_lock);
 		if (ret)
 			break;
@@ -1181,7 +1182,7 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 
 static int kvm_s2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
 {
-	return KVM_PGT_S2(wrprotect, pgt, addr, size);
+	return __S2(kvm_pgtable_stage2_wrprotect, pgt, addr, size);
 }
 /**
  * kvm_stage2_wp_range() - write protect stage2 memory region range
@@ -1743,9 +1744,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		 * PTE, which will be preserved.
 		 */
 		prot &= ~KVM_NV_GUEST_MAP_SZ;
-		ret = KVM_PGT_S2(relax_perms, pgt, fault_ipa, prot, flags);
+		ret = __S2(kvm_pgtable_stage2_relax_perms, pgt, fault_ipa, prot, flags);
 	} else {
-		ret = KVM_PGT_S2(map, pgt, fault_ipa, vma_pagesize,
+		ret = __S2(kvm_pgtable_stage2_map, pgt, fault_ipa, vma_pagesize,
 					     __pfn_to_phys(pfn), prot,
 					     memcache, flags);
 	}
@@ -1771,7 +1772,7 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 
 	read_lock(&vcpu->kvm->mmu_lock);
 	mmu = vcpu->arch.hw_mmu;
-	KVM_PGT_S2(mkyoung, mmu->pgt, fault_ipa, flags);
+	__S2(kvm_pgtable_stage2_mkyoung, mmu->pgt, fault_ipa, flags);
 	read_unlock(&vcpu->kvm->mmu_lock);
 }
 
@@ -1977,7 +1978,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	if (!kvm->arch.mmu.pgt)
 		return false;
 
-	return KVM_PGT_S2(test_clear_young, kvm->arch.mmu.pgt,
+	return __S2(kvm_pgtable_stage2_test_clear_young, kvm->arch.mmu.pgt,
 						   range->start << PAGE_SHIFT,
 						   size, true);
 	/*
@@ -1993,7 +1994,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	if (!kvm->arch.mmu.pgt)
 		return false;
 
-	return KVM_PGT_S2(test_clear_young, kvm->arch.mmu.pgt,
+	return __S2(kvm_pgtable_stage2_test_clear_young, kvm->arch.mmu.pgt,
 						   range->start << PAGE_SHIFT,
 						   size, false);
 }
diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
index 9de9159afa5a1..37d6494d0fd87 100644
--- a/arch/arm64/kvm/pkvm.c
+++ b/arch/arm64/kvm/pkvm.c
@@ -317,7 +317,7 @@ static struct rb_node *find_first_mapping_node(struct rb_root *root, u64 gfn)
 			break;										\
 		else
 
-int pkvm_pgtable_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, struct kvm_pgtable_mm_ops *mm_ops)
+int pkvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, struct kvm_pgtable_mm_ops *mm_ops)
 {
 	pgt->pkvm_mappings	= RB_ROOT;
 	pgt->mmu		= mmu;
@@ -325,7 +325,7 @@ int pkvm_pgtable_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, struct kv
 	return 0;
 }
 
-void pkvm_pgtable_destroy(struct kvm_pgtable *pgt)
+void pkvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
 {
 	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
 	pkvm_handle_t handle = kvm->arch.pkvm.handle;
@@ -345,7 +345,7 @@ void pkvm_pgtable_destroy(struct kvm_pgtable *pgt)
 	}
 }
 
-int pkvm_pgtable_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
+int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
 			   u64 phys, enum kvm_pgtable_prot prot,
 			   void *mc, enum kvm_pgtable_walk_flags flags)
 {
@@ -375,7 +375,7 @@ int pkvm_pgtable_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
 	return ret;
 }
 
-int pkvm_pgtable_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
+int pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
 {
 	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
 	pkvm_handle_t handle = kvm->arch.pkvm.handle;
@@ -394,7 +394,7 @@ int pkvm_pgtable_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
 	return ret;
 }
 
-int pkvm_pgtable_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
+int pkvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
 {
 	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
 	pkvm_handle_t handle = kvm->arch.pkvm.handle;
@@ -411,7 +411,7 @@ int pkvm_pgtable_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
 	return ret;
 }
 
-int pkvm_pgtable_flush(struct kvm_pgtable *pgt, u64 addr, u64 size)
+int pkvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size)
 {
 	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
 	struct pkvm_mapping *mapping;
@@ -423,7 +423,7 @@ int pkvm_pgtable_flush(struct kvm_pgtable *pgt, u64 addr, u64 size)
 	return 0;
 }
 
-bool pkvm_pgtable_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64 size, bool mkold)
+bool pkvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64 size, bool mkold)
 {
 	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
 	pkvm_handle_t handle = kvm->arch.pkvm.handle;
@@ -438,30 +438,30 @@ bool pkvm_pgtable_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64 size,
 	return young;
 }
 
-int pkvm_pgtable_relax_perms(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_prot prot,
+int pkvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_prot prot,
 			     enum kvm_pgtable_walk_flags flags)
 {
 	return kvm_call_hyp_nvhe(__pkvm_host_relax_perms_guest, addr >> PAGE_SHIFT, prot);
 }
 
-void pkvm_pgtable_mkyoung(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_walk_flags flags)
+void pkvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_walk_flags flags)
 {
 	WARN_ON(kvm_call_hyp_nvhe(__pkvm_host_mkyoung_guest, addr >> PAGE_SHIFT));
 }
 
-void pkvm_pgtable_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level)
+void pkvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level)
 {
 	WARN_ON_ONCE(1);
 }
 
-kvm_pte_t *pkvm_pgtable_create_unlinked(struct kvm_pgtable *pgt, u64 phys, s8 level,
+kvm_pte_t *pkvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt, u64 phys, s8 level,
 					enum kvm_pgtable_prot prot, void *mc, bool force_pte)
 {
 	WARN_ON_ONCE(1);
 	return NULL;
 }
 
-int pkvm_pgtable_split(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_mmu_memory_cache *mc)
+int pkvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_mmu_memory_cache *mc)
 {
 	WARN_ON_ONCE(1);
 	return -EINVAL;

-- 
Without deviation from the norm, progress is not possible.

Re: [PATCH v3 11/18] KVM: arm64: Introduce __pkvm_host_unshare_guest()

[Marc Zyngier]

On Tue, 17 Dec 2024 13:33:57 +0000,
Quentin Perret <qperret@google.com> wrote:
> 
> On Tuesday 17 Dec 2024 at 11:29:03 (+0000), Marc Zyngier wrote:
> > > +static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ipa)
> > > +{
> > > +	enum pkvm_page_state state;
> > > +	struct hyp_page *page;
> > > +	kvm_pte_t pte;
> > > +	u64 phys;
> > > +	s8 level;
> > > +	int ret;
> > > +
> > > +	ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level);
> > > +	if (ret)
> > > +		return ret;
> > > +	if (level != KVM_PGTABLE_LAST_LEVEL)
> > 
> > So there is still a very strong assumption that a guest is only
> > provided page mappings, and no blocks?
> 
> Yep, very much so. It's one of the main limitations of the series as-is
> (with the absence of support for mapping anything else than memory in
> guests). Those limitations were mentioned in the cover letter of v1, but
> I should have kept that mention in later versions, sorry!
> 
> The last patch of the series has a tweak to user_mem_abort() to force
> mappings to PTE level which is trivial to do as we already need to do
> similar things for dirty logging. And __pkvm_host_share_guest() doesn't
> take a 'size' parameter in its current form, it assumes it is being
> passed a single pfn. So all in all this works well, and simplifies the
> series a lot.
> 
> Huge-page support should come as a natural extension to this series, but
> I was hoping it could be done separately as that should have no
> *functional* impact observable from userspace. I'm slightly more
> concerned about the lack of support for mapping MMIO, but that too is
> going to be some work, and I guess you should just turn pKVM off if
> you want that for now...
> 
> Happy to address either or both of these limitations as part of this
> series if we think they're strictly required to land this stuff
> upstream, this is obviously up for debate. But that's going to be quite
> a few patches on top :-)

No, I just wanted to make sure I did have the correct interpretation
of what this does. 'd rather have something that works first, and then
add large mapping support. You can even sell it as a performance
improvement! :)

Thanks,

	M.

-- 
Without deviation from the norm, progress is not possible.

Re: [PATCH v3 18/18] KVM: arm64: Plumb the pKVM MMU in KVM

[Quentin Perret]

On Tuesday 17 Dec 2024 at 14:03:37 (+0000), Marc Zyngier wrote:
> My gripe with this is that it makes it much harder to follow what is
> happening by using tags (ctags, etags, whatever). I ended up with the
> hack below, which is super ugly, but preserves the tagging
> functionality for non-pKVM.

Ack.

> I'll scratch my head to find something more elegant...

I find your proposal pretty reasonable -- I had a few different ideas
but they were all really over-engineered, so I figured relying on a
naming convention was the simplest. And any divergence will be flagged
at compile time, so that shouldn't be too hard to maintain looking
forward.

The __S2 name isn't massively descriptive though. Maybe KVM_PGT_CALL()
or something? Thinking about it, this abstraction doesn't need to be
restricted to stage-2 stuff. We could most likely hide the
__pkvm_host_{un}share_hyp() logic behind a pkvm_pgtable_hyp_{un}map()
implementation in pkvm.c as well...

Re: [PATCH v3 18/18] KVM: arm64: Plumb the pKVM MMU in KVM

[Marc Zyngier]

On Tue, 17 Dec 2024 14:31:35 +0000,
Quentin Perret <qperret@google.com> wrote:
> 
> On Tuesday 17 Dec 2024 at 14:03:37 (+0000), Marc Zyngier wrote:
> > My gripe with this is that it makes it much harder to follow what is
> > happening by using tags (ctags, etags, whatever). I ended up with the
> > hack below, which is super ugly, but preserves the tagging
> > functionality for non-pKVM.
> 
> Ack.
> 
> > I'll scratch my head to find something more elegant...
> 
> I find your proposal pretty reasonable -- I had a few different ideas
> but they were all really over-engineered, so I figured relying on a
> naming convention was the simplest. And any divergence will be flagged
> at compile time, so that shouldn't be too hard to maintain looking
> forward.
> 
> The __S2 name isn't massively descriptive though. Maybe KVM_PGT_CALL()
> or something? Thinking about it, this abstraction doesn't need to be
> restricted to stage-2 stuff. We could most likely hide the
> __pkvm_host_{un}share_hyp() logic behind a pkvm_pgtable_hyp_{un}map()
> implementation in pkvm.c as well...

Oh, I'm happy with *any* name. I just changed it to make sure any
missing occurrence would blow up.

And yes, if we can make that more uniform, I'm all for that.

Thanks,

	M.

-- 
Without deviation from the norm, progress is not possible.

Re: [PATCH v3 18/18] KVM: arm64: Plumb the pKVM MMU in KVM

[Quentin Perret]

On Tuesday 17 Dec 2024 at 15:38:21 (+0000), Marc Zyngier wrote:
> On Tue, 17 Dec 2024 14:31:35 +0000,
> Quentin Perret <qperret@google.com> wrote:
> > 
> > On Tuesday 17 Dec 2024 at 14:03:37 (+0000), Marc Zyngier wrote:
> > > My gripe with this is that it makes it much harder to follow what is
> > > happening by using tags (ctags, etags, whatever). I ended up with the
> > > hack below, which is super ugly, but preserves the tagging
> > > functionality for non-pKVM.
> > 
> > Ack.
> > 
> > > I'll scratch my head to find something more elegant...
> > 
> > I find your proposal pretty reasonable -- I had a few different ideas
> > but they were all really over-engineered, so I figured relying on a
> > naming convention was the simplest. And any divergence will be flagged
> > at compile time, so that shouldn't be too hard to maintain looking
> > forward.
> > 
> > The __S2 name isn't massively descriptive though. Maybe KVM_PGT_CALL()
> > or something? Thinking about it, this abstraction doesn't need to be
> > restricted to stage-2 stuff. We could most likely hide the
> > __pkvm_host_{un}share_hyp() logic behind a pkvm_pgtable_hyp_{un}map()
> > implementation in pkvm.c as well...
> 
> Oh, I'm happy with *any* name. I just changed it to make sure any
> missing occurrence would blow up.
> 
> And yes, if we can make that more uniform, I'm all for that.

I had a go at porting the hyp stage-1 code to the same logic and
ended up with the diff below.

It's not completely obvious it is much better than the existing code
TBH. I ended up resorting to odd things like passing a NULL pgt to the
pkvm_pgtable_hyp_*() functions and such. All the mess comes from the
pKVM boot flow, where Linux originally creates the hyp stage-1
page-table, but then frees it after pKVM has initialized and switches to
using hypercalls.

None of this is needed for this series though, so I won't include that
in v4. I'll post it separately once that series lands, and then we can
decide if it's worth it, or if it should be done differently.

diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index d116ab4230e8..b35c909f4d0a 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -152,8 +152,7 @@ static __always_inline unsigned long __kern_hyp_va(unsigned long v)
 #include <asm/kvm_pgtable.h>
 #include <asm/stage2_pgtable.h>
 
-int kvm_share_hyp(void *from, void *to);
-void kvm_unshare_hyp(void *from, void *to);
+void remove_hyp_mappings(void *from, void *to);
 int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot);
 int __create_hyp_mappings(unsigned long start, unsigned long size,
 			  unsigned long phys, enum kvm_pgtable_prot prot);
diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h
index 65f988b6fe0d..db7851459ef3 100644
--- a/arch/arm64/include/asm/kvm_pkvm.h
+++ b/arch/arm64/include/asm/kvm_pkvm.h
@@ -143,6 +143,11 @@ struct pkvm_mapping {
 	u64 pfn;
 };
 
+int pkvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits, struct kvm_pgtable_mm_ops *mm_ops);
+void pkvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt);
+int pkvm_pgtable_hyp_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys,
+			 enum kvm_pgtable_prot prot);
+u64 pkvm_pgtable_hyp_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size);
 int pkvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
 			     struct kvm_pgtable_mm_ops *mm_ops);
 void pkvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 9bcbc7b8ed38..2dada891c199 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -183,7 +183,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	kvm_init_nested(kvm);
 
-	ret = kvm_share_hyp(kvm, kvm + 1);
+	ret = create_hyp_mappings(kvm, kvm + 1, PAGE_HYP);
 	if (ret)
 		return ret;
 
@@ -217,7 +217,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 err_free_cpumask:
 	free_cpumask_var(kvm->arch.supported_cpus);
 err_unshare_kvm:
-	kvm_unshare_hyp(kvm, kvm + 1);
+	remove_hyp_mappings(kvm, kvm + 1);
 	return ret;
 }
 
@@ -268,7 +268,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kfree(kvm->arch.sysreg_masks);
 	kvm_destroy_vcpus(kvm);
 
-	kvm_unshare_hyp(kvm, kvm + 1);
+	remove_hyp_mappings(kvm, kvm + 1);
 
 	kvm_arm_teardown_hypercalls(kvm);
 }
@@ -493,7 +493,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	if (err)
 		return err;
 
-	return kvm_share_hyp(vcpu, vcpu + 1);
+	return create_hyp_mappings(vcpu, vcpu + 1, PAGE_HYP);
 }
 
 void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index ea5484ce1f3b..49acdda3f1d0 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -33,7 +33,7 @@ int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu)
 		return 0;
 
 	/* Make sure the host task fpsimd state is visible to hyp: */
-	ret = kvm_share_hyp(fpsimd, fpsimd + 1);
+	ret = create_hyp_mappings(fpsimd, fpsimd + 1, PAGE_HYP);
 	if (ret)
 		return ret;
 
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 4e6cf4a1a6eb..53e584a5e8d7 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -407,44 +407,20 @@ void __init free_hyp_pgds(void)
 {
 	mutex_lock(&kvm_hyp_pgd_mutex);
 	if (hyp_pgtable) {
-		kvm_pgtable_hyp_destroy(hyp_pgtable);
+		KVM_PGT_CALL(kvm_pgtable_hyp_destroy, hyp_pgtable);
 		kfree(hyp_pgtable);
 		hyp_pgtable = NULL;
 	}
 	mutex_unlock(&kvm_hyp_pgd_mutex);
 }
 
-static bool kvm_host_owns_hyp_mappings(void)
-{
-	if (is_kernel_in_hyp_mode())
-		return false;
-
-	if (static_branch_likely(&kvm_protected_mode_initialized))
-		return false;
-
-	/*
-	 * This can happen at boot time when __create_hyp_mappings() is called
-	 * after the hyp protection has been enabled, but the static key has
-	 * not been flipped yet.
-	 */
-	if (!hyp_pgtable && is_protected_kvm_enabled())
-		return false;
-
-	WARN_ON(!hyp_pgtable);
-
-	return true;
-}
-
 int __create_hyp_mappings(unsigned long start, unsigned long size,
 			  unsigned long phys, enum kvm_pgtable_prot prot)
 {
 	int err;
 
-	if (WARN_ON(!kvm_host_owns_hyp_mappings()))
-		return -EINVAL;
-
 	mutex_lock(&kvm_hyp_pgd_mutex);
-	err = kvm_pgtable_hyp_map(hyp_pgtable, start, size, phys, prot);
+	err = KVM_PGT_CALL(kvm_pgtable_hyp_map, hyp_pgtable, start, size, phys, prot);
 	mutex_unlock(&kvm_hyp_pgd_mutex);
 
 	return err;
@@ -461,138 +437,18 @@ static phys_addr_t kvm_kaddr_to_phys(void *kaddr)
 	}
 }
 
-struct hyp_shared_pfn {
-	u64 pfn;
-	int count;
-	struct rb_node node;
-};
-
-static DEFINE_MUTEX(hyp_shared_pfns_lock);
-static struct rb_root hyp_shared_pfns = RB_ROOT;
-
-static struct hyp_shared_pfn *find_shared_pfn(u64 pfn, struct rb_node ***node,
-					      struct rb_node **parent)
-{
-	struct hyp_shared_pfn *this;
-
-	*node = &hyp_shared_pfns.rb_node;
-	*parent = NULL;
-	while (**node) {
-		this = container_of(**node, struct hyp_shared_pfn, node);
-		*parent = **node;
-		if (this->pfn < pfn)
-			*node = &((**node)->rb_left);
-		else if (this->pfn > pfn)
-			*node = &((**node)->rb_right);
-		else
-			return this;
-	}
-
-	return NULL;
-}
-
-static int share_pfn_hyp(u64 pfn)
-{
-	struct rb_node **node, *parent;
-	struct hyp_shared_pfn *this;
-	int ret = 0;
-
-	mutex_lock(&hyp_shared_pfns_lock);
-	this = find_shared_pfn(pfn, &node, &parent);
-	if (this) {
-		this->count++;
-		goto unlock;
-	}
-
-	this = kzalloc(sizeof(*this), GFP_KERNEL);
-	if (!this) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
-
-	this->pfn = pfn;
-	this->count = 1;
-	rb_link_node(&this->node, parent, node);
-	rb_insert_color(&this->node, &hyp_shared_pfns);
-	ret = kvm_call_hyp_nvhe(__pkvm_host_share_hyp, pfn, 1);
-unlock:
-	mutex_unlock(&hyp_shared_pfns_lock);
-
-	return ret;
-}
-
-static int unshare_pfn_hyp(u64 pfn)
-{
-	struct rb_node **node, *parent;
-	struct hyp_shared_pfn *this;
-	int ret = 0;
-
-	mutex_lock(&hyp_shared_pfns_lock);
-	this = find_shared_pfn(pfn, &node, &parent);
-	if (WARN_ON(!this)) {
-		ret = -ENOENT;
-		goto unlock;
-	}
-
-	this->count--;
-	if (this->count)
-		goto unlock;
-
-	rb_erase(&this->node, &hyp_shared_pfns);
-	kfree(this);
-	ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_hyp, pfn, 1);
-unlock:
-	mutex_unlock(&hyp_shared_pfns_lock);
-
-	return ret;
-}
-
-int kvm_share_hyp(void *from, void *to)
-{
-	phys_addr_t start, end, cur;
-	u64 pfn;
-	int ret;
-
-	if (is_kernel_in_hyp_mode())
-		return 0;
-
-	/*
-	 * The share hcall maps things in the 'fixed-offset' region of the hyp
-	 * VA space, so we can only share physically contiguous data-structures
-	 * for now.
-	 */
-	if (is_vmalloc_or_module_addr(from) || is_vmalloc_or_module_addr(to))
-		return -EINVAL;
-
-	if (kvm_host_owns_hyp_mappings())
-		return create_hyp_mappings(from, to, PAGE_HYP);
-
-	start = ALIGN_DOWN(__pa(from), PAGE_SIZE);
-	end = PAGE_ALIGN(__pa(to));
-	for (cur = start; cur < end; cur += PAGE_SIZE) {
-		pfn = __phys_to_pfn(cur);
-		ret = share_pfn_hyp(pfn);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-void kvm_unshare_hyp(void *from, void *to)
+void remove_hyp_mappings(void *from, void *to)
 {
-	phys_addr_t start, end, cur;
-	u64 pfn;
+	unsigned long start = kern_hyp_va((unsigned long)from);
+	unsigned long end = kern_hyp_va((unsigned long)to);
+	unsigned long size = end - start;
 
-	if (is_kernel_in_hyp_mode() || kvm_host_owns_hyp_mappings() || !from)
+	if (!is_protected_kvm_enabled() || !from)
 		return;
 
-	start = ALIGN_DOWN(__pa(from), PAGE_SIZE);
-	end = PAGE_ALIGN(__pa(to));
-	for (cur = start; cur < end; cur += PAGE_SIZE) {
-		pfn = __phys_to_pfn(cur);
-		WARN_ON(unshare_pfn_hyp(pfn));
-	}
+	mutex_lock(&kvm_hyp_pgd_mutex);
+	WARN_ON(KVM_PGT_CALL(kvm_pgtable_hyp_unmap, hyp_pgtable, start, size) != size);
+	mutex_unlock(&kvm_hyp_pgd_mutex);
 }
 
 /**
@@ -615,9 +471,6 @@ int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot)
 	if (is_kernel_in_hyp_mode())
 		return 0;
 
-	if (!kvm_host_owns_hyp_mappings())
-		return -EPERM;
-
 	start = start & PAGE_MASK;
 	end = PAGE_ALIGN(end);
 
@@ -699,16 +552,6 @@ static int __create_hyp_private_mapping(phys_addr_t phys_addr, size_t size,
 	unsigned long addr;
 	int ret = 0;
 
-	if (!kvm_host_owns_hyp_mappings()) {
-		addr = kvm_call_hyp_nvhe(__pkvm_create_private_mapping,
-					 phys_addr, size, prot);
-		if (IS_ERR_VALUE(addr))
-			return addr;
-		*haddr = addr;
-
-		return 0;
-	}
-
 	size = PAGE_ALIGN(size + offset_in_page(phys_addr));
 	ret = hyp_alloc_private_va_range(size, &addr);
 	if (ret)
@@ -2094,7 +1937,7 @@ int __init kvm_mmu_init(u32 *hyp_va_bits)
 		goto out;
 	}
 
-	err = kvm_pgtable_hyp_init(hyp_pgtable, *hyp_va_bits, &kvm_hyp_mm_ops);
+	err = KVM_PGT_CALL(kvm_pgtable_hyp_init, hyp_pgtable, *hyp_va_bits, &kvm_hyp_mm_ops);
 	if (err)
 		goto out_free_pgtable;
 
@@ -2106,7 +1949,7 @@ int __init kvm_mmu_init(u32 *hyp_va_bits)
 	return 0;
 
 out_destroy_pgtable:
-	kvm_pgtable_hyp_destroy(hyp_pgtable);
+	KVM_PGT_CALL(kvm_pgtable_hyp_destroy, hyp_pgtable);
 out_free_pgtable:
 	kfree(hyp_pgtable);
 	hyp_pgtable = NULL;
diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
index 64de20e8001d..f5a02b4039b1 100644
--- a/arch/arm64/kvm/pkvm.c
+++ b/arch/arm64/kvm/pkvm.c
@@ -270,6 +270,124 @@ static int __init finalize_pkvm(void)
 }
 device_initcall_sync(finalize_pkvm);
 
+struct hyp_shared_page {
+	struct rb_node node;
+	phys_addr_t phys;
+	void *hyp_va;
+	int count;
+};
+static struct rb_root hyp_shared_pages = RB_ROOT;
+
+static struct hyp_shared_page *find_shared_page(void *hyp_va, struct rb_node ***node,
+					       struct rb_node **parent)
+{
+	struct hyp_shared_page *page;
+
+	*node = &hyp_shared_pages.rb_node;
+	*parent = NULL;
+	while (**node) {
+		page = container_of(**node, struct hyp_shared_page, node);
+		*parent = **node;
+		if (page->hyp_va < hyp_va)
+			*node = &((**node)->rb_left);
+		else if (page->hyp_va > hyp_va)
+			*node = &((**node)->rb_right);
+		else
+			return page;
+	}
+
+	return NULL;
+}
+
+int pkvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits, struct kvm_pgtable_mm_ops *mm_ops)
+{
+	if (pgt)
+		return kvm_pgtable_hyp_init(pgt, va_bits, mm_ops);
+	return 0;
+}
+
+void pkvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt)
+{
+	if (pgt)
+		return kvm_pgtable_hyp_destroy(pgt);
+}
+
+static int share_page_hyp(void *hyp_va, phys_addr_t phys)
+{
+	struct rb_node **node, *parent;
+	struct hyp_shared_page *page;
+
+	page = find_shared_page(hyp_va, &node, &parent);
+	if (page) {
+		page->count++;
+		return 0;
+	}
+
+	page = kzalloc(sizeof(*page), GFP_KERNEL);
+	if (!page)
+		return -ENOMEM;
+	page->hyp_va = hyp_va;
+	page->phys = phys;
+	page->count = 1;
+	rb_link_node(&page->node, parent, node);
+	rb_insert_color(&page->node, &hyp_shared_pages);
+
+	return kvm_call_hyp_nvhe(__pkvm_host_share_hyp, phys >> PAGE_SHIFT, 1);
+}
+
+int pkvm_pgtable_hyp_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys,
+			 enum kvm_pgtable_prot prot)
+{
+	u64 off;
+	int ret;
+
+	if (pgt)
+		return kvm_pgtable_hyp_map(pgt, addr, size, phys, prot);
+
+	addr = ALIGN_DOWN(addr, PAGE_SIZE);
+	phys = ALIGN_DOWN(phys, PAGE_SIZE);
+	size = PAGE_ALIGN(size);
+	if (addr != (u64)kern_hyp_va(__va(phys)))
+		return -EINVAL;
+	if (prot != PAGE_HYP)
+		return -EPERM;
+
+	for (off = 0; off < size; off += PAGE_SIZE) {
+		ret = share_page_hyp((void *)(addr + off), phys + off);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+u64 pkvm_pgtable_hyp_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
+{
+	struct rb_node **node, *parent, *next;
+	struct hyp_shared_page *page;
+	u64 pfn, off = 0;
+
+	if (pgt)
+		return kvm_pgtable_hyp_unmap(pgt, addr, size);
+
+	page = find_shared_page((void *)addr, &node, &parent);
+	while (page && ((u64)page->hyp_va == addr + off) && off < size) {
+		next = rb_next(&page->node);
+		page->count--;
+		if (!page->count) {
+			pfn = page->phys >> PAGE_SHIFT;
+			rb_erase(&page->node, &hyp_shared_pages);
+			kfree(page);
+			if (kvm_call_hyp_nvhe(__pkvm_host_unshare_hyp, pfn, 1))
+				break;
+		}
+		off += PAGE_SIZE;
+		page = next ? container_of(next, struct hyp_shared_page, node) : NULL;
+	}
+
+	return off;
+}
+
 static int cmp_mappings(struct rb_node *node, const struct rb_node *parent)
 {
 	struct pkvm_mapping *a = rb_entry(node, struct pkvm_mapping, node);
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 470524b31951..e8b3d08e26dd 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -115,7 +115,7 @@ static int kvm_vcpu_finalize_sve(struct kvm_vcpu *vcpu)
 	if (!buf)
 		return -ENOMEM;
 
-	ret = kvm_share_hyp(buf, buf + reg_sz);
+	ret = create_hyp_mappings(buf, buf + reg_sz, PAGE_HYP);
 	if (ret) {
 		kfree(buf);
 		return ret;
@@ -154,9 +154,9 @@ void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
 	void *sve_state = vcpu->arch.sve_state;
 
-	kvm_unshare_hyp(vcpu, vcpu + 1);
+	remove_hyp_mappings(vcpu, vcpu + 1);
 	if (sve_state)
-		kvm_unshare_hyp(sve_state, sve_state + vcpu_sve_state_size(vcpu));
+		remove_hyp_mappings(sve_state, sve_state + vcpu_sve_state_size(vcpu));
 	kfree(sve_state);
 	kfree(vcpu->arch.ccsidr);
 }
-- 
2.47.1.613.gc27f4b7a9f-goog