[PATCH v3 16/29] KVM: arm64: iommu: Add a memory pool

[Mostafa Saleh <smostafa@google.com>]

IOMMU drivers would require to allocate memory for the shadow page
table. Similar to the host stage-2 CPU page table, the IOMMU pool
is allocated early from the carveout and it's memory is added in
a pool which the IOMMU driver can allocate from and reclaim at
run time.

At this point the nr_pages is 0 as there are no driver, in the next
patches when the SMMUv3 driver is added, it will add it's own function
to return the number of pages needed in kvm/iommu.c.
Unfortunately, this part has 2 leak into kvm/iommu as this happens too
early before drivers can have any init calls.

Signed-off-by: Mostafa Saleh <smostafa@google.com>
---
 arch/arm64/include/asm/kvm_host.h       |  2 +-
 arch/arm64/kvm/hyp/include/nvhe/iommu.h |  5 ++++-
 arch/arm64/kvm/hyp/nvhe/iommu/iommu.c   | 20 +++++++++++++++++++-
 arch/arm64/kvm/hyp/nvhe/setup.c         | 10 +++++++++-
 arch/arm64/kvm/iommu.c                  | 11 +++++++++++
 arch/arm64/kvm/pkvm.c                   |  1 +
 6 files changed, 45 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 43f5a64bbd1d..b42e32ff2a84 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1683,5 +1683,5 @@ struct kvm_iommu_ops;
 int kvm_iommu_register_driver(struct kvm_iommu_driver *kern_ops, struct kvm_iommu_ops *hyp_ops);
 int kvm_iommu_init_driver(void);
 void kvm_iommu_remove_driver(void);
-
+size_t kvm_iommu_pages(void);
 #endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/kvm/hyp/include/nvhe/iommu.h b/arch/arm64/kvm/hyp/include/nvhe/iommu.h
index 219363045b1c..9f4906c6dcc9 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/iommu.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/iommu.h
@@ -10,8 +10,11 @@ struct kvm_iommu_ops {
 	void (*host_stage2_idmap)(phys_addr_t start, phys_addr_t end, int prot);
 };
 
-int kvm_iommu_init(void);
+int kvm_iommu_init(void *pool_base, size_t nr_pages);
 
 void kvm_iommu_host_stage2_idmap(phys_addr_t start, phys_addr_t end,
 				 enum kvm_pgtable_prot prot);
+void *kvm_iommu_donate_pages(u8 order);
+void kvm_iommu_reclaim_pages(void *ptr);
+
 #endif /* __ARM64_KVM_NVHE_IOMMU_H__ */
diff --git a/arch/arm64/kvm/hyp/nvhe/iommu/iommu.c b/arch/arm64/kvm/hyp/nvhe/iommu/iommu.c
index f7d1c8feb358..1673165c7330 100644
--- a/arch/arm64/kvm/hyp/nvhe/iommu/iommu.c
+++ b/arch/arm64/kvm/hyp/nvhe/iommu/iommu.c
@@ -15,6 +15,7 @@ struct kvm_iommu_ops *kvm_iommu_ops;
 
 /* Protected by host_mmu.lock */
 static bool kvm_idmap_initialized;
+static struct hyp_pool iommu_pages_pool;
 
 static inline int pkvm_to_iommu_prot(enum kvm_pgtable_prot prot)
 {
@@ -72,7 +73,7 @@ static int kvm_iommu_snapshot_host_stage2(void)
 	return ret;
 }
 
-int kvm_iommu_init(void)
+int kvm_iommu_init(void *pool_base, size_t nr_pages)
 {
 	int ret;
 
@@ -80,6 +81,13 @@ int kvm_iommu_init(void)
 	    !kvm_iommu_ops->host_stage2_idmap)
 		return -ENODEV;
 
+	if (nr_pages) {
+		ret = hyp_pool_init(&iommu_pages_pool, hyp_virt_to_pfn(pool_base),
+				    nr_pages, 0);
+		if (ret)
+			return ret;
+	}
+
 	ret = kvm_iommu_ops->init();
 	if (ret)
 		return ret;
@@ -95,3 +103,13 @@ void kvm_iommu_host_stage2_idmap(phys_addr_t start, phys_addr_t end,
 		return;
 	kvm_iommu_ops->host_stage2_idmap(start, end, pkvm_to_iommu_prot(prot));
 }
+
+void *kvm_iommu_donate_pages(u8 order)
+{
+	return hyp_alloc_pages(&iommu_pages_pool, order);
+}
+
+void kvm_iommu_reclaim_pages(void *ptr)
+{
+	hyp_put_page(&iommu_pages_pool, ptr);
+}
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index bdbc77395e03..09ecee2cd864 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -21,6 +21,7 @@
 #include <nvhe/trap_handler.h>
 
 unsigned long hyp_nr_cpus;
+size_t hyp_kvm_iommu_pages;
 
 #define hyp_percpu_size ((unsigned long)__per_cpu_end - \
 			 (unsigned long)__per_cpu_start)
@@ -33,6 +34,7 @@ static void *selftest_base;
 static void *ffa_proxy_pages;
 static struct kvm_pgtable_mm_ops pkvm_pgtable_mm_ops;
 static struct hyp_pool hpool;
+static void *iommu_base;
 
 static int divide_memory_pool(void *virt, unsigned long size)
 {
@@ -70,6 +72,12 @@ static int divide_memory_pool(void *virt, unsigned long size)
 	if (!ffa_proxy_pages)
 		return -ENOMEM;
 
+	if (hyp_kvm_iommu_pages) {
+		iommu_base = hyp_early_alloc_contig(hyp_kvm_iommu_pages);
+		if (!iommu_base)
+			return -ENOMEM;
+	}
+
 	return 0;
 }
 
@@ -321,7 +329,7 @@ void __noreturn __pkvm_init_finalise(void)
 	if (ret)
 		goto out;
 
-	ret = kvm_iommu_init();
+	ret = kvm_iommu_init(iommu_base, hyp_kvm_iommu_pages);
 	if (ret)
 		goto out;
 
diff --git a/arch/arm64/kvm/iommu.c b/arch/arm64/kvm/iommu.c
index 39465101074a..0e52cc0e18de 100644
--- a/arch/arm64/kvm/iommu.c
+++ b/arch/arm64/kvm/iommu.c
@@ -9,6 +9,7 @@
 
 struct kvm_iommu_driver *iommu_driver;
 extern struct kvm_iommu_ops *kvm_nvhe_sym(kvm_iommu_ops);
+extern size_t kvm_nvhe_sym(hyp_kvm_iommu_pages);
 
 int kvm_iommu_register_driver(struct kvm_iommu_driver *kern_ops, struct kvm_iommu_ops *el2_ops)
 {
@@ -47,3 +48,13 @@ void kvm_iommu_remove_driver(void)
 	if (smp_load_acquire(&iommu_driver))
 		iommu_driver->remove_driver();
 }
+
+size_t kvm_iommu_pages(void)
+{
+	/*
+	 * This is called very early during setup_arch() where no initcalls,
+	 * so this has to call specific functions per each KVM driver.
+	 */
+	kvm_nvhe_sym(hyp_kvm_iommu_pages) = 0;
+	return 0;
+}
diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
index fcd70bfe44fb..6098beda36fa 100644
--- a/arch/arm64/kvm/pkvm.c
+++ b/arch/arm64/kvm/pkvm.c
@@ -63,6 +63,7 @@ void __init kvm_hyp_reserve(void)
 	hyp_mem_pages += hyp_vmemmap_pages(STRUCT_HYP_PAGE_SIZE);
 	hyp_mem_pages += pkvm_selftest_pages();
 	hyp_mem_pages += hyp_ffa_proxy_pages();
+	hyp_mem_pages += kvm_iommu_pages();
 
 	/*
 	 * Try to allocate a PMD-aligned region to reduce TLB pressure once
-- 
2.50.1.552.g942d659e1b-goog