new file mode 100644
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __KVM_HYP_GFP_H
+#define __KVM_HYP_GFP_H
+
+#include <linux/list.h>
+
+#include <nvhe/memory.h>
+#include <nvhe/spinlock.h>
+
+#define HYP_MAX_ORDER 11U
+#define HYP_NO_ORDER UINT_MAX
+
+struct hyp_pool {
+ hyp_spinlock_t lock;
+ struct list_head free_area[HYP_MAX_ORDER + 1];
+ phys_addr_t range_start;
+ phys_addr_t range_end;
+};
+
+/* GFP flags */
+#define HYP_GFP_NONE 0
+#define HYP_GFP_ZERO 1
+
+/* Allocation */
+void *hyp_alloc_pages(struct hyp_pool *pool, gfp_t mask, unsigned int order);
+void hyp_get_page(void *addr);
+void hyp_put_page(void *addr);
+
+/* Used pages cannot be freed */
+int hyp_pool_init(struct hyp_pool *pool, phys_addr_t phys,
+ unsigned int nr_pages, unsigned int used_pages);
+#endif /* __KVM_HYP_GFP_H */
@@ -6,7 +6,17 @@
#include <linux/types.h>
+struct hyp_pool;
+struct hyp_page {
+ unsigned int refcount;
+ unsigned int order;
+ struct hyp_pool *pool;
+ struct list_head node;
+};
+
extern s64 hyp_physvirt_offset;
+extern u64 __hyp_vmemmap;
+#define hyp_vmemmap ((struct hyp_page *)__hyp_vmemmap)
#define __hyp_pa(virt) ((phys_addr_t)(virt) + hyp_physvirt_offset)
#define __hyp_va(virt) ((void *)((phys_addr_t)(virt) - hyp_physvirt_offset))
@@ -21,4 +31,19 @@ static inline phys_addr_t hyp_virt_to_phys(void *addr)
return __hyp_pa(addr);
}
+#define hyp_phys_to_pfn(phys) ((phys) >> PAGE_SHIFT)
+#define hyp_phys_to_page(phys) (&hyp_vmemmap[hyp_phys_to_pfn(phys)])
+#define hyp_virt_to_page(virt) hyp_phys_to_page(__hyp_pa(virt))
+
+#define hyp_page_to_phys(page) ((phys_addr_t)((page) - hyp_vmemmap) << PAGE_SHIFT)
+#define hyp_page_to_virt(page) __hyp_va(hyp_page_to_phys(page))
+#define hyp_page_to_pool(page) (((struct hyp_page *)page)->pool)
+
+static inline int hyp_page_count(void *addr)
+{
+ struct hyp_page *p = hyp_virt_to_page(addr);
+
+ return p->refcount;
+}
+
#endif /* __KVM_HYP_MEMORY_H */
@@ -10,7 +10,7 @@ lib-objs := clear_page.o copy_page.o memcpy.o memset.o
lib-objs := $(addprefix ../../../lib/, $(lib-objs))
obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o host.o \
- hyp-main.o hyp-smp.o psci-relay.o early_alloc.o stub.o
+ hyp-main.o hyp-smp.o psci-relay.o early_alloc.o stub.o page_alloc.o
obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \
../fpsimd.o ../hyp-entry.o ../exception.o
obj-y += $(lib-objs)
new file mode 100644
@@ -0,0 +1,185 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 Google LLC
+ * Author: Quentin Perret <qperret@google.com>
+ */
+
+#include <asm/kvm_hyp.h>
+#include <nvhe/gfp.h>
+
+u64 __hyp_vmemmap;
+
+/*
+ * Example buddy-tree for a 4-pages physically contiguous pool:
+ *
+ * o : Page 3
+ * /
+ * o-o : Page 2
+ * /
+ * / o : Page 1
+ * / /
+ * o---o-o : Page 0
+ * Order 2 1 0
+ *
+ * Example of requests on this zon:
+ * __find_buddy(pool, page 0, order 0) => page 1
+ * __find_buddy(pool, page 0, order 1) => page 2
+ * __find_buddy(pool, page 1, order 0) => page 0
+ * __find_buddy(pool, page 2, order 0) => page 3
+ */
+static struct hyp_page *__find_buddy(struct hyp_pool *pool, struct hyp_page *p,
+ unsigned int order)
+{
+ phys_addr_t addr = hyp_page_to_phys(p);
+
+ addr ^= (PAGE_SIZE << order);
+ if (addr < pool->range_start || addr >= pool->range_end)
+ return NULL;
+
+ return hyp_phys_to_page(addr);
+}
+
+static void __hyp_attach_page(struct hyp_pool *pool,
+ struct hyp_page *p)
+{
+ unsigned int order = p->order;
+ struct hyp_page *buddy;
+
+ p->order = HYP_NO_ORDER;
+ for (; order < HYP_MAX_ORDER; order++) {
+ /* Nothing to do if the buddy isn't in a free-list */
+ buddy = __find_buddy(pool, p, order);
+ if (!buddy || list_empty(&buddy->node) || buddy->order != order)
+ break;
+
+ /* Otherwise, coalesce the buddies and go one level up */
+ list_del_init(&buddy->node);
+ buddy->order = HYP_NO_ORDER;
+ p = (p < buddy) ? p : buddy;
+ }
+
+ p->order = order;
+ list_add_tail(&p->node, &pool->free_area[order]);
+}
+
+void hyp_put_page(void *addr)
+{
+ struct hyp_page *p = hyp_virt_to_page(addr);
+ struct hyp_pool *pool = hyp_page_to_pool(p);
+
+ hyp_spin_lock(&pool->lock);
+ if (!p->refcount)
+ hyp_panic();
+ p->refcount--;
+ if (!p->refcount)
+ __hyp_attach_page(pool, p);
+ hyp_spin_unlock(&pool->lock);
+}
+
+void hyp_get_page(void *addr)
+{
+ struct hyp_page *p = hyp_virt_to_page(addr);
+ struct hyp_pool *pool = hyp_page_to_pool(p);
+
+ hyp_spin_lock(&pool->lock);
+ p->refcount++;
+ hyp_spin_unlock(&pool->lock);
+}
+
+/* Extract a page from the buddy tree, at a specific order */
+static struct hyp_page *__hyp_extract_page(struct hyp_pool *pool,
+ struct hyp_page *p,
+ unsigned int order)
+{
+ struct hyp_page *buddy;
+
+ if (p->order == HYP_NO_ORDER || p->order < order)
+ return NULL;
+
+ list_del_init(&p->node);
+
+ /* Split the page in two until reaching the requested order */
+ while (p->order > order) {
+ p->order--;
+ buddy = __find_buddy(pool, p, p->order);
+ buddy->order = p->order;
+ list_add_tail(&buddy->node, &pool->free_area[buddy->order]);
+ }
+
+ p->refcount = 1;
+
+ return p;
+}
+
+static void clear_hyp_page(struct hyp_page *p)
+{
+ unsigned long i;
+
+ for (i = 0; i < (1 << p->order); i++)
+ clear_page(hyp_page_to_virt(p) + (i << PAGE_SHIFT));
+}
+
+static void *__hyp_alloc_pages(struct hyp_pool *pool, gfp_t mask,
+ unsigned int order)
+{
+ unsigned int i = order;
+ struct hyp_page *p;
+
+ /* Look for a high-enough-order page */
+ while (i <= HYP_MAX_ORDER && list_empty(&pool->free_area[i]))
+ i++;
+ if (i > HYP_MAX_ORDER)
+ return NULL;
+
+ /* Extract it from the tree at the right order */
+ p = list_first_entry(&pool->free_area[i], struct hyp_page, node);
+ p = __hyp_extract_page(pool, p, order);
+
+ if (mask & HYP_GFP_ZERO)
+ clear_hyp_page(p);
+
+ return p;
+}
+
+void *hyp_alloc_pages(struct hyp_pool *pool, gfp_t mask, unsigned int order)
+{
+ struct hyp_page *p;
+
+ hyp_spin_lock(&pool->lock);
+ p = __hyp_alloc_pages(pool, mask, order);
+ hyp_spin_unlock(&pool->lock);
+
+ return p ? hyp_page_to_virt(p) : NULL;
+}
+
+/* hyp_vmemmap must be backed beforehand */
+int hyp_pool_init(struct hyp_pool *pool, phys_addr_t phys,
+ unsigned int nr_pages, unsigned int used_pages)
+{
+ struct hyp_page *p;
+ int i;
+
+ if (phys % PAGE_SIZE)
+ return -EINVAL;
+
+ hyp_spin_lock_init(&pool->lock);
+ for (i = 0; i <= HYP_MAX_ORDER; i++)
+ INIT_LIST_HEAD(&pool->free_area[i]);
+ pool->range_start = phys;
+ pool->range_end = phys + (nr_pages << PAGE_SHIFT);
+
+ /* Init the vmemmap portion */
+ p = hyp_phys_to_page(phys);
+ memset(p, 0, sizeof(*p) * nr_pages);
+ for (i = 0; i < nr_pages; i++, p++) {
+ p->pool = pool;
+ INIT_LIST_HEAD(&p->node);
+ }
+
+ /* Attach the unused pages to the buddy tree */
+ p = hyp_phys_to_page(phys + (used_pages << PAGE_SHIFT));
+ for (i = used_pages; i < nr_pages; i++, p++)
+ __hyp_attach_page(pool, p);
+
+ return 0;
+}
When memory protection is enabled, the hyp code will require a basic form of memory management in order to allocate and free memory pages at EL2. This is needed for various use-cases, including the creation of hyp mappings or the allocation of stage 2 page tables. To address these use-case, introduce a simple memory allocator in the hyp code. The allocator is designed as a conventional 'buddy allocator', working with a page granularity. It allows to allocate and free physically contiguous pages from memory 'pools', with a guaranteed order alignment in the PA space. Each page in a memory pool is associated with a struct hyp_page which holds the page's metadata, including its refcount, as well as its current order, hence mimicking the kernel's buddy system in the GFP infrastructure. The hyp_page metadata are made accessible through a hyp_vmemmap, following the concept of SPARSE_VMEMMAP in the kernel. Signed-off-by: Quentin Perret <qperret@google.com> --- arch/arm64/kvm/hyp/include/nvhe/gfp.h | 32 ++++ arch/arm64/kvm/hyp/include/nvhe/memory.h | 25 +++ arch/arm64/kvm/hyp/nvhe/Makefile | 2 +- arch/arm64/kvm/hyp/nvhe/page_alloc.c | 185 +++++++++++++++++++++++ 4 files changed, 243 insertions(+), 1 deletion(-) create mode 100644 arch/arm64/kvm/hyp/include/nvhe/gfp.h create mode 100644 arch/arm64/kvm/hyp/nvhe/page_alloc.c