@@ -20,23 +20,34 @@ extern u64 __io_map_base;
int hyp_create_idmap(u32 hyp_va_bits);
int hyp_map_vectors(void);
-int hyp_back_vmemmap(phys_addr_t phys, unsigned long size, phys_addr_t back);
+int hyp_back_vmemmap(phys_addr_t back);
int pkvm_cpu_set_vector(enum arm64_hyp_spectre_vector slot);
int pkvm_create_mappings(void *from, void *to, enum kvm_pgtable_prot prot);
int pkvm_create_mappings_locked(void *from, void *to, enum kvm_pgtable_prot prot);
unsigned long __pkvm_create_private_mapping(phys_addr_t phys, size_t size,
enum kvm_pgtable_prot prot);
-static inline void hyp_vmemmap_range(phys_addr_t phys, unsigned long size,
- unsigned long *start, unsigned long *end)
+static inline unsigned long hyp_vmemmap_memblock_size(struct memblock_region *reg)
{
- unsigned long nr_pages = size >> PAGE_SHIFT;
- struct hyp_page *p = hyp_phys_to_page(phys);
+ unsigned long nr_pages = reg->size >> PAGE_SHIFT;
+ unsigned long start, end;
- *start = (unsigned long)p;
- *end = *start + nr_pages * sizeof(struct hyp_page);
- *start = ALIGN_DOWN(*start, PAGE_SIZE);
- *end = ALIGN(*end, PAGE_SIZE);
+ start = hyp_phys_to_pfn(reg->base) * sizeof(struct hyp_page);
+ end = start + nr_pages * sizeof(struct hyp_page);
+ start = ALIGN_DOWN(start, PAGE_SIZE);
+ end = ALIGN(end, PAGE_SIZE);
+
+ return end - start;
+}
+
+static inline unsigned long hyp_vmemmap_pages(void)
+{
+ unsigned long res = 0, i;
+
+ for (i = 0; i < kvm_nvhe_sym(hyp_memblock_nr); i++)
+ res += hyp_vmemmap_memblock_size(&kvm_nvhe_sym(hyp_memory)[i]);
+
+ return res >> PAGE_SHIFT;
}
static inline unsigned long __hyp_pgtable_max_pages(unsigned long nr_pages)
@@ -103,13 +103,36 @@ int pkvm_create_mappings(void *from, void *to, enum kvm_pgtable_prot prot)
return ret;
}
-int hyp_back_vmemmap(phys_addr_t phys, unsigned long size, phys_addr_t back)
+int hyp_back_vmemmap(phys_addr_t back)
{
- unsigned long start, end;
+ unsigned long i, start, size, end = 0;
+ int ret;
- hyp_vmemmap_range(phys, size, &start, &end);
+ for (i = 0; i < hyp_memblock_nr; i++) {
+ start = hyp_memory[i].base;
+ start = ALIGN_DOWN((u64)hyp_phys_to_page(start), PAGE_SIZE);
+ /*
+ * The beginning of the hyp_vmemmap region for the current
+ * memblock may already be backed by the page backing the end
+ * the previous region, so avoid mapping it twice.
+ */
+ start = max(start, end);
+
+ end = hyp_memory[i].base + hyp_memory[i].size;
+ end = PAGE_ALIGN((u64)hyp_phys_to_page(end));
+ if (start >= end)
+ continue;
+
+ size = end - start;
+ ret = __pkvm_create_mappings(start, size, back, PAGE_HYP);
+ if (ret)
+ return ret;
+
+ memset(hyp_phys_to_virt(back), 0, size);
+ back += size;
+ }
- return __pkvm_create_mappings(start, end - start, back, PAGE_HYP);
+ return 0;
}
static void *__hyp_bp_vect_base;
@@ -234,10 +234,8 @@ int hyp_pool_init(struct hyp_pool *pool, u64 pfn, unsigned int nr_pages,
/* Init the vmemmap portion */
p = hyp_phys_to_page(phys);
- for (i = 0; i < nr_pages; i++) {
- p[i].order = 0;
+ for (i = 0; i < nr_pages; i++)
hyp_set_page_refcounted(&p[i]);
- }
/* Attach the unused pages to the buddy tree */
for (i = reserved_pages; i < nr_pages; i++)
@@ -29,12 +29,11 @@ static struct kvm_pgtable_mm_ops pkvm_pgtable_mm_ops;
static int divide_memory_pool(void *virt, unsigned long size)
{
- unsigned long vstart, vend, nr_pages;
+ unsigned long nr_pages;
hyp_early_alloc_init(virt, size);
- hyp_vmemmap_range(__hyp_pa(virt), size, &vstart, &vend);
- nr_pages = (vend - vstart) >> PAGE_SHIFT;
+ nr_pages = hyp_vmemmap_pages();
vmemmap_base = hyp_early_alloc_contig(nr_pages);
if (!vmemmap_base)
return -ENOMEM;
@@ -76,7 +75,7 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
if (ret)
return ret;
- ret = hyp_back_vmemmap(phys, size, hyp_virt_to_phys(vmemmap_base));
+ ret = hyp_back_vmemmap(hyp_virt_to_phys(vmemmap_base));
if (ret)
return ret;
@@ -54,7 +54,7 @@ static int __init register_memblock_regions(void)
void __init kvm_hyp_reserve(void)
{
- u64 nr_pages, prev, hyp_mem_pages = 0;
+ u64 hyp_mem_pages = 0;
int ret;
if (!is_hyp_mode_available() || is_kernel_in_hyp_mode())
@@ -72,20 +72,7 @@ void __init kvm_hyp_reserve(void)
hyp_mem_pages += hyp_s1_pgtable_pages();
hyp_mem_pages += host_s2_pgtable_pages();
-
- /*
- * The hyp_vmemmap needs to be backed by pages, but these pages
- * themselves need to be present in the vmemmap, so compute the number
- * of pages needed by looking for a fixed point.
- */
- nr_pages = 0;
- do {
- prev = nr_pages;
- nr_pages = hyp_mem_pages + prev;
- nr_pages = DIV_ROUND_UP(nr_pages * sizeof(struct hyp_page), PAGE_SIZE);
- nr_pages += __hyp_pgtable_max_pages(nr_pages);
- } while (nr_pages != prev);
- hyp_mem_pages += nr_pages;
+ hyp_mem_pages += hyp_vmemmap_pages();
/*
* Try to allocate a PMD-aligned region to reduce TLB pressure once
The EL2 vmemmap in nVHE Protected mode is currently very sparse: only memory pages owned by the hypervisor itself have a matching struct hyp_page. But since the size of these structs has been reduced significantly, it appears that we can now afford backing the vmemmap for all of memory. This will simplify a lot memory tracking as the hypervisor will have a place to store metadata (e.g. refcounts) that wouldn't otherwise fit in the 4 SW bits we have in the host stage-2 page-table. Signed-off-by: Quentin Perret <qperret@google.com> --- arch/arm64/kvm/hyp/include/nvhe/mm.h | 29 ++++++++++++++++++-------- arch/arm64/kvm/hyp/nvhe/mm.c | 31 ++++++++++++++++++++++++---- arch/arm64/kvm/hyp/nvhe/page_alloc.c | 4 +--- arch/arm64/kvm/hyp/nvhe/setup.c | 7 +++---- arch/arm64/kvm/hyp/reserved_mem.c | 17 ++------------- 5 files changed, 53 insertions(+), 35 deletions(-)