arm64: mm: install KPTI nG mappings with MMU enabled

In cases where we unmap the kernel while running in user space, we rely
on ASIDs to distinguish the minimal trampoline from the full kernel
mapping, and this means we must use non-global attributes for those
mappings, to ensure they are scoped by ASID and will not hit in the TLB
inadvertently.

We only do this when needed, as this is generally more costly in terms
of TLB pressure, and so we boot without these non-global attributes, and
apply them to all existing kernel mappings once all CPUs are up and we
know whether or not the non-global attributes are needed. At this point,
we cannot simply unmap and remap the entire address space, so we have to
update all existing block and page descriptors in place.

Currently, we go through a lot of trouble to perform these updates with
the MMU and caches off, to avoid violating break before make (BBM) rules
imposed by the architecture. Since we make changes to page tables that
are not covered by the ID map, we gain access to those descriptors by
disabling translations altogether. This means that the stores to memory
are issued with device attributes, and require extra care in terms of
coherency, which is costly. We also rely on the ID map to access a
shared flag, which requires the ID map to be executable and writable at
the same time, which is another thing we'd prefer to avoid.

So let's switch to an approach where we replace the kernel mapping with
a minimal mapping of a few pages that can be used for a minimal, ad-hoc
fixmap that we can use to map each page table in turn as we traverse the
hierarchy.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20220609174320.4035379-3-ardb@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>

1 files changed, 51 insertions, 3 deletions

diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 8d88433de81d..145b43c6c651 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1645,14 +1645,34 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
 }
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+#define KPTI_NG_TEMP_VA		(-(1UL << PMD_SHIFT))
+
+extern
+void create_kpti_ng_temp_pgd(pgd_t *pgdir, phys_addr_t phys, unsigned long virt,
+			     phys_addr_t size, pgprot_t prot,
+			     phys_addr_t (*pgtable_alloc)(int), int flags);
+
+static phys_addr_t kpti_ng_temp_alloc;
+
+static phys_addr_t kpti_ng_pgd_alloc(int shift)
+{
+	kpti_ng_temp_alloc -= PAGE_SIZE;
+	return kpti_ng_temp_alloc;
+}
+
 static void __nocfi
 kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
 {
-	typedef void (kpti_remap_fn)(int, int, phys_addr_t);
+	typedef void (kpti_remap_fn)(int, int, phys_addr_t, unsigned long);
 	extern kpti_remap_fn idmap_kpti_install_ng_mappings;
 	kpti_remap_fn *remap_fn;
 
 	int cpu = smp_processor_id();
+	int levels = CONFIG_PGTABLE_LEVELS;
+	int order = order_base_2(levels);
+	u64 kpti_ng_temp_pgd_pa = 0;
+	pgd_t *kpti_ng_temp_pgd;
+	u64 alloc = 0;
 
 	if (__this_cpu_read(this_cpu_vector) == vectors) {
 		const char *v = arm64_get_bp_hardening_vector(EL1_VECTOR_KPTI);
@@ -1670,12 +1690,40 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
 
 	remap_fn = (void *)__pa_symbol(function_nocfi(idmap_kpti_install_ng_mappings));
 
+	if (!cpu) {
+		alloc = __get_free_pages(GFP_ATOMIC | __GFP_ZERO, order);
+		kpti_ng_temp_pgd = (pgd_t *)(alloc + (levels - 1) * PAGE_SIZE);
+		kpti_ng_temp_alloc = kpti_ng_temp_pgd_pa = __pa(kpti_ng_temp_pgd);
+
+		//
+		// Create a minimal page table hierarchy that permits us to map
+		// the swapper page tables temporarily as we traverse them.
+		//
+		// The physical pages are laid out as follows:
+		//
+		// +--------+-/-------+-/------ +-\\--------+
+		// :  PTE[] : | PMD[] : | PUD[] : || PGD[]  :
+		// +--------+-\-------+-\------ +-//--------+
+		//      ^
+		// The first page is mapped into this hierarchy at a PMD_SHIFT
+		// aligned virtual address, so that we can manipulate the PTE
+		// level entries while the mapping is active. The first entry
+		// covers the PTE[] page itself, the remaining entries are free
+		// to be used as a ad-hoc fixmap.
+		//
+		create_kpti_ng_temp_pgd(kpti_ng_temp_pgd, __pa(alloc),
+					KPTI_NG_TEMP_VA, PAGE_SIZE, PAGE_KERNEL,
+					kpti_ng_pgd_alloc, 0);
+	}
+
 	cpu_install_idmap();
-	remap_fn(cpu, num_online_cpus(), __pa_symbol(swapper_pg_dir));
+	remap_fn(cpu, num_online_cpus(), kpti_ng_temp_pgd_pa, KPTI_NG_TEMP_VA);
 	cpu_uninstall_idmap();
 
-	if (!cpu)
+	if (!cpu) {
+		free_pages(alloc, order);
 		arm64_use_ng_mappings = true;
+	}
 }
 #else
 static void