x86/mm: Pre-allocate P4D/PUD pages for vmalloc area

Pre-allocate the page-table pages for the vmalloc area at the level
which needs synchronization on x86-64, which is P4D for 5-level and
PUD for 4-level paging.

Doing this at boot makes sure no synchronization of that area is
necessary at runtime. The synchronization takes the pgd_lock and
iterates over all page-tables in the system, so it can take quite long
and is better avoided.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Link: https://lore.kernel.org/r/20200721095953.6218-2-joro@8bytes.org

1 files changed, 52 insertions, 0 deletions

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index dbae185511cd..e76bdb001460 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1238,6 +1238,56 @@ static void __init register_page_bootmem_info(void)
 #endif
 }
 
+/*
+ * Pre-allocates page-table pages for the vmalloc area in the kernel page-table.
+ * Only the level which needs to be synchronized between all page-tables is
+ * allocated because the synchronization can be expensive.
+ */
+static void __init preallocate_vmalloc_pages(void)
+{
+	unsigned long addr;
+	const char *lvl;
+
+	for (addr = VMALLOC_START; addr <= VMALLOC_END; addr = ALIGN(addr + 1, PGDIR_SIZE)) {
+		pgd_t *pgd = pgd_offset_k(addr);
+		p4d_t *p4d;
+		pud_t *pud;
+
+		p4d = p4d_offset(pgd, addr);
+		if (p4d_none(*p4d)) {
+			/* Can only happen with 5-level paging */
+			p4d = p4d_alloc(&init_mm, pgd, addr);
+			if (!p4d) {
+				lvl = "p4d";
+				goto failed;
+			}
+		}
+
+		if (pgtable_l5_enabled())
+			continue;
+
+		pud = pud_offset(p4d, addr);
+		if (pud_none(*pud)) {
+			/* Ends up here only with 4-level paging */
+			pud = pud_alloc(&init_mm, p4d, addr);
+			if (!pud) {
+				lvl = "pud";
+				goto failed;
+			}
+		}
+	}
+
+	return;
+
+failed:
+
+	/*
+	 * The pages have to be there now or they will be missing in
+	 * process page-tables later.
+	 */
+	panic("Failed to pre-allocate %s pages for vmalloc area\n", lvl);
+}
+
 void __init mem_init(void)
 {
 	pci_iommu_alloc();
@@ -1261,6 +1311,8 @@ void __init mem_init(void)
 	if (get_gate_vma(&init_mm))
 		kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, PAGE_SIZE, KCORE_USER);
 
+	preallocate_vmalloc_pages();
+
 	mem_init_print_info(NULL);
 }