[PATCH] x86/mm: Pre-allocate p4d/pud pages for vmalloc area

From: Joerg Roedel
Date: Fri Jun 26 2020 - 05:35:01 EST


From: Joerg Roedel <jroedel@xxxxxxx>

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

Doing this at boot makes sure all page-tables in the system have these
pages already and do not need to be synchronized at runtime. The
runtime synchronizatin 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@xxxxxxx>
---
arch/x86/mm/init_64.c | 55 +++++++++++++++++++++++++++++++++++++++++++
1 file changed, 55 insertions(+)

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index dbae185511cd..475a4008445b 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1238,6 +1238,59 @@ 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;
+ int count = 0;
+
+ 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;
+ }
+ count += 1;
+ }
+
+ 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;
+ }
+ count += 1;
+ }
+ }
+
+ return;
+
+failed:
+
+ /*
+ * A failure here is not fatal - If the pages can be allocated later it
+ * will be synchronized to other page-tables.
+ */
+ pr_err("Failed to pre-allocate %s pages for vmalloc area\n", lvl);
+}
+
void __init mem_init(void)
{
pci_iommu_alloc();
@@ -1261,6 +1314,8 @@ 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);
}

--
2.27.0