x86/mm: Expand static page table for fixmap space

We met a kernel panic when enabling earlycon, which is due to the fixmap
address of earlycon is not statically setup.

Currently the static fixmap setup in head_64.S only covers 2M virtual
address space, while it actually could be in 4M space with different
kernel configurations, e.g. when VSYSCALL emulation is disabled.

So increase the static space to 4M for now by defining FIXMAP_PMD_NUM to 2,
and add a build time check to ensure that the fixmap is covered by the
initial static page tables.

Fixes: 1ad83c85 ("x86_64,vsyscall: Make vsyscall emulation configurable")
Suggested-by: NThomas Gleixner <tglx@linutronix.de>
Signed-off-by: NFeng Tang <feng.tang@intel.com>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Tested-by: Nkernel test robot <rong.a.chen@intel.com>
Reviewed-by: Juergen Gross <jgross@suse.com> (Xen parts)
Cc: H Peter Anvin <hpa@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andy Lutomirsky <luto@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20180920025828.23699-1-feng.tang@intel.com

arch/x86/include/asm/fixmap.h

@@ -14,6 +14,16 @@
 #ifndef _ASM_X86_FIXMAP_H
 #define _ASM_X86_FIXMAP_H
 
+/*
+ * Exposed to assembly code for setting up initial page tables. Cannot be
+ * calculated in assembly code (fixmap entries are an enum), but is sanity
+ * checked in the actual fixmap C code to make sure that the fixmap is
+ * covered fully.
+ */
+#define FIXMAP_PMD_NUM	2
+/* fixmap starts downwards from the 507th entry in level2_fixmap_pgt */
+#define FIXMAP_PMD_TOP	507
+
 #ifndef __ASSEMBLY__
 #include <linux/kernel.h>
 #include <asm/acpi.h>

arch/x86/include/asm/pgtable_64.h

@@ -14,6 +14,7 @@
 #include <asm/processor.h>
 #include <linux/bitops.h>
 #include <linux/threads.h>
+#include <asm/fixmap.h>
 
 extern p4d_t level4_kernel_pgt[512];
 extern p4d_t level4_ident_pgt[512];
@@ -22,7 +23,7 @@ extern pud_t level3_ident_pgt[512];
 extern pmd_t level2_kernel_pgt[512];
 extern pmd_t level2_fixmap_pgt[512];
 extern pmd_t level2_ident_pgt[512];
-extern pte_t level1_fixmap_pgt[512];
+extern pte_t level1_fixmap_pgt[512 * FIXMAP_PMD_NUM];
 extern pgd_t init_top_pgt[];
 
 #define swapper_pg_dir init_top_pgt

arch/x86/kernel/head64.c

@@ -35,6 +35,7 @@
 #include <asm/bootparam_utils.h>
 #include <asm/microcode.h>
 #include <asm/kasan.h>
+#include <asm/fixmap.h>
 
 /*
  * Manage page tables very early on.
@@ -166,7 +167,8 @@ unsigned long __head __startup_64(unsigned long physaddr,
 	pud[511] += load_delta;
 
 	pmd = fixup_pointer(level2_fixmap_pgt, physaddr);
-	pmd[506] += load_delta;
+	for (i = FIXMAP_PMD_TOP; i > FIXMAP_PMD_TOP - FIXMAP_PMD_NUM; i--)
+		pmd[i] += load_delta;
 
 	/*
 	 * Set up the identity mapping for the switchover.  These

arch/x86/kernel/head_64.S

@@ -24,6 +24,7 @@
 #include "../entry/calling.h"
 #include <asm/export.h>
 #include <asm/nospec-branch.h>
+#include <asm/fixmap.h>
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/asm-offsets.h>
@@ -445,13 +446,20 @@ NEXT_PAGE(level2_kernel_pgt)
 		KERNEL_IMAGE_SIZE/PMD_SIZE)
 
 NEXT_PAGE(level2_fixmap_pgt)
-	.fill	506,8,0
-	.quad	level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
-	/* 8MB reserved for vsyscalls + a 2MB hole = 4 + 1 entries */
-	.fill	5,8,0
+	.fill	(512 - 4 - FIXMAP_PMD_NUM),8,0
+	pgtno = 0
+	.rept (FIXMAP_PMD_NUM)
+	.quad level1_fixmap_pgt + (pgtno << PAGE_SHIFT) - __START_KERNEL_map \
+		+ _PAGE_TABLE_NOENC;
+	pgtno = pgtno + 1
+	.endr
+	/* 6 MB reserved space + a 2MB hole */
+	.fill	4,8,0
 
 NEXT_PAGE(level1_fixmap_pgt)
+	.rept (FIXMAP_PMD_NUM)
 	.fill	512,8,0
+	.endr
 
 #undef PMDS
 

arch/x86/mm/pgtable.c

@@ -637,6 +637,15 @@ void __native_set_fixmap(enum fixed_addresses idx, pte_t pte)
 {
 	unsigned long address = __fix_to_virt(idx);
 
+#ifdef CONFIG_X86_64
+       /*
+	* Ensure that the static initial page tables are covering the
+	* fixmap completely.
+	*/
+	BUILD_BUG_ON(__end_of_permanent_fixed_addresses >
+		     (FIXMAP_PMD_NUM * PTRS_PER_PTE));
+#endif
+
 	if (idx >= __end_of_fixed_addresses) {
 		BUG();
 		return;

arch/x86/xen/mmu_pv.c

@@ -1907,7 +1907,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	/* L3_k[511] -> level2_fixmap_pgt */
 	convert_pfn_mfn(level3_kernel_pgt);
 
-	/* L3_k[511][506] -> level1_fixmap_pgt */
+	/* L3_k[511][508-FIXMAP_PMD_NUM ... 507] -> level1_fixmap_pgt */
 	convert_pfn_mfn(level2_fixmap_pgt);
 
 	/* We get [511][511] and have Xen's version of level2_kernel_pgt */
@@ -1952,7 +1952,11 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO);
 	set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
 	set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
-	set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO);
+
+	for (i = 0; i < FIXMAP_PMD_NUM; i++) {
+		set_page_prot(level1_fixmap_pgt + i * PTRS_PER_PTE,
+			      PAGE_KERNEL_RO);
+	}
 
 	/* Pin down new L4 */
 	pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE,