linux-kernel - [PATCHv7 13/19] x86/mm: Make early boot code support boot-time switching of paging modes

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Mon, 18 Sep 2017 13:55:47 +0300
From:   "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
To:     Ingo Molnar <mingo@...hat.com>,
        Linus Torvalds <torvalds@...ux-foundation.org>, x86@...nel.org,
        Thomas Gleixner <tglx@...utronix.de>,
        "H. Peter Anvin" <hpa@...or.com>
Cc:     Andrew Morton <akpm@...ux-foundation.org>,
        Andy Lutomirski <luto@...capital.net>,
        Cyrill Gorcunov <gorcunov@...nvz.org>,
        Borislav Petkov <bp@...e.de>, linux-mm@...ck.org,
        linux-kernel@...r.kernel.org,
        "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
Subject: [PATCHv7 13/19] x86/mm: Make early boot code support boot-time switching of paging modes

Early boot code, that setup page table should be able to initialize page
tables for both 4- and 5-level paging modes.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@...ux.intel.com>
---
 arch/x86/kernel/head64.c  | 33 ++++++++++++++++++++++-----------
 arch/x86/kernel/head_64.S | 10 ++++------
 2 files changed, 26 insertions(+), 17 deletions(-)

diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 2dabb2d1b64b..617b42c9bdbb 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -74,13 +74,13 @@ static unsigned int __head *fixup_int(void *ptr, unsigned long physaddr)
 	return fixup_pointer(ptr, physaddr);
 }
 
-static void __head check_la57_support(unsigned long physaddr)
+static bool __head check_la57_support(unsigned long physaddr)
 {
 	if (native_cpuid_eax(0) < 7)
-		return;
+		return false;
 
 	if (!(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31))))
-		return;
+		return false;
 
 	*fixup_int(&pgtable_l5_enabled, physaddr) = 1;
 	*fixup_int(&pgdir_shift, physaddr) = 48;
@@ -88,24 +88,30 @@ static void __head check_la57_support(unsigned long physaddr)
 	*fixup_long(&page_offset_base, physaddr) = __PAGE_OFFSET_BASE57;
 	*fixup_long(&vmalloc_base, physaddr) = __VMALLOC_BASE57;
 	*fixup_long(&vmemmap_base, physaddr) = __VMEMMAP_BASE57;
+
+	return true;
 }
 #else
-static void __head check_la57_support(unsigned long physaddr) {}
+static bool __head check_la57_support(unsigned long physaddr)
+{
+	return false;
+}
 #endif
 
 unsigned long __head __startup_64(unsigned long physaddr,
 				  struct boot_params *bp)
 {
-	unsigned long load_delta;
+	unsigned long load_delta, *p;
 	unsigned long pgtable_flags;
 	pgdval_t *pgd;
 	p4dval_t *p4d;
 	pudval_t *pud;
 	pmdval_t *pmd, pmd_entry;
+	bool la57;
 	int i;
 	unsigned int *next_pgt_ptr;
 
-	check_la57_support(physaddr);
+	la57 = check_la57_support(physaddr);
 
 	/* Is the address too large? */
 	if (physaddr >> MAX_PHYSMEM_BITS)
@@ -130,9 +136,14 @@ unsigned long __head __startup_64(unsigned long physaddr,
 	/* Fixup the physical addresses in the page table */
 
 	pgd = fixup_pointer(&early_top_pgt, physaddr);
-	pgd[pgd_index(__START_KERNEL_map)] += load_delta;
-
-	if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
+	p = pgd + pgd_index(__START_KERNEL_map);
+	if (la57)
+		*p = (unsigned long)level4_kernel_pgt;
+	else
+		*p = (unsigned long)level3_kernel_pgt;
+	*p += _PAGE_TABLE_NOENC - __START_KERNEL_map + load_delta;
+
+	if (la57) {
 		p4d = fixup_pointer(&level4_kernel_pgt, physaddr);
 		p4d[511] += load_delta;
 	}
@@ -157,7 +168,7 @@ unsigned long __head __startup_64(unsigned long physaddr,
 
 	pgtable_flags = _KERNPG_TABLE_NOENC + sme_get_me_mask();
 
-	if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
+	if (la57) {
 		p4d = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr);
 
 		i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD;
@@ -254,7 +265,7 @@ int __init __early_make_pgtable(unsigned long address, pmdval_t pmd)
 	 * critical -- __PAGE_OFFSET would point us back into the dynamic
 	 * range and we might end up looping forever...
 	 */
-	if (!IS_ENABLED(CONFIG_X86_5LEVEL))
+	if (!pgtable_l5_enabled)
 		p4d_p = pgd_p;
 	else if (pgd)
 		p4d_p = (p4dval_t *)((pgd & PTE_PFN_MASK) + __START_KERNEL_map - phys_base);
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index a8409cd23b35..49f8bb43d107 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -121,7 +121,10 @@ ENTRY(secondary_startup_64)
 	/* Enable PAE mode, PGE and LA57 */
 	movl	$(X86_CR4_PAE | X86_CR4_PGE), %ecx
 #ifdef CONFIG_X86_5LEVEL
+	testl	$1, pgtable_l5_enabled(%rip)
+	jz	1f
 	orl	$X86_CR4_LA57, %ecx
+1:
 #endif
 	movq	%rcx, %cr4
 
@@ -350,12 +353,7 @@ GLOBAL(name)
 
 	__INITDATA
 NEXT_PAGE(early_top_pgt)
-	.fill	511,8,0
-#ifdef CONFIG_X86_5LEVEL
-	.quad	level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
-#else
-	.quad	level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
-#endif
+	.fill	512,8,0
 
 NEXT_PAGE(early_dynamic_pgts)
 	.fill	512*EARLY_DYNAMIC_PAGE_TABLES,8,0
-- 
2.14.1