linux-kernel - [PATCH v3 2/2] x86/mm: Create a workarea in the kernel for SME early encryption

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]
Message-ID: <3c483262eb4077b1654b2052bd14a8d011bffde3.1560969363.git.thomas.lendacky@amd.com>
Date:   Wed, 19 Jun 2019 18:40:59 +0000
From:   "Lendacky, Thomas" <Thomas.Lendacky@....com>
To:     "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        "x86@...nel.org" <x86@...nel.org>
CC:     Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
        Dave Hansen <dave.hansen@...ux.intel.com>,
        Andy Lutomirski <luto@...nel.org>,
        Peter Zijlstra <peterz@...radead.org>,
        Lianbo Jiang <lijiang@...hat.com>, Baoquan He <bhe@...hat.com>
Subject: [PATCH v3 2/2] x86/mm: Create a workarea in the kernel for SME early
 encryption

In order for the kernel to be encrypted "in place" during boot, a workarea
outside of the kernel must be used. This SME workarea used during early
encryption of the kernel is situated on a 2MB boundary after the end of
the kernel text, data, etc. sections (_end).  This works well during
initial boot of a compressed kernel because of the relocation used for
decompression of the kernel. But when performing a kexec boot, there's a
chance that the SME workarea may not be mapped by the kexec pagetables or
that some of the other data used by kexec could exist in this range.

Create a section for SME in vmlinux.lds.S. Position it after "_end", which
is after "__end_of_kernel_reserve", so that the memory will be reclaimed
during boot and since this area is all zeroes, it compresses well. This
new section will be part of the kernel image, so kexec will account for it
in pagetable mappings and placement of data after the kernel.

Here's an example of a kernel size without and with the SME section:
	without:
		vmlinux:	36,501,616
		bzImage:	 6,497,344

		100000000-47f37ffff : System RAM
		  1e4000000-1e47677d4 : Kernel code	(0x7677d4)
		  1e47677d5-1e4e2e0bf : Kernel data	(0x6c68ea)
		  1e5074000-1e5372fff : Kernel bss	(0x2fefff)

	with:
		vmlinux:	44,419,408
		bzImage:	 6,503,136

		880000000-c7ff7ffff : System RAM
		  8cf000000-8cf7677d4 : Kernel code	(0x7677d4)
		  8cf7677d5-8cfe2e0bf : Kernel data	(0x6c68ea)
		  8d0074000-8d0372fff : Kernel bss	(0x2fefff)

Tested-by: Lianbo Jiang <lijiang@...hat.com>
Reviewed-by: Baoquan He <bhe@...hat.com>
Reviewed-by: Dave Hansen <dave.hansen@...el.com>
Signed-off-by: Tom Lendacky <thomas.lendacky@....com>
---
 arch/x86/kernel/vmlinux.lds.S      | 25 +++++++++++++++++++++++++
 arch/x86/mm/mem_encrypt_identity.c | 22 ++++++++++++++++++++--
 2 files changed, 45 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index ca2252ca6ad7..147cd020516a 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -387,6 +387,31 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);		/* keep VO_INIT_SIZE page aligned */
 	_end = .;
 
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+	/*
+	 * Early scratch/workarea section: Lives outside of the kernel proper
+	 * (_text - _end).
+	 *
+	 * Resides after _end because even though the .brk section is after
+	 * __end_of_kernel_reserve, the .brk section is later reserved as a
+	 * part of the kernel. Since it is located after __end_of_kernel_reserve
+	 * it will be discarded and become part of the available memory. As
+	 * such, it can only be used by very early boot code and must not be
+	 * needed afterwards.
+	 *
+	 * Currently used by SME for performing in-place encryption of the
+	 * kernel during boot. Resides on a 2MB boundary to simplify the
+	 * pagetable setup used for SME in-place encryption.
+	 */
+	. = ALIGN(HPAGE_SIZE);
+	.init.scratch : AT(ADDR(.init.scratch) - LOAD_OFFSET) {
+		__init_scratch_begin = .;
+		*(.init.scratch)
+		. = ALIGN(HPAGE_SIZE);
+		__init_scratch_end = .;
+	}
+#endif
+
 	STABS_DEBUG
 	DWARF_DEBUG
 
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index 4aa9b1480866..6a8dd483f7d9 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -73,6 +73,19 @@ struct sme_populate_pgd_data {
 	unsigned long vaddr_end;
 };
 
+/*
+ * This work area lives in the .init.scratch section, which lives outside of
+ * the kernel proper. It is sized to hold the intermediate copy buffer and
+ * more than enough pagetable pages.
+ *
+ * By using this section, the kernel can be encrypted in place and it
+ * avoids any possibility of boot parameters or initramfs images being
+ * placed such that the in-place encryption logic overwrites them.  This
+ * section is 2MB aligned to allow for simple pagetable setup using only
+ * PMD entries (see vmlinux.lds.S).
+ */
+static char sme_workarea[2 * PMD_PAGE_SIZE] __section(.init.scratch);
+
 static char sme_cmdline_arg[] __initdata = "mem_encrypt";
 static char sme_cmdline_on[]  __initdata = "on";
 static char sme_cmdline_off[] __initdata = "off";
@@ -314,8 +327,13 @@ void __init sme_encrypt_kernel(struct boot_params *bp)
 	}
 #endif
 
-	/* Set the encryption workarea to be immediately after the kernel */
-	workarea_start = kernel_end;
+	/*
+	 * We're running identity mapped, so we must obtain the address to the
+	 * SME encryption workarea using rip-relative addressing.
+	 */
+	asm ("lea sme_workarea(%%rip), %0"
+	     : "=r" (workarea_start)
+	     : "p" (sme_workarea));
 
 	/*
 	 * Calculate required number of workarea bytes needed:
-- 
2.17.1