linux-kernel - [PATCH RESEND] x86/entry: Don't write to CR3 when restoring to kernel CR3

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-next>] [day] [month] [year] [list]

Message-ID: <20230817121513.1382800-1-jackmanb@google.com>
Date:   Thu, 17 Aug 2023 12:15:13 +0000
From:   Brendan Jackman <jackmanb@...gle.com>
To:     luto@...nel.org
Cc:     tglx@...utronix.de, mingo@...hat.com, bp@...en8.de,
        dave.hansen@...ux.intel.com, x86@...nel.org, hpa@...or.com,
        linux-kernel@...r.kernel.org, laijs@...ux.alibaba.com,
        yosryahmed@...gle.com, reijiw@...gle.com, oweisse@...gle.com,
        Brendan Jackman <jackmanb@...gle.com>
Subject: [PATCH RESEND] x86/entry: Don't write to CR3 when restoring to kernel CR3

From: Lai Jiangshan <laijs@...ux.alibaba.com>

Skip resuming KERNEL pages since it is already KERNEL CR3

Signed-off-by: Lai Jiangshan <laijs@...ux.alibaba.com>
Signed-off-by: Brendan Jackman <jackmanb@...gle.com>
---

While staring at paranoid_exit I was confused about why we had this CR3
write, avoiding it seems like a free optimisation. The original commit
21e94459110252 ("x86/mm: Optimize RESTORE_CR3") says "Most NMI/paranoid
exceptions will not in fact change pagetables" but I didn't't understand
what the "most" was referring to. I then discovered this patch on the
mailing list, Andy said[1] that it looks correct so maybe now is the
time to merge it?

Note there's another patch in [1] as well, the benefit of that one is
not obvious to me though.

We've tested an equivalent patch in our internal kernel.

[1] https://lore.kernel.org/lkml/20200526043507.51977-3-laijs@linux.alibaba.com/
-- >8 --
 arch/x86/entry/calling.h | 13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index f6907627172b..b2458685d56e 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -236,14 +236,13 @@ For 32-bit we have the following conventions - kernel is built with
 .macro RESTORE_CR3 scratch_reg:req save_reg:req
 	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
 
-	ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
-
 	/*
-	 * KERNEL pages can always resume with NOFLUSH as we do
-	 * explicit flushes.
+	 * Skip resuming KERNEL pages since it is already KERNEL CR3.
 	 */
 	bt	$PTI_USER_PGTABLE_BIT, \save_reg
-	jnc	.Lnoflush_\@
+	jnc	.Lend_\@
+
+	ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
 
 	/*
 	 * Check if there's a pending flush for the user ASID we're
@@ -261,10 +260,6 @@ For 32-bit we have the following conventions - kernel is built with
 	SET_NOFLUSH_BIT \save_reg
 
 .Lwrcr3_\@:
-	/*
-	 * The CR3 write could be avoided when not changing its value,
-	 * but would require a CR3 read *and* a scratch register.
-	 */
 	movq	\save_reg, %cr3
 .Lend_\@:
 .endm
-- 
2.41.0.694.ge786442a9b-goog