linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Andy Lutomirski <luto@kernel.org>
To: X86 ML <x86@kernel.org>
Cc: Borislav Petkov <bpetkov@suse.de>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	Brian Gerst <brgerst@gmail.com>,
	Dave Hansen <dave.hansen@intel.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Josh Poimboeuf <jpoimboe@redhat.com>,
	Andy Lutomirski <luto@kernel.org>
Subject: [PATCH v2 09/18] x86/asm: Move SYSENTER_stack to the beginning of struct tss_struct
Date: Tue, 21 Nov 2017 20:44:04 -0800	[thread overview]
Message-ID: <4195a4db127cbf769666e283f5dba551d29d5ef0.1511325444.git.luto@kernel.org> (raw)
In-Reply-To: <cover.1511325444.git.luto@kernel.org>
In-Reply-To: <cover.1511325444.git.luto@kernel.org>

I want SYSENTER_stack to have reliable overflow detection, which
means that it needs to be at the bottom of a page, not the top.
Move it to the beginning of struct tss_struct and page-align it.

Also add an assertion to make sure that the fixed hardware TSS
doesn't cross a page boundary.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
---
 arch/x86/include/asm/processor.h | 21 ++++++++++++---------
 arch/x86/kernel/cpu/common.c     | 22 ++++++++++++++++++++++
 2 files changed, 34 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index d32a3c88a968..8f5dac9dfbdc 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -327,7 +327,16 @@ struct x86_hw_tss {
 
 struct tss_struct {
 	/*
-	 * The hardware state:
+	 * Space for the temporary SYSENTER stack, used for SYSENTER
+	 * and the entry trampoline as well.
+	 */
+	unsigned long		SYSENTER_stack_canary;
+	unsigned long		SYSENTER_stack[64];
+
+	/*
+	 * The fixed hardware portion.  This must not cross a page boundary
+	 * at risk of violating the SDM's advice and potentially triggering
+	 * errata.
 	 */
 	struct x86_hw_tss	x86_tss;
 
@@ -338,15 +347,9 @@ struct tss_struct {
 	 * be within the limit.
 	 */
 	unsigned long		io_bitmap[IO_BITMAP_LONGS + 1];
+} __attribute__((__aligned__(PAGE_SIZE)));
 
-	/*
-	 * Space for the temporary SYSENTER stack.
-	 */
-	unsigned long		SYSENTER_stack_canary;
-	unsigned long		SYSENTER_stack[64];
-} ____cacheline_aligned;
-
-DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss);
+DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss);
 
 /*
  * sizeof(unsigned long) coming from an extra "long" at the end
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 099fca92f6be..1868fe693fe1 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -509,6 +509,28 @@ static inline void setup_cpu_entry_area(int cpu)
 #endif
 
 	__set_fixmap(get_cpu_entry_area_index(cpu, gdt), get_cpu_gdt_paddr(cpu), gdt_prot);
+
+	/*
+	 *
+	 * The Intel SDM says (Volume 3, 7.2.1):
+	 *
+	 *  Avoid placing a page boundary in the part of the TSS that the
+	 *  processor reads during a task switch (the first 104 bytes). The
+	 *  processor may not correctly perform address translations if a
+	 *  boundary occurs in this area. During a task switch, the processor
+	 *  reads and writes into the first 104 bytes of each TSS (using
+	 *  contiguous physical addresses beginning with the physical address
+	 *  of the first byte of the TSS). So, after TSS access begins, if
+	 *  part of the 104 bytes is not physically contiguous, the processor
+	 *  will access incorrect information without generating a page-fault
+	 *  exception.
+	 *
+	 * There are also a lot of errata involving the TSS spanning a page
+	 * boundary.  Assert that we're not doing that.
+	 */
+	BUILD_BUG_ON((offsetof(struct tss_struct, x86_tss) ^
+		      offsetofend(struct tss_struct, x86_tss)) & PAGE_MASK);
+
 }
 
 /* Load the original GDT from the per-cpu structure */
-- 
2.13.6

  parent reply	other threads:[~2017-11-22  4:46 UTC|newest]

Thread overview: 64+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-11-22  4:43 [PATCH v2 00/18] Entry stack switching Andy Lutomirski
2017-11-22  4:43 ` [PATCH v2 01/18] x86/entry/64: Fix entry_SYSCALL_64_after_hwframe IRQ tracing Andy Lutomirski
2017-11-22  5:35   ` Ingo Molnar
2017-11-22  7:45   ` [tip:x86/urgent] x86/entry/64: Fix entry_SYSCALL_64_after_hwframe() " tip-bot for Andy Lutomirski
2017-11-22  4:43 ` [PATCH v2 02/18] x86/asm/64: Allocate and enable the SYSENTER stack Andy Lutomirski
2017-11-22  4:43 ` [PATCH v2 03/18] x86/dumpstack: Add get_stack_info() support for " Andy Lutomirski
2017-11-22 12:10   ` Borislav Petkov
2017-11-22  4:43 ` [PATCH v2 04/18] x86/gdt: Put per-cpu GDT remaps in ascending order Andy Lutomirski
2017-11-22 11:05   ` Borislav Petkov
2017-11-22 15:26     ` Andy Lutomirski
2017-11-22  4:44 ` [PATCH v2 05/18] x86/fixmap: Generalize the GDT fixmap mechanism Andy Lutomirski
2017-11-22 15:33   ` Borislav Petkov
2017-11-22 17:16     ` Andy Lutomirski
2017-11-22 17:32       ` Borislav Petkov
2017-11-23 15:24         ` Andy Lutomirski
2017-11-23 19:24   ` Thomas Gleixner
2017-11-22  4:44 ` [PATCH v2 06/18] x86/kasan/64: Teach KASAN about the cpu_entry_area Andy Lutomirski
2017-11-22  6:19   ` Ingo Molnar
2017-11-22  9:05   ` Andrey Ryabinin
2017-11-22 15:22     ` Andy Lutomirski
2017-11-23 10:08       ` Andrey Ryabinin
2017-11-23 15:22         ` Andy Lutomirski
2017-11-22  4:44 ` [PATCH v2 07/18] x86/asm: Fix assumptions that the HW TSS is at the beginning of cpu_tss Andy Lutomirski
2017-11-22 19:06   ` Borislav Petkov
2017-11-22  4:44 ` [PATCH v2 08/18] x86/dumpstack: Handle stack overflow on all stacks Andy Lutomirski
2017-11-23 11:19   ` Borislav Petkov
2017-11-22  4:44 ` Andy Lutomirski [this message]
2017-11-23 12:00   ` [PATCH v2 09/18] x86/asm: Move SYSENTER_stack to the beginning of struct tss_struct Borislav Petkov
2017-11-23 13:16   ` Denys Vlasenko
2017-11-23 15:02     ` Andy Lutomirski
2017-11-23 19:30   ` Thomas Gleixner
2017-11-22  4:44 ` [PATCH v2 10/18] x86/asm: Remap the TSS into the cpu entry area Andy Lutomirski
2017-11-23 19:32   ` Thomas Gleixner
2017-11-23 19:55   ` Borislav Petkov
2017-11-23 20:15     ` Andy Lutomirski
2017-11-23 20:37       ` Borislav Petkov
2017-11-24  2:40         ` Andy Lutomirski
2017-11-24  4:17           ` Andy Lutomirski
2017-11-22  4:44 ` [PATCH v2 11/18] x86/asm/64: Separate cpu_current_top_of_stack from TSS.sp0 Andy Lutomirski
2017-11-23 19:34   ` Thomas Gleixner
2017-11-22  4:44 ` [PATCH v2 12/18] x86/espfix/64: Stop assuming that pt_regs is on the entry stack Andy Lutomirski
2017-11-23 19:36   ` Thomas Gleixner
2017-11-22  4:44 ` [PATCH v2 13/18] x86/asm/64: Use a percpu trampoline stack for IDT entries Andy Lutomirski
2017-11-23 23:44   ` Thomas Gleixner
2017-11-24  4:14     ` Andy Lutomirski
2017-11-22  4:44 ` [PATCH v2 14/18] x86/asm/64: Return to userspace from the trampoline stack Andy Lutomirski
2017-11-22  4:44 ` [PATCH v2 15/18] x86/entry/64: Create a percpu SYSCALL entry trampoline Andy Lutomirski
2017-11-22  4:44 ` [PATCH v2 16/18] x86/irq: Remove an old outdated comment about context tracking races Andy Lutomirski
2017-11-22  4:44 ` [PATCH v2 17/18] x86/irq/64: In the stack overflow warning, print the offending IP Andy Lutomirski
2017-11-22  4:44 ` [PATCH v2 18/18] x86/entry/64: Move the IST stacks into cpu_entry_area Andy Lutomirski
2017-11-22  6:22 ` [PATCH v2 00/18] Entry stack switching Ingo Molnar
2017-11-22  6:36   ` Ingo Molnar
2017-11-22 16:23   ` Andy Lutomirski
2017-11-23  6:21     ` Ingo Molnar
2017-11-23  6:44       ` Ingo Molnar
2017-11-23  6:58         ` Ingo Molnar
2017-11-23 15:29           ` Andy Lutomirski
2017-11-23 16:41             ` Thomas Gleixner
2017-11-22  7:39 ` WARNING: can't dereference registers at ffffc90004dfff60 for ip error_entry+0x7d/0xd0 (Re: [PATCH v2 00/18] Entry stack switching) Ingo Molnar
2017-11-22  7:43   ` Ingo Molnar
2017-11-22 13:55   ` Josh Poimboeuf
2017-11-22 15:19     ` Andy Lutomirski
2017-11-22 15:56       ` Ingo Molnar
2017-11-22 16:35         ` Andy Lutomirski

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=4195a4db127cbf769666e283f5dba551d29d5ef0.1511325444.git.luto@kernel.org \
    --to=luto@kernel.org \
    --cc=bpetkov@suse.de \
    --cc=brgerst@gmail.com \
    --cc=dave.hansen@intel.com \
    --cc=jpoimboe@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=torvalds@linux-foundation.org \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).