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 14/18] x86/asm/64: Return to userspace from the trampoline stack
Date: Tue, 21 Nov 2017 20:44:09 -0800 [thread overview]
Message-ID: <d59728f48b509805eb3807fc3851d12a1e6a8bbf.1511325444.git.luto@kernel.org> (raw)
In-Reply-To: <cover.1511325444.git.luto@kernel.org>
In-Reply-To: <cover.1511325444.git.luto@kernel.org>
By itself, this is useless. It gives us the ability to run some final
code before exit that cannnot run on the kernel stack. This could
include a CR3 switch a la KAISER or some kernel stack erasing, for
example. (Or even weird things like *changing* which kernel stack
gets used as an ASLR-strengthening mechanism.)
The SYSRET32 path is not covered yet. It could be in the future or
we could just ignore it and force the slow path if needed.
Signed-off-by: Andy Lutomirski <luto@kernel.org>
---
arch/x86/entry/entry_64.S | 55 +++++++++++++++++++++++++++++++++++++++++++----
1 file changed, 51 insertions(+), 4 deletions(-)
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index d55785e9dc8e..1700712103b2 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -326,8 +326,24 @@ syscall_return_via_sysret:
popq %rsi /* skip rcx */
popq %rdx
popq %rsi
+
+ /*
+ * Now all regs are restored except RSP and RDI.
+ * Save old stack pointer and switch to trampoline stack.
+ */
+ movq %rsp, %rdi
+ movq PER_CPU_VAR(cpu_tss + TSS_sp0), %rsp
+
+ pushq RSP-RDI(%rdi) /* RSP */
+ pushq (%rdi) /* RDI */
+
+ /*
+ * We are on the trampoline stack. All regs except RDI are live.
+ * We can do future final exit work right here.
+ */
+
popq %rdi
- movq RSP-ORIG_RAX(%rsp), %rsp
+ popq %rsp
USERGS_SYSRET64
END(entry_SYSCALL_64)
@@ -634,10 +650,41 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode)
ud2
1:
#endif
- SWAPGS
POP_EXTRA_REGS
- POP_C_REGS
- addq $8, %rsp /* skip regs->orig_ax */
+ popq %r11
+ popq %r10
+ popq %r9
+ popq %r8
+ popq %rax
+ popq %rcx
+ popq %rdx
+ popq %rsi
+
+ /*
+ * The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS.
+ * Save old stack pointer and switch to trampoline stack.
+ */
+ movq %rsp, %rdi
+ movq PER_CPU_VAR(cpu_tss + TSS_sp0), %rsp
+
+ /* Copy the IRET frame to the trampoline stack. */
+ pushq 6*8(%rdi) /* SS */
+ pushq 5*8(%rdi) /* RSP */
+ pushq 4*8(%rdi) /* EFLAGS */
+ pushq 3*8(%rdi) /* CS */
+ pushq 2*8(%rdi) /* RIP */
+
+ /* Push user RDI on the trampoline stack. */
+ pushq (%rdi)
+
+ /*
+ * We are on the trampoline stack. All regs except RDI are live.
+ * We can do future final exit work right here.
+ */
+
+ /* Restore RDI. */
+ popq %rdi
+ SWAPGS
INTERRUPT_RETURN
--
2.13.6
next prev parent reply other threads:[~2017-11-22 4:45 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 ` [PATCH v2 09/18] x86/asm: Move SYSENTER_stack to the beginning of struct tss_struct Andy Lutomirski
2017-11-23 12:00 ` 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 ` Andy Lutomirski [this message]
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=d59728f48b509805eb3807fc3851d12a1e6a8bbf.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
all inboxes | Powered by JetHome®