linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Joerg Roedel <joro@8bytes.org>
To: Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@kernel.org>, "H . Peter Anvin" <hpa@zytor.com>
Cc: x86@kernel.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Andy Lutomirski <luto@kernel.org>,
	Dave Hansen <dave.hansen@intel.com>,
	Josh Poimboeuf <jpoimboe@redhat.com>,
	Juergen Gross <jgross@suse.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Borislav Petkov <bp@alien8.de>, Jiri Kosina <jkosina@suse.cz>,
	Boris Ostrovsky <boris.ostrovsky@oracle.com>,
	Brian Gerst <brgerst@gmail.com>,
	David Laight <David.Laight@aculab.com>,
	Denys Vlasenko <dvlasenk@redhat.com>,
	Eduardo Valentin <eduval@amazon.com>,
	Greg KH <gregkh@linuxfoundation.org>,
	Will Deacon <will.deacon@arm.com>,
	aliguori@amazon.com, daniel.gruss@iaik.tugraz.at,
	hughd@google.com, keescook@google.com,
	Andrea Arcangeli <aarcange@redhat.com>,
	Waiman Long <llong@redhat.com>, Pavel Machek <pavel@ucw.cz>,
	jroedel@suse.de, joro@8bytes.org
Subject: [PATCH 09/31] x86/entry/32: Leave the kernel via trampoline stack
Date: Fri,  9 Feb 2018 10:25:18 +0100	[thread overview]
Message-ID: <1518168340-9392-10-git-send-email-joro@8bytes.org> (raw)
In-Reply-To: <1518168340-9392-1-git-send-email-joro@8bytes.org>

From: Joerg Roedel <jroedel@suse.de>

Switch back to the trampoline stack before returning to
userspace.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 arch/x86/entry/entry_32.S | 55 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index e714b53..ba3d8c2 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -338,6 +338,59 @@
 .endm
 
 /*
+ * Switch back from the kernel stack to the entry stack.
+ *
+ * The %esp register must point to pt_regs on the task stack. It will
+ * first calculate the size of the stack-frame to copy, depending on
+ * whether we return to VM86 mode or not. With that it uses 'rep movsb'
+ * to copy the contents of the stack over to the entry stack.
+ *
+ * We must be very careful here, as we can't trust the contents of the
+ * task-stack once we switched to the entry-stack. When an NMI happens
+ * while on the entry-stack, the NMI handler will switch back to the top
+ * of the task stack, overwriting our stack-frame we are about to copy.
+ * Therefore we switch the stack only after everything is copied over.
+ */
+.macro SWITCH_TO_ENTRY_STACK
+
+	ALTERNATIVE     "", "jmp .Lend_\@", X86_FEATURE_XENPV
+
+	/* Bytes to copy */
+	movl	$PTREGS_SIZE, %ecx
+
+#ifdef CONFIG_VM86
+	testl	$(X86_EFLAGS_VM), PT_EFLAGS(%esp)
+	jz	.Lcopy_pt_regs_\@
+
+	/* Additional 4 registers to copy when returning to VM86 mode */
+	addl    $(4 * 4), %ecx
+
+.Lcopy_pt_regs_\@:
+#endif
+
+	/* Initialize source and destination for movsb */
+	movl	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %edi
+	subl	%ecx, %edi
+	movl	%esp, %esi
+
+	/* Save future stack pointer in %ebx */
+	movl %edi, %ebx
+
+	/* Copy over the stack-frame */
+	cld
+	rep movsb
+
+	/*
+	 * Switch to entry-stack - needs to happen after everything is
+	 * copied because the NMI handler will overwrite the task-stack
+	 * when on entry-stack
+	 */
+	movl	%ebx, %esp
+
+.Lend_\@:
+.endm
+
+/*
  * %eax: prev task
  * %edx: next task
  */
@@ -578,6 +631,7 @@ ENTRY(entry_SYSENTER_32)
 
 /* Opportunistic SYSEXIT */
 	TRACE_IRQS_ON			/* User mode traces as IRQs on. */
+	SWITCH_TO_ENTRY_STACK		/* Switch to per-cpu entry stack */
 	movl	PT_EIP(%esp), %edx	/* pt_regs->ip */
 	movl	PT_OLDESP(%esp), %ecx	/* pt_regs->sp */
 1:	mov	PT_FS(%esp), %fs
@@ -665,6 +719,7 @@ ENTRY(entry_INT80_32)
 
 restore_all:
 	TRACE_IRQS_IRET
+	SWITCH_TO_ENTRY_STACK
 .Lrestore_all_notrace:
 	CHECK_AND_APPLY_ESPFIX
 .Lrestore_nocheck:
-- 
2.7.4

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  parent reply	other threads:[~2018-02-09  9:25 UTC|newest]

Thread overview: 93+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-02-09  9:25 [PATCH 00/31 v2] PTI support for x86_32 Joerg Roedel
2018-02-09  9:25 ` [PATCH 01/31] x86/asm-offsets: Move TSS_sp0 and TSS_sp1 to asm-offsets.c Joerg Roedel
2018-02-09  9:25 ` [PATCH 02/31] x86/entry/32: Rename TSS_sysenter_sp0 to TSS_entry_stack Joerg Roedel
2018-02-09  9:25 ` [PATCH 03/31] x86/entry/32: Load task stack from x86_tss.sp1 in SYSENTER handler Joerg Roedel
2018-02-09  9:25 ` [PATCH 04/31] x86/entry/32: Put ESPFIX code into a macro Joerg Roedel
2018-02-09  9:25 ` [PATCH 05/31] x86/entry/32: Unshare NMI return path Joerg Roedel
2018-02-09  9:25 ` [PATCH 06/31] x86/entry/32: Split off return-to-kernel path Joerg Roedel
2018-02-09  9:25 ` [PATCH 07/31] x86/entry/32: Restore segments before int registers Joerg Roedel
2018-02-09  9:25 ` [PATCH 08/31] x86/entry/32: Enter the kernel via trampoline stack Joerg Roedel
2018-02-09  9:25 ` Joerg Roedel [this message]
2018-02-09 17:05   ` [PATCH 09/31] x86/entry/32: Leave " Linus Torvalds
2018-02-09 17:17     ` Denys Vlasenko
2018-02-10 15:26       ` David Laight
2018-02-10 20:18         ` Linus Torvalds
2018-02-09 17:43     ` Andy Lutomirski
2018-02-09 19:06       ` Joerg Roedel
2018-02-09 19:02     ` Joerg Roedel
2018-02-09 19:17       ` Linus Torvalds
2018-02-09 19:25         ` Joerg Roedel
2018-02-09 19:48           ` Linus Torvalds
2018-02-10 15:41             ` David Laight
2018-02-09 19:30       ` Denys Vlasenko
2018-02-09  9:25 ` [PATCH 10/31] x86/entry/32: Introduce SAVE_ALL_NMI and RESTORE_ALL_NMI Joerg Roedel
2018-02-09  9:25 ` [PATCH 11/31] x86/entry/32: Add PTI cr3 switches to NMI handler code Joerg Roedel
2018-02-09  9:25 ` [PATCH 12/31] x86/entry/32: Add PTI cr3 switch to non-NMI entry/exit points Joerg Roedel
2018-02-27 19:18   ` Waiman Long
2018-03-01 12:03     ` Joerg Roedel
2018-03-01 13:34     ` Joerg Roedel
2018-03-01 14:33       ` Waiman Long
2018-03-01 16:50         ` Joerg Roedel
2018-03-01 18:24           ` Brian Gerst
2018-03-01 18:36             ` Dave Hansen
2018-03-01 18:38             ` Linus Torvalds
2018-03-02  9:10               ` Joerg Roedel
2018-03-16 20:55                 ` Andy Lutomirski
2018-03-02  9:07             ` Joerg Roedel
2018-02-09  9:25 ` [PATCH 13/31] x86/entry/32: Handle Entry from Kernel-Mode on Entry-Stack Joerg Roedel
2018-02-09  9:25 ` [PATCH 14/31] x86/pgtable/pae: Unshare kernel PMDs when PTI is enabled Joerg Roedel
2018-02-09  9:25 ` [PATCH 15/31] x86/pgtable/32: Allocate 8k page-tables " Joerg Roedel
2018-02-09  9:25 ` [PATCH 16/31] x86/pgtable: Move pgdp kernel/user conversion functions to pgtable.h Joerg Roedel
2018-02-09  9:25 ` [PATCH 17/31] x86/pgtable: Move pti_set_user_pgd() " Joerg Roedel
2018-02-09  9:25 ` [PATCH 18/31] x86/pgtable: Move two more functions from pgtable_64.h " Joerg Roedel
2018-02-09  9:25 ` [PATCH 19/31] x86/mm/pae: Populate valid user PGD entries Joerg Roedel
2018-02-14  9:45   ` Juergen Gross
2018-02-14 10:00     ` Joerg Roedel
2018-02-09  9:25 ` [PATCH 20/31] x86/mm/pae: Populate the user page-table with user pgd's Joerg Roedel
2018-02-09 17:48   ` Andy Lutomirski
2018-02-09 19:09     ` Joerg Roedel
2018-02-09  9:25 ` [PATCH 21/31] x86/mm/legacy: " Joerg Roedel
2018-02-09  9:25 ` [PATCH 22/31] x86/mm/pti: Add an overflow check to pti_clone_pmds() Joerg Roedel
2018-02-09  9:25 ` [PATCH 23/31] x86/mm/pti: Define X86_CR3_PTI_PCID_USER_BIT on x86_32 Joerg Roedel
2018-02-09 17:42   ` Andy Lutomirski
2018-02-09  9:25 ` [PATCH 24/31] x86/mm/pti: Clone CPU_ENTRY_AREA on PMD level " Joerg Roedel
2018-02-09  9:25 ` [PATCH 25/31] x86/mm/dump_pagetables: Define INIT_PGD Joerg Roedel
2018-02-09  9:25 ` [PATCH 26/31] x86/pgtable/pae: Use separate kernel PMDs for user page-table Joerg Roedel
2018-02-09  9:25 ` [PATCH 27/31] x86/ldt: Reserve address-space range on 32 bit for the LDT Joerg Roedel
2018-02-09  9:25 ` [PATCH 28/31] x86/ldt: Define LDT_END_ADDR Joerg Roedel
2018-02-09  9:25 ` [PATCH 29/31] x86/ldt: Split out sanity check in map_ldt_struct() Joerg Roedel
2018-02-09  9:25 ` [PATCH 30/31] x86/ldt: Enable LDT user-mapping for PAE Joerg Roedel
2018-02-09  9:25 ` [PATCH 31/31] x86/pti: Allow CONFIG_PAGE_TABLE_ISOLATION for x86_32 Joerg Roedel
2018-02-09 12:11 ` [PATCH 00/31 v2] PTI support " Juergen Gross
2018-02-09 13:35   ` Joerg Roedel
2018-02-09 13:54     ` Andrew Cooper
2018-02-09 17:47 ` Andy Lutomirski
2018-02-09 19:11   ` Joerg Roedel
2018-02-10  9:15     ` Adam Borowski
2018-02-10 20:22       ` Linus Torvalds
2018-02-11 10:59         ` Adam Borowski
2018-02-11 17:40           ` Mark D Rustad
2018-02-11 19:42             ` Andy Lutomirski
2018-02-11 20:14               ` Linus Torvalds
2018-02-11 22:12               ` James Bottomley
2018-02-11 22:30                 ` Andy Lutomirski
2018-02-11 23:47                   ` James Bottomley
2018-02-11 22:34               ` Pavel Machek
2018-02-11 23:25               ` Alan Cox
2018-02-12 10:16                 ` Anders Larsen
2018-02-14 10:43               ` Pavel Machek
2018-02-15  3:44                 ` joe.korty
2018-02-16 14:34                   ` Pavel Machek
2018-02-13  8:54             ` Greg KH
2018-02-13 17:25               ` Linus Torvalds
2018-02-14  8:54                 ` Greg KH
2018-02-21 10:26                   ` Lorenzo Colitti
2018-02-21 16:59                     ` Arnd Bergmann
2018-02-22 11:10                       ` Greg KH
2018-02-22 11:18                         ` Arnd Bergmann
2018-03-06 15:39                 ` Jason A. Donenfeld
2018-02-11 19:13     ` Ingo Molnar
2018-02-12 14:51       ` Joerg Roedel
2018-02-09 21:09   ` Pavel Machek
2018-02-09 21:11     ` Linus Torvalds
2018-02-09 21:28     ` Andrew Cooper

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=1518168340-9392-10-git-send-email-joro@8bytes.org \
    --to=joro@8bytes.org \
    --cc=David.Laight@aculab.com \
    --cc=aarcange@redhat.com \
    --cc=aliguori@amazon.com \
    --cc=boris.ostrovsky@oracle.com \
    --cc=bp@alien8.de \
    --cc=brgerst@gmail.com \
    --cc=daniel.gruss@iaik.tugraz.at \
    --cc=dave.hansen@intel.com \
    --cc=dvlasenk@redhat.com \
    --cc=eduval@amazon.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=hpa@zytor.com \
    --cc=hughd@google.com \
    --cc=jgross@suse.com \
    --cc=jkosina@suse.cz \
    --cc=jpoimboe@redhat.com \
    --cc=jroedel@suse.de \
    --cc=keescook@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=llong@redhat.com \
    --cc=luto@kernel.org \
    --cc=mingo@kernel.org \
    --cc=pavel@ucw.cz \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    --cc=will.deacon@arm.com \
    --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).