mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Alexandre Chartre <alexandre.chartre@oracle.com>
To: tglx@linutronix.de, mingo@redhat.com, bp@alien8.de,
	hpa@zytor.com, x86@kernel.org, dave.hansen@linux.intel.com,
	luto@kernel.org, peterz@infradead.org,
	linux-kernel@vger.kernel.org, thomas.lendacky@amd.com,
	jroedel@suse.de
Cc: konrad.wilk@oracle.com, jan.setjeeilers@oracle.com,
	junaids@google.com, oweisse@google.com, rppt@linux.vnet.ibm.com,
	graf@amazon.de, mgross@linux.intel.com, kuzuno@gmail.com,
	alexandre.chartre@oracle.com
Subject: [RFC][PATCH 07/24] x86/entry: Fill ESPFIX stack using C code
Date: Mon,  9 Nov 2020 15:44:08 +0100	[thread overview]
Message-ID: <20201109144425.270789-8-alexandre.chartre@oracle.com> (raw)
In-Reply-To: <20201109144425.270789-1-alexandre.chartre@oracle.com>

The ESPFIX stack is filled using assembly code. Move this code to a C
function so that it is easier to read and modify.

Signed-off-by: Alexandre Chartre <alexandre.chartre@oracle.com>
---
 arch/x86/entry/entry_64.S   | 62 ++++++++++++++++++-------------------
 arch/x86/kernel/espfix_64.c | 41 ++++++++++++++++++++++++
 2 files changed, 72 insertions(+), 31 deletions(-)

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 73e9cd47dc83..6e0b5b010e0b 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -684,8 +684,10 @@ native_irq_return_ldt:
 	 * long (see ESPFIX_STACK_SIZE).  espfix_waddr points to the bottom
 	 * of the ESPFIX stack.
 	 *
-	 * We clobber RAX and RDI in this code.  We stash RDI on the
-	 * normal stack and RAX on the ESPFIX stack.
+	 * We call into C code to fill the ESPFIX stack. We stash registers
+	 * that the C function can clobber on the normal stack. The user RAX
+	 * is stashed first so that it is adjacent to the iret frame which
+	 * will be copied to the ESPFIX stack.
 	 *
 	 * The ESPFIX stack layout we set up looks like this:
 	 *
@@ -699,39 +701,37 @@ native_irq_return_ldt:
 	 * --- bottom of ESPFIX stack ---
 	 */
 
-	pushq	%rdi				/* Stash user RDI */
-	SWAPGS					/* to kernel GS */
-	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi	/* to kernel CR3 */
-
-	movq	PER_CPU_VAR(espfix_waddr), %rdi
-	movq	%rax, (0*8)(%rdi)		/* user RAX */
-	movq	(1*8)(%rsp), %rax		/* user RIP */
-	movq	%rax, (1*8)(%rdi)
-	movq	(2*8)(%rsp), %rax		/* user CS */
-	movq	%rax, (2*8)(%rdi)
-	movq	(3*8)(%rsp), %rax		/* user RFLAGS */
-	movq	%rax, (3*8)(%rdi)
-	movq	(5*8)(%rsp), %rax		/* user SS */
-	movq	%rax, (5*8)(%rdi)
-	movq	(4*8)(%rsp), %rax		/* user RSP */
-	movq	%rax, (4*8)(%rdi)
-	/* Now RAX == RSP. */
-
-	andl	$0xffff0000, %eax		/* RAX = (RSP & 0xffff0000) */
+	/* save registers */
+	pushq	%rax
+	pushq	%rdi
+	pushq	%rsi
+	pushq	%rdx
+	pushq	%rcx
+	pushq	%r8
+	pushq	%r9
+	pushq	%r10
+	pushq	%r11
 
 	/*
-	 * espfix_stack[31:16] == 0.  The page tables are set up such that
-	 * (espfix_stack | (X & 0xffff0000)) points to a read-only alias of
-	 * espfix_waddr for any X.  That is, there are 65536 RO aliases of
-	 * the same page.  Set up RSP so that RSP[31:16] contains the
-	 * respective 16 bits of the /userspace/ RSP and RSP nonetheless
-	 * still points to an RO alias of the ESPFIX stack.
+	 * fill_espfix_stack will copy the iret+rax frame to the ESPFIX
+	 * stack and return with RAX containing a pointer to the ESPFIX
+	 * stack.
 	 */
-	orq	PER_CPU_VAR(espfix_stack), %rax
+	leaq	8*8(%rsp), %rdi		/* points to the iret+rax frame */
+	call	fill_espfix_stack
 
-	SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
-	SWAPGS					/* to user GS */
-	popq	%rdi				/* Restore user RDI */
+	/*
+	 * RAX contains a pointer to the ESPFIX, so restore registers but
+	 * RAX. RAX will be restored from the ESPFIX stack.
+	 */
+	popq	%r11
+	popq	%r10
+	popq	%r9
+	popq	%r8
+	popq	%rcx
+	popq	%rdx
+	popq	%rsi
+	popq	%rdi
 
 	movq	%rax, %rsp
 	UNWIND_HINT_IRET_REGS offset=8
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
index 4fe7af58cfe1..6a81c4bd1542 100644
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -33,6 +33,7 @@
 #include <asm/pgalloc.h>
 #include <asm/setup.h>
 #include <asm/espfix.h>
+#include <asm/entry-common.h>
 
 /*
  * Note: we only need 6*8 = 48 bytes for the espfix stack, but round
@@ -205,3 +206,43 @@ void init_espfix_ap(int cpu)
 	per_cpu(espfix_waddr, cpu) = (unsigned long)stack_page
 				      + (addr & ~PAGE_MASK);
 }
+
+/*
+ * iret frame with an additional user_rax register.
+ */
+struct iret_rax_frame {
+	unsigned long user_rax;
+	unsigned long rip;
+	unsigned long cs;
+	unsigned long rflags;
+	unsigned long rsp;
+	unsigned long ss;
+};
+
+noinstr unsigned long fill_espfix_stack(struct iret_rax_frame *frame)
+{
+	struct iret_rax_frame *espfix_frame;
+	unsigned long rsp;
+
+	native_swapgs();
+	switch_to_kernel_cr3();
+
+	espfix_frame = (struct iret_rax_frame *)this_cpu_read(espfix_waddr);
+	*espfix_frame = *frame;
+
+	/*
+	 * espfix_stack[31:16] == 0.  The page tables are set up such that
+	 * (espfix_stack | (X & 0xffff0000)) points to a read-only alias of
+	 * espfix_waddr for any X.  That is, there are 65536 RO aliases of
+	 * the same page.  Set up RSP so that RSP[31:16] contains the
+	 * respective 16 bits of the /userspace/ RSP and RSP nonetheless
+	 * still points to an RO alias of the ESPFIX stack.
+	 */
+	rsp = ((unsigned long)espfix_frame) & 0xffff0000;
+	rsp |= this_cpu_read(espfix_stack);
+
+	switch_to_user_cr3();
+	native_swapgs();
+
+	return rsp;
+}
-- 
2.18.4


  parent reply	other threads:[~2020-11-09 14:43 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-11-09 14:44 [RFC][PATCH 00/24] x86/pti: Defer CR3 switch to " Alexandre Chartre
2020-11-09 14:44 ` [RFC][PATCH 01/24] x86/syscall: Add wrapper for invoking syscall function Alexandre Chartre
2020-11-09 14:44 ` [RFC][PATCH 02/24] x86/entry: Update asm_call_on_stack to support more function arguments Alexandre Chartre
2020-11-09 14:44 ` [RFC][PATCH 03/24] x86/entry: Consolidate IST entry from userspace Alexandre Chartre
2020-11-09 14:44 ` [RFC][PATCH 04/24] x86/sev-es: Define a setup stack function for the VC idtentry Alexandre Chartre
2020-11-09 14:44 ` [RFC][PATCH 05/24] x86/entry: Implement ret_from_fork body with C code Alexandre Chartre
2020-11-09 14:44 ` [RFC][PATCH 06/24] x86/pti: Provide C variants of PTI switch CR3 macros Alexandre Chartre
2020-11-09 14:44 ` Alexandre Chartre [this message]
2020-11-09 14:44 ` [RFC][PATCH 08/24] x86/entry: Add C version of SWAPGS and SWAPGS_UNSAFE_STACK Alexandre Chartre
2020-11-09 19:55   ` Alexandre Chartre
2020-11-09 14:44 ` [RFC][PATCH 09/24] x86/entry: Add C version of paranoid_entry/exit Alexandre Chartre
2020-11-09 14:44 ` [RFC][PATCH 10/24] x86/pti: Introduce per-task PTI trampoline stack Alexandre Chartre
2020-11-09 14:44 ` [RFC][PATCH 11/24] x86/pti: Function to clone page-table entries from a specified mm Alexandre Chartre
2020-11-09 14:44 ` [RFC][PATCH 12/24] x86/pti: Function to map per-cpu page-table entry Alexandre Chartre
2020-11-09 14:44 ` [RFC][PATCH 13/24] x86/pti: Extend PTI user mappings Alexandre Chartre
2020-11-09 19:56   ` Alexandre Chartre
2020-11-10 23:39     ` Andy Lutomirski
2020-11-11  8:55       ` Alexandre Chartre
2020-11-09 14:44 ` [RFC][PATCH 14/24] x86/pti: Use PTI stack instead of trampoline stack Alexandre Chartre
2020-11-09 14:44 ` [RFC][PATCH 15/24] x86/pti: Execute syscall functions on the kernel stack Alexandre Chartre
2020-11-09 14:44 ` [RFC][PATCH 16/24] x86/pti: Execute IDT handlers " Alexandre Chartre
2020-11-09 14:44 ` [RFC][PATCH 17/24] x86/pti: Execute IDT handlers with error code " Alexandre Chartre
2020-11-09 14:44 ` [RFC][PATCH 18/24] x86/pti: Execute system vector handlers " Alexandre Chartre
2020-11-09 14:44 ` [RFC][PATCH 19/24] x86/pti: Execute page fault handler " Alexandre Chartre
2020-11-09 14:44 ` [RFC][PATCH 20/24] x86/pti: Execute NMI " Alexandre Chartre
2020-11-09 14:44 ` [RFC][PATCH 21/24] x86/entry: Disable stack-protector for IST entry C handlers Alexandre Chartre
2020-11-09 14:44 ` [RFC][PATCH 22/24] x86/entry: Defer paranoid entry/exit to C code Alexandre Chartre
2020-11-09 14:44 ` [RFC][PATCH 23/24] x86/entry: Remove paranoid_entry and paranoid_exit Alexandre Chartre
2020-11-09 14:44 ` [RFC][PATCH 24/24] x86/pti: Defer CR3 switch to C code for non-IST and syscall entries Alexandre Chartre
2020-11-09 19:35 ` [RFC][PATCH 00/24] x86/pti: Defer CR3 switch to C code Dave Hansen
2020-11-09 19:53   ` Alexandre Chartre
  -- strict thread matches above, loose matches on Subject: below --
2020-11-09 11:22 Alexandre Chartre
2020-11-09 11:23 ` [RFC][PATCH 07/24] x86/entry: Fill ESPFIX stack using " Alexandre Chartre

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=20201109144425.270789-8-alexandre.chartre@oracle.com \
    --to=alexandre.chartre@oracle.com \
    --cc=bp@alien8.de \
    --cc=dave.hansen@linux.intel.com \
    --cc=graf@amazon.de \
    --cc=hpa@zytor.com \
    --cc=jan.setjeeilers@oracle.com \
    --cc=jroedel@suse.de \
    --cc=junaids@google.com \
    --cc=konrad.wilk@oracle.com \
    --cc=kuzuno@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luto@kernel.org \
    --cc=mgross@linux.intel.com \
    --cc=mingo@redhat.com \
    --cc=oweisse@google.com \
    --cc=peterz@infradead.org \
    --cc=rppt@linux.vnet.ibm.com \
    --cc=tglx@linutronix.de \
    --cc=thomas.lendacky@amd.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

all inboxes | Powered by JetHome®