All of lore.kernel.org
 help / color / mirror / Atom feed
From: Lai Jiangshan <jiangshanlai@gmail.com>
To: linux-kernel@vger.kernel.org
Cc: x86@kernel.org, Lai Jiangshan <laijs@linux.alibaba.com>,
	Andy Lutomirski <luto@kernel.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	"H. Peter Anvin" <hpa@zytor.com>, Juergen Gross <jgross@suse.com>,
	"Peter Zijlstra (Intel)" <peterz@infradead.org>,
	Joerg Roedel <jroedel@suse.de>,
	Jan Kiszka <jan.kiszka@siemens.com>
Subject: [PATCH V4 25/50] x86/entry: Use idtentry macro for entry_INT80_compat
Date: Tue, 26 Oct 2021 22:32:34 +0800	[thread overview]
Message-ID: <20211026143301.18895-2-jiangshanlai@gmail.com> (raw)
In-Reply-To: <20211026141420.17138-1-jiangshanlai@gmail.com>

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

entry_INT80_compat is identical to idtentry macro except a special
handling for %rax in the prolog.

Add the prolog to idtentry and use idtentry for entry_INT80_compat.

Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
---
 arch/x86/entry/entry_64.S        |  18 ++++++
 arch/x86/entry/entry_64_compat.S | 103 -------------------------------
 arch/x86/include/asm/idtentry.h  |  47 ++++++++++++++
 arch/x86/include/asm/proto.h     |   4 --
 4 files changed, 65 insertions(+), 107 deletions(-)

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 23de2a789e3d..79934c5ee9a1 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -372,6 +372,24 @@ SYM_CODE_START(\asmsym)
 		pushq	$-1			/* ORIG_RAX: no syscall to restart */
 	.endif
 
+	.if \vector == IA32_SYSCALL_VECTOR
+		/*
+		 * User tracing code (ptrace or signal handlers) might assume
+		 * that the saved RAX contains a 32-bit number when we're
+		 * invoking a 32-bit syscall.  Just in case the high bits are
+		 * nonzero, zero-extend the syscall number.  (This could almost
+		 * certainly be deleted with no ill effects.)
+		 */
+		movl	%eax, %eax
+
+		/*
+		 * do_int80_syscall_32() expects regs->orig_ax to be user ax,
+		 * and regs->ax to be $-ENOSYS.
+		 */
+		movq	%rax, (%rsp)
+		movq	$-ENOSYS, %rax
+	.endif
+
 	.if \vector == X86_TRAP_BP
 		/*
 		 * If coming from kernel space, create a 6-word gap to allow the
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 2a4d9532dfd5..ad20302246e4 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -311,106 +311,3 @@ sysret32_from_system_call:
 	swapgs
 	sysretl
 SYM_CODE_END(entry_SYSCALL_compat)
-
-/*
- * 32-bit legacy system call entry.
- *
- * 32-bit x86 Linux system calls traditionally used the INT $0x80
- * instruction.  INT $0x80 lands here.
- *
- * This entry point can be used by 32-bit and 64-bit programs to perform
- * 32-bit system calls.  Instances of INT $0x80 can be found inline in
- * various programs and libraries.  It is also used by the vDSO's
- * __kernel_vsyscall fallback for hardware that doesn't support a faster
- * entry method.  Restarted 32-bit system calls also fall back to INT
- * $0x80 regardless of what instruction was originally used to do the
- * system call.
- *
- * This is considered a slow path.  It is not used by most libc
- * implementations on modern hardware except during process startup.
- *
- * Arguments:
- * eax  system call number
- * ebx  arg1
- * ecx  arg2
- * edx  arg3
- * esi  arg4
- * edi  arg5
- * ebp  arg6
- */
-SYM_CODE_START(entry_INT80_compat)
-	UNWIND_HINT_EMPTY
-	/*
-	 * Interrupts are off on entry.
-	 */
-	ASM_CLAC			/* Do this early to minimize exposure */
-	SWAPGS
-
-	/*
-	 * User tracing code (ptrace or signal handlers) might assume that
-	 * the saved RAX contains a 32-bit number when we're invoking a 32-bit
-	 * syscall.  Just in case the high bits are nonzero, zero-extend
-	 * the syscall number.  (This could almost certainly be deleted
-	 * with no ill effects.)
-	 */
-	movl	%eax, %eax
-
-	/* switch to thread stack expects orig_ax and rdi to be pushed */
-	pushq	%rax			/* pt_regs->orig_ax */
-	pushq	%rdi			/* pt_regs->di */
-
-	/* Need to switch before accessing the thread stack. */
-	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
-
-	/* In the Xen PV case we already run on the thread stack. */
-	ALTERNATIVE "", "jmp .Lint80_keep_stack", X86_FEATURE_XENPV
-
-	movq	%rsp, %rdi
-	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
-
-	pushq	6*8(%rdi)		/* regs->ss */
-	pushq	5*8(%rdi)		/* regs->rsp */
-	pushq	4*8(%rdi)		/* regs->eflags */
-	pushq	3*8(%rdi)		/* regs->cs */
-	pushq	2*8(%rdi)		/* regs->ip */
-	pushq	1*8(%rdi)		/* regs->orig_ax */
-	pushq	(%rdi)			/* pt_regs->di */
-.Lint80_keep_stack:
-
-	pushq	%rsi			/* pt_regs->si */
-	xorl	%esi, %esi		/* nospec   si */
-	pushq	%rdx			/* pt_regs->dx */
-	xorl	%edx, %edx		/* nospec   dx */
-	pushq	%rcx			/* pt_regs->cx */
-	xorl	%ecx, %ecx		/* nospec   cx */
-	pushq	$-ENOSYS		/* pt_regs->ax */
-	pushq   %r8			/* pt_regs->r8 */
-	xorl	%r8d, %r8d		/* nospec   r8 */
-	pushq   %r9			/* pt_regs->r9 */
-	xorl	%r9d, %r9d		/* nospec   r9 */
-	pushq   %r10			/* pt_regs->r10*/
-	xorl	%r10d, %r10d		/* nospec   r10 */
-	pushq   %r11			/* pt_regs->r11 */
-	xorl	%r11d, %r11d		/* nospec   r11 */
-	pushq   %rbx                    /* pt_regs->rbx */
-	xorl	%ebx, %ebx		/* nospec   rbx */
-	pushq   %rbp                    /* pt_regs->rbp */
-	xorl	%ebp, %ebp		/* nospec   rbp */
-	pushq   %r12                    /* pt_regs->r12 */
-	xorl	%r12d, %r12d		/* nospec   r12 */
-	pushq   %r13                    /* pt_regs->r13 */
-	xorl	%r13d, %r13d		/* nospec   r13 */
-	pushq   %r14                    /* pt_regs->r14 */
-	xorl	%r14d, %r14d		/* nospec   r14 */
-	pushq   %r15                    /* pt_regs->r15 */
-	xorl	%r15d, %r15d		/* nospec   r15 */
-
-	UNWIND_HINT_REGS
-
-	cld
-
-	movq	%rsp, %rdi
-	call	do_int80_syscall_32
-	ALTERNATIVE "jmp swapgs_restore_regs_and_return_to_usermode",	\
-		"jmp xenpv_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
-SYM_CODE_END(entry_INT80_compat)
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index 6779def97591..49fabc3e3f0d 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -207,6 +207,20 @@ __visible noinstr void func(struct pt_regs *regs,			\
 									\
 static noinline void __##func(struct pt_regs *regs, u32 vector)
 
+/**
+ * DECLARE_IDTENTRY_IA32_EMULATION - Declare functions for int80
+ * @vector:	Vector number (ignored for C)
+ * @asm_func:	Function name of the entry point
+ * @cfunc:	The C handler called from the ASM entry point (ignored for C)
+ *
+ * Declares two functions:
+ * - The ASM entry point: asm_func
+ * - The XEN PV trap entry point: xen_##asm_func (maybe unused)
+ */
+#define DECLARE_IDTENTRY_IA32_EMULATION(vector, asm_func, cfunc)	\
+	asmlinkage void asm_func(void);					\
+	asmlinkage void xen_##asm_func(void)
+
 /**
  * DECLARE_IDTENTRY_SYSVEC - Declare functions for system vector entry points
  * @vector:	Vector number (ignored for C)
@@ -433,6 +447,35 @@ __visible noinstr void func(struct pt_regs *regs,			\
 #define DECLARE_IDTENTRY_ERRORCODE(vector, func)			\
 	idtentry vector asm_##func func has_error_code=1
 
+/*
+ * 32-bit legacy system call entry.
+ *
+ * 32-bit x86 Linux system calls traditionally used the INT $0x80
+ * instruction.  INT $0x80 lands here.
+ *
+ * This entry point can be used by 32-bit and 64-bit programs to perform
+ * 32-bit system calls.  Instances of INT $0x80 can be found inline in
+ * various programs and libraries.  It is also used by the vDSO's
+ * __kernel_vsyscall fallback for hardware that doesn't support a faster
+ * entry method.  Restarted 32-bit system calls also fall back to INT
+ * $0x80 regardless of what instruction was originally used to do the
+ * system call.
+ *
+ * This is considered a slow path.  It is not used by most libc
+ * implementations on modern hardware except during process startup.
+ *
+ * Arguments:
+ * eax  system call number
+ * ebx  arg1
+ * ecx  arg2
+ * edx  arg3
+ * esi  arg4
+ * edi  arg5
+ * ebp  arg6
+ */
+#define DECLARE_IDTENTRY_IA32_EMULATION(vector, asm_func, cfunc)	\
+	idtentry vector asm_func cfunc has_error_code=0
+
 /* Special case for 32bit IRET 'trap'. Do not emit ASM code */
 #define DECLARE_IDTENTRY_SW(vector, func)
 
@@ -634,6 +677,10 @@ DECLARE_IDTENTRY_IRQ(X86_TRAP_OTHER,	common_interrupt);
 DECLARE_IDTENTRY_IRQ(X86_TRAP_OTHER,	spurious_interrupt);
 #endif
 
+#ifdef CONFIG_IA32_EMULATION
+DECLARE_IDTENTRY_IA32_EMULATION(IA32_SYSCALL_VECTOR,	entry_INT80_compat, do_int80_syscall_32);
+#endif
+
 /* System vector entry points */
 #ifdef CONFIG_X86_LOCAL_APIC
 DECLARE_IDTENTRY_SYSVEC(ERROR_APIC_VECTOR,		sysvec_error_interrupt);
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index ee07b3cae213..7ca5619352e2 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -29,10 +29,6 @@ void entry_SYSENTER_compat(void);
 void __end_entry_SYSENTER_compat(void);
 void entry_SYSCALL_compat(void);
 void entry_SYSCALL_compat_safe_stack(void);
-void entry_INT80_compat(void);
-#ifdef CONFIG_XEN_PV
-void xen_entry_INT80_compat(void);
-#endif
 #endif
 
 void x86_configure_nx(void);
-- 
2.19.1.6.gb485710b


  parent reply	other threads:[~2021-10-26 14:33 UTC|newest]

Thread overview: 59+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-10-26 14:13 [PATCH V4 00/50] x86/entry/64: Convert a bunch of ASM entry code into C code Lai Jiangshan
2021-10-26 14:13 ` [PATCH V4 01/50] x86/entry: Add fence for kernel entry swapgs in paranoid_entry() Lai Jiangshan
2021-10-27 12:19   ` Borislav Petkov
2021-10-28  0:51     ` Lai Jiangshan
2021-10-26 14:13 ` [PATCH V4 02/50] x86/entry: Use the correct fence macro after swapgs in kernel CR3 Lai Jiangshan
2021-10-26 14:13 ` [PATCH V4 03/50] x86/traps: Remove stack-protector from traps.c Lai Jiangshan
2021-10-26 14:13 ` [PATCH V4 04/50] x86/xen: Add xenpv_restore_regs_and_return_to_usermode() Lai Jiangshan
2021-11-02  8:58   ` Borislav Petkov
2021-11-02  9:19     ` Lai Jiangshan
2021-11-02  9:49       ` Borislav Petkov
2021-11-02 11:22         ` H. Peter Anvin
2021-11-02 14:27           ` Borislav Petkov
2021-10-26 14:20 ` [PATCH V4 05/50] x86/entry: Use swapgs and native_iret directly in swapgs_restore_regs_and_return_to_usermode Lai Jiangshan
2021-10-26 14:20 ` [PATCH V4 06/50] compiler_types.h: Add __noinstr_section() for noinstr Lai Jiangshan
2021-10-26 14:24   ` Miguel Ojeda
2021-10-26 14:20 ` [PATCH V4 07/50] x86/entry: Introduce __entry_text for entry code written in C Lai Jiangshan
2021-10-26 14:20 ` [PATCH V4 08/50] x86/entry: Move PTI_USER_* to arch/x86/include/asm/processor-flags.h Lai Jiangshan
2021-10-26 14:20 ` [PATCH V4 09/50] x86: Remove unused kernel_to_user_p4dp() and user_to_kernel_p4dp() Lai Jiangshan
2021-10-26 14:20 ` [PATCH V4 10/50] x86: Replace PTI_PGTABLE_SWITCH_BIT with PTI_USER_PGTABLE_BIT Lai Jiangshan
2021-10-26 14:27 ` [PATCH V4 11/50] x86: Mark __native_read_cr3() & native_write_cr3() as __always_inline Lai Jiangshan
2021-10-26 14:27 ` [PATCH V4 12/50] x86/traps: Move the declaration of native_irq_return_iret into proto.h Lai Jiangshan
2021-10-26 14:27 ` [PATCH V4 13/50] x86/entry: Add arch/x86/entry/entry64.c for C entry code Lai Jiangshan
2021-10-26 14:27 ` [PATCH V4 14/50] x86/entry: Expose the address of .Lgs_change to entry64.c Lai Jiangshan
2021-10-26 14:27 ` [PATCH V4 15/50] x86/entry: Add C verion of SWITCH_TO_KERNEL_CR3 as switch_to_kernel_cr3() Lai Jiangshan
2021-10-26 14:27 ` [PATCH V4 16/50] x86/traps: Add fence_swapgs_{user,kernel}_entry() Lai Jiangshan
2021-10-26 14:27 ` [PATCH V4 17/50] x86/entry: Add C {user,kernel}_entry_swapgs_and_fence() Lai Jiangshan
2021-10-26 14:27 ` [PATCH V4 18/50] x86/traps: Move pt_regs only in fixup_bad_iret() Lai Jiangshan
2021-10-26 14:30 ` [PATCH V4 19/50] x86/entry: Switch the stack after error_entry() returns Lai Jiangshan
2021-10-26 14:30 ` [PATCH V4 20/50] x86/entry: move PUSH_AND_CLEAR_REGS out of error_entry Lai Jiangshan
2021-10-26 14:30 ` [PATCH V4 21/50] x86/entry: Move cld to the start of idtentry Lai Jiangshan
2021-10-26 14:30 ` [PATCH V4 22/50] x86/entry: Don't call error_entry for XENPV Lai Jiangshan
2021-10-26 14:30 ` [PATCH V4 23/50] x86/entry: Convert SWAPGS to swapgs in error_entry() Lai Jiangshan
2021-10-26 14:32 ` [PATCH V4 24/50] x86/entry: Implement the whole error_entry() as C code Lai Jiangshan
2021-10-26 14:32 ` Lai Jiangshan [this message]
2021-10-26 14:34 ` [PATCH V4 26/50] x86/entry: Convert SWAPGS to swapgs in entry_SYSENTER_compat() Lai Jiangshan
2021-10-26 14:34 ` [PATCH V4 27/50] x86: Remove the definition of SWAPGS Lai Jiangshan
2021-10-26 14:34 ` [PATCH V4 28/50] x86/entry: Make paranoid_exit() callable Lai Jiangshan
2021-10-26 14:34 ` [PATCH V4 29/50] x86/entry: Call paranoid_exit() in asm_exc_nmi() Lai Jiangshan
2021-10-26 14:34 ` [PATCH V4 30/50] x86/entry: move PUSH_AND_CLEAR_REGS out of paranoid_entry Lai Jiangshan
2021-10-26 14:34 ` [PATCH V4 31/50] x86/entry: Add the C version ist_switch_to_kernel_cr3() Lai Jiangshan
2021-10-26 14:34 ` [PATCH V4 32/50] x86/entry: Skip CR3 write when the saved CR3 is kernel CR3 in RESTORE_CR3 Lai Jiangshan
2021-10-26 14:34 ` [PATCH V4 33/50] x86/entry: Add the C version ist_restore_cr3() Lai Jiangshan
2021-10-26 14:34 ` [PATCH V4 34/50] x86/entry: Add the C version get_percpu_base() Lai Jiangshan
2021-10-26 14:34 ` [PATCH V4 35/50] x86/entry: Add the C version ist_switch_to_kernel_gsbase() Lai Jiangshan
2021-10-26 14:34 ` [PATCH V4 36/50] x86/entry: Implement the C version ist_paranoid_entry() Lai Jiangshan
2021-10-26 14:34 ` [PATCH V4 37/50] x86/entry: Implement the C version ist_paranoid_exit() Lai Jiangshan
2021-10-26 14:34 ` [PATCH V4 38/50] x86/entry: Add a C macro to define the function body for IST in .entry.text Lai Jiangshan
2021-10-26 14:34 ` [PATCH V4 39/50] x86/debug, mce: Use C entry code Lai Jiangshan
2021-10-26 14:34 ` [PATCH V4 40/50] x86/idtentry.h: Move the definitions *IDTENTRY_{MCE|DEBUG}* up Lai Jiangshan
2021-10-26 14:34 ` [PATCH V4 41/50] x86/nmi: Use DEFINE_IDTENTRY_NMI for nmi Lai Jiangshan
2021-10-26 14:34 ` [PATCH V4 42/50] x86/nmi: Use C entry code Lai Jiangshan
2021-10-26 14:34 ` [PATCH V4 43/50] x86/entry: Add a C macro to define the function body for IST in .entry.text with an error code Lai Jiangshan
2021-10-26 14:34 ` [PATCH V4 44/50] x86/doublefault: Use C entry code Lai Jiangshan
2021-10-26 14:38 ` [PATCH V4 45/50] x86/sev: Add and use ist_vc_switch_off_ist() Lai Jiangshan
2021-10-26 14:38 ` [PATCH V4 46/50] x86/sev: Use C entry code Lai Jiangshan
2021-10-26 14:38 ` [PATCH V4 47/50] x86/entry: Remove ASM function paranoid_entry() and paranoid_exit() Lai Jiangshan
2021-10-26 14:38 ` [PATCH V4 48/50] x86/entry: Remove the unused ASM macros Lai Jiangshan
2021-10-26 14:38 ` [PATCH V4 49/50] x86/entry: Remove save_ret from PUSH_AND_CLEAR_REGS Lai Jiangshan
2021-10-26 14:38 ` [PATCH V4 50/50] x86/syscall/64: Move the checking for sysret to C code Lai Jiangshan

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=20211026143301.18895-2-jiangshanlai@gmail.com \
    --to=jiangshanlai@gmail.com \
    --cc=bp@alien8.de \
    --cc=dave.hansen@linux.intel.com \
    --cc=hpa@zytor.com \
    --cc=jan.kiszka@siemens.com \
    --cc=jgross@suse.com \
    --cc=jroedel@suse.de \
    --cc=laijs@linux.alibaba.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luto@kernel.org \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    --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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.