Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933774AbbFSVMN (ORCPT ); Fri, 19 Jun 2015 17:12:13 -0400 Received: from mail.linuxfoundation.org ([140.211.169.12]:51719 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756078AbbFSUjc (ORCPT ); Fri, 19 Jun 2015 16:39:32 -0400 From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Andy Lutomirski , "H. Peter Anvin" , Binutils , Borislav Petkov , "H.J. Lu" , Jan Beulich , Linus Torvalds , Peter Zijlstra , Thomas Gleixner , Ingo Molnar Subject: [PATCH 4.0 063/105] x86/asm/irq: Stop relying on magic JMP behavior for early_idt_handlers Date: Fri, 19 Jun 2015 13:35:53 -0700 Message-Id: <20150619203600.049309805@linuxfoundation.org> X-Mailer: git-send-email 2.4.4 In-Reply-To: <20150619203558.187802739@linuxfoundation.org> References: <20150619203558.187802739@linuxfoundation.org> User-Agent: quilt/0.64 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 8296 Lines: 255 4.0-stable review patch. If anyone has any objections, please let me know. ------------------ From: Andy Lutomirski commit 425be5679fd292a3c36cb1fe423086708a99f11a upstream. The early_idt_handlers asm code generates an array of entry points spaced nine bytes apart. It's not really clear from that code or from the places that reference it what's going on, and the code only works in the first place because GAS never generates two-byte JMP instructions when jumping to global labels. Clean up the code to generate the correct array stride (member size) explicitly. This should be considerably more robust against screw-ups, as GAS will warn if a .fill directive has a negative count. Using '. =' to advance would have been even more robust (it would generate an actual error if it tried to move backwards), but it would pad with nulls, confusing anyone who tries to disassemble the code. The new scheme should be much clearer to future readers. While we're at it, improve the comments and rename the array and common code. Binutils may start relaxing jumps to non-weak labels. If so, this change will fix our build, and we may need to backport this change. Before, on x86_64: 0000000000000000 : 0: 6a 00 pushq $0x0 2: 6a 00 pushq $0x0 4: e9 00 00 00 00 jmpq 9 5: R_X86_64_PC32 early_idt_handler-0x4 ... 48: 66 90 xchg %ax,%ax 4a: 6a 08 pushq $0x8 4c: e9 00 00 00 00 jmpq 51 4d: R_X86_64_PC32 early_idt_handler-0x4 ... 117: 6a 00 pushq $0x0 119: 6a 1f pushq $0x1f 11b: e9 00 00 00 00 jmpq 120 11c: R_X86_64_PC32 early_idt_handler-0x4 After: 0000000000000000 : 0: 6a 00 pushq $0x0 2: 6a 00 pushq $0x0 4: e9 14 01 00 00 jmpq 11d ... 48: 6a 08 pushq $0x8 4a: e9 d1 00 00 00 jmpq 120 4f: cc int3 50: cc int3 ... 117: 6a 00 pushq $0x0 119: 6a 1f pushq $0x1f 11b: eb 03 jmp 120 11d: cc int3 11e: cc int3 11f: cc int3 Signed-off-by: Andy Lutomirski Acked-by: H. Peter Anvin Cc: Binutils Cc: Borislav Petkov Cc: H.J. Lu Cc: Jan Beulich Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/ac027962af343b0c599cbfcf50b945ad2ef3d7a8.1432336324.git.luto@kernel.org Signed-off-by: Ingo Molnar Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/segment.h | 15 +++++++++++++-- arch/x86/kernel/head64.c | 2 +- arch/x86/kernel/head_32.S | 33 ++++++++++++++++++--------------- arch/x86/kernel/head_64.S | 20 +++++++++++--------- 4 files changed, 43 insertions(+), 27 deletions(-) --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -200,10 +200,21 @@ #define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES * 8) #ifdef __KERNEL__ + +/* + * early_idt_handler_array is an array of entry points referenced in the + * early IDT. For simplicity, it's a real array with one entry point + * every nine bytes. That leaves room for an optional 'push $0' if the + * vector has no error code (two bytes), a 'push $vector_number' (two + * bytes), and a jump to the common entry code (up to five bytes). + */ +#define EARLY_IDT_HANDLER_SIZE 9 + #ifndef __ASSEMBLY__ -extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][2+2+5]; + +extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE]; #ifdef CONFIG_TRACING -#define trace_early_idt_handlers early_idt_handlers +# define trace_early_idt_handler_array early_idt_handler_array #endif /* --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -167,7 +167,7 @@ asmlinkage __visible void __init x86_64_ clear_bss(); for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) - set_intr_gate(i, early_idt_handlers[i]); + set_intr_gate(i, early_idt_handler_array[i]); load_idt((const struct desc_ptr *)&idt_descr); copy_bootdata(__va(real_mode_data)); --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -477,21 +477,22 @@ is486: __INIT setup_once: /* - * Set up a idt with 256 entries pointing to ignore_int, - * interrupt gates. It doesn't actually load idt - that needs - * to be done on each CPU. Interrupts are enabled elsewhere, - * when we can be relatively sure everything is ok. + * Set up a idt with 256 interrupt gates that push zero if there + * is no error code and then jump to early_idt_handler_common. + * It doesn't actually load the idt - that needs to be done on + * each CPU. Interrupts are enabled elsewhere, when we can be + * relatively sure everything is ok. */ movl $idt_table,%edi - movl $early_idt_handlers,%eax + movl $early_idt_handler_array,%eax movl $NUM_EXCEPTION_VECTORS,%ecx 1: movl %eax,(%edi) movl %eax,4(%edi) /* interrupt gate, dpl=0, present */ movl $(0x8E000000 + __KERNEL_CS),2(%edi) - addl $9,%eax + addl $EARLY_IDT_HANDLER_SIZE,%eax addl $8,%edi loop 1b @@ -523,26 +524,28 @@ setup_once: andl $0,setup_once_ref /* Once is enough, thanks */ ret -ENTRY(early_idt_handlers) +ENTRY(early_idt_handler_array) # 36(%esp) %eflags # 32(%esp) %cs # 28(%esp) %eip # 24(%rsp) error code i = 0 .rept NUM_EXCEPTION_VECTORS - .if (EXCEPTION_ERRCODE_MASK >> i) & 1 - ASM_NOP2 - .else + .ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1 pushl $0 # Dummy error code, to make stack frame uniform .endif pushl $i # 20(%esp) Vector number - jmp early_idt_handler + jmp early_idt_handler_common i = i + 1 + .fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc .endr -ENDPROC(early_idt_handlers) +ENDPROC(early_idt_handler_array) - /* This is global to keep gas from relaxing the jumps */ -ENTRY(early_idt_handler) +early_idt_handler_common: + /* + * The stack is the hardware frame, an error code or zero, and the + * vector number. + */ cld cmpl $2,(%esp) # X86_TRAP_NMI @@ -602,7 +605,7 @@ ex_entry: is_nmi: addl $8,%esp /* drop vector number and error code */ iret -ENDPROC(early_idt_handler) +ENDPROC(early_idt_handler_common) /* This is the default interrupt "handler" :-) */ ALIGN --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -321,26 +321,28 @@ bad_address: jmp bad_address __INIT - .globl early_idt_handlers -early_idt_handlers: +ENTRY(early_idt_handler_array) # 104(%rsp) %rflags # 96(%rsp) %cs # 88(%rsp) %rip # 80(%rsp) error code i = 0 .rept NUM_EXCEPTION_VECTORS - .if (EXCEPTION_ERRCODE_MASK >> i) & 1 - ASM_NOP2 - .else + .ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1 pushq $0 # Dummy error code, to make stack frame uniform .endif pushq $i # 72(%rsp) Vector number - jmp early_idt_handler + jmp early_idt_handler_common i = i + 1 + .fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc .endr +ENDPROC(early_idt_handler_array) -/* This is global to keep gas from relaxing the jumps */ -ENTRY(early_idt_handler) +early_idt_handler_common: + /* + * The stack is the hardware frame, an error code or zero, and the + * vector number. + */ cld cmpl $2,(%rsp) # X86_TRAP_NMI @@ -412,7 +414,7 @@ ENTRY(early_idt_handler) is_nmi: addq $16,%rsp # drop vector number and error code INTERRUPT_RETURN -ENDPROC(early_idt_handler) +ENDPROC(early_idt_handler_common) __INITDATA -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in Please read the FAQ at http://www.tux.org/lkml/