diff options
Diffstat (limited to 'arch/x86/vdso/vdso32')
-rw-r--r-- | arch/x86/vdso/vdso32/.gitignore | 1 | ||||
-rw-r--r-- | arch/x86/vdso/vdso32/int80.S | 56 | ||||
-rw-r--r-- | arch/x86/vdso/vdso32/note.S | 44 | ||||
-rw-r--r-- | arch/x86/vdso/vdso32/sigreturn.S | 144 | ||||
-rw-r--r-- | arch/x86/vdso/vdso32/syscall.S | 77 | ||||
-rw-r--r-- | arch/x86/vdso/vdso32/sysenter.S | 116 | ||||
-rw-r--r-- | arch/x86/vdso/vdso32/vdso32.lds.S | 37 |
7 files changed, 475 insertions, 0 deletions
diff --git a/arch/x86/vdso/vdso32/.gitignore b/arch/x86/vdso/vdso32/.gitignore new file mode 100644 index 00000000000..e45fba9d0ce --- /dev/null +++ b/arch/x86/vdso/vdso32/.gitignore @@ -0,0 +1 @@ +vdso32.lds diff --git a/arch/x86/vdso/vdso32/int80.S b/arch/x86/vdso/vdso32/int80.S new file mode 100644 index 00000000000..b15b7c01aed --- /dev/null +++ b/arch/x86/vdso/vdso32/int80.S @@ -0,0 +1,56 @@ +/* + * Code for the vDSO. This version uses the old int $0x80 method. + * + * First get the common code for the sigreturn entry points. + * This must come first. + */ +#include "sigreturn.S" + + .text + .globl __kernel_vsyscall + .type __kernel_vsyscall,@function + ALIGN +__kernel_vsyscall: +.LSTART_vsyscall: + int $0x80 + ret +.LEND_vsyscall: + .size __kernel_vsyscall,.-.LSTART_vsyscall + .previous + + .section .eh_frame,"a",@progbits +.LSTARTFRAMEDLSI: + .long .LENDCIEDLSI-.LSTARTCIEDLSI +.LSTARTCIEDLSI: + .long 0 /* CIE ID */ + .byte 1 /* Version number */ + .string "zR" /* NUL-terminated augmentation string */ + .uleb128 1 /* Code alignment factor */ + .sleb128 -4 /* Data alignment factor */ + .byte 8 /* Return address register column */ + .uleb128 1 /* Augmentation value length */ + .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */ + .byte 0x0c /* DW_CFA_def_cfa */ + .uleb128 4 + .uleb128 4 + .byte 0x88 /* DW_CFA_offset, column 0x8 */ + .uleb128 1 + .align 4 +.LENDCIEDLSI: + .long .LENDFDEDLSI-.LSTARTFDEDLSI /* Length FDE */ +.LSTARTFDEDLSI: + .long .LSTARTFDEDLSI-.LSTARTFRAMEDLSI /* CIE pointer */ + .long .LSTART_vsyscall-. /* PC-relative start address */ + .long .LEND_vsyscall-.LSTART_vsyscall + .uleb128 0 + .align 4 +.LENDFDEDLSI: + .previous + + /* + * Pad out the segment to match the size of the sysenter.S version. + */ +VDSO32_vsyscall_eh_frame_size = 0x40 + .section .data,"aw",@progbits + .space VDSO32_vsyscall_eh_frame_size-(.LENDFDEDLSI-.LSTARTFRAMEDLSI), 0 + .previous diff --git a/arch/x86/vdso/vdso32/note.S b/arch/x86/vdso/vdso32/note.S new file mode 100644 index 00000000000..c83f2573469 --- /dev/null +++ b/arch/x86/vdso/vdso32/note.S @@ -0,0 +1,44 @@ +/* + * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text. + * Here we can supply some information useful to userland. + */ + +#include <linux/version.h> +#include <linux/elfnote.h> + +/* Ideally this would use UTS_NAME, but using a quoted string here + doesn't work. Remember to change this when changing the + kernel's name. */ +ELFNOTE_START(Linux, 0, "a") + .long LINUX_VERSION_CODE +ELFNOTE_END + +#ifdef CONFIG_XEN +/* + * Add a special note telling glibc's dynamic linker a fake hardware + * flavor that it will use to choose the search path for libraries in the + * same way it uses real hardware capabilities like "mmx". + * We supply "nosegneg" as the fake capability, to indicate that we + * do not like negative offsets in instructions using segment overrides, + * since we implement those inefficiently. This makes it possible to + * install libraries optimized to avoid those access patterns in someplace + * like /lib/i686/tls/nosegneg. Note that an /etc/ld.so.conf.d/file + * corresponding to the bits here is needed to make ldconfig work right. + * It should contain: + * hwcap 1 nosegneg + * to match the mapping of bit to name that we give here. + * + * At runtime, the fake hardware feature will be considered to be present + * if its bit is set in the mask word. So, we start with the mask 0, and + * at boot time we set VDSO_NOTE_NONEGSEG_BIT if running under Xen. + */ + +#include "../../xen/vdso.h" /* Defines VDSO_NOTE_NONEGSEG_BIT. */ + +ELFNOTE_START(GNU, 2, "a") + .long 1 /* ncaps */ +VDSO32_NOTE_MASK: /* Symbol used by arch/x86/xen/setup.c */ + .long 0 /* mask */ + .byte VDSO_NOTE_NONEGSEG_BIT; .asciz "nosegneg" /* bit, name */ +ELFNOTE_END +#endif diff --git a/arch/x86/vdso/vdso32/sigreturn.S b/arch/x86/vdso/vdso32/sigreturn.S new file mode 100644 index 00000000000..31776d0efc8 --- /dev/null +++ b/arch/x86/vdso/vdso32/sigreturn.S @@ -0,0 +1,144 @@ +/* + * Common code for the sigreturn entry points in vDSO images. + * So far this code is the same for both int80 and sysenter versions. + * This file is #include'd by int80.S et al to define them first thing. + * The kernel assumes that the addresses of these routines are constant + * for all vDSO implementations. + */ + +#include <linux/linkage.h> +#include <asm/unistd_32.h> +#include <asm/asm-offsets.h> + +#ifndef SYSCALL_ENTER_KERNEL +#define SYSCALL_ENTER_KERNEL int $0x80 +#endif + + .text + .globl __kernel_sigreturn + .type __kernel_sigreturn,@function + ALIGN +__kernel_sigreturn: +.LSTART_sigreturn: + popl %eax /* XXX does this mean it needs unwind info? */ + movl $__NR_sigreturn, %eax + SYSCALL_ENTER_KERNEL +.LEND_sigreturn: + nop + .size __kernel_sigreturn,.-.LSTART_sigreturn + + .globl __kernel_rt_sigreturn + .type __kernel_rt_sigreturn,@function + ALIGN +__kernel_rt_sigreturn: +.LSTART_rt_sigreturn: + movl $__NR_rt_sigreturn, %eax + SYSCALL_ENTER_KERNEL +.LEND_rt_sigreturn: + nop + .size __kernel_rt_sigreturn,.-.LSTART_rt_sigreturn + .previous + + .section .eh_frame,"a",@progbits +.LSTARTFRAMEDLSI1: + .long .LENDCIEDLSI1-.LSTARTCIEDLSI1 +.LSTARTCIEDLSI1: + .long 0 /* CIE ID */ + .byte 1 /* Version number */ + .string "zRS" /* NUL-terminated augmentation string */ + .uleb128 1 /* Code alignment factor */ + .sleb128 -4 /* Data alignment factor */ + .byte 8 /* Return address register column */ + .uleb128 1 /* Augmentation value length */ + .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */ + .byte 0 /* DW_CFA_nop */ + .align 4 +.LENDCIEDLSI1: + .long .LENDFDEDLSI1-.LSTARTFDEDLSI1 /* Length FDE */ +.LSTARTFDEDLSI1: + .long .LSTARTFDEDLSI1-.LSTARTFRAMEDLSI1 /* CIE pointer */ + /* HACK: The dwarf2 unwind routines will subtract 1 from the + return address to get an address in the middle of the + presumed call instruction. Since we didn't get here via + a call, we need to include the nop before the real start + to make up for it. */ + .long .LSTART_sigreturn-1-. /* PC-relative start address */ + .long .LEND_sigreturn-.LSTART_sigreturn+1 + .uleb128 0 /* Augmentation */ + /* What follows are the instructions for the table generation. + We record the locations of each register saved. This is + complicated by the fact that the "CFA" is always assumed to + be the value of the stack pointer in the caller. This means + that we must define the CFA of this body of code to be the + saved value of the stack pointer in the sigcontext. Which + also means that there is no fixed relation to the other + saved registers, which means that we must use DW_CFA_expression + to compute their addresses. It also means that when we + adjust the stack with the popl, we have to do it all over again. */ + +#define do_cfa_expr(offset) \ + .byte 0x0f; /* DW_CFA_def_cfa_expression */ \ + .uleb128 1f-0f; /* length */ \ +0: .byte 0x74; /* DW_OP_breg4 */ \ + .sleb128 offset; /* offset */ \ + .byte 0x06; /* DW_OP_deref */ \ +1: + +#define do_expr(regno, offset) \ + .byte 0x10; /* DW_CFA_expression */ \ + .uleb128 regno; /* regno */ \ + .uleb128 1f-0f; /* length */ \ +0: .byte 0x74; /* DW_OP_breg4 */ \ + .sleb128 offset; /* offset */ \ +1: + + do_cfa_expr(IA32_SIGCONTEXT_sp+4) + do_expr(0, IA32_SIGCONTEXT_ax+4) + do_expr(1, IA32_SIGCONTEXT_cx+4) + do_expr(2, IA32_SIGCONTEXT_dx+4) + do_expr(3, IA32_SIGCONTEXT_bx+4) + do_expr(5, IA32_SIGCONTEXT_bp+4) + do_expr(6, IA32_SIGCONTEXT_si+4) + do_expr(7, IA32_SIGCONTEXT_di+4) + do_expr(8, IA32_SIGCONTEXT_ip+4) + + .byte 0x42 /* DW_CFA_advance_loc 2 -- nop; popl eax. */ + + do_cfa_expr(IA32_SIGCONTEXT_sp) + do_expr(0, IA32_SIGCONTEXT_ax) + do_expr(1, IA32_SIGCONTEXT_cx) + do_expr(2, IA32_SIGCONTEXT_dx) + do_expr(3, IA32_SIGCONTEXT_bx) + do_expr(5, IA32_SIGCONTEXT_bp) + do_expr(6, IA32_SIGCONTEXT_si) + do_expr(7, IA32_SIGCONTEXT_di) + do_expr(8, IA32_SIGCONTEXT_ip) + + .align 4 +.LENDFDEDLSI1: + + .long .LENDFDEDLSI2-.LSTARTFDEDLSI2 /* Length FDE */ +.LSTARTFDEDLSI2: + .long .LSTARTFDEDLSI2-.LSTARTFRAMEDLSI1 /* CIE pointer */ + /* HACK: See above wrt unwind library assumptions. */ + .long .LSTART_rt_sigreturn-1-. /* PC-relative start address */ + .long .LEND_rt_sigreturn-.LSTART_rt_sigreturn+1 + .uleb128 0 /* Augmentation */ + /* What follows are the instructions for the table generation. + We record the locations of each register saved. This is + slightly less complicated than the above, since we don't + modify the stack pointer in the process. */ + + do_cfa_expr(IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_sp) + do_expr(0, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_ax) + do_expr(1, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_cx) + do_expr(2, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_dx) + do_expr(3, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_bx) + do_expr(5, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_bp) + do_expr(6, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_si) + do_expr(7, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_di) + do_expr(8, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_ip) + + .align 4 +.LENDFDEDLSI2: + .previous diff --git a/arch/x86/vdso/vdso32/syscall.S b/arch/x86/vdso/vdso32/syscall.S new file mode 100644 index 00000000000..5415b5613d5 --- /dev/null +++ b/arch/x86/vdso/vdso32/syscall.S @@ -0,0 +1,77 @@ +/* + * Code for the vDSO. This version uses the syscall instruction. + * + * First get the common code for the sigreturn entry points. + * This must come first. + */ +#define SYSCALL_ENTER_KERNEL syscall +#include "sigreturn.S" + +#include <asm/segment.h> + + .text + .globl __kernel_vsyscall + .type __kernel_vsyscall,@function + ALIGN +__kernel_vsyscall: +.LSTART_vsyscall: + push %ebp +.Lpush_ebp: + movl %ecx, %ebp + syscall + movl $__USER32_DS, %ecx + movl %ecx, %ss + movl %ebp, %ecx + popl %ebp +.Lpop_ebp: + ret +.LEND_vsyscall: + .size __kernel_vsyscall,.-.LSTART_vsyscall + + .section .eh_frame,"a",@progbits +.LSTARTFRAME: + .long .LENDCIE-.LSTARTCIE +.LSTARTCIE: + .long 0 /* CIE ID */ + .byte 1 /* Version number */ + .string "zR" /* NUL-terminated augmentation string */ + .uleb128 1 /* Code alignment factor */ + .sleb128 -4 /* Data alignment factor */ + .byte 8 /* Return address register column */ + .uleb128 1 /* Augmentation value length */ + .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */ + .byte 0x0c /* DW_CFA_def_cfa */ + .uleb128 4 + .uleb128 4 + .byte 0x88 /* DW_CFA_offset, column 0x8 */ + .uleb128 1 + .align 4 +.LENDCIE: + + .long .LENDFDE1-.LSTARTFDE1 /* Length FDE */ +.LSTARTFDE1: + .long .LSTARTFDE1-.LSTARTFRAME /* CIE pointer */ + .long .LSTART_vsyscall-. /* PC-relative start address */ + .long .LEND_vsyscall-.LSTART_vsyscall + .uleb128 0 /* Augmentation length */ + /* What follows are the instructions for the table generation. + We have to record all changes of the stack pointer. */ + .byte 0x40 + .Lpush_ebp-.LSTART_vsyscall /* DW_CFA_advance_loc */ + .byte 0x0e /* DW_CFA_def_cfa_offset */ + .uleb128 8 + .byte 0x85, 0x02 /* DW_CFA_offset %ebp -8 */ + .byte 0x40 + .Lpop_ebp-.Lpush_ebp /* DW_CFA_advance_loc */ + .byte 0xc5 /* DW_CFA_restore %ebp */ + .byte 0x0e /* DW_CFA_def_cfa_offset */ + .uleb128 4 + .align 4 +.LENDFDE1: + .previous + + /* + * Pad out the segment to match the size of the sysenter.S version. + */ +VDSO32_vsyscall_eh_frame_size = 0x40 + .section .data,"aw",@progbits + .space VDSO32_vsyscall_eh_frame_size-(.LENDFDE1-.LSTARTFRAME), 0 + .previous diff --git a/arch/x86/vdso/vdso32/sysenter.S b/arch/x86/vdso/vdso32/sysenter.S new file mode 100644 index 00000000000..e2800affa75 --- /dev/null +++ b/arch/x86/vdso/vdso32/sysenter.S @@ -0,0 +1,116 @@ +/* + * Code for the vDSO. This version uses the sysenter instruction. + * + * First get the common code for the sigreturn entry points. + * This must come first. + */ +#include "sigreturn.S" + +/* + * The caller puts arg2 in %ecx, which gets pushed. The kernel will use + * %ecx itself for arg2. The pushing is because the sysexit instruction + * (found in entry.S) requires that we clobber %ecx with the desired %esp. + * User code might expect that %ecx is unclobbered though, as it would be + * for returning via the iret instruction, so we must push and pop. + * + * The caller puts arg3 in %edx, which the sysexit instruction requires + * for %eip. Thus, exactly as for arg2, we must push and pop. + * + * Arg6 is different. The caller puts arg6 in %ebp. Since the sysenter + * instruction clobbers %esp, the user's %esp won't even survive entry + * into the kernel. We store %esp in %ebp. Code in entry.S must fetch + * arg6 from the stack. + * + * You can not use this vsyscall for the clone() syscall because the + * three words on the parent stack do not get copied to the child. + */ + .text + .globl __kernel_vsyscall + .type __kernel_vsyscall,@function + ALIGN +__kernel_vsyscall: +.LSTART_vsyscall: + push %ecx +.Lpush_ecx: + push %edx +.Lpush_edx: + push %ebp +.Lenter_kernel: + movl %esp,%ebp + sysenter + + /* 7: align return point with nop's to make disassembly easier */ + .space 7,0x90 + + /* 14: System call restart point is here! (SYSENTER_RETURN-2) */ + jmp .Lenter_kernel + /* 16: System call normal return point is here! */ +VDSO32_SYSENTER_RETURN: /* Symbol used by sysenter.c via vdso32-syms.h */ + pop %ebp +.Lpop_ebp: + pop %edx +.Lpop_edx: + pop %ecx +.Lpop_ecx: + ret +.LEND_vsyscall: + .size __kernel_vsyscall,.-.LSTART_vsyscall + .previous + + .section .eh_frame,"a",@progbits +.LSTARTFRAMEDLSI: + .long .LENDCIEDLSI-.LSTARTCIEDLSI +.LSTARTCIEDLSI: + .long 0 /* CIE ID */ + .byte 1 /* Version number */ + .string "zR" /* NUL-terminated augmentation string */ + .uleb128 1 /* Code alignment factor */ + .sleb128 -4 /* Data alignment factor */ + .byte 8 /* Return address register column */ + .uleb128 1 /* Augmentation value length */ + .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */ + .byte 0x0c /* DW_CFA_def_cfa */ + .uleb128 4 + .uleb128 4 + .byte 0x88 /* DW_CFA_offset, column 0x8 */ + .uleb128 1 + .align 4 +.LENDCIEDLSI: + .long .LENDFDEDLSI-.LSTARTFDEDLSI /* Length FDE */ +.LSTARTFDEDLSI: + .long .LSTARTFDEDLSI-.LSTARTFRAMEDLSI /* CIE pointer */ + .long .LSTART_vsyscall-. /* PC-relative start address */ + .long .LEND_vsyscall-.LSTART_vsyscall + .uleb128 0 + /* What follows are the instructions for the table generation. + We have to record all changes of the stack pointer. */ + .byte 0x40 + (.Lpush_ecx-.LSTART_vsyscall) /* DW_CFA_advance_loc */ + .byte 0x0e /* DW_CFA_def_cfa_offset */ + .byte 0x08 /* RA at offset 8 now */ + .byte 0x40 + (.Lpush_edx-.Lpush_ecx) /* DW_CFA_advance_loc */ + .byte 0x0e /* DW_CFA_def_cfa_offset */ + .byte 0x0c /* RA at offset 12 now */ + .byte 0x40 + (.Lenter_kernel-.Lpush_edx) /* DW_CFA_advance_loc */ + .byte 0x0e /* DW_CFA_def_cfa_offset */ + .byte 0x10 /* RA at offset 16 now */ + .byte 0x85, 0x04 /* DW_CFA_offset %ebp -16 */ + /* Finally the epilogue. */ + .byte 0x40 + (.Lpop_ebp-.Lenter_kernel) /* DW_CFA_advance_loc */ + .byte 0x0e /* DW_CFA_def_cfa_offset */ + .byte 0x0c /* RA at offset 12 now */ + .byte 0xc5 /* DW_CFA_restore %ebp */ + .byte 0x40 + (.Lpop_edx-.Lpop_ebp) /* DW_CFA_advance_loc */ + .byte 0x0e /* DW_CFA_def_cfa_offset */ + .byte 0x08 /* RA at offset 8 now */ + .byte 0x40 + (.Lpop_ecx-.Lpop_edx) /* DW_CFA_advance_loc */ + .byte 0x0e /* DW_CFA_def_cfa_offset */ + .byte 0x04 /* RA at offset 4 now */ + .align 4 +.LENDFDEDLSI: + .previous + + /* + * Emit a symbol with the size of this .eh_frame data, + * to verify it matches the other versions. + */ +VDSO32_vsyscall_eh_frame_size = (.LENDFDEDLSI-.LSTARTFRAMEDLSI) diff --git a/arch/x86/vdso/vdso32/vdso32.lds.S b/arch/x86/vdso/vdso32/vdso32.lds.S new file mode 100644 index 00000000000..976124bb5f9 --- /dev/null +++ b/arch/x86/vdso/vdso32/vdso32.lds.S @@ -0,0 +1,37 @@ +/* + * Linker script for 32-bit vDSO. + * We #include the file to define the layout details. + * Here we only choose the prelinked virtual address. + * + * This file defines the version script giving the user-exported symbols in + * the DSO. We can define local symbols here called VDSO* to make their + * values visible using the asm-x86/vdso.h macros from the kernel proper. + */ + +#define VDSO_PRELINK 0 +#include "../vdso-layout.lds.S" + +/* The ELF entry point can be used to set the AT_SYSINFO value. */ +ENTRY(__kernel_vsyscall); + +/* + * This controls what userland symbols we export from the vDSO. + */ +VERSION +{ + LINUX_2.5 { + global: + __kernel_vsyscall; + __kernel_sigreturn; + __kernel_rt_sigreturn; + local: *; + }; +} + +/* + * Symbols we define here called VDSO* get their values into vdso32-syms.h. + */ +VDSO32_PRELINK = VDSO_PRELINK; +VDSO32_vsyscall = __kernel_vsyscall; +VDSO32_sigreturn = __kernel_sigreturn; +VDSO32_rt_sigreturn = __kernel_rt_sigreturn; |