freebsd-dev/sys/kern/imgact_aout.c

374 lines
10 KiB
C
Raw Normal View History

/*-
* SPDX-License-Identifier: BSD-2-Clause-FreeBSD
*
* Copyright (c) 1993, David Greenman
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
1995-09-08 13:24:33 +00:00
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*/
2003-06-11 00:56:59 +00:00
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include <sys/param.h>
#include <sys/exec.h>
#include <sys/imgact.h>
#include <sys/imgact_aout.h>
#include <sys/kernel.h>
#include <sys/limits.h>
#include <sys/lock.h>
#include <sys/malloc.h>
#include <sys/mutex.h>
#include <sys/proc.h>
#include <sys/racct.h>
#include <sys/resourcevar.h>
#include <sys/signalvar.h>
#include <sys/syscall.h>
#include <sys/sysent.h>
#include <sys/systm.h>
#include <sys/vnode.h>
#include <machine/frame.h>
#include <machine/md_var.h>
#include <vm/vm.h>
#include <vm/pmap.h>
#include <vm/vm_map.h>
#include <vm/vm_object.h>
#include <vm/vm_param.h>
#ifdef __amd64__
#include <compat/freebsd32/freebsd32_signal.h>
#include <compat/freebsd32/freebsd32_util.h>
#include <compat/freebsd32/freebsd32_proto.h>
#include <compat/freebsd32/freebsd32_syscall.h>
#include <compat/ia32/ia32_signal.h>
#endif
2002-03-19 21:25:46 +00:00
static int exec_aout_imgact(struct image_params *imgp);
static int aout_fixup(uintptr_t *stack_base, struct image_params *imgp);
1995-12-02 16:32:03 +00:00
i386 4/4G split. The change makes the user and kernel address spaces on i386 independent, giving each almost the full 4G of usable virtual addresses except for one PDE at top used for trampoline and per-CPU trampoline stacks, and system structures that must be always mapped, namely IDT, GDT, common TSS and LDT, and process-private TSS and LDT if allocated. By using 1:1 mapping for the kernel text and data, it appeared possible to eliminate assembler part of the locore.S which bootstraps initial page table and KPTmap. The code is rewritten in C and moved into the pmap_cold(). The comment in vmparam.h explains the KVA layout. There is no PCID mechanism available in protected mode, so each kernel/user switch forth and back completely flushes the TLB, except for the trampoline PTD region. The TLB invalidations for userspace becomes trivial, because IPI handlers switch page tables. On the other hand, context switches no longer need to reload %cr3. copyout(9) was rewritten to use vm_fault_quick_hold(). An issue for new copyout(9) is compatibility with wiring user buffers around sysctl handlers. This explains two kind of locks for copyout ptes and accounting of the vslock() calls. The vm_fault_quick_hold() AKA slow path, is only tried after the 'fast path' failed, which temporary changes mapping to the userspace and copies the data to/from small per-cpu buffer in the trampoline. If a page fault occurs during the copy, it is short-circuit by exception.s to not even reach C code. The change was motivated by the need to implement the Meltdown mitigation, but instead of KPTI the full split is done. The i386 architecture already shows the sizing problems, in particular, it is impossible to link clang and lld with debugging. I expect that the issues due to the virtual address space limits would only exaggerate and the split gives more liveness to the platform. Tested by: pho Discussed with: bde Sponsored by: The FreeBSD Foundation MFC after: 1 month Differential revision: https://reviews.freebsd.org/D14633
2018-04-13 20:30:49 +00:00
#define AOUT32_USRSTACK 0xbfc00000
#if defined(__i386__)
i386 4/4G split. The change makes the user and kernel address spaces on i386 independent, giving each almost the full 4G of usable virtual addresses except for one PDE at top used for trampoline and per-CPU trampoline stacks, and system structures that must be always mapped, namely IDT, GDT, common TSS and LDT, and process-private TSS and LDT if allocated. By using 1:1 mapping for the kernel text and data, it appeared possible to eliminate assembler part of the locore.S which bootstraps initial page table and KPTmap. The code is rewritten in C and moved into the pmap_cold(). The comment in vmparam.h explains the KVA layout. There is no PCID mechanism available in protected mode, so each kernel/user switch forth and back completely flushes the TLB, except for the trampoline PTD region. The TLB invalidations for userspace becomes trivial, because IPI handlers switch page tables. On the other hand, context switches no longer need to reload %cr3. copyout(9) was rewritten to use vm_fault_quick_hold(). An issue for new copyout(9) is compatibility with wiring user buffers around sysctl handlers. This explains two kind of locks for copyout ptes and accounting of the vslock() calls. The vm_fault_quick_hold() AKA slow path, is only tried after the 'fast path' failed, which temporary changes mapping to the userspace and copies the data to/from small per-cpu buffer in the trampoline. If a page fault occurs during the copy, it is short-circuit by exception.s to not even reach C code. The change was motivated by the need to implement the Meltdown mitigation, but instead of KPTI the full split is done. The i386 architecture already shows the sizing problems, in particular, it is impossible to link clang and lld with debugging. I expect that the issues due to the virtual address space limits would only exaggerate and the split gives more liveness to the platform. Tested by: pho Discussed with: bde Sponsored by: The FreeBSD Foundation MFC after: 1 month Differential revision: https://reviews.freebsd.org/D14633
2018-04-13 20:30:49 +00:00
#define AOUT32_PS_STRINGS (AOUT32_USRSTACK - sizeof(struct ps_strings))
struct sysentvec aout_sysvec = {
.sv_size = SYS_MAXSYSCALL,
.sv_table = sysent,
.sv_transtrap = NULL,
.sv_fixup = aout_fixup,
.sv_sendsig = sendsig,
.sv_sigcode = sigcode,
.sv_szsigcode = &szsigcode,
.sv_name = "FreeBSD a.out",
.sv_coredump = NULL,
.sv_imgact_try = NULL,
.sv_minsigstksz = MINSIGSTKSZ,
.sv_minuser = VM_MIN_ADDRESS,
i386 4/4G split. The change makes the user and kernel address spaces on i386 independent, giving each almost the full 4G of usable virtual addresses except for one PDE at top used for trampoline and per-CPU trampoline stacks, and system structures that must be always mapped, namely IDT, GDT, common TSS and LDT, and process-private TSS and LDT if allocated. By using 1:1 mapping for the kernel text and data, it appeared possible to eliminate assembler part of the locore.S which bootstraps initial page table and KPTmap. The code is rewritten in C and moved into the pmap_cold(). The comment in vmparam.h explains the KVA layout. There is no PCID mechanism available in protected mode, so each kernel/user switch forth and back completely flushes the TLB, except for the trampoline PTD region. The TLB invalidations for userspace becomes trivial, because IPI handlers switch page tables. On the other hand, context switches no longer need to reload %cr3. copyout(9) was rewritten to use vm_fault_quick_hold(). An issue for new copyout(9) is compatibility with wiring user buffers around sysctl handlers. This explains two kind of locks for copyout ptes and accounting of the vslock() calls. The vm_fault_quick_hold() AKA slow path, is only tried after the 'fast path' failed, which temporary changes mapping to the userspace and copies the data to/from small per-cpu buffer in the trampoline. If a page fault occurs during the copy, it is short-circuit by exception.s to not even reach C code. The change was motivated by the need to implement the Meltdown mitigation, but instead of KPTI the full split is done. The i386 architecture already shows the sizing problems, in particular, it is impossible to link clang and lld with debugging. I expect that the issues due to the virtual address space limits would only exaggerate and the split gives more liveness to the platform. Tested by: pho Discussed with: bde Sponsored by: The FreeBSD Foundation MFC after: 1 month Differential revision: https://reviews.freebsd.org/D14633
2018-04-13 20:30:49 +00:00
.sv_maxuser = AOUT32_USRSTACK,
.sv_usrstack = AOUT32_USRSTACK,
.sv_psstrings = AOUT32_PS_STRINGS,
.sv_psstringssz = sizeof(struct ps_strings),
.sv_stackprot = VM_PROT_ALL,
.sv_copyout_strings = exec_copyout_strings,
.sv_setregs = exec_setregs,
.sv_fixlimit = NULL,
.sv_maxssiz = NULL,
.sv_flags = SV_ABI_FREEBSD | SV_AOUT | SV_IA32 | SV_ILP32,
Reorganize syscall entry and leave handling. Extend struct sysvec with three new elements: sv_fetch_syscall_args - the method to fetch syscall arguments from usermode into struct syscall_args. The structure is machine-depended (this might be reconsidered after all architectures are converted). sv_set_syscall_retval - the method to set a return value for usermode from the syscall. It is a generalization of cpu_set_syscall_retval(9) to allow ABIs to override the way to set a return value. sv_syscallnames - the table of syscall names. Use sv_set_syscall_retval in kern_sigsuspend() instead of hardcoding the call to cpu_set_syscall_retval(). The new functions syscallenter(9) and syscallret(9) are provided that use sv_*syscall* pointers and contain the common repeated code from the syscall() implementations for the architecture-specific syscall trap handlers. Syscallenter() fetches arguments, calls syscall implementation from ABI sysent table, and set up return frame. The end of syscall bookkeeping is done by syscallret(). Take advantage of single place for MI syscall handling code and implement ptrace_lwpinfo pl_flags PL_FLAG_SCE, PL_FLAG_SCX and PL_FLAG_EXEC. The SCE and SCX flags notify the debugger that the thread is stopped at syscall entry or return point respectively. The EXEC flag augments SCX and notifies debugger that the process address space was changed by one of exec(2)-family syscalls. The i386, amd64, sparc64, sun4v, powerpc and ia64 syscall()s are changed to use syscallenter()/syscallret(). MIPS and arm are not converted and use the mostly unchanged syscall() implementation. Reviewed by: jhb, marcel, marius, nwhitehorn, stas Tested by: marcel (ia64), marius (sparc64), nwhitehorn (powerpc), stas (mips) MFC after: 1 month
2010-05-23 18:32:02 +00:00
.sv_set_syscall_retval = cpu_set_syscall_retval,
.sv_fetch_syscall_args = cpu_fetch_syscall_args,
.sv_syscallnames = syscallnames,
.sv_schedtail = NULL,
.sv_thread_detach = NULL,
.sv_trap = NULL,
.sv_onexec_old = exec_onexec_old,
.sv_onexit = exit_onexit,
.sv_set_fork_retval = x86_set_fork_retval,
};
#elif defined(__amd64__)
#include "vdso_ia32_offsets.h"
extern const char _binary_elf_vdso32_so_1_start[];
extern const char _binary_elf_vdso32_so_1_end[];
extern char _binary_elf_vdso32_so_1_size;
#define AOUT32_PS_STRINGS \
(AOUT32_USRSTACK - sizeof(struct freebsd32_ps_strings))
i386 4/4G split. The change makes the user and kernel address spaces on i386 independent, giving each almost the full 4G of usable virtual addresses except for one PDE at top used for trampoline and per-CPU trampoline stacks, and system structures that must be always mapped, namely IDT, GDT, common TSS and LDT, and process-private TSS and LDT if allocated. By using 1:1 mapping for the kernel text and data, it appeared possible to eliminate assembler part of the locore.S which bootstraps initial page table and KPTmap. The code is rewritten in C and moved into the pmap_cold(). The comment in vmparam.h explains the KVA layout. There is no PCID mechanism available in protected mode, so each kernel/user switch forth and back completely flushes the TLB, except for the trampoline PTD region. The TLB invalidations for userspace becomes trivial, because IPI handlers switch page tables. On the other hand, context switches no longer need to reload %cr3. copyout(9) was rewritten to use vm_fault_quick_hold(). An issue for new copyout(9) is compatibility with wiring user buffers around sysctl handlers. This explains two kind of locks for copyout ptes and accounting of the vslock() calls. The vm_fault_quick_hold() AKA slow path, is only tried after the 'fast path' failed, which temporary changes mapping to the userspace and copies the data to/from small per-cpu buffer in the trampoline. If a page fault occurs during the copy, it is short-circuit by exception.s to not even reach C code. The change was motivated by the need to implement the Meltdown mitigation, but instead of KPTI the full split is done. The i386 architecture already shows the sizing problems, in particular, it is impossible to link clang and lld with debugging. I expect that the issues due to the virtual address space limits would only exaggerate and the split gives more liveness to the platform. Tested by: pho Discussed with: bde Sponsored by: The FreeBSD Foundation MFC after: 1 month Differential revision: https://reviews.freebsd.org/D14633
2018-04-13 20:30:49 +00:00
#define AOUT32_MINUSER FREEBSD32_MINUSER
extern const char *freebsd32_syscallnames[];
extern u_long ia32_maxssiz;
static int aout_szsigcode;
struct sysentvec aout_sysvec = {
.sv_size = FREEBSD32_SYS_MAXSYSCALL,
.sv_table = freebsd32_sysent,
.sv_transtrap = NULL,
.sv_fixup = aout_fixup,
.sv_sendsig = ia32_sendsig,
.sv_sigcode = _binary_elf_vdso32_so_1_start,
.sv_szsigcode = &aout_szsigcode,
.sv_name = "FreeBSD a.out",
.sv_coredump = NULL,
.sv_imgact_try = NULL,
.sv_minsigstksz = MINSIGSTKSZ,
.sv_minuser = AOUT32_MINUSER,
.sv_maxuser = AOUT32_USRSTACK,
.sv_usrstack = AOUT32_USRSTACK,
.sv_psstrings = AOUT32_PS_STRINGS,
.sv_psstringssz = sizeof(struct freebsd32_ps_strings),
.sv_stackprot = VM_PROT_ALL,
.sv_copyout_strings = freebsd32_copyout_strings,
.sv_setregs = ia32_setregs,
.sv_fixlimit = ia32_fixlimit,
.sv_maxssiz = &ia32_maxssiz,
.sv_flags = SV_ABI_FREEBSD | SV_AOUT | SV_IA32 | SV_ILP32,
.sv_set_syscall_retval = ia32_set_syscall_retval,
.sv_fetch_syscall_args = ia32_fetch_syscall_args,
.sv_syscallnames = freebsd32_syscallnames,
.sv_onexec_old = exec_onexec_old,
.sv_onexit = exit_onexit,
.sv_set_fork_retval = x86_set_fork_retval,
};
static void
aout_sysent(void *arg __unused)
{
aout_szsigcode = (int)(uintptr_t)&_binary_elf_vdso32_so_1_size;
}
SYSINIT(aout_sysent, SI_SUB_EXEC, SI_ORDER_ANY, aout_sysent, NULL);
#else
#error "Only ia32 arch is supported"
#endif
static int
aout_fixup(uintptr_t *stack_base, struct image_params *imgp)
{
*stack_base -= sizeof(uint32_t);
if (suword32((void *)*stack_base, imgp->args->argc) != 0)
return (EFAULT);
return (0);
}
static int
exec_aout_imgact(struct image_params *imgp)
{
const struct exec *a_out;
struct vmspace *vmspace;
vm_map_t map;
vm_object_t object;
vm_offset_t text_end, data_end;
unsigned long virtual_offset;
unsigned long file_offset;
unsigned long bss_size;
int error;
a_out = (const struct exec *)imgp->image_header;
/*
* Linux and *BSD binaries look very much alike,
1995-05-30 08:16:23 +00:00
* only the machine id is different:
1995-06-11 19:33:05 +00:00
* 0x64 for Linux, 0x86 for *BSD, 0x00 for BSDI.
* NetBSD is in network byte order.. ugh.
*/
if (((a_out->a_midmag >> 16) & 0xff) != 0x86 &&
((a_out->a_midmag >> 16) & 0xff) != 0 &&
((((int)ntohl(a_out->a_midmag)) >> 16) & 0xff) != 0x86)
return (-1);
/*
* Set file/virtual offset based on a.out variant.
* We do two cases: host byte order and network byte order
* (for NetBSD compatibility)
*/
switch ((int)(a_out->a_midmag & 0xffff)) {
case ZMAGIC:
virtual_offset = 0;
if (a_out->a_text) {
file_offset = PAGE_SIZE;
} else {
/* Bill's "screwball mode" */
file_offset = 0;
}
break;
case QMAGIC:
virtual_offset = PAGE_SIZE;
file_offset = 0;
/* Pass PS_STRINGS for BSD/OS binaries only. */
if (N_GETMID(*a_out) == MID_ZERO)
imgp->ps_strings = (void *)aout_sysvec.sv_psstrings;
break;
default:
/* NetBSD compatibility */
switch ((int)(ntohl(a_out->a_midmag) & 0xffff)) {
case ZMAGIC:
case QMAGIC:
virtual_offset = PAGE_SIZE;
file_offset = 0;
break;
default:
return (-1);
}
}
bss_size = roundup(a_out->a_bss, PAGE_SIZE);
/*
* Check various fields in header for validity/bounds.
*/
if (/* entry point must lay with text region */
a_out->a_entry < virtual_offset ||
a_out->a_entry >= virtual_offset + a_out->a_text ||
/* text and data size must each be page rounded */
a_out->a_text & PAGE_MASK || a_out->a_data & PAGE_MASK
#ifdef __amd64__
||
/* overflows */
virtual_offset + a_out->a_text + a_out->a_data + bss_size > UINT_MAX
#endif
)
return (-1);
/* text + data can't exceed file size */
if (a_out->a_data + a_out->a_text > imgp->attr->va_size)
return (EFAULT);
/*
* text/data/bss must not exceed limits
*/
Locking for the per-process resource limits structure. - struct plimit includes a mutex to protect a reference count. The plimit structure is treated similarly to struct ucred in that is is always copy on write, so having a reference to a structure is sufficient to read from it without needing a further lock. - The proc lock protects the p_limit pointer and must be held while reading limits from a process to keep the limit structure from changing out from under you while reading from it. - Various global limits that are ints are not protected by a lock since int writes are atomic on all the archs we support and thus a lock wouldn't buy us anything. - All accesses to individual resource limits from a process are abstracted behind a simple lim_rlimit(), lim_max(), and lim_cur() API that return either an rlimit, or the current or max individual limit of the specified resource from a process. - dosetrlimit() was renamed to kern_setrlimit() to match existing style of other similar syscall helper functions. - The alpha OSF/1 compat layer no longer calls getrlimit() and setrlimit() (it didn't used the stackgap when it should have) but uses lim_rlimit() and kern_setrlimit() instead. - The svr4 compat no longer uses the stackgap for resource limits calls, but uses lim_rlimit() and kern_setrlimit() instead. - The ibcs2 compat no longer uses the stackgap for resource limits. It also no longer uses the stackgap for accessing sysctl's for the ibcs2_sysconf() syscall but uses kernel_sysctl() instead. As a result, ibcs2_sysconf() no longer needs Giant. - The p_rlimit macro no longer exists. Submitted by: mtm (mostly, I only did a few cleanups and catchups) Tested on: i386 Compiled on: alpha, amd64
2004-02-04 21:52:57 +00:00
PROC_LOCK(imgp->proc);
if (/* text can't exceed maximum text size */
a_out->a_text > maxtsiz ||
/* data + bss can't exceed rlimit */
a_out->a_data + bss_size > lim_cur_proc(imgp->proc, RLIMIT_DATA) ||
racct_set(imgp->proc, RACCT_DATA, a_out->a_data + bss_size) != 0) {
Switch to use shared vnode locks for text files during image activation. kern_execve() locks text vnode exclusive to be able to set and clear VV_TEXT flag. VV_TEXT is mutually exclusive with the v_writecount > 0 condition. The change removes VV_TEXT, replacing it with the condition v_writecount <= -1, and puts v_writecount under the vnode interlock. Each text reference decrements v_writecount. To clear the text reference when the segment is unmapped, it is recorded in the vm_map_entry backed by the text file as MAP_ENTRY_VN_TEXT flag, and v_writecount is incremented on the map entry removal The operations like VOP_ADD_WRITECOUNT() and VOP_SET_TEXT() check that v_writecount does not contradict the desired change. vn_writecheck() is now racy and its use was eliminated everywhere except access. Atomic check for writeability and increment of v_writecount is performed by the VOP. vn_truncate() now increments v_writecount around VOP_SETATTR() call, lack of which is arguably a bug on its own. nullfs bypasses v_writecount to the lower vnode always, so nullfs vnode has its own v_writecount correct, and lower vnode gets all references, since object->handle is always lower vnode. On the text vnode' vm object dealloc, the v_writecount value is reset to zero, and deadfs vop_unset_text short-circuit the operation. Reclamation of lowervp always reclaims all nullfs vnodes referencing lowervp first, so no stray references are left. Reviewed by: markj, trasz Tested by: mjg, pho Sponsored by: The FreeBSD Foundation MFC after: 1 month Differential revision: https://reviews.freebsd.org/D19923
2019-05-05 11:20:43 +00:00
PROC_UNLOCK(imgp->proc);
return (ENOMEM);
Locking for the per-process resource limits structure. - struct plimit includes a mutex to protect a reference count. The plimit structure is treated similarly to struct ucred in that is is always copy on write, so having a reference to a structure is sufficient to read from it without needing a further lock. - The proc lock protects the p_limit pointer and must be held while reading limits from a process to keep the limit structure from changing out from under you while reading from it. - Various global limits that are ints are not protected by a lock since int writes are atomic on all the archs we support and thus a lock wouldn't buy us anything. - All accesses to individual resource limits from a process are abstracted behind a simple lim_rlimit(), lim_max(), and lim_cur() API that return either an rlimit, or the current or max individual limit of the specified resource from a process. - dosetrlimit() was renamed to kern_setrlimit() to match existing style of other similar syscall helper functions. - The alpha OSF/1 compat layer no longer calls getrlimit() and setrlimit() (it didn't used the stackgap when it should have) but uses lim_rlimit() and kern_setrlimit() instead. - The svr4 compat no longer uses the stackgap for resource limits calls, but uses lim_rlimit() and kern_setrlimit() instead. - The ibcs2 compat no longer uses the stackgap for resource limits. It also no longer uses the stackgap for accessing sysctl's for the ibcs2_sysconf() syscall but uses kernel_sysctl() instead. As a result, ibcs2_sysconf() no longer needs Giant. - The p_rlimit macro no longer exists. Submitted by: mtm (mostly, I only did a few cleanups and catchups) Tested on: i386 Compiled on: alpha, amd64
2004-02-04 21:52:57 +00:00
}
PROC_UNLOCK(imgp->proc);
/*
* Avoid a possible deadlock if the current address space is destroyed
* and that address space maps the locked vnode. In the common case,
* the locked vnode's v_usecount is decremented but remains greater
* than zero. Consequently, the vnode lock is not needed by vrele().
* However, in cases where the vnode lock is external, such as nullfs,
* v_usecount may become zero.
*/
VOP_UNLOCK(imgp->vp);
/*
* Destroy old process VM and create a new one (with a new stack)
*/
error = exec_new_vmspace(imgp, &aout_sysvec);
Switch to use shared vnode locks for text files during image activation. kern_execve() locks text vnode exclusive to be able to set and clear VV_TEXT flag. VV_TEXT is mutually exclusive with the v_writecount > 0 condition. The change removes VV_TEXT, replacing it with the condition v_writecount <= -1, and puts v_writecount under the vnode interlock. Each text reference decrements v_writecount. To clear the text reference when the segment is unmapped, it is recorded in the vm_map_entry backed by the text file as MAP_ENTRY_VN_TEXT flag, and v_writecount is incremented on the map entry removal The operations like VOP_ADD_WRITECOUNT() and VOP_SET_TEXT() check that v_writecount does not contradict the desired change. vn_writecheck() is now racy and its use was eliminated everywhere except access. Atomic check for writeability and increment of v_writecount is performed by the VOP. vn_truncate() now increments v_writecount around VOP_SETATTR() call, lack of which is arguably a bug on its own. nullfs bypasses v_writecount to the lower vnode always, so nullfs vnode has its own v_writecount correct, and lower vnode gets all references, since object->handle is always lower vnode. On the text vnode' vm object dealloc, the v_writecount value is reset to zero, and deadfs vop_unset_text short-circuit the operation. Reclamation of lowervp always reclaims all nullfs vnodes referencing lowervp first, so no stray references are left. Reviewed by: markj, trasz Tested by: mjg, pho Sponsored by: The FreeBSD Foundation MFC after: 1 month Differential revision: https://reviews.freebsd.org/D19923
2019-05-05 11:20:43 +00:00
vn_lock(imgp->vp, LK_SHARED | LK_RETRY);
if (error)
return (error);
/*
* The vm space can be changed by exec_new_vmspace
*/
vmspace = imgp->proc->p_vmspace;
object = imgp->object;
map = &vmspace->vm_map;
vm_map_lock(map);
vm_object_reference(object);
text_end = virtual_offset + a_out->a_text;
error = vm_map_insert(map, object,
file_offset,
virtual_offset, text_end,
VM_PROT_READ | VM_PROT_EXECUTE, VM_PROT_ALL,
Switch to use shared vnode locks for text files during image activation. kern_execve() locks text vnode exclusive to be able to set and clear VV_TEXT flag. VV_TEXT is mutually exclusive with the v_writecount > 0 condition. The change removes VV_TEXT, replacing it with the condition v_writecount <= -1, and puts v_writecount under the vnode interlock. Each text reference decrements v_writecount. To clear the text reference when the segment is unmapped, it is recorded in the vm_map_entry backed by the text file as MAP_ENTRY_VN_TEXT flag, and v_writecount is incremented on the map entry removal The operations like VOP_ADD_WRITECOUNT() and VOP_SET_TEXT() check that v_writecount does not contradict the desired change. vn_writecheck() is now racy and its use was eliminated everywhere except access. Atomic check for writeability and increment of v_writecount is performed by the VOP. vn_truncate() now increments v_writecount around VOP_SETATTR() call, lack of which is arguably a bug on its own. nullfs bypasses v_writecount to the lower vnode always, so nullfs vnode has its own v_writecount correct, and lower vnode gets all references, since object->handle is always lower vnode. On the text vnode' vm object dealloc, the v_writecount value is reset to zero, and deadfs vop_unset_text short-circuit the operation. Reclamation of lowervp always reclaims all nullfs vnodes referencing lowervp first, so no stray references are left. Reviewed by: markj, trasz Tested by: mjg, pho Sponsored by: The FreeBSD Foundation MFC after: 1 month Differential revision: https://reviews.freebsd.org/D19923
2019-05-05 11:20:43 +00:00
MAP_COPY_ON_WRITE | MAP_PREFAULT | MAP_VN_EXEC);
if (error) {
vm_map_unlock(map);
vm_object_deallocate(object);
return (error);
}
Switch to use shared vnode locks for text files during image activation. kern_execve() locks text vnode exclusive to be able to set and clear VV_TEXT flag. VV_TEXT is mutually exclusive with the v_writecount > 0 condition. The change removes VV_TEXT, replacing it with the condition v_writecount <= -1, and puts v_writecount under the vnode interlock. Each text reference decrements v_writecount. To clear the text reference when the segment is unmapped, it is recorded in the vm_map_entry backed by the text file as MAP_ENTRY_VN_TEXT flag, and v_writecount is incremented on the map entry removal The operations like VOP_ADD_WRITECOUNT() and VOP_SET_TEXT() check that v_writecount does not contradict the desired change. vn_writecheck() is now racy and its use was eliminated everywhere except access. Atomic check for writeability and increment of v_writecount is performed by the VOP. vn_truncate() now increments v_writecount around VOP_SETATTR() call, lack of which is arguably a bug on its own. nullfs bypasses v_writecount to the lower vnode always, so nullfs vnode has its own v_writecount correct, and lower vnode gets all references, since object->handle is always lower vnode. On the text vnode' vm object dealloc, the v_writecount value is reset to zero, and deadfs vop_unset_text short-circuit the operation. Reclamation of lowervp always reclaims all nullfs vnodes referencing lowervp first, so no stray references are left. Reviewed by: markj, trasz Tested by: mjg, pho Sponsored by: The FreeBSD Foundation MFC after: 1 month Differential revision: https://reviews.freebsd.org/D19923
2019-05-05 11:20:43 +00:00
VOP_SET_TEXT_CHECKED(imgp->vp);
data_end = text_end + a_out->a_data;
if (a_out->a_data) {
vm_object_reference(object);
error = vm_map_insert(map, object,
file_offset + a_out->a_text,
text_end, data_end,
VM_PROT_ALL, VM_PROT_ALL,
Switch to use shared vnode locks for text files during image activation. kern_execve() locks text vnode exclusive to be able to set and clear VV_TEXT flag. VV_TEXT is mutually exclusive with the v_writecount > 0 condition. The change removes VV_TEXT, replacing it with the condition v_writecount <= -1, and puts v_writecount under the vnode interlock. Each text reference decrements v_writecount. To clear the text reference when the segment is unmapped, it is recorded in the vm_map_entry backed by the text file as MAP_ENTRY_VN_TEXT flag, and v_writecount is incremented on the map entry removal The operations like VOP_ADD_WRITECOUNT() and VOP_SET_TEXT() check that v_writecount does not contradict the desired change. vn_writecheck() is now racy and its use was eliminated everywhere except access. Atomic check for writeability and increment of v_writecount is performed by the VOP. vn_truncate() now increments v_writecount around VOP_SETATTR() call, lack of which is arguably a bug on its own. nullfs bypasses v_writecount to the lower vnode always, so nullfs vnode has its own v_writecount correct, and lower vnode gets all references, since object->handle is always lower vnode. On the text vnode' vm object dealloc, the v_writecount value is reset to zero, and deadfs vop_unset_text short-circuit the operation. Reclamation of lowervp always reclaims all nullfs vnodes referencing lowervp first, so no stray references are left. Reviewed by: markj, trasz Tested by: mjg, pho Sponsored by: The FreeBSD Foundation MFC after: 1 month Differential revision: https://reviews.freebsd.org/D19923
2019-05-05 11:20:43 +00:00
MAP_COPY_ON_WRITE | MAP_PREFAULT | MAP_VN_EXEC);
if (error) {
vm_map_unlock(map);
vm_object_deallocate(object);
return (error);
}
Switch to use shared vnode locks for text files during image activation. kern_execve() locks text vnode exclusive to be able to set and clear VV_TEXT flag. VV_TEXT is mutually exclusive with the v_writecount > 0 condition. The change removes VV_TEXT, replacing it with the condition v_writecount <= -1, and puts v_writecount under the vnode interlock. Each text reference decrements v_writecount. To clear the text reference when the segment is unmapped, it is recorded in the vm_map_entry backed by the text file as MAP_ENTRY_VN_TEXT flag, and v_writecount is incremented on the map entry removal The operations like VOP_ADD_WRITECOUNT() and VOP_SET_TEXT() check that v_writecount does not contradict the desired change. vn_writecheck() is now racy and its use was eliminated everywhere except access. Atomic check for writeability and increment of v_writecount is performed by the VOP. vn_truncate() now increments v_writecount around VOP_SETATTR() call, lack of which is arguably a bug on its own. nullfs bypasses v_writecount to the lower vnode always, so nullfs vnode has its own v_writecount correct, and lower vnode gets all references, since object->handle is always lower vnode. On the text vnode' vm object dealloc, the v_writecount value is reset to zero, and deadfs vop_unset_text short-circuit the operation. Reclamation of lowervp always reclaims all nullfs vnodes referencing lowervp first, so no stray references are left. Reviewed by: markj, trasz Tested by: mjg, pho Sponsored by: The FreeBSD Foundation MFC after: 1 month Differential revision: https://reviews.freebsd.org/D19923
2019-05-05 11:20:43 +00:00
VOP_SET_TEXT_CHECKED(imgp->vp);
}
if (bss_size) {
error = vm_map_insert(map, NULL, 0,
data_end, data_end + bss_size,
VM_PROT_ALL, VM_PROT_ALL, 0);
if (error) {
vm_map_unlock(map);
return (error);
}
}
vm_map_unlock(map);
/* Fill in process VM information */
vmspace->vm_tsize = a_out->a_text >> PAGE_SHIFT;
vmspace->vm_dsize = (a_out->a_data + bss_size) >> PAGE_SHIFT;
vmspace->vm_taddr = (caddr_t) (uintptr_t) virtual_offset;
vmspace->vm_daddr = (caddr_t) (uintptr_t)
(virtual_offset + a_out->a_text);
error = exec_map_stack(imgp);
if (error != 0)
return (error);
/* Fill in image_params */
imgp->interpreted = 0;
imgp->entry_addr = a_out->a_entry;
1995-05-30 08:16:23 +00:00
imgp->proc->p_sysent = &aout_sysvec;
return (0);
}
/*
* Tell kern_execve.c about it, with a little help from the linker.
*/
static struct execsw aout_execsw = {
.ex_imgact = exec_aout_imgact,
.ex_name = "a.out"
};
EXEC_SET(aout, aout_execsw);