qemu/linux-user/qemu.h

761 lines
28 KiB
C
Raw Normal View History

#ifndef QEMU_H
#define QEMU_H
linux-user: Provide safe_syscall for fixing races between signals and syscalls If a signal is delivered immediately before a blocking system call the handler will only be called after the system call returns, which may be a long time later or never. This is fixed by using a function (safe_syscall) that checks if a guest signal is pending prior to making a system call, and if so does not call the system call and returns -TARGET_ERESTARTSYS. If a signal is received between the check and the system call host_signal_handler() rewinds execution to before the check. This rewinding has the effect of closing the race window so that safe_syscall will reliably either (a) go into the host syscall with no unprocessed guest signals pending or or (b) return -TARGET_ERESTARTSYS so that the caller can deal with the signals. Implementing this requires a per-host-architecture assembly language fragment. This will also resolve the mishandling of the SA_RESTART flag where we would restart a host system call and not call the guest signal handler until the syscall finally completed -- syscall restarting now always happens at the guest syscall level so the guest signal handler will run. (The host syscall will never be restarted because if the host kernel rewinds the PC to point at the syscall insn for a restart then our host_signal_handler() will see this and arrange the guest PC rewind.) This commit contains the infrastructure for implementing safe_syscall and the assembly language fragment for x86-64, but does not change any syscalls to use it. Signed-off-by: Timothy Edward Baldwin <T.E.Baldwin99@members.leeds.ac.uk> Message-id: 1441497448-32489-14-git-send-email-T.E.Baldwin99@members.leeds.ac.uk [PMM: * Avoid having an architecture if-ladder in configure by putting linux-user/host/$(ARCH) on the include path and including safe-syscall.inc.S from it * Avoid ifdef ladder in signal.c by creating new hostdep.h to hold host-architecture-specific things * Added copyright/license header to safe-syscall.inc.S * Rewrote commit message * Added comments to safe-syscall.inc.S * Changed calling convention of safe_syscall() to match syscall() (returns -1 and host error in errno on failure) * Added a long comment in qemu.h about how to use safe_syscall() to implement guest syscalls. ] RV: squashed Peters "fixup! linux-user: compile on non-x86-64 hosts" patch Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2016-05-12 20:47:46 +03:00
#include "hostdep.h"
#include "cpu.h"
#include "exec/exec-all.h"
#include "exec/cpu_ldst.h"
#undef DEBUG_REMAP
#ifdef DEBUG_REMAP
#endif /* DEBUG_REMAP */
#include "exec/user/abitypes.h"
#include "exec/user/thunk.h"
#include "syscall_defs.h"
#include "target_syscall.h"
#include "exec/gdbstub.h"
/* This is the size of the host kernel's sigset_t, needed where we make
* direct system calls that take a sigset_t pointer and a size.
*/
#define SIGSET_T_SIZE (_NSIG / 8)
/* This struct is used to hold certain information about the image.
* Basically, it replicates in user space what would be certain
* task_struct fields in the kernel
*/
struct image_info {
abi_ulong load_bias;
abi_ulong load_addr;
abi_ulong start_code;
abi_ulong end_code;
abi_ulong start_data;
abi_ulong end_data;
abi_ulong start_brk;
abi_ulong brk;
abi_ulong reserve_brk;
abi_ulong start_mmap;
abi_ulong start_stack;
abi_ulong stack_limit;
abi_ulong entry;
abi_ulong code_offset;
abi_ulong data_offset;
abi_ulong saved_auxv;
abi_ulong auxv_len;
abi_ulong arg_start;
abi_ulong arg_end;
abi_ulong arg_strings;
abi_ulong env_strings;
abi_ulong file_string;
uint32_t elf_flags;
avoid TABs in files that only contain a few Most files that have TABs only contain a handful of them. Change them to spaces so that we don't confuse people. disas, standard-headers, linux-headers and libdecnumber are imported from other projects and probably should be exempted from the check. Outside those, after this patch the following files still contain both 8-space and TAB sequences at the beginning of the line. Many of them have a majority of TABs, or were initially committed with all tabs. bsd-user/i386/target_syscall.h bsd-user/x86_64/target_syscall.h crypto/aes.c hw/audio/fmopl.c hw/audio/fmopl.h hw/block/tc58128.c hw/display/cirrus_vga.c hw/display/xenfb.c hw/dma/etraxfs_dma.c hw/intc/sh_intc.c hw/misc/mst_fpga.c hw/net/pcnet.c hw/sh4/sh7750.c hw/timer/m48t59.c hw/timer/sh_timer.c include/crypto/aes.h include/disas/bfd.h include/hw/sh4/sh.h libdecnumber/decNumber.c linux-headers/asm-generic/unistd.h linux-headers/linux/kvm.h linux-user/alpha/target_syscall.h linux-user/arm/nwfpe/double_cpdo.c linux-user/arm/nwfpe/fpa11_cpdt.c linux-user/arm/nwfpe/fpa11_cprt.c linux-user/arm/nwfpe/fpa11.h linux-user/flat.h linux-user/flatload.c linux-user/i386/target_syscall.h linux-user/ppc/target_syscall.h linux-user/sparc/target_syscall.h linux-user/syscall.c linux-user/syscall_defs.h linux-user/x86_64/target_syscall.h slirp/cksum.c slirp/if.c slirp/ip.h slirp/ip_icmp.c slirp/ip_icmp.h slirp/ip_input.c slirp/ip_output.c slirp/mbuf.c slirp/misc.c slirp/sbuf.c slirp/socket.c slirp/socket.h slirp/tcp_input.c slirp/tcpip.h slirp/tcp_output.c slirp/tcp_subr.c slirp/tcp_timer.c slirp/tftp.c slirp/udp.c slirp/udp.h target/cris/cpu.h target/cris/mmu.c target/cris/op_helper.c target/sh4/helper.c target/sh4/op_helper.c target/sh4/translate.c tcg/sparc/tcg-target.inc.c tests/tcg/cris/check_addo.c tests/tcg/cris/check_moveq.c tests/tcg/cris/check_swap.c tests/tcg/multiarch/test-mmap.c ui/vnc-enc-hextile-template.h ui/vnc-enc-zywrle.h util/envlist.c util/readline.c The following have only TABs: bsd-user/i386/target_signal.h bsd-user/sparc64/target_signal.h bsd-user/sparc64/target_syscall.h bsd-user/sparc/target_signal.h bsd-user/sparc/target_syscall.h bsd-user/x86_64/target_signal.h crypto/desrfb.c hw/audio/intel-hda-defs.h hw/core/uboot_image.h hw/sh4/sh7750_regnames.c hw/sh4/sh7750_regs.h include/hw/cris/etraxfs_dma.h linux-user/alpha/termbits.h linux-user/arm/nwfpe/fpopcode.h linux-user/arm/nwfpe/fpsr.h linux-user/arm/syscall_nr.h linux-user/arm/target_signal.h linux-user/cris/target_signal.h linux-user/i386/target_signal.h linux-user/linux_loop.h linux-user/m68k/target_signal.h linux-user/microblaze/target_signal.h linux-user/mips64/target_signal.h linux-user/mips/target_signal.h linux-user/mips/target_syscall.h linux-user/mips/termbits.h linux-user/ppc/target_signal.h linux-user/sh4/target_signal.h linux-user/sh4/termbits.h linux-user/sparc64/target_syscall.h linux-user/sparc/target_signal.h linux-user/x86_64/target_signal.h linux-user/x86_64/termbits.h pc-bios/optionrom/optionrom.h slirp/mbuf.h slirp/misc.h slirp/sbuf.h slirp/tcp.h slirp/tcp_timer.h slirp/tcp_var.h target/i386/svm.h target/sparc/asi.h target/xtensa/core-dc232b/xtensa-modules.inc.c target/xtensa/core-dc233c/xtensa-modules.inc.c target/xtensa/core-de212/core-isa.h target/xtensa/core-de212/xtensa-modules.inc.c target/xtensa/core-fsf/xtensa-modules.inc.c target/xtensa/core-sample_controller/core-isa.h target/xtensa/core-sample_controller/xtensa-modules.inc.c target/xtensa/core-test_kc705_be/core-isa.h target/xtensa/core-test_kc705_be/xtensa-modules.inc.c tests/tcg/cris/check_abs.c tests/tcg/cris/check_addc.c tests/tcg/cris/check_addcm.c tests/tcg/cris/check_addoq.c tests/tcg/cris/check_bound.c tests/tcg/cris/check_ftag.c tests/tcg/cris/check_int64.c tests/tcg/cris/check_lz.c tests/tcg/cris/check_openpf5.c tests/tcg/cris/check_sigalrm.c tests/tcg/cris/crisutils.h tests/tcg/cris/sys.c tests/tcg/i386/test-i386-ssse3.c ui/vgafont.h Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20181213223737.11793-3-pbonzini@redhat.com> Reviewed-by: Aleksandar Markovic <amarkovic@wavecomp.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> Acked-by: Richard Henderson <richard.henderson@linaro.org> Acked-by: Eric Blake <eblake@redhat.com> Acked-by: David Gibson <david@gibson.dropbear.id.au> Reviewed-by: Stefan Markovic <smarkovic@wavecomp.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2018-12-14 01:37:37 +03:00
int personality;
abi_ulong alignment;
/* The fields below are used in FDPIC mode. */
abi_ulong loadmap_addr;
uint16_t nsegs;
void *loadsegs;
abi_ulong pt_dynamic_addr;
abi_ulong interpreter_loadmap_addr;
abi_ulong interpreter_pt_dynamic_addr;
struct image_info *other_info;
#ifdef TARGET_MIPS
int fp_abi;
int interp_fp_abi;
#endif
};
#ifdef TARGET_I386
/* Information about the current linux thread */
struct vm86_saved_state {
uint32_t eax; /* return code */
uint32_t ebx;
uint32_t ecx;
uint32_t edx;
uint32_t esi;
uint32_t edi;
uint32_t ebp;
uint32_t esp;
uint32_t eflags;
uint32_t eip;
uint16_t cs, ss, ds, es, fs, gs;
};
#endif
#if defined(TARGET_ARM) && defined(TARGET_ABI32)
/* FPU emulator */
#include "nwfpe/fpa11.h"
#endif
#define MAX_SIGQUEUE_SIZE 1024
struct emulated_sigtable {
int pending; /* true if signal is pending */
target_siginfo_t info;
};
/* NOTE: we force a big alignment so that the stack stored after is
aligned too */
typedef struct TaskState {
pid_t ts_tid; /* tid (or pid) of this task */
#ifdef TARGET_ARM
# ifdef TARGET_ABI32
/* FPA state */
FPA11 fpa;
# endif
int swi_errno;
#endif
#if defined(TARGET_I386) && !defined(TARGET_X86_64)
abi_ulong target_v86;
struct vm86_saved_state vm86_saved_regs;
struct target_vm86plus_struct vm86plus;
uint32_t v86flags;
uint32_t v86mask;
#endif
abi_ulong child_tidptr;
#ifdef TARGET_M68K
abi_ulong tp_value;
#endif
#if defined(TARGET_ARM) || defined(TARGET_M68K)
/* Extra fields for semihosted binaries. */
abi_ulong heap_base;
abi_ulong heap_limit;
#endif
abi_ulong stack_base;
int used; /* non zero if used */
struct image_info *info;
struct linux_binprm *bprm;
struct emulated_sigtable sync_signal;
struct emulated_sigtable sigtab[TARGET_NSIG];
linux-user: Fix race between multiple signals If multiple host signals are received in quick succession they would be queued in TaskState then delivered to the guest in spite of signals being supposed to be blocked by the guest signal handler's sa_mask. Fix this by decoupling the guest signal mask from the host signal mask, so we can have protected sections where all host signals are blocked. In particular we block signals from when host_signal_handler() queues a signal from the guest until process_pending_signals() has unqueued it. We also block signals while we are manipulating the guest signal mask in emulation of sigprocmask and similar syscalls. Blocking host signals also ensures the correct behaviour with respect to multiple threads and the overrun count of timer related signals. Alas blocking and queuing in qemu is still needed because of virtual processor exceptions, SIGSEGV and SIGBUS. Blocking signals inside process_pending_signals() protects against concurrency problems that would otherwise happen if host_signal_handler() ran and accessed the signal data structures while process_pending_signals() was manipulating them. Since we now track the guest signal mask separately from that of the host, the sigsuspend system calls must track the signal mask passed to them, because when we process signals as we leave the sigsuspend the guest signal mask in force is that passed to sigsuspend. Signed-off-by: Timothy Edward Baldwin <T.E.Baldwin99@members.leeds.ac.uk> Message-id: 1441497448-32489-19-git-send-email-T.E.Baldwin99@members.leeds.ac.uk [PMM: make signal_pending a simple flag rather than a word with two flag bits; ensure we don't call block_signals() twice in sigreturn codepaths; document and assert() the guarantee that using do_sigprocmask() to get the current mask never fails; use the qemu atomics.h functions rather than raw volatile variable access; add extra commentary and documentation; block SIGSEGV/SIGBUS in block_signals() and in process_pending_signals() because they can't occur synchronously here; check the right do_sigprocmask() call for errors in ssetmask syscall; expand commit message; fixed sigsuspend() hanging] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Riku Voipio <riku.voipio@linaro.org>
2016-05-27 17:51:49 +03:00
/* This thread's signal mask, as requested by the guest program.
* The actual signal mask of this thread may differ:
* + we don't let SIGSEGV and SIGBUS be blocked while running guest code
* + sometimes we block all signals to avoid races
*/
sigset_t signal_mask;
/* The signal mask imposed by a guest sigsuspend syscall, if we are
* currently in the middle of such a syscall
*/
sigset_t sigsuspend_mask;
/* Nonzero if we're leaving a sigsuspend and sigsuspend_mask is valid. */
int in_sigsuspend;
/* Nonzero if process_pending_signals() needs to do something (either
* handle a pending signal or unblock signals).
* This flag is written from a signal handler so should be accessed via
* the qatomic_read() and qatomic_set() functions. (It is not accessed
linux-user: Fix race between multiple signals If multiple host signals are received in quick succession they would be queued in TaskState then delivered to the guest in spite of signals being supposed to be blocked by the guest signal handler's sa_mask. Fix this by decoupling the guest signal mask from the host signal mask, so we can have protected sections where all host signals are blocked. In particular we block signals from when host_signal_handler() queues a signal from the guest until process_pending_signals() has unqueued it. We also block signals while we are manipulating the guest signal mask in emulation of sigprocmask and similar syscalls. Blocking host signals also ensures the correct behaviour with respect to multiple threads and the overrun count of timer related signals. Alas blocking and queuing in qemu is still needed because of virtual processor exceptions, SIGSEGV and SIGBUS. Blocking signals inside process_pending_signals() protects against concurrency problems that would otherwise happen if host_signal_handler() ran and accessed the signal data structures while process_pending_signals() was manipulating them. Since we now track the guest signal mask separately from that of the host, the sigsuspend system calls must track the signal mask passed to them, because when we process signals as we leave the sigsuspend the guest signal mask in force is that passed to sigsuspend. Signed-off-by: Timothy Edward Baldwin <T.E.Baldwin99@members.leeds.ac.uk> Message-id: 1441497448-32489-19-git-send-email-T.E.Baldwin99@members.leeds.ac.uk [PMM: make signal_pending a simple flag rather than a word with two flag bits; ensure we don't call block_signals() twice in sigreturn codepaths; document and assert() the guarantee that using do_sigprocmask() to get the current mask never fails; use the qemu atomics.h functions rather than raw volatile variable access; add extra commentary and documentation; block SIGSEGV/SIGBUS in block_signals() and in process_pending_signals() because they can't occur synchronously here; check the right do_sigprocmask() call for errors in ssetmask syscall; expand commit message; fixed sigsuspend() hanging] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Riku Voipio <riku.voipio@linaro.org>
2016-05-27 17:51:49 +03:00
* from multiple threads.)
*/
int signal_pending;
/* This thread's sigaltstack, if it has one */
struct target_sigaltstack sigaltstack_used;
} __attribute__((aligned(16))) TaskState;
extern char *exec_path;
void init_task_state(TaskState *ts);
void task_settid(TaskState *);
void stop_all_tasks(void);
extern const char *qemu_uname_release;
extern unsigned long mmap_min_addr;
/* ??? See if we can avoid exposing so much of the loader internals. */
/* Read a good amount of data initially, to hopefully get all the
program headers loaded. */
#define BPRM_BUF_SIZE 1024
/*
* This structure is used to hold the arguments that are
* used when loading binaries.
*/
struct linux_binprm {
char buf[BPRM_BUF_SIZE] __attribute__((aligned));
abi_ulong p;
avoid TABs in files that only contain a few Most files that have TABs only contain a handful of them. Change them to spaces so that we don't confuse people. disas, standard-headers, linux-headers and libdecnumber are imported from other projects and probably should be exempted from the check. Outside those, after this patch the following files still contain both 8-space and TAB sequences at the beginning of the line. Many of them have a majority of TABs, or were initially committed with all tabs. bsd-user/i386/target_syscall.h bsd-user/x86_64/target_syscall.h crypto/aes.c hw/audio/fmopl.c hw/audio/fmopl.h hw/block/tc58128.c hw/display/cirrus_vga.c hw/display/xenfb.c hw/dma/etraxfs_dma.c hw/intc/sh_intc.c hw/misc/mst_fpga.c hw/net/pcnet.c hw/sh4/sh7750.c hw/timer/m48t59.c hw/timer/sh_timer.c include/crypto/aes.h include/disas/bfd.h include/hw/sh4/sh.h libdecnumber/decNumber.c linux-headers/asm-generic/unistd.h linux-headers/linux/kvm.h linux-user/alpha/target_syscall.h linux-user/arm/nwfpe/double_cpdo.c linux-user/arm/nwfpe/fpa11_cpdt.c linux-user/arm/nwfpe/fpa11_cprt.c linux-user/arm/nwfpe/fpa11.h linux-user/flat.h linux-user/flatload.c linux-user/i386/target_syscall.h linux-user/ppc/target_syscall.h linux-user/sparc/target_syscall.h linux-user/syscall.c linux-user/syscall_defs.h linux-user/x86_64/target_syscall.h slirp/cksum.c slirp/if.c slirp/ip.h slirp/ip_icmp.c slirp/ip_icmp.h slirp/ip_input.c slirp/ip_output.c slirp/mbuf.c slirp/misc.c slirp/sbuf.c slirp/socket.c slirp/socket.h slirp/tcp_input.c slirp/tcpip.h slirp/tcp_output.c slirp/tcp_subr.c slirp/tcp_timer.c slirp/tftp.c slirp/udp.c slirp/udp.h target/cris/cpu.h target/cris/mmu.c target/cris/op_helper.c target/sh4/helper.c target/sh4/op_helper.c target/sh4/translate.c tcg/sparc/tcg-target.inc.c tests/tcg/cris/check_addo.c tests/tcg/cris/check_moveq.c tests/tcg/cris/check_swap.c tests/tcg/multiarch/test-mmap.c ui/vnc-enc-hextile-template.h ui/vnc-enc-zywrle.h util/envlist.c util/readline.c The following have only TABs: bsd-user/i386/target_signal.h bsd-user/sparc64/target_signal.h bsd-user/sparc64/target_syscall.h bsd-user/sparc/target_signal.h bsd-user/sparc/target_syscall.h bsd-user/x86_64/target_signal.h crypto/desrfb.c hw/audio/intel-hda-defs.h hw/core/uboot_image.h hw/sh4/sh7750_regnames.c hw/sh4/sh7750_regs.h include/hw/cris/etraxfs_dma.h linux-user/alpha/termbits.h linux-user/arm/nwfpe/fpopcode.h linux-user/arm/nwfpe/fpsr.h linux-user/arm/syscall_nr.h linux-user/arm/target_signal.h linux-user/cris/target_signal.h linux-user/i386/target_signal.h linux-user/linux_loop.h linux-user/m68k/target_signal.h linux-user/microblaze/target_signal.h linux-user/mips64/target_signal.h linux-user/mips/target_signal.h linux-user/mips/target_syscall.h linux-user/mips/termbits.h linux-user/ppc/target_signal.h linux-user/sh4/target_signal.h linux-user/sh4/termbits.h linux-user/sparc64/target_syscall.h linux-user/sparc/target_signal.h linux-user/x86_64/target_signal.h linux-user/x86_64/termbits.h pc-bios/optionrom/optionrom.h slirp/mbuf.h slirp/misc.h slirp/sbuf.h slirp/tcp.h slirp/tcp_timer.h slirp/tcp_var.h target/i386/svm.h target/sparc/asi.h target/xtensa/core-dc232b/xtensa-modules.inc.c target/xtensa/core-dc233c/xtensa-modules.inc.c target/xtensa/core-de212/core-isa.h target/xtensa/core-de212/xtensa-modules.inc.c target/xtensa/core-fsf/xtensa-modules.inc.c target/xtensa/core-sample_controller/core-isa.h target/xtensa/core-sample_controller/xtensa-modules.inc.c target/xtensa/core-test_kc705_be/core-isa.h target/xtensa/core-test_kc705_be/xtensa-modules.inc.c tests/tcg/cris/check_abs.c tests/tcg/cris/check_addc.c tests/tcg/cris/check_addcm.c tests/tcg/cris/check_addoq.c tests/tcg/cris/check_bound.c tests/tcg/cris/check_ftag.c tests/tcg/cris/check_int64.c tests/tcg/cris/check_lz.c tests/tcg/cris/check_openpf5.c tests/tcg/cris/check_sigalrm.c tests/tcg/cris/crisutils.h tests/tcg/cris/sys.c tests/tcg/i386/test-i386-ssse3.c ui/vgafont.h Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20181213223737.11793-3-pbonzini@redhat.com> Reviewed-by: Aleksandar Markovic <amarkovic@wavecomp.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> Acked-by: Richard Henderson <richard.henderson@linaro.org> Acked-by: Eric Blake <eblake@redhat.com> Acked-by: David Gibson <david@gibson.dropbear.id.au> Reviewed-by: Stefan Markovic <smarkovic@wavecomp.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2018-12-14 01:37:37 +03:00
int fd;
int e_uid, e_gid;
int argc, envc;
char **argv;
char **envp;
char * filename; /* Name of binary */
int (*core_dump)(int, const CPUArchState *); /* coredump routine */
};
linux-user: Add strace support for printing arguments of ioctl() This patch implements functionality for strace argument printing for ioctls. When running ioctls through qemu with "-strace", they get printed in format: "ioctl(fd_num,0x*,0x*) = ret_value" where the request code an the ioctl's third argument get printed in a hexadicemal format. This patch changes that by enabling strace to print both the request code name and the contents of the third argument. For example, when running ioctl RTC_SET_TIME with "-strace", with changes from this patch, it gets printed in this way: "ioctl(3,RTC_SET_TIME,{12,13,15,20,10,119,0,0,0}) = 0" In case of IOC_R type ioctls, the contents of the third argument get printed after the return value, and the argument inside the ioctl call gets printed as pointer in hexadecimal format. For example, when running RTC_RD_TIME with "-strace", with changes from this patch, it gets printed in this way: "ioctl(3,RTC_RD_TIME,0x40800374) = 0 ({22,9,13,11,5,120,0,0,0})" In case of IOC_RW type ioctls, the contents of the third argument get printed both inside the ioctl call and after the return value. Implementation notes: Functions "print_ioctl()" and "print_syscall_ret_ioctl()", that are defined in "strace.c", are listed in file "strace.list" as "call" and "result" value for ioctl. Structure definition "IOCTLEntry" as well as predefined values for IOC_R, IOC_W and IOC_RW were cut and pasted from file "syscall.c" to file "qemu.h" so that they can be used by these functions to print the contents of the third ioctl argument. Also, the "static" identifier for array "ioctl_entries[]" was removed and this array was declared as "extern" in "qemu.h" so that it can also be used by these functions. To decode the structure type of the ioctl third argument, function "thunk_print()" was defined in file "thunk.c" and its definition is somewhat simillar to that of function "thunk_convert()". Signed-off-by: Filip Bozuta <Filip.Bozuta@syrmia.com> Reviewed-by: Laurent Vivier <laurent@vivier.eu> Message-Id: <20200619124727.18080-3-filip.bozuta@syrmia.com> [lv: fix close-bracket] Signed-off-by: Laurent Vivier <laurent@vivier.eu>
2020-06-19 15:47:27 +03:00
typedef struct IOCTLEntry IOCTLEntry;
typedef abi_long do_ioctl_fn(const IOCTLEntry *ie, uint8_t *buf_temp,
int fd, int cmd, abi_long arg);
struct IOCTLEntry {
int target_cmd;
unsigned int host_cmd;
const char *name;
int access;
do_ioctl_fn *do_ioctl;
const argtype arg_type[5];
};
extern IOCTLEntry ioctl_entries[];
#define IOC_R 0x0001
#define IOC_W 0x0002
#define IOC_RW (IOC_R | IOC_W)
void do_init_thread(struct target_pt_regs *regs, struct image_info *infop);
abi_ulong loader_build_argptr(int envc, int argc, abi_ulong sp,
abi_ulong stringp, int push_ptr);
int loader_exec(int fdexec, const char *filename, char **argv, char **envp,
struct target_pt_regs * regs, struct image_info *infop,
struct linux_binprm *);
/* Returns true if the image uses the FDPIC ABI. If this is the case,
* we have to provide some information (loadmap, pt_dynamic_info) such
* that the program can be relocated adequately. This is also useful
* when handling signals.
*/
int info_is_fdpic(struct image_info *info);
uint32_t get_elf_eflags(int fd);
int load_elf_binary(struct linux_binprm *bprm, struct image_info *info);
int load_flt_binary(struct linux_binprm *bprm, struct image_info *info);
abi_long memcpy_to_target(abi_ulong dest, const void *src,
unsigned long len);
void target_set_brk(abi_ulong new_brk);
abi_long do_brk(abi_ulong new_brk);
void syscall_init(void);
abi_long do_syscall(void *cpu_env, int num, abi_long arg1,
abi_long arg2, abi_long arg3, abi_long arg4,
abi_long arg5, abi_long arg6, abi_long arg7,
abi_long arg8);
extern __thread CPUState *thread_cpu;
void cpu_loop(CPUArchState *env);
const char *target_strerror(int err);
int get_osversion(void);
void init_qemu_uname_release(void);
void fork_start(void);
void fork_end(int child);
/**
* probe_guest_base:
* @image_name: the executable being loaded
* @loaddr: the lowest fixed address in the executable
* @hiaddr: the highest fixed address in the executable
*
* Creates the initial guest address space in the host memory space.
*
* If @loaddr == 0, then no address in the executable is fixed,
* i.e. it is fully relocatable. In that case @hiaddr is the size
* of the executable.
*
* This function will not return if a valid value for guest_base
* cannot be chosen. On return, the executable loader can expect
*
* target_mmap(loaddr, hiaddr - loaddr, ...)
*
* to succeed.
*/
void probe_guest_base(const char *image_name,
abi_ulong loaddr, abi_ulong hiaddr);
#include "qemu/log.h"
linux-user: Provide safe_syscall for fixing races between signals and syscalls If a signal is delivered immediately before a blocking system call the handler will only be called after the system call returns, which may be a long time later or never. This is fixed by using a function (safe_syscall) that checks if a guest signal is pending prior to making a system call, and if so does not call the system call and returns -TARGET_ERESTARTSYS. If a signal is received between the check and the system call host_signal_handler() rewinds execution to before the check. This rewinding has the effect of closing the race window so that safe_syscall will reliably either (a) go into the host syscall with no unprocessed guest signals pending or or (b) return -TARGET_ERESTARTSYS so that the caller can deal with the signals. Implementing this requires a per-host-architecture assembly language fragment. This will also resolve the mishandling of the SA_RESTART flag where we would restart a host system call and not call the guest signal handler until the syscall finally completed -- syscall restarting now always happens at the guest syscall level so the guest signal handler will run. (The host syscall will never be restarted because if the host kernel rewinds the PC to point at the syscall insn for a restart then our host_signal_handler() will see this and arrange the guest PC rewind.) This commit contains the infrastructure for implementing safe_syscall and the assembly language fragment for x86-64, but does not change any syscalls to use it. Signed-off-by: Timothy Edward Baldwin <T.E.Baldwin99@members.leeds.ac.uk> Message-id: 1441497448-32489-14-git-send-email-T.E.Baldwin99@members.leeds.ac.uk [PMM: * Avoid having an architecture if-ladder in configure by putting linux-user/host/$(ARCH) on the include path and including safe-syscall.inc.S from it * Avoid ifdef ladder in signal.c by creating new hostdep.h to hold host-architecture-specific things * Added copyright/license header to safe-syscall.inc.S * Rewrote commit message * Added comments to safe-syscall.inc.S * Changed calling convention of safe_syscall() to match syscall() (returns -1 and host error in errno on failure) * Added a long comment in qemu.h about how to use safe_syscall() to implement guest syscalls. ] RV: squashed Peters "fixup! linux-user: compile on non-x86-64 hosts" patch Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2016-05-12 20:47:46 +03:00
/* safe_syscall.S */
/**
* safe_syscall:
* @int number: number of system call to make
* ...: arguments to the system call
*
* Call a system call if guest signal not pending.
* This has the same API as the libc syscall() function, except that it
* may return -1 with errno == TARGET_ERESTARTSYS if a signal was pending.
*
* Returns: the system call result, or -1 with an error code in errno
* (Errnos are host errnos; we rely on TARGET_ERESTARTSYS not clashing
* with any of the host errno values.)
*/
/* A guide to using safe_syscall() to handle interactions between guest
* syscalls and guest signals:
*
* Guest syscalls come in two flavours:
*
* (1) Non-interruptible syscalls
*
* These are guest syscalls that never get interrupted by signals and
* so never return EINTR. They can be implemented straightforwardly in
* QEMU: just make sure that if the implementation code has to make any
* blocking calls that those calls are retried if they return EINTR.
* It's also OK to implement these with safe_syscall, though it will be
* a little less efficient if a signal is delivered at the 'wrong' moment.
*
linux-user: Fix race between multiple signals If multiple host signals are received in quick succession they would be queued in TaskState then delivered to the guest in spite of signals being supposed to be blocked by the guest signal handler's sa_mask. Fix this by decoupling the guest signal mask from the host signal mask, so we can have protected sections where all host signals are blocked. In particular we block signals from when host_signal_handler() queues a signal from the guest until process_pending_signals() has unqueued it. We also block signals while we are manipulating the guest signal mask in emulation of sigprocmask and similar syscalls. Blocking host signals also ensures the correct behaviour with respect to multiple threads and the overrun count of timer related signals. Alas blocking and queuing in qemu is still needed because of virtual processor exceptions, SIGSEGV and SIGBUS. Blocking signals inside process_pending_signals() protects against concurrency problems that would otherwise happen if host_signal_handler() ran and accessed the signal data structures while process_pending_signals() was manipulating them. Since we now track the guest signal mask separately from that of the host, the sigsuspend system calls must track the signal mask passed to them, because when we process signals as we leave the sigsuspend the guest signal mask in force is that passed to sigsuspend. Signed-off-by: Timothy Edward Baldwin <T.E.Baldwin99@members.leeds.ac.uk> Message-id: 1441497448-32489-19-git-send-email-T.E.Baldwin99@members.leeds.ac.uk [PMM: make signal_pending a simple flag rather than a word with two flag bits; ensure we don't call block_signals() twice in sigreturn codepaths; document and assert() the guarantee that using do_sigprocmask() to get the current mask never fails; use the qemu atomics.h functions rather than raw volatile variable access; add extra commentary and documentation; block SIGSEGV/SIGBUS in block_signals() and in process_pending_signals() because they can't occur synchronously here; check the right do_sigprocmask() call for errors in ssetmask syscall; expand commit message; fixed sigsuspend() hanging] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Riku Voipio <riku.voipio@linaro.org>
2016-05-27 17:51:49 +03:00
* Some non-interruptible syscalls need to be handled using block_signals()
* to block signals for the duration of the syscall. This mainly applies
* to code which needs to modify the data structures used by the
* host_signal_handler() function and the functions it calls, including
* all syscalls which change the thread's signal mask.
*
linux-user: Provide safe_syscall for fixing races between signals and syscalls If a signal is delivered immediately before a blocking system call the handler will only be called after the system call returns, which may be a long time later or never. This is fixed by using a function (safe_syscall) that checks if a guest signal is pending prior to making a system call, and if so does not call the system call and returns -TARGET_ERESTARTSYS. If a signal is received between the check and the system call host_signal_handler() rewinds execution to before the check. This rewinding has the effect of closing the race window so that safe_syscall will reliably either (a) go into the host syscall with no unprocessed guest signals pending or or (b) return -TARGET_ERESTARTSYS so that the caller can deal with the signals. Implementing this requires a per-host-architecture assembly language fragment. This will also resolve the mishandling of the SA_RESTART flag where we would restart a host system call and not call the guest signal handler until the syscall finally completed -- syscall restarting now always happens at the guest syscall level so the guest signal handler will run. (The host syscall will never be restarted because if the host kernel rewinds the PC to point at the syscall insn for a restart then our host_signal_handler() will see this and arrange the guest PC rewind.) This commit contains the infrastructure for implementing safe_syscall and the assembly language fragment for x86-64, but does not change any syscalls to use it. Signed-off-by: Timothy Edward Baldwin <T.E.Baldwin99@members.leeds.ac.uk> Message-id: 1441497448-32489-14-git-send-email-T.E.Baldwin99@members.leeds.ac.uk [PMM: * Avoid having an architecture if-ladder in configure by putting linux-user/host/$(ARCH) on the include path and including safe-syscall.inc.S from it * Avoid ifdef ladder in signal.c by creating new hostdep.h to hold host-architecture-specific things * Added copyright/license header to safe-syscall.inc.S * Rewrote commit message * Added comments to safe-syscall.inc.S * Changed calling convention of safe_syscall() to match syscall() (returns -1 and host error in errno on failure) * Added a long comment in qemu.h about how to use safe_syscall() to implement guest syscalls. ] RV: squashed Peters "fixup! linux-user: compile on non-x86-64 hosts" patch Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2016-05-12 20:47:46 +03:00
* (2) Interruptible syscalls
*
* These are guest syscalls that can be interrupted by signals and
* for which we need to either return EINTR or arrange for the guest
* syscall to be restarted. This category includes both syscalls which
* always restart (and in the kernel return -ERESTARTNOINTR), ones
* which only restart if there is no handler (kernel returns -ERESTARTNOHAND
* or -ERESTART_RESTARTBLOCK), and the most common kind which restart
* if the handler was registered with SA_RESTART (kernel returns
* -ERESTARTSYS). System calls which are only interruptible in some
* situations (like 'open') also need to be handled this way.
*
* Here it is important that the host syscall is made
* via this safe_syscall() function, and *not* via the host libc.
* If the host libc is used then the implementation will appear to work
* most of the time, but there will be a race condition where a
* signal could arrive just before we make the host syscall inside libc,
* and then then guest syscall will not correctly be interrupted.
* Instead the implementation of the guest syscall can use the safe_syscall
* function but otherwise just return the result or errno in the usual
* way; the main loop code will take care of restarting the syscall
* if appropriate.
*
* (If the implementation needs to make multiple host syscalls this is
* OK; any which might really block must be via safe_syscall(); for those
* which are only technically blocking (ie which we know in practice won't
* stay in the host kernel indefinitely) it's OK to use libc if necessary.
* You must be able to cope with backing out correctly if some safe_syscall
* you make in the implementation returns either -TARGET_ERESTARTSYS or
* EINTR though.)
*
linux-user: Fix race between multiple signals If multiple host signals are received in quick succession they would be queued in TaskState then delivered to the guest in spite of signals being supposed to be blocked by the guest signal handler's sa_mask. Fix this by decoupling the guest signal mask from the host signal mask, so we can have protected sections where all host signals are blocked. In particular we block signals from when host_signal_handler() queues a signal from the guest until process_pending_signals() has unqueued it. We also block signals while we are manipulating the guest signal mask in emulation of sigprocmask and similar syscalls. Blocking host signals also ensures the correct behaviour with respect to multiple threads and the overrun count of timer related signals. Alas blocking and queuing in qemu is still needed because of virtual processor exceptions, SIGSEGV and SIGBUS. Blocking signals inside process_pending_signals() protects against concurrency problems that would otherwise happen if host_signal_handler() ran and accessed the signal data structures while process_pending_signals() was manipulating them. Since we now track the guest signal mask separately from that of the host, the sigsuspend system calls must track the signal mask passed to them, because when we process signals as we leave the sigsuspend the guest signal mask in force is that passed to sigsuspend. Signed-off-by: Timothy Edward Baldwin <T.E.Baldwin99@members.leeds.ac.uk> Message-id: 1441497448-32489-19-git-send-email-T.E.Baldwin99@members.leeds.ac.uk [PMM: make signal_pending a simple flag rather than a word with two flag bits; ensure we don't call block_signals() twice in sigreturn codepaths; document and assert() the guarantee that using do_sigprocmask() to get the current mask never fails; use the qemu atomics.h functions rather than raw volatile variable access; add extra commentary and documentation; block SIGSEGV/SIGBUS in block_signals() and in process_pending_signals() because they can't occur synchronously here; check the right do_sigprocmask() call for errors in ssetmask syscall; expand commit message; fixed sigsuspend() hanging] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Riku Voipio <riku.voipio@linaro.org>
2016-05-27 17:51:49 +03:00
* block_signals() cannot be used for interruptible syscalls.
*
linux-user: Provide safe_syscall for fixing races between signals and syscalls If a signal is delivered immediately before a blocking system call the handler will only be called after the system call returns, which may be a long time later or never. This is fixed by using a function (safe_syscall) that checks if a guest signal is pending prior to making a system call, and if so does not call the system call and returns -TARGET_ERESTARTSYS. If a signal is received between the check and the system call host_signal_handler() rewinds execution to before the check. This rewinding has the effect of closing the race window so that safe_syscall will reliably either (a) go into the host syscall with no unprocessed guest signals pending or or (b) return -TARGET_ERESTARTSYS so that the caller can deal with the signals. Implementing this requires a per-host-architecture assembly language fragment. This will also resolve the mishandling of the SA_RESTART flag where we would restart a host system call and not call the guest signal handler until the syscall finally completed -- syscall restarting now always happens at the guest syscall level so the guest signal handler will run. (The host syscall will never be restarted because if the host kernel rewinds the PC to point at the syscall insn for a restart then our host_signal_handler() will see this and arrange the guest PC rewind.) This commit contains the infrastructure for implementing safe_syscall and the assembly language fragment for x86-64, but does not change any syscalls to use it. Signed-off-by: Timothy Edward Baldwin <T.E.Baldwin99@members.leeds.ac.uk> Message-id: 1441497448-32489-14-git-send-email-T.E.Baldwin99@members.leeds.ac.uk [PMM: * Avoid having an architecture if-ladder in configure by putting linux-user/host/$(ARCH) on the include path and including safe-syscall.inc.S from it * Avoid ifdef ladder in signal.c by creating new hostdep.h to hold host-architecture-specific things * Added copyright/license header to safe-syscall.inc.S * Rewrote commit message * Added comments to safe-syscall.inc.S * Changed calling convention of safe_syscall() to match syscall() (returns -1 and host error in errno on failure) * Added a long comment in qemu.h about how to use safe_syscall() to implement guest syscalls. ] RV: squashed Peters "fixup! linux-user: compile on non-x86-64 hosts" patch Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2016-05-12 20:47:46 +03:00
*
* How and why the safe_syscall implementation works:
*
* The basic setup is that we make the host syscall via a known
* section of host native assembly. If a signal occurs, our signal
* handler checks the interrupted host PC against the addresse of that
* known section. If the PC is before or at the address of the syscall
* instruction then we change the PC to point at a "return
* -TARGET_ERESTARTSYS" code path instead, and then exit the signal handler
* (causing the safe_syscall() call to immediately return that value).
* Then in the main.c loop if we see this magic return value we adjust
* the guest PC to wind it back to before the system call, and invoke
* the guest signal handler as usual.
*
* This winding-back will happen in two cases:
* (1) signal came in just before we took the host syscall (a race);
* in this case we'll take the guest signal and have another go
* at the syscall afterwards, and this is indistinguishable for the
* guest from the timing having been different such that the guest
* signal really did win the race
* (2) signal came in while the host syscall was blocking, and the
* host kernel decided the syscall should be restarted;
* in this case we want to restart the guest syscall also, and so
* rewinding is the right thing. (Note that "restart" semantics mean
* "first call the signal handler, then reattempt the syscall".)
* The other situation to consider is when a signal came in while the
* host syscall was blocking, and the host kernel decided that the syscall
* should not be restarted; in this case QEMU's host signal handler will
* be invoked with the PC pointing just after the syscall instruction,
* with registers indicating an EINTR return; the special code in the
* handler will not kick in, and we will return EINTR to the guest as
* we should.
*
* Notice that we can leave the host kernel to make the decision for
* us about whether to do a restart of the syscall or not; we do not
* need to check SA_RESTART flags in QEMU or distinguish the various
* kinds of restartability.
*/
#ifdef HAVE_SAFE_SYSCALL
/* The core part of this function is implemented in assembly */
extern long safe_syscall_base(int *pending, long number, ...);
#define safe_syscall(...) \
({ \
long ret_; \
int *psp_ = &((TaskState *)thread_cpu->opaque)->signal_pending; \
ret_ = safe_syscall_base(psp_, __VA_ARGS__); \
if (is_error(ret_)) { \
errno = -ret_; \
ret_ = -1; \
} \
ret_; \
})
#else
/* Fallback for architectures which don't yet provide a safe-syscall assembly
* fragment; note that this is racy!
* This should go away when all host architectures have been updated.
*/
#define safe_syscall syscall
#endif
/* syscall.c */
int host_to_target_waitstatus(int status);
/* strace.c */
void print_syscall(void *cpu_env, int num,
abi_long arg1, abi_long arg2, abi_long arg3,
abi_long arg4, abi_long arg5, abi_long arg6);
void print_syscall_ret(void *cpu_env, int num, abi_long ret,
linux-user: Extend strace support to enable argument printing after syscall execution Structure "struct syscallname" in file "strace.c" is used for "-strace" to print arguments and return values of syscalls. The last field of this structure "result" represents the calling function that prints the return values. This field was extended in this patch so that this function takes all syscalls arguments beside the return value. In this way, it enables "-strace" to print arguments of syscalls that have changed after the syscall execution. This extension will be useful as there are many syscalls that return values inside their arguments (i.e. listxattr() that returns the list of extended attributes inside the "list" argument). Implementation notes: Since there are already three existing "print_syscall_ret*" functions inside "strace.c" ("print_syscall_ret_addr()", "print_syscall_ret_adjtimex()", "print_syscall_ret_newselect()"), they were changed to have all syscall arguments beside the return value. This was done so that these functions don't cause build errors (even though syscall arguments are not used in these functions). There is code repetition in these functions for checking the return value and printing the approppriate error message (this code is also located in print_syscall_ret() at the end of "strace.c"). That is the reason why a function "syscall_print_err()" was added for this code and put inside these functions. Functions "print_newselect()" and "print_syscall_ret_newselect()" were changed to use this new implemented functionality and not store the syscall argument values in separate static variables. Signed-off-by: Filip Bozuta <Filip.Bozuta@syrmia.com> Reviewed-by: Laurent Vivier <laurent@vivier.eu> Message-Id: <20200619123331.17387-2-filip.bozuta@syrmia.com> Signed-off-by: Laurent Vivier <laurent@vivier.eu>
2020-06-19 15:33:26 +03:00
abi_long arg1, abi_long arg2, abi_long arg3,
abi_long arg4, abi_long arg5, abi_long arg6);
/**
* print_taken_signal:
* @target_signum: target signal being taken
* @tinfo: target_siginfo_t which will be passed to the guest for the signal
*
* Print strace output indicating that this signal is being taken by the guest,
* in a format similar to:
* --- SIGSEGV {si_signo=SIGSEGV, si_code=SI_KERNEL, si_addr=0} ---
*/
void print_taken_signal(int target_signum, const target_siginfo_t *tinfo);
/* signal.c */
void process_pending_signals(CPUArchState *cpu_env);
void signal_init(void);
int queue_signal(CPUArchState *env, int sig, int si_type,
target_siginfo_t *info);
void host_to_target_siginfo(target_siginfo_t *tinfo, const siginfo_t *info);
void target_to_host_siginfo(siginfo_t *info, const target_siginfo_t *tinfo);
int target_to_host_signal(int sig);
int host_to_target_signal(int sig);
long do_sigreturn(CPUArchState *env);
long do_rt_sigreturn(CPUArchState *env);
abi_long do_sigaltstack(abi_ulong uss_addr, abi_ulong uoss_addr, abi_ulong sp);
int do_sigprocmask(int how, const sigset_t *set, sigset_t *oldset);
abi_long do_swapcontext(CPUArchState *env, abi_ulong uold_ctx,
abi_ulong unew_ctx, abi_long ctx_size);
linux-user: Fix race between multiple signals If multiple host signals are received in quick succession they would be queued in TaskState then delivered to the guest in spite of signals being supposed to be blocked by the guest signal handler's sa_mask. Fix this by decoupling the guest signal mask from the host signal mask, so we can have protected sections where all host signals are blocked. In particular we block signals from when host_signal_handler() queues a signal from the guest until process_pending_signals() has unqueued it. We also block signals while we are manipulating the guest signal mask in emulation of sigprocmask and similar syscalls. Blocking host signals also ensures the correct behaviour with respect to multiple threads and the overrun count of timer related signals. Alas blocking and queuing in qemu is still needed because of virtual processor exceptions, SIGSEGV and SIGBUS. Blocking signals inside process_pending_signals() protects against concurrency problems that would otherwise happen if host_signal_handler() ran and accessed the signal data structures while process_pending_signals() was manipulating them. Since we now track the guest signal mask separately from that of the host, the sigsuspend system calls must track the signal mask passed to them, because when we process signals as we leave the sigsuspend the guest signal mask in force is that passed to sigsuspend. Signed-off-by: Timothy Edward Baldwin <T.E.Baldwin99@members.leeds.ac.uk> Message-id: 1441497448-32489-19-git-send-email-T.E.Baldwin99@members.leeds.ac.uk [PMM: make signal_pending a simple flag rather than a word with two flag bits; ensure we don't call block_signals() twice in sigreturn codepaths; document and assert() the guarantee that using do_sigprocmask() to get the current mask never fails; use the qemu atomics.h functions rather than raw volatile variable access; add extra commentary and documentation; block SIGSEGV/SIGBUS in block_signals() and in process_pending_signals() because they can't occur synchronously here; check the right do_sigprocmask() call for errors in ssetmask syscall; expand commit message; fixed sigsuspend() hanging] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Riku Voipio <riku.voipio@linaro.org>
2016-05-27 17:51:49 +03:00
/**
* block_signals: block all signals while handling this guest syscall
*
* Block all signals, and arrange that the signal mask is returned to
* its correct value for the guest before we resume execution of guest code.
* If this function returns non-zero, then the caller should immediately
* return -TARGET_ERESTARTSYS to the main loop, which will take the pending
* signal and restart execution of the syscall.
* If block_signals() returns zero, then the caller can continue with
* emulation of the system call knowing that no signals can be taken
* (and therefore that no race conditions will result).
* This should only be called once, because if it is called a second time
* it will always return non-zero. (Think of it like a mutex that can't
* be recursively locked.)
* Signals will be unblocked again by process_pending_signals().
*
* Return value: non-zero if there was a pending signal, zero if not.
*/
int block_signals(void); /* Returns non zero if signal pending */
#ifdef TARGET_I386
/* vm86.c */
void save_v86_state(CPUX86State *env);
void handle_vm86_trap(CPUX86State *env, int trapno);
void handle_vm86_fault(CPUX86State *env);
int do_vm86(CPUX86State *env, long subfunction, abi_ulong v86_addr);
#elif defined(TARGET_SPARC64)
void sparc64_set_context(CPUSPARCState *env);
void sparc64_get_context(CPUSPARCState *env);
#endif
/* mmap.c */
int target_mprotect(abi_ulong start, abi_ulong len, int prot);
abi_long target_mmap(abi_ulong start, abi_ulong len, int prot,
int flags, int fd, abi_ulong offset);
int target_munmap(abi_ulong start, abi_ulong len);
abi_long target_mremap(abi_ulong old_addr, abi_ulong old_size,
abi_ulong new_size, unsigned long flags,
abi_ulong new_addr);
extern unsigned long last_brk;
extern abi_ulong mmap_next_start;
abi_ulong mmap_find_vma(abi_ulong, abi_ulong, abi_ulong);
void mmap_fork_start(void);
void mmap_fork_end(int child);
/* main.c */
extern unsigned long guest_stack_size;
/* user access */
#define VERIFY_READ 0
#define VERIFY_WRITE 1 /* implies read access */
static inline int access_ok(int type, abi_ulong addr, abi_ulong size)
{
return guest_addr_valid(addr) &&
(size == 0 || guest_addr_valid(addr + size - 1)) &&
page_check_range((target_ulong)addr, size,
(type == VERIFY_READ) ? PAGE_READ : (PAGE_READ | PAGE_WRITE)) == 0;
}
/* NOTE __get_user and __put_user use host pointers and don't check access.
These are usually used to access struct data members once the struct has
been locked - usually with lock_user_struct. */
/*
* Tricky points:
* - Use __builtin_choose_expr to avoid type promotion from ?:,
* - Invalid sizes result in a compile time error stemming from
* the fact that abort has no parameters.
* - It's easier to use the endian-specific unaligned load/store
* functions than host-endian unaligned load/store plus tswapN.
* - The pragmas are necessary only to silence a clang false-positive
* warning: see https://bugs.llvm.org/show_bug.cgi?id=39113 .
* - gcc has bugs in its _Pragma() support in some versions, eg
* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=83256 -- so we only
* include the warning-suppression pragmas for clang
*/
#if defined(__clang__) && __has_warning("-Waddress-of-packed-member")
#define PRAGMA_DISABLE_PACKED_WARNING \
_Pragma("GCC diagnostic push"); \
_Pragma("GCC diagnostic ignored \"-Waddress-of-packed-member\"")
#define PRAGMA_REENABLE_PACKED_WARNING \
_Pragma("GCC diagnostic pop")
#else
#define PRAGMA_DISABLE_PACKED_WARNING
#define PRAGMA_REENABLE_PACKED_WARNING
#endif
#define __put_user_e(x, hptr, e) \
do { \
PRAGMA_DISABLE_PACKED_WARNING; \
(__builtin_choose_expr(sizeof(*(hptr)) == 1, stb_p, \
__builtin_choose_expr(sizeof(*(hptr)) == 2, stw_##e##_p, \
__builtin_choose_expr(sizeof(*(hptr)) == 4, stl_##e##_p, \
__builtin_choose_expr(sizeof(*(hptr)) == 8, stq_##e##_p, abort)))) \
((hptr), (x)), (void)0); \
PRAGMA_REENABLE_PACKED_WARNING; \
} while (0)
#define __get_user_e(x, hptr, e) \
do { \
PRAGMA_DISABLE_PACKED_WARNING; \
((x) = (typeof(*hptr))( \
__builtin_choose_expr(sizeof(*(hptr)) == 1, ldub_p, \
__builtin_choose_expr(sizeof(*(hptr)) == 2, lduw_##e##_p, \
__builtin_choose_expr(sizeof(*(hptr)) == 4, ldl_##e##_p, \
__builtin_choose_expr(sizeof(*(hptr)) == 8, ldq_##e##_p, abort)))) \
(hptr)), (void)0); \
PRAGMA_REENABLE_PACKED_WARNING; \
} while (0)
#ifdef TARGET_WORDS_BIGENDIAN
# define __put_user(x, hptr) __put_user_e(x, hptr, be)
# define __get_user(x, hptr) __get_user_e(x, hptr, be)
#else
# define __put_user(x, hptr) __put_user_e(x, hptr, le)
# define __get_user(x, hptr) __get_user_e(x, hptr, le)
#endif
/* put_user()/get_user() take a guest address and check access */
/* These are usually used to access an atomic data type, such as an int,
* that has been passed by address. These internally perform locking
* and unlocking on the data type.
*/
#define put_user(x, gaddr, target_type) \
({ \
abi_ulong __gaddr = (gaddr); \
target_type *__hptr; \
abi_long __ret = 0; \
if ((__hptr = lock_user(VERIFY_WRITE, __gaddr, sizeof(target_type), 0))) { \
__put_user((x), __hptr); \
unlock_user(__hptr, __gaddr, sizeof(target_type)); \
} else \
__ret = -TARGET_EFAULT; \
__ret; \
})
#define get_user(x, gaddr, target_type) \
({ \
abi_ulong __gaddr = (gaddr); \
target_type *__hptr; \
abi_long __ret = 0; \
if ((__hptr = lock_user(VERIFY_READ, __gaddr, sizeof(target_type), 1))) { \
__get_user((x), __hptr); \
unlock_user(__hptr, __gaddr, 0); \
} else { \
/* avoid warning */ \
(x) = 0; \
__ret = -TARGET_EFAULT; \
} \
__ret; \
})
#define put_user_ual(x, gaddr) put_user((x), (gaddr), abi_ulong)
#define put_user_sal(x, gaddr) put_user((x), (gaddr), abi_long)
#define put_user_u64(x, gaddr) put_user((x), (gaddr), uint64_t)
#define put_user_s64(x, gaddr) put_user((x), (gaddr), int64_t)
#define put_user_u32(x, gaddr) put_user((x), (gaddr), uint32_t)
#define put_user_s32(x, gaddr) put_user((x), (gaddr), int32_t)
#define put_user_u16(x, gaddr) put_user((x), (gaddr), uint16_t)
#define put_user_s16(x, gaddr) put_user((x), (gaddr), int16_t)
#define put_user_u8(x, gaddr) put_user((x), (gaddr), uint8_t)
#define put_user_s8(x, gaddr) put_user((x), (gaddr), int8_t)
#define get_user_ual(x, gaddr) get_user((x), (gaddr), abi_ulong)
#define get_user_sal(x, gaddr) get_user((x), (gaddr), abi_long)
#define get_user_u64(x, gaddr) get_user((x), (gaddr), uint64_t)
#define get_user_s64(x, gaddr) get_user((x), (gaddr), int64_t)
#define get_user_u32(x, gaddr) get_user((x), (gaddr), uint32_t)
#define get_user_s32(x, gaddr) get_user((x), (gaddr), int32_t)
#define get_user_u16(x, gaddr) get_user((x), (gaddr), uint16_t)
#define get_user_s16(x, gaddr) get_user((x), (gaddr), int16_t)
#define get_user_u8(x, gaddr) get_user((x), (gaddr), uint8_t)
#define get_user_s8(x, gaddr) get_user((x), (gaddr), int8_t)
/* copy_from_user() and copy_to_user() are usually used to copy data
* buffers between the target and host. These internally perform
* locking/unlocking of the memory.
*/
abi_long copy_from_user(void *hptr, abi_ulong gaddr, size_t len);
abi_long copy_to_user(abi_ulong gaddr, void *hptr, size_t len);
/* Functions for accessing guest memory. The tget and tput functions
read/write single values, byteswapping as necessary. The lock_user function
gets a pointer to a contiguous area of guest memory, but does not perform
any byteswapping. lock_user may return either a pointer to the guest
memory, or a temporary buffer. */
/* Lock an area of guest memory into the host. If copy is true then the
host area will have the same contents as the guest. */
static inline void *lock_user(int type, abi_ulong guest_addr, long len, int copy)
{
if (!access_ok(type, guest_addr, len))
return NULL;
#ifdef DEBUG_REMAP
{
void *addr;
addr = g_malloc(len);
if (copy)
memcpy(addr, g2h(guest_addr), len);
else
memset(addr, 0, len);
return addr;
}
#else
return g2h(guest_addr);
#endif
}
/* Unlock an area of guest memory. The first LEN bytes must be
flushed back to guest memory. host_ptr = NULL is explicitly
allowed and does nothing. */
static inline void unlock_user(void *host_ptr, abi_ulong guest_addr,
long len)
{
#ifdef DEBUG_REMAP
if (!host_ptr)
return;
if (host_ptr == g2h(guest_addr))
return;
if (len > 0)
memcpy(g2h(guest_addr), host_ptr, len);
g_free(host_ptr);
#endif
}
/* Return the length of a string in target memory or -TARGET_EFAULT if
access error. */
abi_long target_strlen(abi_ulong gaddr);
/* Like lock_user but for null terminated strings. */
static inline void *lock_user_string(abi_ulong guest_addr)
{
abi_long len;
len = target_strlen(guest_addr);
if (len < 0)
return NULL;
return lock_user(VERIFY_READ, guest_addr, (long)(len + 1), 1);
}
/* Helper macros for locking/unlocking a target struct. */
#define lock_user_struct(type, host_ptr, guest_addr, copy) \
(host_ptr = lock_user(type, guest_addr, sizeof(*host_ptr), copy))
#define unlock_user_struct(host_ptr, guest_addr, copy) \
unlock_user(host_ptr, guest_addr, (copy) ? sizeof(*host_ptr) : 0)
#include <pthread.h>
static inline int is_error(abi_long ret)
{
return (abi_ulong)ret >= (abi_ulong)(-4096);
}
2020-06-19 15:33:31 +03:00
#if TARGET_ABI_BITS == 32
static inline uint64_t target_offset64(uint32_t word0, uint32_t word1)
{
#ifdef TARGET_WORDS_BIGENDIAN
return ((uint64_t)word0 << 32) | word1;
#else
return ((uint64_t)word1 << 32) | word0;
#endif
}
#else /* TARGET_ABI_BITS == 32 */
static inline uint64_t target_offset64(uint64_t word0, uint64_t word1)
{
return word0;
}
#endif /* TARGET_ABI_BITS != 32 */
linux-user: Add strace support for printing arguments for ioctls used for terminals and serial lines Functions "print_ioctl()" and "print_syscall_ret_ioctl()" are used to print arguments of "ioctl()" with "-strace". These functions use "thunk_print()", which is defined in "thunk.c", to print the contents of ioctl's third arguments that are not basic types. However, this function doesn't handle ioctls of group ioctl_tty which are used for terminals and serial lines. These ioctls use a type "struct termios" which thunk type is defined in a non standard way using "STRUCT_SPECIAL()". This means that this type is not decoded regularly using "thunk_convert()" and uses special converting functions "target_to_host_termios()" and "host_to_target_termios()", which are defined in "syscall.c" to decode it's values. For simillar reasons, this type is also not printed regularly using "thunk_print()". That is the reason why a separate printing function "print_termios()" is defined in file "strace.c". This function decodes and prints flag values of the "termios" structure. Implementation notes: Function "print_termios()" was implemented in "strace.c" using an existing function "print_flags()" to print flag values of "struct termios" fields. Also, recently implemented function "print_enums()" was also used to print enumareted values which are contained in the fields of 'struct termios'. These flag values were defined using an existing macro "FLAG_TARGET()" that generates aproppriate target flag values and string representations of these flags. Also, the recently defined macro "ENUM_TARGET()" was used to generate aproppriate enumarated values and their respective string representations. Function "print_termios()" was declared in "qemu.h" so that it can be accessed in "syscall.c". Type "StructEntry" defined in "exec/user/thunk.h" contains information that is used to decode structure values. Field "void print(void *arg)" was added in this structure as a special print function. Also, function "thunk_print()" was changed a little so that it uses this special print function in case it is defined. This printing function was instantiated with the defined "print_termios()" in "syscall.c" in "struct_termios_def". Signed-off-by: Filip Bozuta <Filip.Bozuta@syrmia.com> Reviewed-by: Laurent Vivier <laurent@vivier.eu> Message-Id: <20200723210233.349690-4-Filip.Bozuta@syrmia.com> Signed-off-by: Laurent Vivier <laurent@vivier.eu>
2020-07-24 00:02:33 +03:00
void print_termios(void *arg);
linux-user: Add strace support for printing arguments of truncate()/ftruncate() and getsid() This patch implements strace argument printing functionality for following syscalls: * truncate, ftruncate - truncate a file to a specified length int truncate/truncate64(const char *path, off_t length) int ftruncate/ftruncate64(int fd, off_t length) man page: https://man7.org/linux/man-pages/man2/truncate.2.html * getsid - get session ID pid_t getsid(pid_t pid) man page: https://man7.org/linux/man-pages/man2/getsid.2.html Implementation notes: Syscalls truncate/truncate64 take string argument types and thus a separate print function "print_truncate/print_truncate64" is stated in file "strace.list". This function is defined and implemented in "strace.c" by using an existing function used to print string arguments: "print_string()". For syscall ftruncate64, a separate printing function was also stated in "strace.c" as it requires a special kind of handling. The other syscalls have only primitive argument types, so the rest of the implementation was handled by stating an appropriate printing format in file "strace.list". Function "regpairs_aligned()" was cut & pasted from "syscall.c" to "qemu.h" as it is used by functions "print_truncate64()" and "print_ftruncate64()" to print the offset arguments of "truncate64()" and "ftruncate64()". Signed-off-by: Filip Bozuta <Filip.Bozuta@syrmia.com> Reviewed-by: Laurent Vivier <laurent@vivier.eu> Message-Id: <20200811164553.27713-3-Filip.Bozuta@syrmia.com> Signed-off-by: Laurent Vivier <laurent@vivier.eu>
2020-08-11 19:45:50 +03:00
/* ARM EABI and MIPS expect 64bit types aligned even on pairs or registers */
#ifdef TARGET_ARM
static inline int regpairs_aligned(void *cpu_env, int num)
{
return ((((CPUARMState *)cpu_env)->eabi) == 1) ;
}
#elif defined(TARGET_MIPS) && (TARGET_ABI_BITS == 32)
static inline int regpairs_aligned(void *cpu_env, int num) { return 1; }
#elif defined(TARGET_PPC) && !defined(TARGET_PPC64)
/*
* SysV AVI for PPC32 expects 64bit parameters to be passed on odd/even pairs
* of registers which translates to the same as ARM/MIPS, because we start with
* r3 as arg1
*/
static inline int regpairs_aligned(void *cpu_env, int num) { return 1; }
#elif defined(TARGET_SH4)
/* SH4 doesn't align register pairs, except for p{read,write}64 */
static inline int regpairs_aligned(void *cpu_env, int num)
{
switch (num) {
case TARGET_NR_pread64:
case TARGET_NR_pwrite64:
return 1;
default:
return 0;
}
}
#elif defined(TARGET_XTENSA)
static inline int regpairs_aligned(void *cpu_env, int num) { return 1; }
#else
static inline int regpairs_aligned(void *cpu_env, int num) { return 0; }
#endif
/**
* preexit_cleanup: housekeeping before the guest exits
*
* env: the CPU state
* code: the exit code
*/
void preexit_cleanup(CPUArchState *env, int code);
/* Include target-specific struct and function definitions;
* they may need access to the target-independent structures
* above, so include them last.
*/
#include "target_cpu.h"
#include "target_structs.h"
#endif /* QEMU_H */