linux/arch/powerpc/kernel/signal_64.c

856 lines
26 KiB
C
Raw Normal View History

/*
* PowerPC version
* Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
*
* Derived from "arch/i386/kernel/signal.c"
* Copyright (C) 1991, 1992 Linus Torvalds
* 1997-11-28 Modified for POSIX.1b signals by Richard Henderson
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/kernel.h>
#include <linux/signal.h>
#include <linux/errno.h>
#include <linux/wait.h>
#include <linux/unistd.h>
#include <linux/stddef.h>
#include <linux/elf.h>
#include <linux/ptrace.h>
#include <linux/ratelimit.h>
#include <asm/sigcontext.h>
#include <asm/ucontext.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/unistd.h>
#include <asm/cacheflush.h>
#include <asm/syscalls.h>
#include <asm/vdso.h>
#include <asm/switch_to.h>
#include <asm/tm.h>
#include <asm/asm-prototypes.h>
#include "signal.h"
#define GP_REGS_SIZE min(sizeof(elf_gregset_t), sizeof(struct pt_regs))
#define FP_REGS_SIZE sizeof(elf_fpregset_t)
#define TRAMP_TRACEBACK 3
#define TRAMP_SIZE 6
/*
* When we have signals to deliver, we set up on the user stack,
* going down from the original stack pointer:
* 1) a rt_sigframe struct which contains the ucontext
* 2) a gap of __SIGNAL_FRAMESIZE bytes which acts as a dummy caller
* frame for the signal handler.
*/
struct rt_sigframe {
/* sys_rt_sigreturn requires the ucontext be the first field */
struct ucontext uc;
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
struct ucontext uc_transact;
#endif
unsigned long _unused[2];
unsigned int tramp[TRAMP_SIZE];
struct siginfo __user *pinfo;
void __user *puc;
struct siginfo info;
/* New 64 bit little-endian ABI allows redzone of 512 bytes below sp */
char abigap[USER_REDZONE_SIZE];
} __attribute__ ((aligned (16)));
static const char fmt32[] = KERN_INFO \
"%s[%d]: bad frame in %s: %08lx nip %08lx lr %08lx\n";
static const char fmt64[] = KERN_INFO \
"%s[%d]: bad frame in %s: %016lx nip %016lx lr %016lx\n";
/*
* This computes a quad word aligned pointer inside the vmx_reserve array
* element. For historical reasons sigcontext might not be quad word aligned,
* but the location we write the VMX regs to must be. See the comment in
* sigcontext for more detail.
*/
#ifdef CONFIG_ALTIVEC
static elf_vrreg_t __user *sigcontext_vmx_regs(struct sigcontext __user *sc)
{
return (elf_vrreg_t __user *) (((unsigned long)sc->vmx_reserve + 15) & ~0xful);
}
#endif
/*
* Set up the sigcontext for the signal frame.
*/
static long setup_sigcontext(struct sigcontext __user *sc,
struct task_struct *tsk, int signr, sigset_t *set,
unsigned long handler, int ctx_has_vsx_region)
{
/* When CONFIG_ALTIVEC is set, we _always_ setup v_regs even if the
* process never used altivec yet (MSR_VEC is zero in pt_regs of
* the context). This is very important because we must ensure we
* don't lose the VRSAVE content that may have been set prior to
* the process doing its first vector operation
* Userland shall check AT_HWCAP to know whether it can rely on the
* v_regs pointer or not
*/
#ifdef CONFIG_ALTIVEC
elf_vrreg_t __user *v_regs = sigcontext_vmx_regs(sc);
unsigned long vrsave;
#endif
struct pt_regs *regs = tsk->thread.regs;
unsigned long msr = regs->msr;
long err = 0;
BUG_ON(tsk != current);
#ifdef CONFIG_ALTIVEC
err |= __put_user(v_regs, &sc->v_regs);
/* save altivec registers */
if (tsk->thread.used_vr) {
flush_altivec_to_thread(tsk);
/* Copy 33 vec registers (vr0..31 and vscr) to the stack */
err |= __copy_to_user(v_regs, &tsk->thread.vr_state,
33 * sizeof(vector128));
/* set MSR_VEC in the MSR value in the frame to indicate that sc->v_reg)
* contains valid data.
*/
msr |= MSR_VEC;
}
/* We always copy to/from vrsave, it's 0 if we don't have or don't
* use altivec.
*/
vrsave = 0;
if (cpu_has_feature(CPU_FTR_ALTIVEC)) {
vrsave = mfspr(SPRN_VRSAVE);
tsk->thread.vrsave = vrsave;
}
err |= __put_user(vrsave, (u32 __user *)&v_regs[33]);
#else /* CONFIG_ALTIVEC */
err |= __put_user(0, &sc->v_regs);
#endif /* CONFIG_ALTIVEC */
flush_fp_to_thread(tsk);
/* copy fpr regs and fpscr */
err |= copy_fpr_to_user(&sc->fp_regs, tsk);
/*
* Clear the MSR VSX bit to indicate there is no valid state attached
* to this context, except in the specific case below where we set it.
*/
msr &= ~MSR_VSX;
powerpc: Introduce VSX thread_struct and CONFIG_VSX The layout of the new VSR registers and how they overlap on top of the legacy FPR and VR registers is: VSR doubleword 0 VSR doubleword 1 ---------------------------------------------------------------- VSR[0] | FPR[0] | | ---------------------------------------------------------------- VSR[1] | FPR[1] | | ---------------------------------------------------------------- | ... | | | ... | | ---------------------------------------------------------------- VSR[30] | FPR[30] | | ---------------------------------------------------------------- VSR[31] | FPR[31] | | ---------------------------------------------------------------- VSR[32] | VR[0] | ---------------------------------------------------------------- VSR[33] | VR[1] | ---------------------------------------------------------------- | ... | | ... | ---------------------------------------------------------------- VSR[62] | VR[30] | ---------------------------------------------------------------- VSR[63] | VR[31] | ---------------------------------------------------------------- VSX has 64 128bit registers. The first 32 regs overlap with the FP registers and hence extend them with and additional 64 bits. The second 32 regs overlap with the VMX registers. This commit introduces the thread_struct changes required to reflect this register layout. Ptrace and signals code is updated so that the floating point registers are correctly accessed from the thread_struct when CONFIG_VSX is enabled. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2008-06-25 04:07:18 +00:00
#ifdef CONFIG_VSX
/*
* Copy VSX low doubleword to local buffer for formatting,
* then out to userspace. Update v_regs to point after the
* VMX data.
*/
if (tsk->thread.used_vsr && ctx_has_vsx_region) {
flush_vsx_to_thread(tsk);
v_regs += ELF_NVRREG;
err |= copy_vsx_to_user(v_regs, tsk);
/* set MSR_VSX in the MSR value in the frame to
* indicate that sc->vs_reg) contains valid data.
*/
msr |= MSR_VSX;
}
powerpc: Introduce VSX thread_struct and CONFIG_VSX The layout of the new VSR registers and how they overlap on top of the legacy FPR and VR registers is: VSR doubleword 0 VSR doubleword 1 ---------------------------------------------------------------- VSR[0] | FPR[0] | | ---------------------------------------------------------------- VSR[1] | FPR[1] | | ---------------------------------------------------------------- | ... | | | ... | | ---------------------------------------------------------------- VSR[30] | FPR[30] | | ---------------------------------------------------------------- VSR[31] | FPR[31] | | ---------------------------------------------------------------- VSR[32] | VR[0] | ---------------------------------------------------------------- VSR[33] | VR[1] | ---------------------------------------------------------------- | ... | | ... | ---------------------------------------------------------------- VSR[62] | VR[30] | ---------------------------------------------------------------- VSR[63] | VR[31] | ---------------------------------------------------------------- VSX has 64 128bit registers. The first 32 regs overlap with the FP registers and hence extend them with and additional 64 bits. The second 32 regs overlap with the VMX registers. This commit introduces the thread_struct changes required to reflect this register layout. Ptrace and signals code is updated so that the floating point registers are correctly accessed from the thread_struct when CONFIG_VSX is enabled. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2008-06-25 04:07:18 +00:00
#endif /* CONFIG_VSX */
err |= __put_user(&sc->gp_regs, &sc->regs);
powerpc: Fix various syscall/signal/swapcontext bugs A careful reading of the recent changes to the system call entry/exit paths revealed several problems, plus some things that could be simplified and improved: * 32-bit wasn't testing the _TIF_NOERROR bit in the syscall fast exit path, so it was only doing anything with it once it saw some other bit being set. In other words, the noerror behaviour would apply to the next system call where we had to reschedule or deliver a signal, which is not necessarily the current system call. * 32-bit wasn't doing the call to ptrace_notify in the syscall exit path when the _TIF_SINGLESTEP bit was set. * _TIF_RESTOREALL was in both _TIF_USER_WORK_MASK and _TIF_PERSYSCALL_MASK, which is odd since _TIF_RESTOREALL is only set by system calls. I took it out of _TIF_USER_WORK_MASK. * On 64-bit, _TIF_RESTOREALL wasn't causing the non-volatile registers to be restored (unless perhaps a signal was delivered or the syscall was traced or single-stepped). Thus the non-volatile registers weren't restored on exit from a signal handler. We probably got away with it mostly because signal handlers written in C wouldn't alter the non-volatile registers. * On 32-bit I simplified the code and made it more like 64-bit by making the syscall exit path jump to ret_from_except to handle preemption and signal delivery. * 32-bit was calling do_signal unnecessarily when _TIF_RESTOREALL was set - but I think because of that 32-bit was actually restoring the non-volatile registers on exit from a signal handler. * I changed the order of enabling interrupts and saving the non-volatile registers before calling do_syscall_trace_leave; now we enable interrupts first. Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-03-08 02:24:22 +00:00
WARN_ON(!FULL_REGS(regs));
err |= __copy_to_user(&sc->gp_regs, regs, GP_REGS_SIZE);
err |= __put_user(msr, &sc->gp_regs[PT_MSR]);
err |= __put_user(signr, &sc->signal);
err |= __put_user(handler, &sc->handler);
if (set != NULL)
err |= __put_user(set->sig[0], &sc->oldmask);
return err;
}
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
/*
* As above, but Transactional Memory is in use, so deliver sigcontexts
* containing checkpointed and transactional register states.
*
* To do this, we treclaim (done before entering here) to gather both sets of
* registers and set up the 'normal' sigcontext registers with rolled-back
* register values such that a simple signal handler sees a correct
* checkpointed register state. If interested, a TM-aware sighandler can
* examine the transactional registers in the 2nd sigcontext to determine the
* real origin of the signal.
*/
static long setup_tm_sigcontexts(struct sigcontext __user *sc,
struct sigcontext __user *tm_sc,
struct task_struct *tsk,
int signr, sigset_t *set, unsigned long handler)
{
/* When CONFIG_ALTIVEC is set, we _always_ setup v_regs even if the
* process never used altivec yet (MSR_VEC is zero in pt_regs of
* the context). This is very important because we must ensure we
* don't lose the VRSAVE content that may have been set prior to
* the process doing its first vector operation
* Userland shall check AT_HWCAP to know wether it can rely on the
* v_regs pointer or not.
*/
#ifdef CONFIG_ALTIVEC
elf_vrreg_t __user *v_regs = sigcontext_vmx_regs(sc);
elf_vrreg_t __user *tm_v_regs = sigcontext_vmx_regs(tm_sc);
#endif
struct pt_regs *regs = tsk->thread.regs;
unsigned long msr = tsk->thread.ckpt_regs.msr;
long err = 0;
BUG_ON(tsk != current);
BUG_ON(!MSR_TM_ACTIVE(regs->msr));
powerpc: Don't corrupt transactional state when using FP/VMX in kernel Currently, when we have a process using the transactional memory facilities on POWER8 (that is, the processor is in transactional or suspended state), and the process enters the kernel and the kernel then uses the floating-point or vector (VMX/Altivec) facility, we end up corrupting the user-visible FP/VMX/VSX state. This happens, for example, if a page fault causes a copy-on-write operation, because the copy_page function will use VMX to do the copy on POWER8. The test program below demonstrates the bug. The bug happens because when FP/VMX state for a transactional process is stored in the thread_struct, we store the checkpointed state in .fp_state/.vr_state and the transactional (current) state in .transact_fp/.transact_vr. However, when the kernel wants to use FP/VMX, it calls enable_kernel_fp() or enable_kernel_altivec(), which saves the current state in .fp_state/.vr_state. Furthermore, when we return to the user process we return with FP/VMX/VSX disabled. The next time the process uses FP/VMX/VSX, we don't know which set of state (the current register values, .fp_state/.vr_state, or .transact_fp/.transact_vr) we should be using, since we have no way to tell if we are still in the same transaction, and if not, whether the previous transaction succeeded or failed. Thus it is necessary to strictly adhere to the rule that if FP has been enabled at any point in a transaction, we must keep FP enabled for the user process with the current transactional state in the FP registers, until we detect that it is no longer in a transaction. Similarly for VMX; once enabled it must stay enabled until the process is no longer transactional. In order to keep this rule, we add a new thread_info flag which we test when returning from the kernel to userspace, called TIF_RESTORE_TM. This flag indicates that there is FP/VMX/VSX state to be restored before entering userspace, and when it is set the .tm_orig_msr field in the thread_struct indicates what state needs to be restored. The restoration is done by restore_tm_state(). The TIF_RESTORE_TM bit is set by new giveup_fpu/altivec_maybe_transactional helpers, which are called from enable_kernel_fp/altivec, giveup_vsx, and flush_fp/altivec_to_thread instead of giveup_fpu/altivec. The other thing to be done is to get the transactional FP/VMX/VSX state from .fp_state/.vr_state when doing reclaim, if that state has been saved there by giveup_fpu/altivec_maybe_transactional. Having done this, we set the FP/VMX bit in the thread's MSR after reclaim to indicate that that part of the state is now valid (having been reclaimed from the processor's checkpointed state). Finally, in the signal handling code, we move the clearing of the transactional state bits in the thread's MSR a bit earlier, before calling flush_fp_to_thread(), so that we don't unnecessarily set the TIF_RESTORE_TM bit. This is the test program: /* Michael Neuling 4/12/2013 * * See if the altivec state is leaked out of an aborted transaction due to * kernel vmx copy loops. * * gcc -m64 htm_vmxcopy.c -o htm_vmxcopy * */ /* We don't use all of these, but for reference: */ int main(int argc, char *argv[]) { long double vecin = 1.3; long double vecout; unsigned long pgsize = getpagesize(); int i; int fd; int size = pgsize*16; char tmpfile[] = "/tmp/page_faultXXXXXX"; char buf[pgsize]; char *a; uint64_t aborted = 0; fd = mkstemp(tmpfile); assert(fd >= 0); memset(buf, 0, pgsize); for (i = 0; i < size; i += pgsize) assert(write(fd, buf, pgsize) == pgsize); unlink(tmpfile); a = mmap(NULL, size, PROT_READ|PROT_WRITE, MAP_PRIVATE, fd, 0); assert(a != MAP_FAILED); asm __volatile__( "lxvd2x 40,0,%[vecinptr] ; " // set 40 to initial value TBEGIN "beq 3f ;" TSUSPEND "xxlxor 40,40,40 ; " // set 40 to 0 "std 5, 0(%[map]) ;" // cause kernel vmx copy page TABORT TRESUME TEND "li %[res], 0 ;" "b 5f ;" "3: ;" // Abort handler "li %[res], 1 ;" "5: ;" "stxvd2x 40,0,%[vecoutptr] ; " : [res]"=r"(aborted) : [vecinptr]"r"(&vecin), [vecoutptr]"r"(&vecout), [map]"r"(a) : "memory", "r0", "r3", "r4", "r5", "r6", "r7"); if (aborted && (vecin != vecout)){ printf("FAILED: vector state leaked on abort %f != %f\n", (double)vecin, (double)vecout); exit(1); } munmap(a, size); close(fd); printf("PASSED!\n"); return 0; } Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-01-13 04:56:29 +00:00
/* Remove TM bits from thread's MSR. The MSR in the sigcontext
* just indicates to userland that we were doing a transaction, but we
* don't want to return in transactional state. This also ensures
* that flush_fp_to_thread won't set TIF_RESTORE_TM again.
*/
regs->msr &= ~MSR_TS_MASK;
flush_fp_to_thread(tsk);
#ifdef CONFIG_ALTIVEC
err |= __put_user(v_regs, &sc->v_regs);
err |= __put_user(tm_v_regs, &tm_sc->v_regs);
/* save altivec registers */
if (tsk->thread.used_vr) {
flush_altivec_to_thread(tsk);
/* Copy 33 vec registers (vr0..31 and vscr) to the stack */
err |= __copy_to_user(v_regs, &tsk->thread.vr_state,
33 * sizeof(vector128));
/* If VEC was enabled there are transactional VRs valid too,
* else they're a copy of the checkpointed VRs.
*/
if (msr & MSR_VEC)
err |= __copy_to_user(tm_v_regs,
&tsk->thread.transact_vr,
33 * sizeof(vector128));
else
err |= __copy_to_user(tm_v_regs,
&tsk->thread.vr_state,
33 * sizeof(vector128));
/* set MSR_VEC in the MSR value in the frame to indicate
* that sc->v_reg contains valid data.
*/
msr |= MSR_VEC;
}
/* We always copy to/from vrsave, it's 0 if we don't have or don't
* use altivec.
*/
if (cpu_has_feature(CPU_FTR_ALTIVEC))
tsk->thread.vrsave = mfspr(SPRN_VRSAVE);
err |= __put_user(tsk->thread.vrsave, (u32 __user *)&v_regs[33]);
if (msr & MSR_VEC)
err |= __put_user(tsk->thread.transact_vrsave,
(u32 __user *)&tm_v_regs[33]);
else
err |= __put_user(tsk->thread.vrsave,
(u32 __user *)&tm_v_regs[33]);
#else /* CONFIG_ALTIVEC */
err |= __put_user(0, &sc->v_regs);
err |= __put_user(0, &tm_sc->v_regs);
#endif /* CONFIG_ALTIVEC */
/* copy fpr regs and fpscr */
err |= copy_fpr_to_user(&sc->fp_regs, tsk);
if (msr & MSR_FP)
err |= copy_transact_fpr_to_user(&tm_sc->fp_regs, tsk);
else
err |= copy_fpr_to_user(&tm_sc->fp_regs, tsk);
#ifdef CONFIG_VSX
/*
* Copy VSX low doubleword to local buffer for formatting,
* then out to userspace. Update v_regs to point after the
* VMX data.
*/
if (tsk->thread.used_vsr) {
flush_vsx_to_thread(tsk);
v_regs += ELF_NVRREG;
tm_v_regs += ELF_NVRREG;
err |= copy_vsx_to_user(v_regs, tsk);
if (msr & MSR_VSX)
err |= copy_transact_vsx_to_user(tm_v_regs, tsk);
else
err |= copy_vsx_to_user(tm_v_regs, tsk);
/* set MSR_VSX in the MSR value in the frame to
* indicate that sc->vs_reg) contains valid data.
*/
msr |= MSR_VSX;
}
#endif /* CONFIG_VSX */
err |= __put_user(&sc->gp_regs, &sc->regs);
err |= __put_user(&tm_sc->gp_regs, &tm_sc->regs);
WARN_ON(!FULL_REGS(regs));
err |= __copy_to_user(&tm_sc->gp_regs, regs, GP_REGS_SIZE);
err |= __copy_to_user(&sc->gp_regs,
&tsk->thread.ckpt_regs, GP_REGS_SIZE);
err |= __put_user(msr, &tm_sc->gp_regs[PT_MSR]);
err |= __put_user(msr, &sc->gp_regs[PT_MSR]);
err |= __put_user(signr, &sc->signal);
err |= __put_user(handler, &sc->handler);
if (set != NULL)
err |= __put_user(set->sig[0], &sc->oldmask);
return err;
}
#endif
/*
* Restore the sigcontext from the signal frame.
*/
static long restore_sigcontext(struct task_struct *tsk, sigset_t *set, int sig,
struct sigcontext __user *sc)
{
#ifdef CONFIG_ALTIVEC
elf_vrreg_t __user *v_regs;
#endif
unsigned long err = 0;
unsigned long save_r13 = 0;
unsigned long msr;
struct pt_regs *regs = tsk->thread.regs;
#ifdef CONFIG_VSX
int i;
#endif
BUG_ON(tsk != current);
/* If this is not a signal return, we preserve the TLS in r13 */
if (!sig)
save_r13 = regs->gpr[13];
/* copy the GPRs */
err |= __copy_from_user(regs->gpr, sc->gp_regs, sizeof(regs->gpr));
err |= __get_user(regs->nip, &sc->gp_regs[PT_NIP]);
/* get MSR separately, transfer the LE bit if doing signal return */
err |= __get_user(msr, &sc->gp_regs[PT_MSR]);
if (sig)
regs->msr = (regs->msr & ~MSR_LE) | (msr & MSR_LE);
err |= __get_user(regs->orig_gpr3, &sc->gp_regs[PT_ORIG_R3]);
err |= __get_user(regs->ctr, &sc->gp_regs[PT_CTR]);
err |= __get_user(regs->link, &sc->gp_regs[PT_LNK]);
err |= __get_user(regs->xer, &sc->gp_regs[PT_XER]);
err |= __get_user(regs->ccr, &sc->gp_regs[PT_CCR]);
/* skip SOFTE */
regs->trap = 0;
err |= __get_user(regs->dar, &sc->gp_regs[PT_DAR]);
err |= __get_user(regs->dsisr, &sc->gp_regs[PT_DSISR]);
err |= __get_user(regs->result, &sc->gp_regs[PT_RESULT]);
if (!sig)
regs->gpr[13] = save_r13;
if (set != NULL)
err |= __get_user(set->sig[0], &sc->oldmask);
/*
* Force reload of FP/VEC.
* This has to be done before copying stuff into tsk->thread.fpr/vr
* for the reasons explained in the previous comment.
*/
regs->msr &= ~(MSR_FP | MSR_FE0 | MSR_FE1 | MSR_VEC | MSR_VSX);
#ifdef CONFIG_ALTIVEC
err |= __get_user(v_regs, &sc->v_regs);
if (err)
return err;
if (v_regs && !access_ok(VERIFY_READ, v_regs, 34 * sizeof(vector128)))
return -EFAULT;
/* Copy 33 vec registers (vr0..31 and vscr) from the stack */
if (v_regs != NULL && (msr & MSR_VEC) != 0) {
err |= __copy_from_user(&tsk->thread.vr_state, v_regs,
33 * sizeof(vector128));
tsk->thread.used_vr = true;
} else if (tsk->thread.used_vr) {
memset(&tsk->thread.vr_state, 0, 33 * sizeof(vector128));
}
/* Always get VRSAVE back */
if (v_regs != NULL)
err |= __get_user(tsk->thread.vrsave, (u32 __user *)&v_regs[33]);
else
tsk->thread.vrsave = 0;
if (cpu_has_feature(CPU_FTR_ALTIVEC))
mtspr(SPRN_VRSAVE, tsk->thread.vrsave);
#endif /* CONFIG_ALTIVEC */
powerpc: Introduce VSX thread_struct and CONFIG_VSX The layout of the new VSR registers and how they overlap on top of the legacy FPR and VR registers is: VSR doubleword 0 VSR doubleword 1 ---------------------------------------------------------------- VSR[0] | FPR[0] | | ---------------------------------------------------------------- VSR[1] | FPR[1] | | ---------------------------------------------------------------- | ... | | | ... | | ---------------------------------------------------------------- VSR[30] | FPR[30] | | ---------------------------------------------------------------- VSR[31] | FPR[31] | | ---------------------------------------------------------------- VSR[32] | VR[0] | ---------------------------------------------------------------- VSR[33] | VR[1] | ---------------------------------------------------------------- | ... | | ... | ---------------------------------------------------------------- VSR[62] | VR[30] | ---------------------------------------------------------------- VSR[63] | VR[31] | ---------------------------------------------------------------- VSX has 64 128bit registers. The first 32 regs overlap with the FP registers and hence extend them with and additional 64 bits. The second 32 regs overlap with the VMX registers. This commit introduces the thread_struct changes required to reflect this register layout. Ptrace and signals code is updated so that the floating point registers are correctly accessed from the thread_struct when CONFIG_VSX is enabled. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2008-06-25 04:07:18 +00:00
/* restore floating point */
err |= copy_fpr_from_user(tsk, &sc->fp_regs);
#ifdef CONFIG_VSX
/*
* Get additional VSX data. Update v_regs to point after the
* VMX data. Copy VSX low doubleword from userspace to local
* buffer for formatting, then into the taskstruct.
*/
v_regs += ELF_NVRREG;
if ((msr & MSR_VSX) != 0) {
err |= copy_vsx_from_user(tsk, v_regs);
tsk->thread.used_vsr = true;
} else {
for (i = 0; i < 32 ; i++)
tsk->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = 0;
}
powerpc: Introduce VSX thread_struct and CONFIG_VSX The layout of the new VSR registers and how they overlap on top of the legacy FPR and VR registers is: VSR doubleword 0 VSR doubleword 1 ---------------------------------------------------------------- VSR[0] | FPR[0] | | ---------------------------------------------------------------- VSR[1] | FPR[1] | | ---------------------------------------------------------------- | ... | | | ... | | ---------------------------------------------------------------- VSR[30] | FPR[30] | | ---------------------------------------------------------------- VSR[31] | FPR[31] | | ---------------------------------------------------------------- VSR[32] | VR[0] | ---------------------------------------------------------------- VSR[33] | VR[1] | ---------------------------------------------------------------- | ... | | ... | ---------------------------------------------------------------- VSR[62] | VR[30] | ---------------------------------------------------------------- VSR[63] | VR[31] | ---------------------------------------------------------------- VSX has 64 128bit registers. The first 32 regs overlap with the FP registers and hence extend them with and additional 64 bits. The second 32 regs overlap with the VMX registers. This commit introduces the thread_struct changes required to reflect this register layout. Ptrace and signals code is updated so that the floating point registers are correctly accessed from the thread_struct when CONFIG_VSX is enabled. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2008-06-25 04:07:18 +00:00
#endif
return err;
}
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
/*
* Restore the two sigcontexts from the frame of a transactional processes.
*/
static long restore_tm_sigcontexts(struct task_struct *tsk,
struct sigcontext __user *sc,
struct sigcontext __user *tm_sc)
{
#ifdef CONFIG_ALTIVEC
elf_vrreg_t __user *v_regs, *tm_v_regs;
#endif
unsigned long err = 0;
unsigned long msr;
struct pt_regs *regs = tsk->thread.regs;
#ifdef CONFIG_VSX
int i;
#endif
BUG_ON(tsk != current);
/* copy the GPRs */
err |= __copy_from_user(regs->gpr, tm_sc->gp_regs, sizeof(regs->gpr));
err |= __copy_from_user(&tsk->thread.ckpt_regs, sc->gp_regs,
sizeof(regs->gpr));
/*
* TFHAR is restored from the checkpointed 'wound-back' ucontext's NIP.
* TEXASR was set by the signal delivery reclaim, as was TFIAR.
* Users doing anything abhorrent like thread-switching w/ signals for
* TM-Suspended code will have to back TEXASR/TFIAR up themselves.
* For the case of getting a signal and simply returning from it,
* we don't need to re-copy them here.
*/
err |= __get_user(regs->nip, &tm_sc->gp_regs[PT_NIP]);
err |= __get_user(tsk->thread.tm_tfhar, &sc->gp_regs[PT_NIP]);
/* get MSR separately, transfer the LE bit if doing signal return */
err |= __get_user(msr, &sc->gp_regs[PT_MSR]);
/* Don't allow reserved mode. */
if (MSR_TM_RESV(msr))
return -EINVAL;
/* pull in MSR TM from user context */
regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr & MSR_TS_MASK);
/* pull in MSR LE from user context */
regs->msr = (regs->msr & ~MSR_LE) | (msr & MSR_LE);
/* The following non-GPR non-FPR non-VR state is also checkpointed: */
err |= __get_user(regs->ctr, &tm_sc->gp_regs[PT_CTR]);
err |= __get_user(regs->link, &tm_sc->gp_regs[PT_LNK]);
err |= __get_user(regs->xer, &tm_sc->gp_regs[PT_XER]);
err |= __get_user(regs->ccr, &tm_sc->gp_regs[PT_CCR]);
err |= __get_user(tsk->thread.ckpt_regs.ctr,
&sc->gp_regs[PT_CTR]);
err |= __get_user(tsk->thread.ckpt_regs.link,
&sc->gp_regs[PT_LNK]);
err |= __get_user(tsk->thread.ckpt_regs.xer,
&sc->gp_regs[PT_XER]);
err |= __get_user(tsk->thread.ckpt_regs.ccr,
&sc->gp_regs[PT_CCR]);
/* These regs are not checkpointed; they can go in 'regs'. */
err |= __get_user(regs->trap, &sc->gp_regs[PT_TRAP]);
err |= __get_user(regs->dar, &sc->gp_regs[PT_DAR]);
err |= __get_user(regs->dsisr, &sc->gp_regs[PT_DSISR]);
err |= __get_user(regs->result, &sc->gp_regs[PT_RESULT]);
/*
* Force reload of FP/VEC.
* This has to be done before copying stuff into tsk->thread.fpr/vr
* for the reasons explained in the previous comment.
*/
regs->msr &= ~(MSR_FP | MSR_FE0 | MSR_FE1 | MSR_VEC | MSR_VSX);
#ifdef CONFIG_ALTIVEC
err |= __get_user(v_regs, &sc->v_regs);
err |= __get_user(tm_v_regs, &tm_sc->v_regs);
if (err)
return err;
if (v_regs && !access_ok(VERIFY_READ, v_regs, 34 * sizeof(vector128)))
return -EFAULT;
if (tm_v_regs && !access_ok(VERIFY_READ,
tm_v_regs, 34 * sizeof(vector128)))
return -EFAULT;
/* Copy 33 vec registers (vr0..31 and vscr) from the stack */
if (v_regs != NULL && tm_v_regs != NULL && (msr & MSR_VEC) != 0) {
err |= __copy_from_user(&tsk->thread.vr_state, v_regs,
33 * sizeof(vector128));
err |= __copy_from_user(&tsk->thread.transact_vr, tm_v_regs,
33 * sizeof(vector128));
current->thread.used_vr = true;
}
else if (tsk->thread.used_vr) {
memset(&tsk->thread.vr_state, 0, 33 * sizeof(vector128));
memset(&tsk->thread.transact_vr, 0, 33 * sizeof(vector128));
}
/* Always get VRSAVE back */
if (v_regs != NULL && tm_v_regs != NULL) {
err |= __get_user(tsk->thread.vrsave,
(u32 __user *)&v_regs[33]);
err |= __get_user(tsk->thread.transact_vrsave,
(u32 __user *)&tm_v_regs[33]);
}
else {
tsk->thread.vrsave = 0;
tsk->thread.transact_vrsave = 0;
}
if (cpu_has_feature(CPU_FTR_ALTIVEC))
mtspr(SPRN_VRSAVE, tsk->thread.vrsave);
#endif /* CONFIG_ALTIVEC */
/* restore floating point */
err |= copy_fpr_from_user(tsk, &sc->fp_regs);
err |= copy_transact_fpr_from_user(tsk, &tm_sc->fp_regs);
#ifdef CONFIG_VSX
/*
* Get additional VSX data. Update v_regs to point after the
* VMX data. Copy VSX low doubleword from userspace to local
* buffer for formatting, then into the taskstruct.
*/
if (v_regs && ((msr & MSR_VSX) != 0)) {
v_regs += ELF_NVRREG;
tm_v_regs += ELF_NVRREG;
err |= copy_vsx_from_user(tsk, v_regs);
err |= copy_transact_vsx_from_user(tsk, tm_v_regs);
tsk->thread.used_vsr = true;
} else {
for (i = 0; i < 32 ; i++) {
tsk->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = 0;
tsk->thread.transact_fp.fpr[i][TS_VSRLOWOFFSET] = 0;
}
}
#endif
tm_enable();
powerpc/tm: Disable IRQ in tm_recheckpoint We can't take an IRQ when we're about to do a trechkpt as our GPR state is set to user GPR values. We've hit this when running some IBM Java stress tests in the lab resulting in the following dump: cpu 0x3f: Vector: 700 (Program Check) at [c000000007eb3d40] pc: c000000000050074: restore_gprs+0xc0/0x148 lr: 00000000b52a8184 sp: ac57d360 msr: 8000000100201030 current = 0xc00000002c500000 paca = 0xc000000007dbfc00 softe: 0 irq_happened: 0x00 pid = 34535, comm = Pooled Thread # R00 = 00000000b52a8184 R16 = 00000000b3e48fda R01 = 00000000ac57d360 R17 = 00000000ade79bd8 R02 = 00000000ac586930 R18 = 000000000fac9bcc R03 = 00000000ade60000 R19 = 00000000ac57f930 R04 = 00000000f6624918 R20 = 00000000ade79be8 R05 = 00000000f663f238 R21 = 00000000ac218a54 R06 = 0000000000000002 R22 = 000000000f956280 R07 = 0000000000000008 R23 = 000000000000007e R08 = 000000000000000a R24 = 000000000000000c R09 = 00000000b6e69160 R25 = 00000000b424cf00 R10 = 0000000000000181 R26 = 00000000f66256d4 R11 = 000000000f365ec0 R27 = 00000000b6fdcdd0 R12 = 00000000f66400f0 R28 = 0000000000000001 R13 = 00000000ada71900 R29 = 00000000ade5a300 R14 = 00000000ac2185a8 R30 = 00000000f663f238 R15 = 0000000000000004 R31 = 00000000f6624918 pc = c000000000050074 restore_gprs+0xc0/0x148 cfar= c00000000004fe28 dont_restore_vec+0x1c/0x1a4 lr = 00000000b52a8184 msr = 8000000100201030 cr = 24804888 ctr = 0000000000000000 xer = 0000000000000000 trap = 700 This moves tm_recheckpoint to a C function and moves the tm_restore_sprs into that function. It then adds IRQ disabling over the trechkpt critical section. It also sets the TEXASR FS in the signals code to ensure this is never set now that we explictly write the TM sprs in tm_recheckpoint. Signed-off-by: Michael Neuling <mikey@neuling.org> cc: stable@vger.kernel.org Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-04-04 09:19:48 +00:00
/* Make sure the transaction is marked as failed */
tsk->thread.tm_texasr |= TEXASR_FS;
/* This loads the checkpointed FP/VEC state, if used */
tm_recheckpoint(&tsk->thread, msr);
/* This loads the speculative FP/VEC state, if used */
if (msr & MSR_FP) {
do_load_up_transact_fpu(&tsk->thread);
regs->msr |= (MSR_FP | tsk->thread.fpexc_mode);
}
#ifdef CONFIG_ALTIVEC
if (msr & MSR_VEC) {
do_load_up_transact_altivec(&tsk->thread);
regs->msr |= MSR_VEC;
}
#endif
return err;
}
#endif
/*
* Setup the trampoline code on the stack
*/
static long setup_trampoline(unsigned int syscall, unsigned int __user *tramp)
{
int i;
long err = 0;
/* addi r1, r1, __SIGNAL_FRAMESIZE # Pop the dummy stackframe */
err |= __put_user(0x38210000UL | (__SIGNAL_FRAMESIZE & 0xffff), &tramp[0]);
/* li r0, __NR_[rt_]sigreturn| */
err |= __put_user(0x38000000UL | (syscall & 0xffff), &tramp[1]);
/* sc */
err |= __put_user(0x44000002UL, &tramp[2]);
/* Minimal traceback info */
for (i=TRAMP_TRACEBACK; i < TRAMP_SIZE ;i++)
err |= __put_user(0, &tramp[i]);
if (!err)
flush_icache_range((unsigned long) &tramp[0],
(unsigned long) &tramp[TRAMP_SIZE]);
return err;
}
/*
* Userspace code may pass a ucontext which doesn't include VSX added
* at the end. We need to check for this case.
*/
#define UCONTEXTSIZEWITHOUTVSX \
(sizeof(struct ucontext) - 32*sizeof(long))
/*
* Handle {get,set,swap}_context operations
*/
int sys_swapcontext(struct ucontext __user *old_ctx,
struct ucontext __user *new_ctx,
long ctx_size, long r6, long r7, long r8, struct pt_regs *regs)
{
unsigned char tmp;
sigset_t set;
unsigned long new_msr = 0;
int ctx_has_vsx_region = 0;
BUG_ON(regs != current->thread.regs);
if (new_ctx &&
get_user(new_msr, &new_ctx->uc_mcontext.gp_regs[PT_MSR]))
return -EFAULT;
/*
* Check that the context is not smaller than the original
* size (with VMX but without VSX)
*/
if (ctx_size < UCONTEXTSIZEWITHOUTVSX)
return -EINVAL;
/*
* If the new context state sets the MSR VSX bits but
* it doesn't provide VSX state.
*/
if ((ctx_size < sizeof(struct ucontext)) &&
(new_msr & MSR_VSX))
return -EINVAL;
/* Does the context have enough room to store VSX data? */
if (ctx_size >= sizeof(struct ucontext))
ctx_has_vsx_region = 1;
if (old_ctx != NULL) {
if (!access_ok(VERIFY_WRITE, old_ctx, ctx_size)
|| setup_sigcontext(&old_ctx->uc_mcontext, current, 0, NULL, 0,
ctx_has_vsx_region)
|| __copy_to_user(&old_ctx->uc_sigmask,
&current->blocked, sizeof(sigset_t)))
return -EFAULT;
}
if (new_ctx == NULL)
return 0;
if (!access_ok(VERIFY_READ, new_ctx, ctx_size)
|| __get_user(tmp, (u8 __user *) new_ctx)
|| __get_user(tmp, (u8 __user *) new_ctx + ctx_size - 1))
return -EFAULT;
/*
* If we get a fault copying the context into the kernel's
* image of the user's registers, we can't just return -EFAULT
* because the user's registers will be corrupted. For instance
* the NIP value may have been updated but not some of the
* other registers. Given that we have done the access_ok
* and successfully read the first and last bytes of the region
* above, this should only happen in an out-of-memory situation
* or if another thread unmaps the region containing the context.
* We kill the task with a SIGSEGV in this situation.
*/
if (__copy_from_user(&set, &new_ctx->uc_sigmask, sizeof(set)))
do_exit(SIGSEGV);
set_current_blocked(&set);
if (restore_sigcontext(current, NULL, 0, &new_ctx->uc_mcontext))
do_exit(SIGSEGV);
/* This returns like rt_sigreturn */
[PATCH] syscall entry/exit revamp This cleanup patch speeds up the null syscall path on ppc64 by about 3%, and brings the ppc32 and ppc64 code slightly closer together. The ppc64 code was checking current_thread_info()->flags twice in the syscall exit path; once for TIF_SYSCALL_T_OR_A before disabling interrupts, and then again for TIF_SIGPENDING|TIF_NEED_RESCHED etc after disabling interrupts. Now we do the same as ppc32 -- check the flags only once in the fast path, and re-enable interrupts if necessary in the ptrace case. The patch abolishes the 'syscall_noerror' member of struct thread_info and replaces it with a TIF_NOERROR bit in the flags, which is handled in the slow path. This shortens the syscall entry code, which no longer needs to clear syscall_noerror. The patch adds a TIF_SAVE_NVGPRS flag which causes the syscall exit slow path to save the non-volatile GPRs into a signal frame. This removes the need for the assembly wrappers around sys_sigsuspend(), sys_rt_sigsuspend(), et al which existed solely to save those registers in advance. It also means I don't have to add new wrappers for ppoll() and pselect(), which is what I was supposed to be doing when I got distracted into this... Finally, it unifies the ppc64 and ppc32 methods of handling syscall exit directly into a signal handler (as required by sigsuspend et al) by introducing a TIF_RESTOREALL flag which causes _all_ the registers to be reloaded from the pt_regs by taking the ret_from_exception path, instead of the normal syscall exit path which stomps on the callee-saved GPRs. It appears to pass an LTP test run on ppc64, and passes basic testing on ppc32 too. Brief tests of ptrace functionality with strace and gdb also appear OK. I wouldn't send it to Linus for 2.6.15 just yet though :) Signed-off-by: David Woodhouse <dwmw2@infradead.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-15 18:52:18 +00:00
set_thread_flag(TIF_RESTOREALL);
return 0;
}
/*
* Do a signal return; undo the signal stack.
*/
int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5,
unsigned long r6, unsigned long r7, unsigned long r8,
struct pt_regs *regs)
{
struct ucontext __user *uc = (struct ucontext __user *)regs->gpr[1];
sigset_t set;
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
unsigned long msr;
#endif
BUG_ON(current->thread.regs != regs);
/* Always make any pending restarted system calls return -EINTR */
all arches, signal: move restart_block to struct task_struct If an attacker can cause a controlled kernel stack overflow, overwriting the restart block is a very juicy exploit target. This is because the restart_block is held in the same memory allocation as the kernel stack. Moving the restart block to struct task_struct prevents this exploit by making the restart_block harder to locate. Note that there are other fields in thread_info that are also easy targets, at least on some architectures. It's also a decent simplification, since the restart code is more or less identical on all architectures. [james.hogan@imgtec.com: metag: align thread_info::supervisor_stack] Signed-off-by: Andy Lutomirski <luto@amacapital.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Kees Cook <keescook@chromium.org> Cc: David Miller <davem@davemloft.net> Acked-by: Richard Weinberger <richard@nod.at> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Matt Turner <mattst88@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Haavard Skinnemoen <hskinnemoen@gmail.com> Cc: Hans-Christian Egtvedt <egtvedt@samfundet.no> Cc: Steven Miao <realmz6@gmail.com> Cc: Mark Salter <msalter@redhat.com> Cc: Aurelien Jacquiot <a-jacquiot@ti.com> Cc: Mikael Starvik <starvik@axis.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: David Howells <dhowells@redhat.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Michal Simek <monstr@monstr.eu> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Jonas Bonn <jonas@southpole.se> Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Helge Deller <deller@gmx.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc) Tested-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc) Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Chen Liqin <liqin.linux@gmail.com> Cc: Lennox Wu <lennox.wu@gmail.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: Chris Zankel <chris@zankel.net> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Guenter Roeck <linux@roeck-us.net> Signed-off-by: James Hogan <james.hogan@imgtec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-12 23:01:14 +00:00
current->restart_block.fn = do_no_restart_syscall;
if (!access_ok(VERIFY_READ, uc, sizeof(*uc)))
goto badframe;
if (__copy_from_user(&set, &uc->uc_sigmask, sizeof(set)))
goto badframe;
set_current_blocked(&set);
powerpc: signals: Discard transaction state from signal frames Userspace can begin and suspend a transaction within the signal handler which means they might enter sys_rt_sigreturn() with the processor in suspended state. sys_rt_sigreturn() wants to restore process context (which may have been in a transaction before signal delivery). To do this it must restore TM SPRS. To achieve this, any transaction initiated within the signal frame must be discarded in order to be able to restore TM SPRs as TM SPRs can only be manipulated non-transactionally.. >From the PowerPC ISA: TM Bad Thing Exception [Category: Transactional Memory] An attempt is made to execute a mtspr targeting a TM register in other than Non-transactional state. Not doing so results in a TM Bad Thing: [12045.221359] Kernel BUG at c000000000050a40 [verbose debug info unavailable] [12045.221470] Unexpected TM Bad Thing exception at c000000000050a40 (msr 0x201033) [12045.221540] Oops: Unrecoverable exception, sig: 6 [#1] [12045.221586] SMP NR_CPUS=2048 NUMA PowerNV [12045.221634] Modules linked in: xt_CHECKSUM iptable_mangle ipt_MASQUERADE nf_nat_masquerade_ipv4 iptable_nat nf_nat_ipv4 nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack ipt_REJECT nf_reject_ipv4 xt_tcpudp bridge stp llc ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter ip_tables x_tables kvm_hv kvm uio_pdrv_genirq ipmi_powernv uio powernv_rng ipmi_msghandler autofs4 ses enclosure scsi_transport_sas bnx2x ipr mdio libcrc32c [12045.222167] CPU: 68 PID: 6178 Comm: sigreturnpanic Not tainted 4.7.0 #34 [12045.222224] task: c0000000fce38600 ti: c0000000fceb4000 task.ti: c0000000fceb4000 [12045.222293] NIP: c000000000050a40 LR: c0000000000163bc CTR: 0000000000000000 [12045.222361] REGS: c0000000fceb7ac0 TRAP: 0700 Not tainted (4.7.0) [12045.222418] MSR: 9000000300201033 <SF,HV,ME,IR,DR,RI,LE,TM[SE]> CR: 28444280 XER: 20000000 [12045.222625] CFAR: c0000000000163b8 SOFTE: 0 PACATMSCRATCH: 900000014280f033 GPR00: 01100000b8000001 c0000000fceb7d40 c00000000139c100 c0000000fce390d0 GPR04: 900000034280f033 0000000000000000 0000000000000000 0000000000000000 GPR08: 0000000000000000 b000000000001033 0000000000000001 0000000000000000 GPR12: 0000000000000000 c000000002926400 0000000000000000 0000000000000000 GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR20: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR24: 0000000000000000 00003ffff98cadd0 00003ffff98cb470 0000000000000000 GPR28: 900000034280f033 c0000000fceb7ea0 0000000000000001 c0000000fce390d0 [12045.223535] NIP [c000000000050a40] tm_restore_sprs+0xc/0x1c [12045.223584] LR [c0000000000163bc] tm_recheckpoint+0x5c/0xa0 [12045.223630] Call Trace: [12045.223655] [c0000000fceb7d80] [c000000000026e74] sys_rt_sigreturn+0x494/0x6c0 [12045.223738] [c0000000fceb7e30] [c0000000000092e0] system_call+0x38/0x108 [12045.223806] Instruction dump: [12045.223841] 7c800164 4e800020 7c0022a6 f80304a8 7c0222a6 f80304b0 7c0122a6 f80304b8 [12045.223955] 4e800020 e80304a8 7c0023a6 e80304b0 <7c0223a6> e80304b8 7c0123a6 4e800020 [12045.224074] ---[ end trace cb8002ee240bae76 ]--- It isn't clear exactly if there is really a use case for userspace returning with a suspended transaction, however, doing so doesn't (on its own) constitute a bad frame. As such, this patch simply discards the transactional state of the context calling the sigreturn and continues. Reported-by: Laurent Dufour <ldufour@linux.vnet.ibm.com> Signed-off-by: Cyril Bur <cyrilbur@gmail.com> Tested-by: Laurent Dufour <ldufour@linux.vnet.ibm.com> Reviewed-by: Laurent Dufour <ldufour@linux.vnet.ibm.com> Acked-by: Simon Guo <wei.guo.simon@gmail.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2016-08-23 00:46:17 +00:00
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
powerpc: signals: Discard transaction state from signal frames Userspace can begin and suspend a transaction within the signal handler which means they might enter sys_rt_sigreturn() with the processor in suspended state. sys_rt_sigreturn() wants to restore process context (which may have been in a transaction before signal delivery). To do this it must restore TM SPRS. To achieve this, any transaction initiated within the signal frame must be discarded in order to be able to restore TM SPRs as TM SPRs can only be manipulated non-transactionally.. >From the PowerPC ISA: TM Bad Thing Exception [Category: Transactional Memory] An attempt is made to execute a mtspr targeting a TM register in other than Non-transactional state. Not doing so results in a TM Bad Thing: [12045.221359] Kernel BUG at c000000000050a40 [verbose debug info unavailable] [12045.221470] Unexpected TM Bad Thing exception at c000000000050a40 (msr 0x201033) [12045.221540] Oops: Unrecoverable exception, sig: 6 [#1] [12045.221586] SMP NR_CPUS=2048 NUMA PowerNV [12045.221634] Modules linked in: xt_CHECKSUM iptable_mangle ipt_MASQUERADE nf_nat_masquerade_ipv4 iptable_nat nf_nat_ipv4 nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack ipt_REJECT nf_reject_ipv4 xt_tcpudp bridge stp llc ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter ip_tables x_tables kvm_hv kvm uio_pdrv_genirq ipmi_powernv uio powernv_rng ipmi_msghandler autofs4 ses enclosure scsi_transport_sas bnx2x ipr mdio libcrc32c [12045.222167] CPU: 68 PID: 6178 Comm: sigreturnpanic Not tainted 4.7.0 #34 [12045.222224] task: c0000000fce38600 ti: c0000000fceb4000 task.ti: c0000000fceb4000 [12045.222293] NIP: c000000000050a40 LR: c0000000000163bc CTR: 0000000000000000 [12045.222361] REGS: c0000000fceb7ac0 TRAP: 0700 Not tainted (4.7.0) [12045.222418] MSR: 9000000300201033 <SF,HV,ME,IR,DR,RI,LE,TM[SE]> CR: 28444280 XER: 20000000 [12045.222625] CFAR: c0000000000163b8 SOFTE: 0 PACATMSCRATCH: 900000014280f033 GPR00: 01100000b8000001 c0000000fceb7d40 c00000000139c100 c0000000fce390d0 GPR04: 900000034280f033 0000000000000000 0000000000000000 0000000000000000 GPR08: 0000000000000000 b000000000001033 0000000000000001 0000000000000000 GPR12: 0000000000000000 c000000002926400 0000000000000000 0000000000000000 GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR20: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR24: 0000000000000000 00003ffff98cadd0 00003ffff98cb470 0000000000000000 GPR28: 900000034280f033 c0000000fceb7ea0 0000000000000001 c0000000fce390d0 [12045.223535] NIP [c000000000050a40] tm_restore_sprs+0xc/0x1c [12045.223584] LR [c0000000000163bc] tm_recheckpoint+0x5c/0xa0 [12045.223630] Call Trace: [12045.223655] [c0000000fceb7d80] [c000000000026e74] sys_rt_sigreturn+0x494/0x6c0 [12045.223738] [c0000000fceb7e30] [c0000000000092e0] system_call+0x38/0x108 [12045.223806] Instruction dump: [12045.223841] 7c800164 4e800020 7c0022a6 f80304a8 7c0222a6 f80304b0 7c0122a6 f80304b8 [12045.223955] 4e800020 e80304a8 7c0023a6 e80304b0 <7c0223a6> e80304b8 7c0123a6 4e800020 [12045.224074] ---[ end trace cb8002ee240bae76 ]--- It isn't clear exactly if there is really a use case for userspace returning with a suspended transaction, however, doing so doesn't (on its own) constitute a bad frame. As such, this patch simply discards the transactional state of the context calling the sigreturn and continues. Reported-by: Laurent Dufour <ldufour@linux.vnet.ibm.com> Signed-off-by: Cyril Bur <cyrilbur@gmail.com> Tested-by: Laurent Dufour <ldufour@linux.vnet.ibm.com> Reviewed-by: Laurent Dufour <ldufour@linux.vnet.ibm.com> Acked-by: Simon Guo <wei.guo.simon@gmail.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2016-08-23 00:46:17 +00:00
/*
* If there is a transactional state then throw it away.
* The purpose of a sigreturn is to destroy all traces of the
* signal frame, this includes any transactional state created
* within in. We only check for suspended as we can never be
* active in the kernel, we are active, there is nothing better to
* do than go ahead and Bad Thing later.
* The cause is not important as there will never be a
* recheckpoint so it's not user visible.
*/
if (MSR_TM_SUSPENDED(mfmsr()))
tm_reclaim_current(0);
if (__get_user(msr, &uc->uc_mcontext.gp_regs[PT_MSR]))
goto badframe;
if (MSR_TM_ACTIVE(msr)) {
/* We recheckpoint on return. */
struct ucontext __user *uc_transact;
if (__get_user(uc_transact, &uc->uc_link))
goto badframe;
if (restore_tm_sigcontexts(current, &uc->uc_mcontext,
&uc_transact->uc_mcontext))
goto badframe;
}
else
/* Fall through, for non-TM restore */
#endif
if (restore_sigcontext(current, NULL, 1, &uc->uc_mcontext))
goto badframe;
if (restore_altstack(&uc->uc_stack))
goto badframe;
[PATCH] syscall entry/exit revamp This cleanup patch speeds up the null syscall path on ppc64 by about 3%, and brings the ppc32 and ppc64 code slightly closer together. The ppc64 code was checking current_thread_info()->flags twice in the syscall exit path; once for TIF_SYSCALL_T_OR_A before disabling interrupts, and then again for TIF_SIGPENDING|TIF_NEED_RESCHED etc after disabling interrupts. Now we do the same as ppc32 -- check the flags only once in the fast path, and re-enable interrupts if necessary in the ptrace case. The patch abolishes the 'syscall_noerror' member of struct thread_info and replaces it with a TIF_NOERROR bit in the flags, which is handled in the slow path. This shortens the syscall entry code, which no longer needs to clear syscall_noerror. The patch adds a TIF_SAVE_NVGPRS flag which causes the syscall exit slow path to save the non-volatile GPRs into a signal frame. This removes the need for the assembly wrappers around sys_sigsuspend(), sys_rt_sigsuspend(), et al which existed solely to save those registers in advance. It also means I don't have to add new wrappers for ppoll() and pselect(), which is what I was supposed to be doing when I got distracted into this... Finally, it unifies the ppc64 and ppc32 methods of handling syscall exit directly into a signal handler (as required by sigsuspend et al) by introducing a TIF_RESTOREALL flag which causes _all_ the registers to be reloaded from the pt_regs by taking the ret_from_exception path, instead of the normal syscall exit path which stomps on the callee-saved GPRs. It appears to pass an LTP test run on ppc64, and passes basic testing on ppc32 too. Brief tests of ptrace functionality with strace and gdb also appear OK. I wouldn't send it to Linus for 2.6.15 just yet though :) Signed-off-by: David Woodhouse <dwmw2@infradead.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-15 18:52:18 +00:00
set_thread_flag(TIF_RESTOREALL);
return 0;
badframe:
if (show_unhandled_signals)
printk_ratelimited(regs->msr & MSR_64BIT ? fmt64 : fmt32,
current->comm, current->pid, "rt_sigreturn",
(long)uc, regs->nip, regs->link);
force_sig(SIGSEGV, current);
return 0;
}
int handle_rt_signal64(struct ksignal *ksig, sigset_t *set,
struct task_struct *tsk)
{
struct rt_sigframe __user *frame;
unsigned long newsp = 0;
long err = 0;
struct pt_regs *regs = tsk->thread.regs;
BUG_ON(tsk != current);
frame = get_sigframe(ksig, get_tm_stackpointer(tsk), sizeof(*frame), 0);
if (unlikely(frame == NULL))
goto badframe;
err |= __put_user(&frame->info, &frame->pinfo);
err |= __put_user(&frame->uc, &frame->puc);
err |= copy_siginfo_to_user(&frame->info, &ksig->info);
if (err)
goto badframe;
/* Create the ucontext. */
err |= __put_user(0, &frame->uc.uc_flags);
err |= __save_altstack(&frame->uc.uc_stack, regs->gpr[1]);
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
if (MSR_TM_ACTIVE(regs->msr)) {
/* The ucontext_t passed to userland points to the second
* ucontext_t (for transactional state) with its uc_link ptr.
*/
err |= __put_user(&frame->uc_transact, &frame->uc.uc_link);
err |= setup_tm_sigcontexts(&frame->uc.uc_mcontext,
&frame->uc_transact.uc_mcontext,
tsk, ksig->sig, NULL,
(unsigned long)ksig->ka.sa.sa_handler);
} else
#endif
{
err |= __put_user(0, &frame->uc.uc_link);
err |= setup_sigcontext(&frame->uc.uc_mcontext, tsk, ksig->sig,
NULL, (unsigned long)ksig->ka.sa.sa_handler,
1);
}
err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
if (err)
goto badframe;
/* Make sure signal handler doesn't get spurious FP exceptions */
tsk->thread.fp_state.fpscr = 0;
/* Set up to return from userspace. */
if (vdso64_rt_sigtramp && tsk->mm->context.vdso_base) {
regs->link = tsk->mm->context.vdso_base + vdso64_rt_sigtramp;
} else {
err |= setup_trampoline(__NR_rt_sigreturn, &frame->tramp[0]);
if (err)
goto badframe;
regs->link = (unsigned long) &frame->tramp[0];
}
/* Allocate a dummy caller frame for the signal handler. */
newsp = ((unsigned long)frame) - __SIGNAL_FRAMESIZE;
err |= put_user(regs->gpr[1], (unsigned long __user *)newsp);
/* Set up "regs" so we "return" to the signal handler. */
if (is_elf2_task()) {
regs->nip = (unsigned long) ksig->ka.sa.sa_handler;
regs->gpr[12] = regs->nip;
} else {
/* Handler is *really* a pointer to the function descriptor for
* the signal routine. The first entry in the function
* descriptor is the entry address of signal and the second
* entry is the TOC value we need to use.
*/
func_descr_t __user *funct_desc_ptr =
(func_descr_t __user *) ksig->ka.sa.sa_handler;
err |= get_user(regs->nip, &funct_desc_ptr->entry);
err |= get_user(regs->gpr[2], &funct_desc_ptr->toc);
}
/* enter the signal handler in native-endian mode */
regs->msr &= ~MSR_LE;
regs->msr |= (MSR_KERNEL & MSR_LE);
regs->gpr[1] = newsp;
regs->gpr[3] = ksig->sig;
regs->result = 0;
if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
err |= get_user(regs->gpr[4], (unsigned long __user *)&frame->pinfo);
err |= get_user(regs->gpr[5], (unsigned long __user *)&frame->puc);
regs->gpr[6] = (unsigned long) frame;
} else {
regs->gpr[4] = (unsigned long)&frame->uc.uc_mcontext;
}
if (err)
goto badframe;
return 0;
badframe:
if (show_unhandled_signals)
printk_ratelimited(regs->msr & MSR_64BIT ? fmt64 : fmt32,
tsk->comm, tsk->pid, "setup_rt_frame",
(long)frame, regs->nip, regs->link);
return 1;
}