OpenCloudOS-Kernel/arch/powerpc/kernel/signal_32.c

1357 lines
38 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Signal handling for 32bit PPC and 32bit tasks on 64bit PPC
*
* PowerPC version
* Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
* Copyright (C) 2001 IBM
* Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
* Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu)
*
* Derived from "arch/i386/kernel/signal.c"
* Copyright (C) 1991, 1992 Linus Torvalds
* 1997-11-28 Modified for POSIX.1b signals by Richard Henderson
*/
#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/elf.h>
#include <linux/ptrace.h>
#include <linux/pagemap.h>
#include <linux/ratelimit.h>
#include <linux/syscalls.h>
#ifdef CONFIG_PPC64
#include <linux/compat.h>
#else
#include <linux/wait.h>
#include <linux/unistd.h>
#include <linux/stddef.h>
#include <linux/tty.h>
#include <linux/binfmts.h>
#endif
#include <linux/uaccess.h>
#include <asm/cacheflush.h>
#include <asm/syscalls.h>
#include <asm/sigcontext.h>
#include <asm/vdso.h>
#include <asm/switch_to.h>
#include <asm/tm.h>
#include <asm/asm-prototypes.h>
#ifdef CONFIG_PPC64
#include "ppc32.h"
#include <asm/unistd.h>
#else
#include <asm/ucontext.h>
#endif
#include "signal.h"
#ifdef CONFIG_PPC64
#define old_sigaction old_sigaction32
#define sigcontext sigcontext32
#define mcontext mcontext32
#define ucontext ucontext32
/*
* 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) - sizeof(elf_vsrreghalf_t32))
/*
* Returning 0 means we return to userspace via
* ret_from_except and thus restore all user
* registers from *regs. This is what we need
* to do when a signal has been delivered.
*/
#define GP_REGS_SIZE min(sizeof(elf_gregset_t32), sizeof(struct pt_regs32))
#undef __SIGNAL_FRAMESIZE
#define __SIGNAL_FRAMESIZE __SIGNAL_FRAMESIZE32
#undef ELF_NVRREG
#define ELF_NVRREG ELF_NVRREG32
/*
* Functions for flipping sigsets (thanks to brain dead generic
* implementation that makes things simple for little endian only)
*/
#define unsafe_put_sigset_t unsafe_put_compat_sigset
#define unsafe_get_sigset_t unsafe_get_compat_sigset
#define to_user_ptr(p) ptr_to_compat(p)
#define from_user_ptr(p) compat_ptr(p)
static __always_inline int
__unsafe_save_general_regs(struct pt_regs *regs, struct mcontext __user *frame)
{
elf_greg_t64 *gregs = (elf_greg_t64 *)regs;
int val, i;
[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>
2005-11-16 02:52:18 +08:00
for (i = 0; i <= PT_RESULT; i ++) {
/* Force usr to alway see softe as 1 (interrupts enabled) */
if (i == PT_SOFTE)
val = 1;
else
val = gregs[i];
unsafe_put_user(val, &frame->mc_gregs[i], failed);
[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>
2005-11-16 02:52:18 +08:00
}
return 0;
failed:
return 1;
}
static __always_inline int
__unsafe_restore_general_regs(struct pt_regs *regs, struct mcontext __user *sr)
{
elf_greg_t64 *gregs = (elf_greg_t64 *)regs;
int i;
for (i = 0; i <= PT_RESULT; i++) {
if ((i == PT_MSR) || (i == PT_SOFTE))
continue;
unsafe_get_user(gregs[i], &sr->mc_gregs[i], failed);
}
return 0;
failed:
return 1;
}
#else /* CONFIG_PPC64 */
#define GP_REGS_SIZE min(sizeof(elf_gregset_t), sizeof(struct pt_regs))
#define unsafe_put_sigset_t(uset, set, label) do { \
sigset_t __user *__us = uset ; \
const sigset_t *__s = set; \
\
unsafe_copy_to_user(__us, __s, sizeof(*__us), label); \
} while (0)
#define unsafe_get_sigset_t unsafe_get_user_sigset
#define to_user_ptr(p) ((unsigned long)(p))
#define from_user_ptr(p) ((void __user *)(p))
static __always_inline int
__unsafe_save_general_regs(struct pt_regs *regs, struct mcontext __user *frame)
{
unsafe_copy_to_user(&frame->mc_gregs, regs, GP_REGS_SIZE, failed);
return 0;
failed:
return 1;
}
static __always_inline
int __unsafe_restore_general_regs(struct pt_regs *regs, struct mcontext __user *sr)
{
/* copy up to but not including MSR */
unsafe_copy_from_user(regs, &sr->mc_gregs, PT_MSR * sizeof(elf_greg_t), failed);
/* copy from orig_r3 (the word after the MSR) up to the end */
unsafe_copy_from_user(&regs->orig_gpr3, &sr->mc_gregs[PT_ORIG_R3],
GP_REGS_SIZE - PT_ORIG_R3 * sizeof(elf_greg_t), failed);
return 0;
failed:
return 1;
}
#endif
#define unsafe_save_general_regs(regs, frame, label) do { \
if (__unsafe_save_general_regs(regs, frame)) \
goto label; \
} while (0)
#define unsafe_restore_general_regs(regs, frame, label) do { \
if (__unsafe_restore_general_regs(regs, frame)) \
goto label; \
} while (0)
/*
* When we have signals to deliver, we set up on the
* user stack, going down from the original stack pointer:
* an ABI gap of 56 words
* an mcontext struct
* a sigcontext struct
* a gap of __SIGNAL_FRAMESIZE bytes
*
* Each of these things must be a multiple of 16 bytes in size. The following
* structure represent all of this except the __SIGNAL_FRAMESIZE gap
*
*/
struct sigframe {
struct sigcontext sctx; /* the sigcontext */
struct mcontext mctx; /* all the register values */
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
struct sigcontext sctx_transact;
struct mcontext mctx_transact;
#endif
/*
* Programs using the rs6000/xcoff abi can save up to 19 gp
* regs and 18 fp regs below sp before decrementing it.
*/
int abigap[56];
};
/*
* When we have rt signals to deliver, we set up on the
* user stack, going down from the original stack pointer:
* one rt_sigframe struct (siginfo + ucontext + ABI gap)
* a gap of __SIGNAL_FRAMESIZE+16 bytes
* (the +16 is to get the siginfo and ucontext in the same
* positions as in older kernels).
*
* Each of these things must be a multiple of 16 bytes in size.
*
*/
struct rt_sigframe {
#ifdef CONFIG_PPC64
compat_siginfo_t info;
#else
struct siginfo info;
#endif
struct ucontext uc;
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
struct ucontext uc_transact;
#endif
/*
* Programs using the rs6000/xcoff abi can save up to 19 gp
* regs and 18 fp regs below sp before decrementing it.
*/
int abigap[56];
};
unsigned long get_min_sigframe_size_32(void)
{
return max(sizeof(struct rt_sigframe) + __SIGNAL_FRAMESIZE + 16,
sizeof(struct sigframe) + __SIGNAL_FRAMESIZE);
}
/*
* Save the current user registers on the user stack.
* We only save the altivec/spe registers if the process has used
* altivec/spe instructions at some point.
*/
static void prepare_save_user_regs(int ctx_has_vsx_region)
{
/* Make sure floating point registers are stored in regs */
flush_fp_to_thread(current);
#ifdef CONFIG_ALTIVEC
if (current->thread.used_vr)
flush_altivec_to_thread(current);
if (cpu_has_feature(CPU_FTR_ALTIVEC))
current->thread.vrsave = mfspr(SPRN_VRSAVE);
#endif
#ifdef CONFIG_VSX
if (current->thread.used_vsr && ctx_has_vsx_region)
flush_vsx_to_thread(current);
#endif
#ifdef CONFIG_SPE
if (current->thread.used_spe)
flush_spe_to_thread(current);
#endif
}
static int __unsafe_save_user_regs(struct pt_regs *regs, struct mcontext __user *frame,
struct mcontext __user *tm_frame, int ctx_has_vsx_region)
{
unsigned long msr = regs->msr;
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 12:07:18 +08:00
/* save general registers */
unsafe_save_general_regs(regs, frame, failed);
#ifdef CONFIG_ALTIVEC
/* save altivec registers */
if (current->thread.used_vr) {
unsafe_copy_to_user(&frame->mc_vregs, &current->thread.vr_state,
ELF_NVRREG * sizeof(vector128), failed);
/* set MSR_VEC in the saved MSR value to indicate that
frame->mc_vregs contains valid data */
msr |= MSR_VEC;
}
/* else assert((regs->msr & MSR_VEC) == 0) */
/* We always copy to/from vrsave, it's 0 if we don't have or don't
* use altivec. Since VSCR only contains 32 bits saved in the least
* significant bits of a vector, we "cheat" and stuff VRSAVE in the
* most significant bits of that same vector. --BenH
* Note that the current VRSAVE value is in the SPR at this point.
*/
unsafe_put_user(current->thread.vrsave, (u32 __user *)&frame->mc_vregs[32],
failed);
#endif /* CONFIG_ALTIVEC */
unsafe_copy_fpr_to_user(&frame->mc_fregs, current, failed);
/*
* 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;
#ifdef CONFIG_VSX
/*
* Copy VSR 0-31 upper half from thread_struct to local
* buffer, then write that to userspace. Also set MSR_VSX in
* the saved MSR value to indicate that frame->mc_vregs
* contains valid data
*/
if (current->thread.used_vsr && ctx_has_vsx_region) {
unsafe_copy_vsx_to_user(&frame->mc_vsregs, current, failed);
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 12:07:18 +08:00
#endif /* CONFIG_VSX */
#ifdef CONFIG_SPE
/* save spe registers */
if (current->thread.used_spe) {
unsafe_copy_to_user(&frame->mc_vregs, current->thread.evr,
ELF_NEVRREG * sizeof(u32), failed);
/* set MSR_SPE in the saved MSR value to indicate that
frame->mc_vregs contains valid data */
msr |= MSR_SPE;
}
/* else assert((regs->msr & MSR_SPE) == 0) */
/* We always copy to/from spefscr */
unsafe_put_user(current->thread.spefscr,
(u32 __user *)&frame->mc_vregs + ELF_NEVRREG, failed);
#endif /* CONFIG_SPE */
unsafe_put_user(msr, &frame->mc_gregs[PT_MSR], failed);
/* We need to write 0 the MSR top 32 bits in the tm frame so that we
* can check it on the restore to see if TM is active
*/
if (tm_frame)
unsafe_put_user(0, &tm_frame->mc_gregs[PT_MSR], failed);
return 0;
failed:
return 1;
}
#define unsafe_save_user_regs(regs, frame, tm_frame, has_vsx, label) do { \
if (__unsafe_save_user_regs(regs, frame, tm_frame, has_vsx)) \
goto label; \
} while (0)
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
/*
* Save the current user registers on the user stack.
* We only save the altivec/spe registers if the process has used
* altivec/spe instructions at some point.
* We also save the transactional registers to a second ucontext in the
* frame.
*
* See __unsafe_save_user_regs() and signal_64.c:setup_tm_sigcontexts().
*/
static void prepare_save_tm_user_regs(void)
{
WARN_ON(tm_suspend_disabled);
if (cpu_has_feature(CPU_FTR_ALTIVEC))
current->thread.ckvrsave = mfspr(SPRN_VRSAVE);
}
static int save_tm_user_regs_unsafe(struct pt_regs *regs, struct mcontext __user *frame,
struct mcontext __user *tm_frame, unsigned long msr)
{
/* Save both sets of general registers */
unsafe_save_general_regs(&current->thread.ckpt_regs, frame, failed);
unsafe_save_general_regs(regs, tm_frame, failed);
/* Stash the top half of the 64bit MSR into the 32bit MSR word
* of the transactional mcontext. This way we have a backward-compatible
* MSR in the 'normal' (checkpointed) mcontext and additionally one can
* also look at what type of transaction (T or S) was active at the
* time of the signal.
*/
unsafe_put_user((msr >> 32), &tm_frame->mc_gregs[PT_MSR], failed);
/* save altivec registers */
if (current->thread.used_vr) {
unsafe_copy_to_user(&frame->mc_vregs, &current->thread.ckvr_state,
ELF_NVRREG * sizeof(vector128), failed);
if (msr & MSR_VEC)
unsafe_copy_to_user(&tm_frame->mc_vregs,
&current->thread.vr_state,
ELF_NVRREG * sizeof(vector128), failed);
else
unsafe_copy_to_user(&tm_frame->mc_vregs,
&current->thread.ckvr_state,
ELF_NVRREG * sizeof(vector128), failed);
/* set MSR_VEC in the saved MSR value to indicate that
* frame->mc_vregs 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. Since VSCR only contains 32 bits saved in the least
* significant bits of a vector, we "cheat" and stuff VRSAVE in the
* most significant bits of that same vector. --BenH
*/
unsafe_put_user(current->thread.ckvrsave,
(u32 __user *)&frame->mc_vregs[32], failed);
if (msr & MSR_VEC)
unsafe_put_user(current->thread.vrsave,
(u32 __user *)&tm_frame->mc_vregs[32], failed);
else
unsafe_put_user(current->thread.ckvrsave,
(u32 __user *)&tm_frame->mc_vregs[32], failed);
unsafe_copy_ckfpr_to_user(&frame->mc_fregs, current, failed);
if (msr & MSR_FP)
unsafe_copy_fpr_to_user(&tm_frame->mc_fregs, current, failed);
else
unsafe_copy_ckfpr_to_user(&tm_frame->mc_fregs, current, failed);
/*
* Copy VSR 0-31 upper half from thread_struct to local
* buffer, then write that to userspace. Also set MSR_VSX in
* the saved MSR value to indicate that frame->mc_vregs
* contains valid data
*/
if (current->thread.used_vsr) {
unsafe_copy_ckvsx_to_user(&frame->mc_vsregs, current, failed);
if (msr & MSR_VSX)
unsafe_copy_vsx_to_user(&tm_frame->mc_vsregs, current, failed);
else
unsafe_copy_ckvsx_to_user(&tm_frame->mc_vsregs, current, failed);
msr |= MSR_VSX;
}
unsafe_put_user(msr, &frame->mc_gregs[PT_MSR], failed);
return 0;
failed:
return 1;
}
#else
static void prepare_save_tm_user_regs(void) { }
static int save_tm_user_regs_unsafe(struct pt_regs *regs, struct mcontext __user *frame,
struct mcontext __user *tm_frame, unsigned long msr)
{
return 0;
}
#endif
#define unsafe_save_tm_user_regs(regs, frame, tm_frame, msr, label) do { \
if (save_tm_user_regs_unsafe(regs, frame, tm_frame, msr)) \
goto label; \
} while (0)
/*
* Restore the current user register values from the user stack,
* (except for MSR).
*/
static long restore_user_regs(struct pt_regs *regs,
struct mcontext __user *sr, int sig)
{
unsigned int save_r2 = 0;
unsigned long msr;
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 12:07:18 +08:00
#ifdef CONFIG_VSX
int i;
#endif
if (!user_read_access_begin(sr, sizeof(*sr)))
return 1;
/*
* restore general registers but not including MSR or SOFTE. Also
* take care of keeping r2 (TLS) intact if not a signal
*/
if (!sig)
save_r2 = (unsigned int)regs->gpr[2];
unsafe_restore_general_regs(regs, sr, failed);
set_trap_norestart(regs);
unsafe_get_user(msr, &sr->mc_gregs[PT_MSR], failed);
if (!sig)
regs->gpr[2] = (unsigned long) save_r2;
/* if doing signal return, restore the previous little-endian mode */
if (sig)
regs_set_return_msr(regs, (regs->msr & ~MSR_LE) | (msr & MSR_LE));
#ifdef 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 12:07:18 +08:00
/*
* Force the process to reload the altivec registers from
* current->thread when it next does altivec instructions
*/
regs_set_return_msr(regs, regs->msr & ~MSR_VEC);
if (msr & MSR_VEC) {
/* restore altivec registers from the stack */
unsafe_copy_from_user(&current->thread.vr_state, &sr->mc_vregs,
sizeof(sr->mc_vregs), failed);
current->thread.used_vr = true;
} else if (current->thread.used_vr)
memset(&current->thread.vr_state, 0,
ELF_NVRREG * sizeof(vector128));
/* Always get VRSAVE back */
unsafe_get_user(current->thread.vrsave, (u32 __user *)&sr->mc_vregs[32], failed);
if (cpu_has_feature(CPU_FTR_ALTIVEC))
mtspr(SPRN_VRSAVE, current->thread.vrsave);
#endif /* CONFIG_ALTIVEC */
unsafe_copy_fpr_from_user(current, &sr->mc_fregs, failed);
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 12:07:18 +08:00
#ifdef CONFIG_VSX
/*
* Force the process to reload the VSX registers from
* current->thread when it next does VSX instruction.
*/
regs_set_return_msr(regs, regs->msr & ~MSR_VSX);
if (msr & MSR_VSX) {
/*
* Restore altivec registers from the stack to a local
* buffer, then write this out to the thread_struct
*/
unsafe_copy_vsx_from_user(current, &sr->mc_vsregs, failed);
current->thread.used_vsr = true;
} else if (current->thread.used_vsr)
for (i = 0; i < 32 ; i++)
current->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 12:07:18 +08:00
#endif /* CONFIG_VSX */
/*
* force the process to reload the FP registers from
* current->thread when it next does FP instructions
*/
regs_set_return_msr(regs, regs->msr & ~(MSR_FP | MSR_FE0 | MSR_FE1));
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 12:07:18 +08:00
#ifdef CONFIG_SPE
/*
* Force the process to reload the spe registers from
* current->thread when it next does spe instructions.
* Since this is user ABI, we must enforce the sizing.
*/
BUILD_BUG_ON(sizeof(current->thread.spe) != ELF_NEVRREG * sizeof(u32));
regs_set_return_msr(regs, regs->msr & ~MSR_SPE);
if (msr & MSR_SPE) {
/* restore spe registers from the stack */
unsafe_copy_from_user(&current->thread.spe, &sr->mc_vregs,
sizeof(current->thread.spe), failed);
current->thread.used_spe = true;
} else if (current->thread.used_spe)
memset(&current->thread.spe, 0, sizeof(current->thread.spe));
/* Always get SPEFSCR back */
unsafe_get_user(current->thread.spefscr, (u32 __user *)&sr->mc_vregs + ELF_NEVRREG, failed);
#endif /* CONFIG_SPE */
user_read_access_end();
return 0;
failed:
user_read_access_end();
return 1;
}
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
/*
* Restore the current user register values from the user stack, except for
* MSR, and recheckpoint the original checkpointed register state for processes
* in transactions.
*/
static long restore_tm_user_regs(struct pt_regs *regs,
struct mcontext __user *sr,
struct mcontext __user *tm_sr)
{
unsigned long msr, msr_hi;
int i;
if (tm_suspend_disabled)
return 1;
/*
* restore general registers but not including MSR or SOFTE. Also
* take care of keeping r2 (TLS) intact if not a signal.
* See comment in signal_64.c:restore_tm_sigcontexts();
* TFHAR is restored from the checkpointed NIP; TEXASR and TFIAR
* were set by the signal delivery.
*/
if (!user_read_access_begin(sr, sizeof(*sr)))
return 1;
unsafe_restore_general_regs(&current->thread.ckpt_regs, sr, failed);
unsafe_get_user(current->thread.tm_tfhar, &sr->mc_gregs[PT_NIP], failed);
unsafe_get_user(msr, &sr->mc_gregs[PT_MSR], failed);
/* Restore the previous little-endian mode */
regs_set_return_msr(regs, (regs->msr & ~MSR_LE) | (msr & MSR_LE));
regs_set_return_msr(regs, regs->msr & ~MSR_VEC);
if (msr & MSR_VEC) {
/* restore altivec registers from the stack */
unsafe_copy_from_user(&current->thread.ckvr_state, &sr->mc_vregs,
sizeof(sr->mc_vregs), failed);
current->thread.used_vr = true;
} else if (current->thread.used_vr) {
memset(&current->thread.vr_state, 0,
ELF_NVRREG * sizeof(vector128));
memset(&current->thread.ckvr_state, 0,
ELF_NVRREG * sizeof(vector128));
}
/* Always get VRSAVE back */
unsafe_get_user(current->thread.ckvrsave,
(u32 __user *)&sr->mc_vregs[32], failed);
if (cpu_has_feature(CPU_FTR_ALTIVEC))
mtspr(SPRN_VRSAVE, current->thread.ckvrsave);
regs_set_return_msr(regs, regs->msr & ~(MSR_FP | MSR_FE0 | MSR_FE1));
unsafe_copy_fpr_from_user(current, &sr->mc_fregs, failed);
regs_set_return_msr(regs, regs->msr & ~MSR_VSX);
if (msr & MSR_VSX) {
/*
* Restore altivec registers from the stack to a local
* buffer, then write this out to the thread_struct
*/
unsafe_copy_ckvsx_from_user(current, &sr->mc_vsregs, failed);
current->thread.used_vsr = true;
} else if (current->thread.used_vsr)
for (i = 0; i < 32 ; i++) {
current->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = 0;
current->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET] = 0;
}
user_read_access_end();
if (!user_read_access_begin(tm_sr, sizeof(*tm_sr)))
return 1;
unsafe_restore_general_regs(regs, tm_sr, failed);
/* restore altivec registers from the stack */
if (msr & MSR_VEC)
unsafe_copy_from_user(&current->thread.vr_state, &tm_sr->mc_vregs,
sizeof(sr->mc_vregs), failed);
/* Always get VRSAVE back */
unsafe_get_user(current->thread.vrsave,
(u32 __user *)&tm_sr->mc_vregs[32], failed);
unsafe_copy_ckfpr_from_user(current, &tm_sr->mc_fregs, failed);
if (msr & MSR_VSX) {
/*
* Restore altivec registers from the stack to a local
* buffer, then write this out to the thread_struct
*/
unsafe_copy_vsx_from_user(current, &tm_sr->mc_vsregs, failed);
current->thread.used_vsr = true;
}
/* Get the top half of the MSR from the user context */
unsafe_get_user(msr_hi, &tm_sr->mc_gregs[PT_MSR], failed);
msr_hi <<= 32;
user_read_access_end();
/* If TM bits are set to the reserved value, it's an invalid context */
if (MSR_TM_RESV(msr_hi))
return 1;
powerpc/tm: Set MSR[TS] just prior to recheckpoint On a signal handler return, the user could set a context with MSR[TS] bits set, and these bits would be copied to task regs->msr. At restore_tm_sigcontexts(), after current task regs->msr[TS] bits are set, several __get_user() are called and then a recheckpoint is executed. This is a problem since a page fault (in kernel space) could happen when calling __get_user(). If it happens, the process MSR[TS] bits were already set, but recheckpoint was not executed, and SPRs are still invalid. The page fault can cause the current process to be de-scheduled, with MSR[TS] active and without tm_recheckpoint() being called. More importantly, without TEXASR[FS] bit set also. Since TEXASR might not have the FS bit set, and when the process is scheduled back, it will try to reclaim, which will be aborted because of the CPU is not in the suspended state, and, then, recheckpoint. This recheckpoint will restore thread->texasr into TEXASR SPR, which might be zero, hitting a BUG_ON(). kernel BUG at /build/linux-sf3Co9/linux-4.9.30/arch/powerpc/kernel/tm.S:434! cpu 0xb: Vector: 700 (Program Check) at [c00000041f1576d0] pc: c000000000054550: restore_gprs+0xb0/0x180 lr: 0000000000000000 sp: c00000041f157950 msr: 8000000100021033 current = 0xc00000041f143000 paca = 0xc00000000fb86300 softe: 0 irq_happened: 0x01 pid = 1021, comm = kworker/11:1 kernel BUG at /build/linux-sf3Co9/linux-4.9.30/arch/powerpc/kernel/tm.S:434! Linux version 4.9.0-3-powerpc64le (debian-kernel@lists.debian.org) (gcc version 6.3.0 20170516 (Debian 6.3.0-18) ) #1 SMP Debian 4.9.30-2+deb9u2 (2017-06-26) enter ? for help [c00000041f157b30] c00000000001bc3c tm_recheckpoint.part.11+0x6c/0xa0 [c00000041f157b70] c00000000001d184 __switch_to+0x1e4/0x4c0 [c00000041f157bd0] c00000000082eeb8 __schedule+0x2f8/0x990 [c00000041f157cb0] c00000000082f598 schedule+0x48/0xc0 [c00000041f157ce0] c0000000000f0d28 worker_thread+0x148/0x610 [c00000041f157d80] c0000000000f96b0 kthread+0x120/0x140 [c00000041f157e30] c00000000000c0e0 ret_from_kernel_thread+0x5c/0x7c This patch simply delays the MSR[TS] set, so, if there is any page fault in the __get_user() section, it does not have regs->msr[TS] set, since the TM structures are still invalid, thus avoiding doing TM operations for in-kernel exceptions and possible process reschedule. With this patch, the MSR[TS] will only be set just before recheckpointing and setting TEXASR[FS] = 1, thus avoiding an interrupt with TM registers in invalid state. Other than that, if CONFIG_PREEMPT is set, there might be a preemption just after setting MSR[TS] and before tm_recheckpoint(), thus, this block must be atomic from a preemption perspective, thus, calling preempt_disable/enable() on this code. It is not possible to move tm_recheckpoint to happen earlier, because it is required to get the checkpointed registers from userspace, with __get_user(), thus, the only way to avoid this undesired behavior is delaying the MSR[TS] set. The 32-bits signal handler seems to be safe this current issue, but, it might be exposed to the preemption issue, thus, disabling preemption in this chunk of code. Changes from v2: * Run the critical section with preempt_disable. Fixes: 87b4e5393af7 ("powerpc/tm: Fix return of active 64bit signals") Cc: stable@vger.kernel.org (v3.9+) Signed-off-by: Breno Leitao <leitao@debian.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-11-22 03:21:09 +08:00
/*
* Disabling preemption, since it is unsafe to be preempted
* with MSR[TS] set without recheckpointing.
*/
preempt_disable();
/*
* CAUTION:
* After regs->MSR[TS] being updated, make sure that get_user(),
* put_user() or similar functions are *not* called. These
* functions can generate page faults which will cause the process
* to be de-scheduled with MSR[TS] set but without calling
* tm_recheckpoint(). This can cause a bug.
*
* Pull in the MSR TM bits from the user context
*/
regs_set_return_msr(regs, (regs->msr & ~MSR_TS_MASK) | (msr_hi & MSR_TS_MASK));
/* Now, recheckpoint. This loads up all of the checkpointed (older)
* registers, including FP and V[S]Rs. After recheckpointing, the
* transactional versions should be loaded.
*/
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 17:19:48 +08:00
/* Make sure the transaction is marked as failed */
current->thread.tm_texasr |= TEXASR_FS;
/* This loads the checkpointed FP/VEC state, if used */
powerpc: Always save/restore checkpointed regs during treclaim/trecheckpoint Lazy save and restore of FP/Altivec means that a userspace process can be sent to userspace with FP or Altivec disabled and loaded only as required (by way of an FP/Altivec unavailable exception). Transactional Memory complicates this situation as a transaction could be started without FP/Altivec being loaded up. This causes the hardware to checkpoint incorrect registers. Handling FP/Altivec unavailable exceptions while a thread is transactional requires a reclaim and recheckpoint to ensure the CPU has correct state for both sets of registers. tm_reclaim() has optimisations to not always save the FP/Altivec registers to the checkpointed save area. This was originally done because the caller might have information that the checkpointed registers aren't valid due to lazy save and restore. We've also been a little vague as to how tm_reclaim() leaves the FP/Altivec state since it doesn't necessarily always save it to the thread struct. This has lead to an (incorrect) assumption that it leaves the checkpointed state on the CPU. tm_recheckpoint() has similar optimisations in reverse. It may not always reload the checkpointed FP/Altivec registers from the thread struct before the trecheckpoint. It is therefore quite unclear where it expects to get the state from. This didn't help with the assumption made about tm_reclaim(). These optimisations sit in what is by definition a slow path. If a process has to go through a reclaim/recheckpoint then its transaction will be doomed on returning to userspace. This mean that the process will be unable to complete its transaction and be forced to its failure handler. This is already an out if line case for userspace. Furthermore, the cost of copying 64 times 128 bits from registers isn't very long[0] (at all) on modern processors. As such it appears these optimisations have only served to increase code complexity and are unlikely to have had a measurable performance impact. Our transactional memory handling has been riddled with bugs. A cause of this has been difficulty in following the code flow, code complexity has not been our friend here. It makes sense to remove these optimisations in favour of a (hopefully) more stable implementation. This patch does mean that some times the assembly will needlessly save 'junk' registers which will subsequently get overwritten with the correct value by the C code which calls the assembly function. This small inefficiency is far outweighed by the reduction in complexity for general TM code, context switching paths, and transactional facility unavailable exception handler. 0: I tried to measure it once for other work and found that it was hiding in the noise of everything else I was working with. I find it exceedingly likely this will be the case here. Signed-off-by: Cyril Bur <cyrilbur@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-11-02 11:09:05 +08:00
tm_recheckpoint(&current->thread);
/* This loads the speculative FP/VEC state, if used */
powerpc: tm: Always use fp_state and vr_state to store live registers There is currently an inconsistency as to how the entire CPU register state is saved and restored when a thread uses transactional memory (TM). Using transactional memory results in the CPU having duplicated (almost) all of its register state. This duplication results in a set of registers which can be considered 'live', those being currently modified by the instructions being executed and another set that is frozen at a point in time. On context switch, both sets of state have to be saved and (later) restored. These two states are often called a variety of different things. Common terms for the state which only exists after the CPU has entered a transaction (performed a TBEGIN instruction) in hardware are 'transactional' or 'speculative'. Between a TBEGIN and a TEND or TABORT (or an event that causes the hardware to abort), regardless of the use of TSUSPEND the transactional state can be referred to as the live state. The second state is often to referred to as the 'checkpointed' state and is a duplication of the live state when the TBEGIN instruction is executed. This state is kept in the hardware and will be rolled back to on transaction failure. Currently all the registers stored in pt_regs are ALWAYS the live registers, that is, when a thread has transactional registers their values are stored in pt_regs and the checkpointed state is in ckpt_regs. A strange opposite is true for fp_state/vr_state. When a thread is non transactional fp_state/vr_state holds the live registers. When a thread has initiated a transaction fp_state/vr_state holds the checkpointed state and transact_fp/transact_vr become the structure which holds the live state (at this point it is a transactional state). This method creates confusion as to where the live state is, in some circumstances it requires extra work to determine where to put the live state and prevents the use of common functions designed (probably before TM) to save the live state. With this patch pt_regs, fp_state and vr_state all represent the same thing and the other structures [pending rename] are for checkpointed state. Acked-by: Simon Guo <wei.guo.simon@gmail.com> Signed-off-by: Cyril Bur <cyrilbur@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-09-23 14:18:24 +08:00
msr_check_and_set(msr & (MSR_FP | MSR_VEC));
if (msr & MSR_FP) {
powerpc: tm: Always use fp_state and vr_state to store live registers There is currently an inconsistency as to how the entire CPU register state is saved and restored when a thread uses transactional memory (TM). Using transactional memory results in the CPU having duplicated (almost) all of its register state. This duplication results in a set of registers which can be considered 'live', those being currently modified by the instructions being executed and another set that is frozen at a point in time. On context switch, both sets of state have to be saved and (later) restored. These two states are often called a variety of different things. Common terms for the state which only exists after the CPU has entered a transaction (performed a TBEGIN instruction) in hardware are 'transactional' or 'speculative'. Between a TBEGIN and a TEND or TABORT (or an event that causes the hardware to abort), regardless of the use of TSUSPEND the transactional state can be referred to as the live state. The second state is often to referred to as the 'checkpointed' state and is a duplication of the live state when the TBEGIN instruction is executed. This state is kept in the hardware and will be rolled back to on transaction failure. Currently all the registers stored in pt_regs are ALWAYS the live registers, that is, when a thread has transactional registers their values are stored in pt_regs and the checkpointed state is in ckpt_regs. A strange opposite is true for fp_state/vr_state. When a thread is non transactional fp_state/vr_state holds the live registers. When a thread has initiated a transaction fp_state/vr_state holds the checkpointed state and transact_fp/transact_vr become the structure which holds the live state (at this point it is a transactional state). This method creates confusion as to where the live state is, in some circumstances it requires extra work to determine where to put the live state and prevents the use of common functions designed (probably before TM) to save the live state. With this patch pt_regs, fp_state and vr_state all represent the same thing and the other structures [pending rename] are for checkpointed state. Acked-by: Simon Guo <wei.guo.simon@gmail.com> Signed-off-by: Cyril Bur <cyrilbur@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-09-23 14:18:24 +08:00
load_fp_state(&current->thread.fp_state);
regs_set_return_msr(regs, regs->msr | (MSR_FP | current->thread.fpexc_mode));
}
if (msr & MSR_VEC) {
powerpc: tm: Always use fp_state and vr_state to store live registers There is currently an inconsistency as to how the entire CPU register state is saved and restored when a thread uses transactional memory (TM). Using transactional memory results in the CPU having duplicated (almost) all of its register state. This duplication results in a set of registers which can be considered 'live', those being currently modified by the instructions being executed and another set that is frozen at a point in time. On context switch, both sets of state have to be saved and (later) restored. These two states are often called a variety of different things. Common terms for the state which only exists after the CPU has entered a transaction (performed a TBEGIN instruction) in hardware are 'transactional' or 'speculative'. Between a TBEGIN and a TEND or TABORT (or an event that causes the hardware to abort), regardless of the use of TSUSPEND the transactional state can be referred to as the live state. The second state is often to referred to as the 'checkpointed' state and is a duplication of the live state when the TBEGIN instruction is executed. This state is kept in the hardware and will be rolled back to on transaction failure. Currently all the registers stored in pt_regs are ALWAYS the live registers, that is, when a thread has transactional registers their values are stored in pt_regs and the checkpointed state is in ckpt_regs. A strange opposite is true for fp_state/vr_state. When a thread is non transactional fp_state/vr_state holds the live registers. When a thread has initiated a transaction fp_state/vr_state holds the checkpointed state and transact_fp/transact_vr become the structure which holds the live state (at this point it is a transactional state). This method creates confusion as to where the live state is, in some circumstances it requires extra work to determine where to put the live state and prevents the use of common functions designed (probably before TM) to save the live state. With this patch pt_regs, fp_state and vr_state all represent the same thing and the other structures [pending rename] are for checkpointed state. Acked-by: Simon Guo <wei.guo.simon@gmail.com> Signed-off-by: Cyril Bur <cyrilbur@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-09-23 14:18:24 +08:00
load_vr_state(&current->thread.vr_state);
regs_set_return_msr(regs, regs->msr | MSR_VEC);
}
powerpc/tm: Set MSR[TS] just prior to recheckpoint On a signal handler return, the user could set a context with MSR[TS] bits set, and these bits would be copied to task regs->msr. At restore_tm_sigcontexts(), after current task regs->msr[TS] bits are set, several __get_user() are called and then a recheckpoint is executed. This is a problem since a page fault (in kernel space) could happen when calling __get_user(). If it happens, the process MSR[TS] bits were already set, but recheckpoint was not executed, and SPRs are still invalid. The page fault can cause the current process to be de-scheduled, with MSR[TS] active and without tm_recheckpoint() being called. More importantly, without TEXASR[FS] bit set also. Since TEXASR might not have the FS bit set, and when the process is scheduled back, it will try to reclaim, which will be aborted because of the CPU is not in the suspended state, and, then, recheckpoint. This recheckpoint will restore thread->texasr into TEXASR SPR, which might be zero, hitting a BUG_ON(). kernel BUG at /build/linux-sf3Co9/linux-4.9.30/arch/powerpc/kernel/tm.S:434! cpu 0xb: Vector: 700 (Program Check) at [c00000041f1576d0] pc: c000000000054550: restore_gprs+0xb0/0x180 lr: 0000000000000000 sp: c00000041f157950 msr: 8000000100021033 current = 0xc00000041f143000 paca = 0xc00000000fb86300 softe: 0 irq_happened: 0x01 pid = 1021, comm = kworker/11:1 kernel BUG at /build/linux-sf3Co9/linux-4.9.30/arch/powerpc/kernel/tm.S:434! Linux version 4.9.0-3-powerpc64le (debian-kernel@lists.debian.org) (gcc version 6.3.0 20170516 (Debian 6.3.0-18) ) #1 SMP Debian 4.9.30-2+deb9u2 (2017-06-26) enter ? for help [c00000041f157b30] c00000000001bc3c tm_recheckpoint.part.11+0x6c/0xa0 [c00000041f157b70] c00000000001d184 __switch_to+0x1e4/0x4c0 [c00000041f157bd0] c00000000082eeb8 __schedule+0x2f8/0x990 [c00000041f157cb0] c00000000082f598 schedule+0x48/0xc0 [c00000041f157ce0] c0000000000f0d28 worker_thread+0x148/0x610 [c00000041f157d80] c0000000000f96b0 kthread+0x120/0x140 [c00000041f157e30] c00000000000c0e0 ret_from_kernel_thread+0x5c/0x7c This patch simply delays the MSR[TS] set, so, if there is any page fault in the __get_user() section, it does not have regs->msr[TS] set, since the TM structures are still invalid, thus avoiding doing TM operations for in-kernel exceptions and possible process reschedule. With this patch, the MSR[TS] will only be set just before recheckpointing and setting TEXASR[FS] = 1, thus avoiding an interrupt with TM registers in invalid state. Other than that, if CONFIG_PREEMPT is set, there might be a preemption just after setting MSR[TS] and before tm_recheckpoint(), thus, this block must be atomic from a preemption perspective, thus, calling preempt_disable/enable() on this code. It is not possible to move tm_recheckpoint to happen earlier, because it is required to get the checkpointed registers from userspace, with __get_user(), thus, the only way to avoid this undesired behavior is delaying the MSR[TS] set. The 32-bits signal handler seems to be safe this current issue, but, it might be exposed to the preemption issue, thus, disabling preemption in this chunk of code. Changes from v2: * Run the critical section with preempt_disable. Fixes: 87b4e5393af7 ("powerpc/tm: Fix return of active 64bit signals") Cc: stable@vger.kernel.org (v3.9+) Signed-off-by: Breno Leitao <leitao@debian.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-11-22 03:21:09 +08:00
preempt_enable();
return 0;
failed:
user_read_access_end();
return 1;
}
#else
static long restore_tm_user_regs(struct pt_regs *regs, struct mcontext __user *sr,
struct mcontext __user *tm_sr)
{
return 0;
}
#endif
#ifdef CONFIG_PPC64
#define copy_siginfo_to_user copy_siginfo_to_user32
#endif /* CONFIG_PPC64 */
/*
* Set up a signal frame for a "real-time" signal handler
* (one which gets siginfo).
*/
int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset,
struct task_struct *tsk)
{
struct rt_sigframe __user *frame;
struct mcontext __user *mctx;
struct mcontext __user *tm_mctx = NULL;
unsigned long newsp = 0;
unsigned long tramp;
struct pt_regs *regs = tsk->thread.regs;
powerpc/tm: Fix clearing MSR[TS] in current when reclaiming on signal delivery After a treclaim, we expect to be in non-transactional state. If we don't clear the current thread's MSR[TS] before we get preempted, then tm_recheckpoint_new_task() will recheckpoint and we get rescheduled in suspended transaction state. When handling a signal caught in transactional state, handle_rt_signal64() calls get_tm_stackpointer() that treclaims the transaction using tm_reclaim_current() but without clearing the thread's MSR[TS]. This can cause the TM Bad Thing exception below if later we pagefault and get preempted trying to access the user's sigframe, using __put_user(). Afterwards, when we are rescheduled back into do_page_fault() (but now in suspended state since the thread's MSR[TS] was not cleared), upon executing 'rfid' after completion of the page fault handling, the exception is raised because a transition from suspended to non-transactional state is invalid. Unexpected TM Bad Thing exception at c00000000000de44 (msr 0x8000000302a03031) tm_scratch=800000010280b033 Oops: Unrecoverable exception, sig: 6 [#1] LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries CPU: 25 PID: 15547 Comm: a.out Not tainted 5.4.0-rc2 #32 NIP: c00000000000de44 LR: c000000000034728 CTR: 0000000000000000 REGS: c00000003fe7bd70 TRAP: 0700 Not tainted (5.4.0-rc2) MSR: 8000000302a03031 <SF,VEC,VSX,FP,ME,IR,DR,LE,TM[SE]> CR: 44000884 XER: 00000000 CFAR: c00000000000dda4 IRQMASK: 0 PACATMSCRATCH: 800000010280b033 GPR00: c000000000034728 c000000f65a17c80 c000000001662800 00007fffacf3fd78 GPR04: 0000000000001000 0000000000001000 0000000000000000 c000000f611f8af0 GPR08: 0000000000000000 0000000078006001 0000000000000000 000c000000000000 GPR12: c000000f611f84b0 c00000003ffcb200 0000000000000000 0000000000000000 GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR20: 0000000000000000 0000000000000000 0000000000000000 c000000f611f8140 GPR24: 0000000000000000 00007fffacf3fd68 c000000f65a17d90 c000000f611f7800 GPR28: c000000f65a17e90 c000000f65a17e90 c000000001685e18 00007fffacf3f000 NIP [c00000000000de44] fast_exception_return+0xf4/0x1b0 LR [c000000000034728] handle_rt_signal64+0x78/0xc50 Call Trace: [c000000f65a17c80] [c000000000034710] handle_rt_signal64+0x60/0xc50 (unreliable) [c000000f65a17d30] [c000000000023640] do_notify_resume+0x330/0x460 [c000000f65a17e20] [c00000000000dcc4] ret_from_except_lite+0x70/0x74 Instruction dump: 7c4ff120 e8410170 7c5a03a6 38400000 f8410060 e8010070 e8410080 e8610088 60000000 60000000 e8810090 e8210078 <4c000024> 48000000 e8610178 88ed0989 ---[ end trace 93094aa44b442f87 ]--- The simplified sequence of events that triggers the above exception is: ... # userspace in NON-TRANSACTIONAL state tbegin # userspace in TRANSACTIONAL state signal delivery # kernelspace in SUSPENDED state handle_rt_signal64() get_tm_stackpointer() treclaim # kernelspace in NON-TRANSACTIONAL state __put_user() page fault happens. We will never get back here because of the TM Bad Thing exception. page fault handling kicks in and we voluntarily preempt ourselves do_page_fault() __schedule() __switch_to(other_task) our task is rescheduled and we recheckpoint because the thread's MSR[TS] was not cleared __switch_to(our_task) switch_to_tm() tm_recheckpoint_new_task() trechkpt # kernelspace in SUSPENDED state The page fault handling resumes, but now we are in suspended transaction state do_page_fault() completes rfid <----- trying to get back where the page fault happened (we were non-transactional back then) TM Bad Thing # illegal transition from suspended to non-transactional This patch fixes that issue by clearing the current thread's MSR[TS] just after treclaim in get_tm_stackpointer() so that we stay in non-transactional state in case we are preempted. In order to make treclaim and clearing the thread's MSR[TS] atomic from a preemption perspective when CONFIG_PREEMPT is set, preempt_disable/enable() is used. It's also necessary to save the previous value of the thread's MSR before get_tm_stackpointer() is called so that it can be exposed to the signal handler later in setup_tm_sigcontexts() to inform the userspace MSR at the moment of the signal delivery. Found with tm-signal-context-force-tm kernel selftest. Fixes: 2b0a576d15e0 ("powerpc: Add new transactional memory state to the signal context") Cc: stable@vger.kernel.org # v3.9 Signed-off-by: Gustavo Luiz Duarte <gustavold@linux.ibm.com> Acked-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20200211033831.11165-1-gustavold@linux.ibm.com
2020-02-11 11:38:29 +08:00
/* Save the thread's msr before get_tm_stackpointer() changes it */
unsigned long msr = regs->msr;
/* Set up Signal Frame */
frame = get_sigframe(ksig, tsk, sizeof(*frame), 1);
mctx = &frame->uc.uc_mcontext;
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
tm_mctx = &frame->uc_transact.uc_mcontext;
#endif
if (MSR_TM_ACTIVE(msr))
prepare_save_tm_user_regs();
else
prepare_save_user_regs(1);
powerpc/signal32: Fix Oops on sigreturn with unmapped VDSO PPC32 encounters a KUAP fault when trying to handle a signal with VDSO unmapped. Kernel attempted to read user page (7fc07ec0) - exploit attempt? (uid: 0) BUG: Unable to handle kernel data access on read at 0x7fc07ec0 Faulting instruction address: 0xc00111d4 Oops: Kernel access of bad area, sig: 11 [#1] BE PAGE_SIZE=16K PREEMPT CMPC885 CPU: 0 PID: 353 Comm: sigreturn_vdso Not tainted 5.12.0-rc4-s3k-dev-01553-gb30c310ea220 #4814 NIP: c00111d4 LR: c0005a28 CTR: 00000000 REGS: cadb3dd0 TRAP: 0300 Not tainted (5.12.0-rc4-s3k-dev-01553-gb30c310ea220) MSR: 00009032 <EE,ME,IR,DR,RI> CR: 48000884 XER: 20000000 DAR: 7fc07ec0 DSISR: 88000000 GPR00: c0007788 cadb3e90 c28d4a40 7fc07ec0 7fc07ed0 000004e0 7fc07ce0 00000000 GPR08: 00000001 00000001 7fc07ec0 00000000 28000282 1001b828 100a0920 00000000 GPR16: 100cac0c 100b0000 105c43a4 105c5685 100d0000 100d0000 100d0000 100b2e9e GPR24: ffffffff 105c43c8 00000000 7fc07ec8 cadb3f40 cadb3ec8 c28d4a40 00000000 NIP [c00111d4] flush_icache_range+0x90/0xb4 LR [c0005a28] handle_signal32+0x1bc/0x1c4 Call Trace: [cadb3e90] [100d0000] 0x100d0000 (unreliable) [cadb3ec0] [c0007788] do_notify_resume+0x260/0x314 [cadb3f20] [c000c764] syscall_exit_prepare+0x120/0x184 [cadb3f30] [c00100b4] ret_from_syscall+0xc/0x28 --- interrupt: c00 at 0xfe807f8 NIP: 0fe807f8 LR: 10001060 CTR: c0139378 REGS: cadb3f40 TRAP: 0c00 Not tainted (5.12.0-rc4-s3k-dev-01553-gb30c310ea220) MSR: 0000d032 <EE,PR,ME,IR,DR,RI> CR: 28000482 XER: 20000000 GPR00: 00000025 7fc081c0 77bb1690 00000000 0000000a 28000482 00000001 0ff03a38 GPR08: 0000d032 00006de5 c28d4a40 00000009 88000482 1001b828 100a0920 00000000 GPR16: 100cac0c 100b0000 105c43a4 105c5685 100d0000 100d0000 100d0000 100b2e9e GPR24: ffffffff 105c43c8 00000000 77ba7628 10002398 10010000 10002124 00024000 NIP [0fe807f8] 0xfe807f8 LR [10001060] 0x10001060 --- interrupt: c00 Instruction dump: 38630010 7c001fac 38630010 4200fff0 7c0004ac 4c00012c 4e800020 7c001fac 2c0a0000 38630010 4082ffcc 4bffffe4 <7c00186c> 2c070000 39430010 4082ff8c ---[ end trace 3973fb72b049cb06 ]--- This is because flush_icache_range() is called on user addresses. The same problem was detected some time ago on PPC64. It was fixed by enabling KUAP in commit 59bee45b9712 ("powerpc/mm: Fix missing KUAP disable in flush_coherent_icache()"). PPC32 doesn't use flush_coherent_icache() and fallbacks on clean_dcache_range() and invalidate_icache_range(). We could fix it similarly by enabling user access in those functions, but this is overkill for just flushing two instructions. The two instructions are 8 bytes aligned, so a single dcbst/icbi is enough to flush them. Do like __patch_instruction() and inline a dcbst followed by an icbi just after the write of the instructions, while user access is still allowed. The isync is not required because rfi will be used to return to user. icbi() is handled as a read so read-write user access is needed. Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/bde9154e5351a5ac7bca3d59cdb5a5e8edacbb79.1617199569.git.christophe.leroy@csgroup.eu
2021-03-31 22:07:04 +08:00
if (!user_access_begin(frame, sizeof(*frame)))
goto badframe;
/* Put the siginfo & fill in most of the ucontext */
unsafe_put_user(0, &frame->uc.uc_flags, failed);
#ifdef CONFIG_PPC64
unsafe_compat_save_altstack(&frame->uc.uc_stack, regs->gpr[1], failed);
#else
unsafe_save_altstack(&frame->uc.uc_stack, regs->gpr[1], failed);
#endif
unsafe_put_user(to_user_ptr(&frame->uc.uc_mcontext), &frame->uc.uc_regs, failed);
if (MSR_TM_ACTIVE(msr)) {
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
unsafe_put_user((unsigned long)&frame->uc_transact,
&frame->uc.uc_link, failed);
unsafe_put_user((unsigned long)tm_mctx,
&frame->uc_transact.uc_regs, failed);
#endif
unsafe_save_tm_user_regs(regs, mctx, tm_mctx, msr, failed);
} else {
unsafe_put_user(0, &frame->uc.uc_link, failed);
unsafe_save_user_regs(regs, mctx, tm_mctx, 1, failed);
}
/* Save user registers on the stack */
if (tsk->mm->context.vdso) {
tramp = VDSO32_SYMBOL(tsk->mm->context.vdso, sigtramp_rt32);
} else {
tramp = (unsigned long)mctx->mc_pad;
unsafe_put_user(PPC_RAW_LI(_R0, __NR_rt_sigreturn), &mctx->mc_pad[0], failed);
unsafe_put_user(PPC_RAW_SC(), &mctx->mc_pad[1], failed);
powerpc/signal32: Fix Oops on sigreturn with unmapped VDSO PPC32 encounters a KUAP fault when trying to handle a signal with VDSO unmapped. Kernel attempted to read user page (7fc07ec0) - exploit attempt? (uid: 0) BUG: Unable to handle kernel data access on read at 0x7fc07ec0 Faulting instruction address: 0xc00111d4 Oops: Kernel access of bad area, sig: 11 [#1] BE PAGE_SIZE=16K PREEMPT CMPC885 CPU: 0 PID: 353 Comm: sigreturn_vdso Not tainted 5.12.0-rc4-s3k-dev-01553-gb30c310ea220 #4814 NIP: c00111d4 LR: c0005a28 CTR: 00000000 REGS: cadb3dd0 TRAP: 0300 Not tainted (5.12.0-rc4-s3k-dev-01553-gb30c310ea220) MSR: 00009032 <EE,ME,IR,DR,RI> CR: 48000884 XER: 20000000 DAR: 7fc07ec0 DSISR: 88000000 GPR00: c0007788 cadb3e90 c28d4a40 7fc07ec0 7fc07ed0 000004e0 7fc07ce0 00000000 GPR08: 00000001 00000001 7fc07ec0 00000000 28000282 1001b828 100a0920 00000000 GPR16: 100cac0c 100b0000 105c43a4 105c5685 100d0000 100d0000 100d0000 100b2e9e GPR24: ffffffff 105c43c8 00000000 7fc07ec8 cadb3f40 cadb3ec8 c28d4a40 00000000 NIP [c00111d4] flush_icache_range+0x90/0xb4 LR [c0005a28] handle_signal32+0x1bc/0x1c4 Call Trace: [cadb3e90] [100d0000] 0x100d0000 (unreliable) [cadb3ec0] [c0007788] do_notify_resume+0x260/0x314 [cadb3f20] [c000c764] syscall_exit_prepare+0x120/0x184 [cadb3f30] [c00100b4] ret_from_syscall+0xc/0x28 --- interrupt: c00 at 0xfe807f8 NIP: 0fe807f8 LR: 10001060 CTR: c0139378 REGS: cadb3f40 TRAP: 0c00 Not tainted (5.12.0-rc4-s3k-dev-01553-gb30c310ea220) MSR: 0000d032 <EE,PR,ME,IR,DR,RI> CR: 28000482 XER: 20000000 GPR00: 00000025 7fc081c0 77bb1690 00000000 0000000a 28000482 00000001 0ff03a38 GPR08: 0000d032 00006de5 c28d4a40 00000009 88000482 1001b828 100a0920 00000000 GPR16: 100cac0c 100b0000 105c43a4 105c5685 100d0000 100d0000 100d0000 100b2e9e GPR24: ffffffff 105c43c8 00000000 77ba7628 10002398 10010000 10002124 00024000 NIP [0fe807f8] 0xfe807f8 LR [10001060] 0x10001060 --- interrupt: c00 Instruction dump: 38630010 7c001fac 38630010 4200fff0 7c0004ac 4c00012c 4e800020 7c001fac 2c0a0000 38630010 4082ffcc 4bffffe4 <7c00186c> 2c070000 39430010 4082ff8c ---[ end trace 3973fb72b049cb06 ]--- This is because flush_icache_range() is called on user addresses. The same problem was detected some time ago on PPC64. It was fixed by enabling KUAP in commit 59bee45b9712 ("powerpc/mm: Fix missing KUAP disable in flush_coherent_icache()"). PPC32 doesn't use flush_coherent_icache() and fallbacks on clean_dcache_range() and invalidate_icache_range(). We could fix it similarly by enabling user access in those functions, but this is overkill for just flushing two instructions. The two instructions are 8 bytes aligned, so a single dcbst/icbi is enough to flush them. Do like __patch_instruction() and inline a dcbst followed by an icbi just after the write of the instructions, while user access is still allowed. The isync is not required because rfi will be used to return to user. icbi() is handled as a read so read-write user access is needed. Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/bde9154e5351a5ac7bca3d59cdb5a5e8edacbb79.1617199569.git.christophe.leroy@csgroup.eu
2021-03-31 22:07:04 +08:00
asm("dcbst %y0; sync; icbi %y0; sync" :: "Z" (mctx->mc_pad[0]));
}
unsafe_put_sigset_t(&frame->uc.uc_sigmask, oldset, failed);
powerpc/signal32: Fix Oops on sigreturn with unmapped VDSO PPC32 encounters a KUAP fault when trying to handle a signal with VDSO unmapped. Kernel attempted to read user page (7fc07ec0) - exploit attempt? (uid: 0) BUG: Unable to handle kernel data access on read at 0x7fc07ec0 Faulting instruction address: 0xc00111d4 Oops: Kernel access of bad area, sig: 11 [#1] BE PAGE_SIZE=16K PREEMPT CMPC885 CPU: 0 PID: 353 Comm: sigreturn_vdso Not tainted 5.12.0-rc4-s3k-dev-01553-gb30c310ea220 #4814 NIP: c00111d4 LR: c0005a28 CTR: 00000000 REGS: cadb3dd0 TRAP: 0300 Not tainted (5.12.0-rc4-s3k-dev-01553-gb30c310ea220) MSR: 00009032 <EE,ME,IR,DR,RI> CR: 48000884 XER: 20000000 DAR: 7fc07ec0 DSISR: 88000000 GPR00: c0007788 cadb3e90 c28d4a40 7fc07ec0 7fc07ed0 000004e0 7fc07ce0 00000000 GPR08: 00000001 00000001 7fc07ec0 00000000 28000282 1001b828 100a0920 00000000 GPR16: 100cac0c 100b0000 105c43a4 105c5685 100d0000 100d0000 100d0000 100b2e9e GPR24: ffffffff 105c43c8 00000000 7fc07ec8 cadb3f40 cadb3ec8 c28d4a40 00000000 NIP [c00111d4] flush_icache_range+0x90/0xb4 LR [c0005a28] handle_signal32+0x1bc/0x1c4 Call Trace: [cadb3e90] [100d0000] 0x100d0000 (unreliable) [cadb3ec0] [c0007788] do_notify_resume+0x260/0x314 [cadb3f20] [c000c764] syscall_exit_prepare+0x120/0x184 [cadb3f30] [c00100b4] ret_from_syscall+0xc/0x28 --- interrupt: c00 at 0xfe807f8 NIP: 0fe807f8 LR: 10001060 CTR: c0139378 REGS: cadb3f40 TRAP: 0c00 Not tainted (5.12.0-rc4-s3k-dev-01553-gb30c310ea220) MSR: 0000d032 <EE,PR,ME,IR,DR,RI> CR: 28000482 XER: 20000000 GPR00: 00000025 7fc081c0 77bb1690 00000000 0000000a 28000482 00000001 0ff03a38 GPR08: 0000d032 00006de5 c28d4a40 00000009 88000482 1001b828 100a0920 00000000 GPR16: 100cac0c 100b0000 105c43a4 105c5685 100d0000 100d0000 100d0000 100b2e9e GPR24: ffffffff 105c43c8 00000000 77ba7628 10002398 10010000 10002124 00024000 NIP [0fe807f8] 0xfe807f8 LR [10001060] 0x10001060 --- interrupt: c00 Instruction dump: 38630010 7c001fac 38630010 4200fff0 7c0004ac 4c00012c 4e800020 7c001fac 2c0a0000 38630010 4082ffcc 4bffffe4 <7c00186c> 2c070000 39430010 4082ff8c ---[ end trace 3973fb72b049cb06 ]--- This is because flush_icache_range() is called on user addresses. The same problem was detected some time ago on PPC64. It was fixed by enabling KUAP in commit 59bee45b9712 ("powerpc/mm: Fix missing KUAP disable in flush_coherent_icache()"). PPC32 doesn't use flush_coherent_icache() and fallbacks on clean_dcache_range() and invalidate_icache_range(). We could fix it similarly by enabling user access in those functions, but this is overkill for just flushing two instructions. The two instructions are 8 bytes aligned, so a single dcbst/icbi is enough to flush them. Do like __patch_instruction() and inline a dcbst followed by an icbi just after the write of the instructions, while user access is still allowed. The isync is not required because rfi will be used to return to user. icbi() is handled as a read so read-write user access is needed. Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/bde9154e5351a5ac7bca3d59cdb5a5e8edacbb79.1617199569.git.christophe.leroy@csgroup.eu
2021-03-31 22:07:04 +08:00
user_access_end();
if (copy_siginfo_to_user(&frame->info, &ksig->info))
goto badframe;
regs->link = tramp;
#ifdef CONFIG_PPC_FPU_REGS
tsk->thread.fp_state.fpscr = 0; /* turn off all fp exceptions */
#endif
/* create a stack frame for the caller of the handler */
newsp = ((unsigned long)frame) - (__SIGNAL_FRAMESIZE + 16);
if (put_user(regs->gpr[1], (u32 __user *)newsp))
goto badframe;
/* Fill registers for signal handler */
regs->gpr[1] = newsp;
regs->gpr[3] = ksig->sig;
regs->gpr[4] = (unsigned long)&frame->info;
regs->gpr[5] = (unsigned long)&frame->uc;
regs->gpr[6] = (unsigned long)frame;
regs_set_return_ip(regs, (unsigned long) ksig->ka.sa.sa_handler);
/* enter the signal handler in native-endian mode */
regs_set_return_msr(regs, (regs->msr & ~MSR_LE) | (MSR_KERNEL & MSR_LE));
return 0;
failed:
powerpc/signal32: Fix Oops on sigreturn with unmapped VDSO PPC32 encounters a KUAP fault when trying to handle a signal with VDSO unmapped. Kernel attempted to read user page (7fc07ec0) - exploit attempt? (uid: 0) BUG: Unable to handle kernel data access on read at 0x7fc07ec0 Faulting instruction address: 0xc00111d4 Oops: Kernel access of bad area, sig: 11 [#1] BE PAGE_SIZE=16K PREEMPT CMPC885 CPU: 0 PID: 353 Comm: sigreturn_vdso Not tainted 5.12.0-rc4-s3k-dev-01553-gb30c310ea220 #4814 NIP: c00111d4 LR: c0005a28 CTR: 00000000 REGS: cadb3dd0 TRAP: 0300 Not tainted (5.12.0-rc4-s3k-dev-01553-gb30c310ea220) MSR: 00009032 <EE,ME,IR,DR,RI> CR: 48000884 XER: 20000000 DAR: 7fc07ec0 DSISR: 88000000 GPR00: c0007788 cadb3e90 c28d4a40 7fc07ec0 7fc07ed0 000004e0 7fc07ce0 00000000 GPR08: 00000001 00000001 7fc07ec0 00000000 28000282 1001b828 100a0920 00000000 GPR16: 100cac0c 100b0000 105c43a4 105c5685 100d0000 100d0000 100d0000 100b2e9e GPR24: ffffffff 105c43c8 00000000 7fc07ec8 cadb3f40 cadb3ec8 c28d4a40 00000000 NIP [c00111d4] flush_icache_range+0x90/0xb4 LR [c0005a28] handle_signal32+0x1bc/0x1c4 Call Trace: [cadb3e90] [100d0000] 0x100d0000 (unreliable) [cadb3ec0] [c0007788] do_notify_resume+0x260/0x314 [cadb3f20] [c000c764] syscall_exit_prepare+0x120/0x184 [cadb3f30] [c00100b4] ret_from_syscall+0xc/0x28 --- interrupt: c00 at 0xfe807f8 NIP: 0fe807f8 LR: 10001060 CTR: c0139378 REGS: cadb3f40 TRAP: 0c00 Not tainted (5.12.0-rc4-s3k-dev-01553-gb30c310ea220) MSR: 0000d032 <EE,PR,ME,IR,DR,RI> CR: 28000482 XER: 20000000 GPR00: 00000025 7fc081c0 77bb1690 00000000 0000000a 28000482 00000001 0ff03a38 GPR08: 0000d032 00006de5 c28d4a40 00000009 88000482 1001b828 100a0920 00000000 GPR16: 100cac0c 100b0000 105c43a4 105c5685 100d0000 100d0000 100d0000 100b2e9e GPR24: ffffffff 105c43c8 00000000 77ba7628 10002398 10010000 10002124 00024000 NIP [0fe807f8] 0xfe807f8 LR [10001060] 0x10001060 --- interrupt: c00 Instruction dump: 38630010 7c001fac 38630010 4200fff0 7c0004ac 4c00012c 4e800020 7c001fac 2c0a0000 38630010 4082ffcc 4bffffe4 <7c00186c> 2c070000 39430010 4082ff8c ---[ end trace 3973fb72b049cb06 ]--- This is because flush_icache_range() is called on user addresses. The same problem was detected some time ago on PPC64. It was fixed by enabling KUAP in commit 59bee45b9712 ("powerpc/mm: Fix missing KUAP disable in flush_coherent_icache()"). PPC32 doesn't use flush_coherent_icache() and fallbacks on clean_dcache_range() and invalidate_icache_range(). We could fix it similarly by enabling user access in those functions, but this is overkill for just flushing two instructions. The two instructions are 8 bytes aligned, so a single dcbst/icbi is enough to flush them. Do like __patch_instruction() and inline a dcbst followed by an icbi just after the write of the instructions, while user access is still allowed. The isync is not required because rfi will be used to return to user. icbi() is handled as a read so read-write user access is needed. Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/bde9154e5351a5ac7bca3d59cdb5a5e8edacbb79.1617199569.git.christophe.leroy@csgroup.eu
2021-03-31 22:07:04 +08:00
user_access_end();
badframe:
signal_fault(tsk, regs, "handle_rt_signal32", frame);
return 1;
}
/*
* OK, we're invoking a handler
*/
int handle_signal32(struct ksignal *ksig, sigset_t *oldset,
struct task_struct *tsk)
{
struct sigcontext __user *sc;
struct sigframe __user *frame;
struct mcontext __user *mctx;
struct mcontext __user *tm_mctx = NULL;
unsigned long newsp = 0;
unsigned long tramp;
struct pt_regs *regs = tsk->thread.regs;
/* Save the thread's msr before get_tm_stackpointer() changes it */
unsigned long msr = regs->msr;
/* Set up Signal Frame */
frame = get_sigframe(ksig, tsk, sizeof(*frame), 1);
mctx = &frame->mctx;
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
tm_mctx = &frame->mctx_transact;
#endif
if (MSR_TM_ACTIVE(msr))
prepare_save_tm_user_regs();
else
prepare_save_user_regs(1);
powerpc/signal32: Fix Oops on sigreturn with unmapped VDSO PPC32 encounters a KUAP fault when trying to handle a signal with VDSO unmapped. Kernel attempted to read user page (7fc07ec0) - exploit attempt? (uid: 0) BUG: Unable to handle kernel data access on read at 0x7fc07ec0 Faulting instruction address: 0xc00111d4 Oops: Kernel access of bad area, sig: 11 [#1] BE PAGE_SIZE=16K PREEMPT CMPC885 CPU: 0 PID: 353 Comm: sigreturn_vdso Not tainted 5.12.0-rc4-s3k-dev-01553-gb30c310ea220 #4814 NIP: c00111d4 LR: c0005a28 CTR: 00000000 REGS: cadb3dd0 TRAP: 0300 Not tainted (5.12.0-rc4-s3k-dev-01553-gb30c310ea220) MSR: 00009032 <EE,ME,IR,DR,RI> CR: 48000884 XER: 20000000 DAR: 7fc07ec0 DSISR: 88000000 GPR00: c0007788 cadb3e90 c28d4a40 7fc07ec0 7fc07ed0 000004e0 7fc07ce0 00000000 GPR08: 00000001 00000001 7fc07ec0 00000000 28000282 1001b828 100a0920 00000000 GPR16: 100cac0c 100b0000 105c43a4 105c5685 100d0000 100d0000 100d0000 100b2e9e GPR24: ffffffff 105c43c8 00000000 7fc07ec8 cadb3f40 cadb3ec8 c28d4a40 00000000 NIP [c00111d4] flush_icache_range+0x90/0xb4 LR [c0005a28] handle_signal32+0x1bc/0x1c4 Call Trace: [cadb3e90] [100d0000] 0x100d0000 (unreliable) [cadb3ec0] [c0007788] do_notify_resume+0x260/0x314 [cadb3f20] [c000c764] syscall_exit_prepare+0x120/0x184 [cadb3f30] [c00100b4] ret_from_syscall+0xc/0x28 --- interrupt: c00 at 0xfe807f8 NIP: 0fe807f8 LR: 10001060 CTR: c0139378 REGS: cadb3f40 TRAP: 0c00 Not tainted (5.12.0-rc4-s3k-dev-01553-gb30c310ea220) MSR: 0000d032 <EE,PR,ME,IR,DR,RI> CR: 28000482 XER: 20000000 GPR00: 00000025 7fc081c0 77bb1690 00000000 0000000a 28000482 00000001 0ff03a38 GPR08: 0000d032 00006de5 c28d4a40 00000009 88000482 1001b828 100a0920 00000000 GPR16: 100cac0c 100b0000 105c43a4 105c5685 100d0000 100d0000 100d0000 100b2e9e GPR24: ffffffff 105c43c8 00000000 77ba7628 10002398 10010000 10002124 00024000 NIP [0fe807f8] 0xfe807f8 LR [10001060] 0x10001060 --- interrupt: c00 Instruction dump: 38630010 7c001fac 38630010 4200fff0 7c0004ac 4c00012c 4e800020 7c001fac 2c0a0000 38630010 4082ffcc 4bffffe4 <7c00186c> 2c070000 39430010 4082ff8c ---[ end trace 3973fb72b049cb06 ]--- This is because flush_icache_range() is called on user addresses. The same problem was detected some time ago on PPC64. It was fixed by enabling KUAP in commit 59bee45b9712 ("powerpc/mm: Fix missing KUAP disable in flush_coherent_icache()"). PPC32 doesn't use flush_coherent_icache() and fallbacks on clean_dcache_range() and invalidate_icache_range(). We could fix it similarly by enabling user access in those functions, but this is overkill for just flushing two instructions. The two instructions are 8 bytes aligned, so a single dcbst/icbi is enough to flush them. Do like __patch_instruction() and inline a dcbst followed by an icbi just after the write of the instructions, while user access is still allowed. The isync is not required because rfi will be used to return to user. icbi() is handled as a read so read-write user access is needed. Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/bde9154e5351a5ac7bca3d59cdb5a5e8edacbb79.1617199569.git.christophe.leroy@csgroup.eu
2021-03-31 22:07:04 +08:00
if (!user_access_begin(frame, sizeof(*frame)))
goto badframe;
sc = (struct sigcontext __user *) &frame->sctx;
#if _NSIG != 64
#error "Please adjust handle_signal()"
#endif
unsafe_put_user(to_user_ptr(ksig->ka.sa.sa_handler), &sc->handler, failed);
unsafe_put_user(oldset->sig[0], &sc->oldmask, failed);
#ifdef CONFIG_PPC64
unsafe_put_user((oldset->sig[0] >> 32), &sc->_unused[3], failed);
#else
unsafe_put_user(oldset->sig[1], &sc->_unused[3], failed);
#endif
unsafe_put_user(to_user_ptr(mctx), &sc->regs, failed);
unsafe_put_user(ksig->sig, &sc->signal, failed);
if (MSR_TM_ACTIVE(msr))
unsafe_save_tm_user_regs(regs, mctx, tm_mctx, msr, failed);
else
unsafe_save_user_regs(regs, mctx, tm_mctx, 1, failed);
if (tsk->mm->context.vdso) {
tramp = VDSO32_SYMBOL(tsk->mm->context.vdso, sigtramp32);
} else {
tramp = (unsigned long)mctx->mc_pad;
unsafe_put_user(PPC_RAW_LI(_R0, __NR_sigreturn), &mctx->mc_pad[0], failed);
unsafe_put_user(PPC_RAW_SC(), &mctx->mc_pad[1], failed);
powerpc/signal32: Fix Oops on sigreturn with unmapped VDSO PPC32 encounters a KUAP fault when trying to handle a signal with VDSO unmapped. Kernel attempted to read user page (7fc07ec0) - exploit attempt? (uid: 0) BUG: Unable to handle kernel data access on read at 0x7fc07ec0 Faulting instruction address: 0xc00111d4 Oops: Kernel access of bad area, sig: 11 [#1] BE PAGE_SIZE=16K PREEMPT CMPC885 CPU: 0 PID: 353 Comm: sigreturn_vdso Not tainted 5.12.0-rc4-s3k-dev-01553-gb30c310ea220 #4814 NIP: c00111d4 LR: c0005a28 CTR: 00000000 REGS: cadb3dd0 TRAP: 0300 Not tainted (5.12.0-rc4-s3k-dev-01553-gb30c310ea220) MSR: 00009032 <EE,ME,IR,DR,RI> CR: 48000884 XER: 20000000 DAR: 7fc07ec0 DSISR: 88000000 GPR00: c0007788 cadb3e90 c28d4a40 7fc07ec0 7fc07ed0 000004e0 7fc07ce0 00000000 GPR08: 00000001 00000001 7fc07ec0 00000000 28000282 1001b828 100a0920 00000000 GPR16: 100cac0c 100b0000 105c43a4 105c5685 100d0000 100d0000 100d0000 100b2e9e GPR24: ffffffff 105c43c8 00000000 7fc07ec8 cadb3f40 cadb3ec8 c28d4a40 00000000 NIP [c00111d4] flush_icache_range+0x90/0xb4 LR [c0005a28] handle_signal32+0x1bc/0x1c4 Call Trace: [cadb3e90] [100d0000] 0x100d0000 (unreliable) [cadb3ec0] [c0007788] do_notify_resume+0x260/0x314 [cadb3f20] [c000c764] syscall_exit_prepare+0x120/0x184 [cadb3f30] [c00100b4] ret_from_syscall+0xc/0x28 --- interrupt: c00 at 0xfe807f8 NIP: 0fe807f8 LR: 10001060 CTR: c0139378 REGS: cadb3f40 TRAP: 0c00 Not tainted (5.12.0-rc4-s3k-dev-01553-gb30c310ea220) MSR: 0000d032 <EE,PR,ME,IR,DR,RI> CR: 28000482 XER: 20000000 GPR00: 00000025 7fc081c0 77bb1690 00000000 0000000a 28000482 00000001 0ff03a38 GPR08: 0000d032 00006de5 c28d4a40 00000009 88000482 1001b828 100a0920 00000000 GPR16: 100cac0c 100b0000 105c43a4 105c5685 100d0000 100d0000 100d0000 100b2e9e GPR24: ffffffff 105c43c8 00000000 77ba7628 10002398 10010000 10002124 00024000 NIP [0fe807f8] 0xfe807f8 LR [10001060] 0x10001060 --- interrupt: c00 Instruction dump: 38630010 7c001fac 38630010 4200fff0 7c0004ac 4c00012c 4e800020 7c001fac 2c0a0000 38630010 4082ffcc 4bffffe4 <7c00186c> 2c070000 39430010 4082ff8c ---[ end trace 3973fb72b049cb06 ]--- This is because flush_icache_range() is called on user addresses. The same problem was detected some time ago on PPC64. It was fixed by enabling KUAP in commit 59bee45b9712 ("powerpc/mm: Fix missing KUAP disable in flush_coherent_icache()"). PPC32 doesn't use flush_coherent_icache() and fallbacks on clean_dcache_range() and invalidate_icache_range(). We could fix it similarly by enabling user access in those functions, but this is overkill for just flushing two instructions. The two instructions are 8 bytes aligned, so a single dcbst/icbi is enough to flush them. Do like __patch_instruction() and inline a dcbst followed by an icbi just after the write of the instructions, while user access is still allowed. The isync is not required because rfi will be used to return to user. icbi() is handled as a read so read-write user access is needed. Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/bde9154e5351a5ac7bca3d59cdb5a5e8edacbb79.1617199569.git.christophe.leroy@csgroup.eu
2021-03-31 22:07:04 +08:00
asm("dcbst %y0; sync; icbi %y0; sync" :: "Z" (mctx->mc_pad[0]));
}
powerpc/signal32: Fix Oops on sigreturn with unmapped VDSO PPC32 encounters a KUAP fault when trying to handle a signal with VDSO unmapped. Kernel attempted to read user page (7fc07ec0) - exploit attempt? (uid: 0) BUG: Unable to handle kernel data access on read at 0x7fc07ec0 Faulting instruction address: 0xc00111d4 Oops: Kernel access of bad area, sig: 11 [#1] BE PAGE_SIZE=16K PREEMPT CMPC885 CPU: 0 PID: 353 Comm: sigreturn_vdso Not tainted 5.12.0-rc4-s3k-dev-01553-gb30c310ea220 #4814 NIP: c00111d4 LR: c0005a28 CTR: 00000000 REGS: cadb3dd0 TRAP: 0300 Not tainted (5.12.0-rc4-s3k-dev-01553-gb30c310ea220) MSR: 00009032 <EE,ME,IR,DR,RI> CR: 48000884 XER: 20000000 DAR: 7fc07ec0 DSISR: 88000000 GPR00: c0007788 cadb3e90 c28d4a40 7fc07ec0 7fc07ed0 000004e0 7fc07ce0 00000000 GPR08: 00000001 00000001 7fc07ec0 00000000 28000282 1001b828 100a0920 00000000 GPR16: 100cac0c 100b0000 105c43a4 105c5685 100d0000 100d0000 100d0000 100b2e9e GPR24: ffffffff 105c43c8 00000000 7fc07ec8 cadb3f40 cadb3ec8 c28d4a40 00000000 NIP [c00111d4] flush_icache_range+0x90/0xb4 LR [c0005a28] handle_signal32+0x1bc/0x1c4 Call Trace: [cadb3e90] [100d0000] 0x100d0000 (unreliable) [cadb3ec0] [c0007788] do_notify_resume+0x260/0x314 [cadb3f20] [c000c764] syscall_exit_prepare+0x120/0x184 [cadb3f30] [c00100b4] ret_from_syscall+0xc/0x28 --- interrupt: c00 at 0xfe807f8 NIP: 0fe807f8 LR: 10001060 CTR: c0139378 REGS: cadb3f40 TRAP: 0c00 Not tainted (5.12.0-rc4-s3k-dev-01553-gb30c310ea220) MSR: 0000d032 <EE,PR,ME,IR,DR,RI> CR: 28000482 XER: 20000000 GPR00: 00000025 7fc081c0 77bb1690 00000000 0000000a 28000482 00000001 0ff03a38 GPR08: 0000d032 00006de5 c28d4a40 00000009 88000482 1001b828 100a0920 00000000 GPR16: 100cac0c 100b0000 105c43a4 105c5685 100d0000 100d0000 100d0000 100b2e9e GPR24: ffffffff 105c43c8 00000000 77ba7628 10002398 10010000 10002124 00024000 NIP [0fe807f8] 0xfe807f8 LR [10001060] 0x10001060 --- interrupt: c00 Instruction dump: 38630010 7c001fac 38630010 4200fff0 7c0004ac 4c00012c 4e800020 7c001fac 2c0a0000 38630010 4082ffcc 4bffffe4 <7c00186c> 2c070000 39430010 4082ff8c ---[ end trace 3973fb72b049cb06 ]--- This is because flush_icache_range() is called on user addresses. The same problem was detected some time ago on PPC64. It was fixed by enabling KUAP in commit 59bee45b9712 ("powerpc/mm: Fix missing KUAP disable in flush_coherent_icache()"). PPC32 doesn't use flush_coherent_icache() and fallbacks on clean_dcache_range() and invalidate_icache_range(). We could fix it similarly by enabling user access in those functions, but this is overkill for just flushing two instructions. The two instructions are 8 bytes aligned, so a single dcbst/icbi is enough to flush them. Do like __patch_instruction() and inline a dcbst followed by an icbi just after the write of the instructions, while user access is still allowed. The isync is not required because rfi will be used to return to user. icbi() is handled as a read so read-write user access is needed. Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/bde9154e5351a5ac7bca3d59cdb5a5e8edacbb79.1617199569.git.christophe.leroy@csgroup.eu
2021-03-31 22:07:04 +08:00
user_access_end();
regs->link = tramp;
#ifdef CONFIG_PPC_FPU_REGS
tsk->thread.fp_state.fpscr = 0; /* turn off all fp exceptions */
#endif
/* create a stack frame for the caller of the handler */
newsp = ((unsigned long)frame) - __SIGNAL_FRAMESIZE;
if (put_user(regs->gpr[1], (u32 __user *)newsp))
goto badframe;
regs->gpr[1] = newsp;
regs->gpr[3] = ksig->sig;
regs->gpr[4] = (unsigned long) sc;
regs_set_return_ip(regs, (unsigned long) ksig->ka.sa.sa_handler);
/* enter the signal handler in native-endian mode */
regs_set_return_msr(regs, (regs->msr & ~MSR_LE) | (MSR_KERNEL & MSR_LE));
return 0;
failed:
powerpc/signal32: Fix Oops on sigreturn with unmapped VDSO PPC32 encounters a KUAP fault when trying to handle a signal with VDSO unmapped. Kernel attempted to read user page (7fc07ec0) - exploit attempt? (uid: 0) BUG: Unable to handle kernel data access on read at 0x7fc07ec0 Faulting instruction address: 0xc00111d4 Oops: Kernel access of bad area, sig: 11 [#1] BE PAGE_SIZE=16K PREEMPT CMPC885 CPU: 0 PID: 353 Comm: sigreturn_vdso Not tainted 5.12.0-rc4-s3k-dev-01553-gb30c310ea220 #4814 NIP: c00111d4 LR: c0005a28 CTR: 00000000 REGS: cadb3dd0 TRAP: 0300 Not tainted (5.12.0-rc4-s3k-dev-01553-gb30c310ea220) MSR: 00009032 <EE,ME,IR,DR,RI> CR: 48000884 XER: 20000000 DAR: 7fc07ec0 DSISR: 88000000 GPR00: c0007788 cadb3e90 c28d4a40 7fc07ec0 7fc07ed0 000004e0 7fc07ce0 00000000 GPR08: 00000001 00000001 7fc07ec0 00000000 28000282 1001b828 100a0920 00000000 GPR16: 100cac0c 100b0000 105c43a4 105c5685 100d0000 100d0000 100d0000 100b2e9e GPR24: ffffffff 105c43c8 00000000 7fc07ec8 cadb3f40 cadb3ec8 c28d4a40 00000000 NIP [c00111d4] flush_icache_range+0x90/0xb4 LR [c0005a28] handle_signal32+0x1bc/0x1c4 Call Trace: [cadb3e90] [100d0000] 0x100d0000 (unreliable) [cadb3ec0] [c0007788] do_notify_resume+0x260/0x314 [cadb3f20] [c000c764] syscall_exit_prepare+0x120/0x184 [cadb3f30] [c00100b4] ret_from_syscall+0xc/0x28 --- interrupt: c00 at 0xfe807f8 NIP: 0fe807f8 LR: 10001060 CTR: c0139378 REGS: cadb3f40 TRAP: 0c00 Not tainted (5.12.0-rc4-s3k-dev-01553-gb30c310ea220) MSR: 0000d032 <EE,PR,ME,IR,DR,RI> CR: 28000482 XER: 20000000 GPR00: 00000025 7fc081c0 77bb1690 00000000 0000000a 28000482 00000001 0ff03a38 GPR08: 0000d032 00006de5 c28d4a40 00000009 88000482 1001b828 100a0920 00000000 GPR16: 100cac0c 100b0000 105c43a4 105c5685 100d0000 100d0000 100d0000 100b2e9e GPR24: ffffffff 105c43c8 00000000 77ba7628 10002398 10010000 10002124 00024000 NIP [0fe807f8] 0xfe807f8 LR [10001060] 0x10001060 --- interrupt: c00 Instruction dump: 38630010 7c001fac 38630010 4200fff0 7c0004ac 4c00012c 4e800020 7c001fac 2c0a0000 38630010 4082ffcc 4bffffe4 <7c00186c> 2c070000 39430010 4082ff8c ---[ end trace 3973fb72b049cb06 ]--- This is because flush_icache_range() is called on user addresses. The same problem was detected some time ago on PPC64. It was fixed by enabling KUAP in commit 59bee45b9712 ("powerpc/mm: Fix missing KUAP disable in flush_coherent_icache()"). PPC32 doesn't use flush_coherent_icache() and fallbacks on clean_dcache_range() and invalidate_icache_range(). We could fix it similarly by enabling user access in those functions, but this is overkill for just flushing two instructions. The two instructions are 8 bytes aligned, so a single dcbst/icbi is enough to flush them. Do like __patch_instruction() and inline a dcbst followed by an icbi just after the write of the instructions, while user access is still allowed. The isync is not required because rfi will be used to return to user. icbi() is handled as a read so read-write user access is needed. Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/bde9154e5351a5ac7bca3d59cdb5a5e8edacbb79.1617199569.git.christophe.leroy@csgroup.eu
2021-03-31 22:07:04 +08:00
user_access_end();
badframe:
signal_fault(tsk, regs, "handle_signal32", frame);
return 1;
}
static int do_setcontext(struct ucontext __user *ucp, struct pt_regs *regs, int sig)
{
sigset_t set;
struct mcontext __user *mcp;
if (!user_read_access_begin(ucp, sizeof(*ucp)))
return -EFAULT;
unsafe_get_sigset_t(&set, &ucp->uc_sigmask, failed);
#ifdef CONFIG_PPC64
{
u32 cmcp;
unsafe_get_user(cmcp, &ucp->uc_regs, failed);
mcp = (struct mcontext __user *)(u64)cmcp;
}
#else
unsafe_get_user(mcp, &ucp->uc_regs, failed);
#endif
user_read_access_end();
set_current_blocked(&set);
if (restore_user_regs(regs, mcp, sig))
return -EFAULT;
return 0;
failed:
user_read_access_end();
return -EFAULT;
}
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
static int do_setcontext_tm(struct ucontext __user *ucp,
struct ucontext __user *tm_ucp,
struct pt_regs *regs)
{
sigset_t set;
struct mcontext __user *mcp;
struct mcontext __user *tm_mcp;
u32 cmcp;
u32 tm_cmcp;
if (!user_read_access_begin(ucp, sizeof(*ucp)))
return -EFAULT;
unsafe_get_sigset_t(&set, &ucp->uc_sigmask, failed);
unsafe_get_user(cmcp, &ucp->uc_regs, failed);
user_read_access_end();
if (__get_user(tm_cmcp, &tm_ucp->uc_regs))
return -EFAULT;
mcp = (struct mcontext __user *)(u64)cmcp;
tm_mcp = (struct mcontext __user *)(u64)tm_cmcp;
/* no need to check access_ok(mcp), since mcp < 4GB */
set_current_blocked(&set);
if (restore_tm_user_regs(regs, mcp, tm_mcp))
return -EFAULT;
return 0;
failed:
user_read_access_end();
return -EFAULT;
}
#endif
#ifdef CONFIG_PPC64
COMPAT_SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx,
struct ucontext __user *, new_ctx, int, ctx_size)
#else
SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx,
struct ucontext __user *, new_ctx, long, ctx_size)
#endif
{
struct pt_regs *regs = current_pt_regs();
int ctx_has_vsx_region = 0;
#ifdef CONFIG_PPC64
unsigned long new_msr = 0;
if (new_ctx) {
struct mcontext __user *mcp;
u32 cmcp;
/*
* Get pointer to the real mcontext. No need for
* access_ok since we are dealing with compat
* pointers.
*/
if (__get_user(cmcp, &new_ctx->uc_regs))
return -EFAULT;
mcp = (struct mcontext __user *)(u64)cmcp;
if (__get_user(new_msr, &mcp->mc_gregs[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;
#else
/* Context size is for future use. Right now, we only make sure
* we are passed something we understand
*/
if (ctx_size < sizeof(struct ucontext))
return -EINVAL;
#endif
if (old_ctx != NULL) {
struct mcontext __user *mctx;
/*
* old_ctx might not be 16-byte aligned, in which
* case old_ctx->uc_mcontext won't be either.
* Because we have the old_ctx->uc_pad2 field
* before old_ctx->uc_mcontext, we need to round down
* from &old_ctx->uc_mcontext to a 16-byte boundary.
*/
mctx = (struct mcontext __user *)
((unsigned long) &old_ctx->uc_mcontext & ~0xfUL);
prepare_save_user_regs(ctx_has_vsx_region);
if (!user_write_access_begin(old_ctx, ctx_size))
return -EFAULT;
unsafe_save_user_regs(regs, mctx, NULL, ctx_has_vsx_region, failed);
unsafe_put_sigset_t(&old_ctx->uc_sigmask, &current->blocked, failed);
unsafe_put_user(to_user_ptr(mctx), &old_ctx->uc_regs, failed);
user_write_access_end();
}
if (new_ctx == NULL)
return 0;
Remove 'type' argument from access_ok() function Nobody has actually used the type (VERIFY_READ vs VERIFY_WRITE) argument of the user address range verification function since we got rid of the old racy i386-only code to walk page tables by hand. It existed because the original 80386 would not honor the write protect bit when in kernel mode, so you had to do COW by hand before doing any user access. But we haven't supported that in a long time, and these days the 'type' argument is a purely historical artifact. A discussion about extending 'user_access_begin()' to do the range checking resulted this patch, because there is no way we're going to move the old VERIFY_xyz interface to that model. And it's best done at the end of the merge window when I've done most of my merges, so let's just get this done once and for all. This patch was mostly done with a sed-script, with manual fix-ups for the cases that weren't of the trivial 'access_ok(VERIFY_xyz' form. There were a couple of notable cases: - csky still had the old "verify_area()" name as an alias. - the iter_iov code had magical hardcoded knowledge of the actual values of VERIFY_{READ,WRITE} (not that they mattered, since nothing really used it) - microblaze used the type argument for a debug printout but other than those oddities this should be a total no-op patch. I tried to fix up all architectures, did fairly extensive grepping for access_ok() uses, and the changes are trivial, but I may have missed something. Any missed conversion should be trivially fixable, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 10:57:57 +08:00
if (!access_ok(new_ctx, ctx_size) ||
fault_in_readable((char __user *)new_ctx, ctx_size))
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 (do_setcontext(new_ctx, regs, 0)) {
signal: Replace force_fatal_sig with force_exit_sig when in doubt Recently to prevent issues with SECCOMP_RET_KILL and similar signals being changed before they are delivered SA_IMMUTABLE was added. Unfortunately this broke debuggers[1][2] which reasonably expect to be able to trap synchronous SIGTRAP and SIGSEGV even when the target process is not configured to handle those signals. Add force_exit_sig and use it instead of force_fatal_sig where historically the code has directly called do_exit. This has the implementation benefits of going through the signal exit path (including generating core dumps) without the danger of allowing userspace to ignore or change these signals. This avoids userspace regressions as older kernels exited with do_exit which debuggers also can not intercept. In the future is should be possible to improve the quality of implementation of the kernel by changing some of these force_exit_sig calls to force_fatal_sig. That can be done where it matters on a case-by-case basis with careful analysis. Reported-by: Kyle Huey <me@kylehuey.com> Reported-by: kernel test robot <oliver.sang@intel.com> [1] https://lkml.kernel.org/r/CAP045AoMY4xf8aC_4QU_-j7obuEPYgTcnQQP3Yxk=2X90jtpjw@mail.gmail.com [2] https://lkml.kernel.org/r/20211117150258.GB5403@xsang-OptiPlex-9020 Fixes: 00b06da29cf9 ("signal: Add SA_IMMUTABLE to ensure forced siganls do not get changed") Fixes: a3616a3c0272 ("signal/m68k: Use force_sigsegv(SIGSEGV) in fpsp040_die") Fixes: 83a1f27ad773 ("signal/powerpc: On swapcontext failure force SIGSEGV") Fixes: 9bc508cf0791 ("signal/s390: Use force_sigsegv in default_trap_handler") Fixes: 086ec444f866 ("signal/sparc32: In setup_rt_frame and setup_fram use force_fatal_sig") Fixes: c317d306d550 ("signal/sparc32: Exit with a fatal signal when try_to_clear_window_buffer fails") Fixes: 695dd0d634df ("signal/x86: In emulate_vsyscall force a signal instead of calling do_exit") Fixes: 1fbd60df8a85 ("signal/vm86_32: Properly send SIGSEGV when the vm86 state cannot be saved.") Fixes: 941edc5bf174 ("exit/syscall_user_dispatch: Send ordinary signals on failure") Link: https://lkml.kernel.org/r/871r3dqfv8.fsf_-_@email.froward.int.ebiederm.org Reviewed-by: Kees Cook <keescook@chromium.org> Tested-by: Kees Cook <keescook@chromium.org> Tested-by: Kyle Huey <khuey@kylehuey.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2021-11-19 04:23:21 +08:00
force_exit_sig(SIGSEGV);
return -EFAULT;
}
[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>
2005-11-16 02:52:18 +08:00
set_thread_flag(TIF_RESTOREALL);
return 0;
failed:
user_write_access_end();
return -EFAULT;
}
#ifdef CONFIG_PPC64
COMPAT_SYSCALL_DEFINE0(rt_sigreturn)
#else
SYSCALL_DEFINE0(rt_sigreturn)
#endif
{
struct rt_sigframe __user *rt_sf;
struct pt_regs *regs = current_pt_regs();
powerpc/tm: Unset MSR[TS] if not recheckpointing There is a TM Bad Thing bug that can be caused when you return from a signal context in a suspended transaction but with ucontext MSR[TS] unset. This forces regs->msr[TS] to be set at syscall entrance (since the CPU state is transactional). It also calls treclaim() to flush the transaction state, which is done based on the live (mfmsr) MSR state. Since user context MSR[TS] is not set, then restore_tm_sigcontexts() is not called, thus, not executing recheckpoint, keeping the CPU state as not transactional. When calling rfid, SRR1 will have MSR[TS] set, but the CPU state is non transactional, causing the TM Bad Thing with the following stack: [ 33.862316] Bad kernel stack pointer 3fffd9dce3e0 at c00000000000c47c cpu 0x8: Vector: 700 (Program Check) at [c00000003ff7fd40] pc: c00000000000c47c: fast_exception_return+0xac/0xb4 lr: 00003fff865f442c sp: 3fffd9dce3e0 msr: 8000000102a03031 current = 0xc00000041f68b700 paca = 0xc00000000fb84800 softe: 0 irq_happened: 0x01 pid = 1721, comm = tm-signal-sigre Linux version 4.9.0-3-powerpc64le (debian-kernel@lists.debian.org) (gcc version 6.3.0 20170516 (Debian 6.3.0-18) ) #1 SMP Debian 4.9.30-2+deb9u2 (2017-06-26) WARNING: exception is not recoverable, can't continue The same problem happens on 32-bits signal handler, and the fix is very similar, if tm_recheckpoint() is not executed, then regs->msr[TS] should be zeroed. This patch also fixes a sparse warning related to lack of indentation when CONFIG_PPC_TRANSACTIONAL_MEM is set. Fixes: 2b0a576d15e0e ("powerpc: Add new transactional memory state to the signal context") CC: Stable <stable@vger.kernel.org> # 3.10+ Signed-off-by: Breno Leitao <leitao@debian.org> Tested-by: Michal Suchánek <msuchanek@suse.de> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-11-27 04:12:00 +08:00
int tm_restore = 0;
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
struct ucontext __user *uc_transact;
unsigned long msr_hi;
unsigned long tmp;
#endif
/* 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>
2015-02-13 07:01:14 +08:00
current->restart_block.fn = do_no_restart_syscall;
rt_sf = (struct rt_sigframe __user *)
(regs->gpr[1] + __SIGNAL_FRAMESIZE + 16);
Remove 'type' argument from access_ok() function Nobody has actually used the type (VERIFY_READ vs VERIFY_WRITE) argument of the user address range verification function since we got rid of the old racy i386-only code to walk page tables by hand. It existed because the original 80386 would not honor the write protect bit when in kernel mode, so you had to do COW by hand before doing any user access. But we haven't supported that in a long time, and these days the 'type' argument is a purely historical artifact. A discussion about extending 'user_access_begin()' to do the range checking resulted this patch, because there is no way we're going to move the old VERIFY_xyz interface to that model. And it's best done at the end of the merge window when I've done most of my merges, so let's just get this done once and for all. This patch was mostly done with a sed-script, with manual fix-ups for the cases that weren't of the trivial 'access_ok(VERIFY_xyz' form. There were a couple of notable cases: - csky still had the old "verify_area()" name as an alias. - the iter_iov code had magical hardcoded knowledge of the actual values of VERIFY_{READ,WRITE} (not that they mattered, since nothing really used it) - microblaze used the type argument for a debug printout but other than those oddities this should be a total no-op patch. I tried to fix up all architectures, did fairly extensive grepping for access_ok() uses, and the changes are trivial, but I may have missed something. Any missed conversion should be trivially fixable, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 10:57:57 +08:00
if (!access_ok(rt_sf, sizeof(*rt_sf)))
goto bad;
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 08:46:17 +08:00
#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 08:46:17 +08:00
/*
* 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(tmp, &rt_sf->uc.uc_link))
goto bad;
uc_transact = (struct ucontext __user *)(uintptr_t)tmp;
if (uc_transact) {
u32 cmcp;
struct mcontext __user *mcp;
if (__get_user(cmcp, &uc_transact->uc_regs))
return -EFAULT;
mcp = (struct mcontext __user *)(u64)cmcp;
/* The top 32 bits of the MSR are stashed in the transactional
* ucontext. */
if (__get_user(msr_hi, &mcp->mc_gregs[PT_MSR]))
goto bad;
if (MSR_TM_ACTIVE(msr_hi<<32)) {
powerpc/tm: Fix oops on sigreturn on systems without TM On systems like P9 powernv where we have no TM (or P8 booted with ppc_tm=off), userspace can construct a signal context which still has the MSR TS bits set. The kernel tries to restore this context which results in the following crash: Unexpected TM Bad Thing exception at c0000000000022fc (msr 0x8000000102a03031) tm_scratch=800000020280f033 Oops: Unrecoverable exception, sig: 6 [#1] LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries Modules linked in: CPU: 0 PID: 1636 Comm: sigfuz Not tainted 5.2.0-11043-g0a8ad0ffa4 #69 NIP: c0000000000022fc LR: 00007fffb2d67e48 CTR: 0000000000000000 REGS: c00000003fffbd70 TRAP: 0700 Not tainted (5.2.0-11045-g7142b497d8) MSR: 8000000102a03031 <SF,VEC,VSX,FP,ME,IR,DR,LE,TM[E]> CR: 42004242 XER: 00000000 CFAR: c0000000000022e0 IRQMASK: 0 GPR00: 0000000000000072 00007fffb2b6e560 00007fffb2d87f00 0000000000000669 GPR04: 00007fffb2b6e728 0000000000000000 0000000000000000 00007fffb2b6f2a8 GPR08: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR12: 0000000000000000 00007fffb2b76900 0000000000000000 0000000000000000 GPR16: 00007fffb2370000 00007fffb2d84390 00007fffea3a15ac 000001000a250420 GPR20: 00007fffb2b6f260 0000000010001770 0000000000000000 0000000000000000 GPR24: 00007fffb2d843a0 00007fffea3a14a0 0000000000010000 0000000000800000 GPR28: 00007fffea3a14d8 00000000003d0f00 0000000000000000 00007fffb2b6e728 NIP [c0000000000022fc] rfi_flush_fallback+0x7c/0x80 LR [00007fffb2d67e48] 0x7fffb2d67e48 Call Trace: Instruction dump: e96a0220 e96a02a8 e96a0330 e96a03b8 394a0400 4200ffdc 7d2903a6 e92d0c00 e94d0c08 e96d0c10 e82d0c18 7db242a6 <4c000024> 7db243a6 7db142a6 f82d0c18 The problem is the signal code assumes TM is enabled when CONFIG_PPC_TRANSACTIONAL_MEM is enabled. This may not be the case as with P9 powernv or if `ppc_tm=off` is used on P8. This means any local user can crash the system. Fix the problem by returning a bad stack frame to the user if they try to set the MSR TS bits with sigreturn() on systems where TM is not supported. Found with sigfuz kernel selftest on P9. This fixes CVE-2019-13648. Fixes: 2b0a576d15e0 ("powerpc: Add new transactional memory state to the signal context") Cc: stable@vger.kernel.org # v3.9 Reported-by: Praveen Pandey <Praveen.Pandey@in.ibm.com> Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20190719050502.405-1-mikey@neuling.org
2019-07-19 13:05:02 +08:00
/* Trying to start TM on non TM system */
if (!cpu_has_feature(CPU_FTR_TM))
goto bad;
/* We only recheckpoint on return if we're
* transaction.
*/
tm_restore = 1;
if (do_setcontext_tm(&rt_sf->uc, uc_transact, regs))
goto bad;
}
}
powerpc/tm: Unset MSR[TS] if not recheckpointing There is a TM Bad Thing bug that can be caused when you return from a signal context in a suspended transaction but with ucontext MSR[TS] unset. This forces regs->msr[TS] to be set at syscall entrance (since the CPU state is transactional). It also calls treclaim() to flush the transaction state, which is done based on the live (mfmsr) MSR state. Since user context MSR[TS] is not set, then restore_tm_sigcontexts() is not called, thus, not executing recheckpoint, keeping the CPU state as not transactional. When calling rfid, SRR1 will have MSR[TS] set, but the CPU state is non transactional, causing the TM Bad Thing with the following stack: [ 33.862316] Bad kernel stack pointer 3fffd9dce3e0 at c00000000000c47c cpu 0x8: Vector: 700 (Program Check) at [c00000003ff7fd40] pc: c00000000000c47c: fast_exception_return+0xac/0xb4 lr: 00003fff865f442c sp: 3fffd9dce3e0 msr: 8000000102a03031 current = 0xc00000041f68b700 paca = 0xc00000000fb84800 softe: 0 irq_happened: 0x01 pid = 1721, comm = tm-signal-sigre Linux version 4.9.0-3-powerpc64le (debian-kernel@lists.debian.org) (gcc version 6.3.0 20170516 (Debian 6.3.0-18) ) #1 SMP Debian 4.9.30-2+deb9u2 (2017-06-26) WARNING: exception is not recoverable, can't continue The same problem happens on 32-bits signal handler, and the fix is very similar, if tm_recheckpoint() is not executed, then regs->msr[TS] should be zeroed. This patch also fixes a sparse warning related to lack of indentation when CONFIG_PPC_TRANSACTIONAL_MEM is set. Fixes: 2b0a576d15e0e ("powerpc: Add new transactional memory state to the signal context") CC: Stable <stable@vger.kernel.org> # 3.10+ Signed-off-by: Breno Leitao <leitao@debian.org> Tested-by: Michal Suchánek <msuchanek@suse.de> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-11-27 04:12:00 +08:00
if (!tm_restore) {
/*
* Unset regs->msr because ucontext MSR TS is not
* set, and recheckpoint was not called. This avoid
* hitting a TM Bad thing at RFID
*/
regs_set_return_msr(regs, regs->msr & ~MSR_TS_MASK);
powerpc/tm: Unset MSR[TS] if not recheckpointing There is a TM Bad Thing bug that can be caused when you return from a signal context in a suspended transaction but with ucontext MSR[TS] unset. This forces regs->msr[TS] to be set at syscall entrance (since the CPU state is transactional). It also calls treclaim() to flush the transaction state, which is done based on the live (mfmsr) MSR state. Since user context MSR[TS] is not set, then restore_tm_sigcontexts() is not called, thus, not executing recheckpoint, keeping the CPU state as not transactional. When calling rfid, SRR1 will have MSR[TS] set, but the CPU state is non transactional, causing the TM Bad Thing with the following stack: [ 33.862316] Bad kernel stack pointer 3fffd9dce3e0 at c00000000000c47c cpu 0x8: Vector: 700 (Program Check) at [c00000003ff7fd40] pc: c00000000000c47c: fast_exception_return+0xac/0xb4 lr: 00003fff865f442c sp: 3fffd9dce3e0 msr: 8000000102a03031 current = 0xc00000041f68b700 paca = 0xc00000000fb84800 softe: 0 irq_happened: 0x01 pid = 1721, comm = tm-signal-sigre Linux version 4.9.0-3-powerpc64le (debian-kernel@lists.debian.org) (gcc version 6.3.0 20170516 (Debian 6.3.0-18) ) #1 SMP Debian 4.9.30-2+deb9u2 (2017-06-26) WARNING: exception is not recoverable, can't continue The same problem happens on 32-bits signal handler, and the fix is very similar, if tm_recheckpoint() is not executed, then regs->msr[TS] should be zeroed. This patch also fixes a sparse warning related to lack of indentation when CONFIG_PPC_TRANSACTIONAL_MEM is set. Fixes: 2b0a576d15e0e ("powerpc: Add new transactional memory state to the signal context") CC: Stable <stable@vger.kernel.org> # 3.10+ Signed-off-by: Breno Leitao <leitao@debian.org> Tested-by: Michal Suchánek <msuchanek@suse.de> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-11-27 04:12:00 +08:00
}
/* Fall through, for non-TM restore */
#endif
powerpc/tm: Unset MSR[TS] if not recheckpointing There is a TM Bad Thing bug that can be caused when you return from a signal context in a suspended transaction but with ucontext MSR[TS] unset. This forces regs->msr[TS] to be set at syscall entrance (since the CPU state is transactional). It also calls treclaim() to flush the transaction state, which is done based on the live (mfmsr) MSR state. Since user context MSR[TS] is not set, then restore_tm_sigcontexts() is not called, thus, not executing recheckpoint, keeping the CPU state as not transactional. When calling rfid, SRR1 will have MSR[TS] set, but the CPU state is non transactional, causing the TM Bad Thing with the following stack: [ 33.862316] Bad kernel stack pointer 3fffd9dce3e0 at c00000000000c47c cpu 0x8: Vector: 700 (Program Check) at [c00000003ff7fd40] pc: c00000000000c47c: fast_exception_return+0xac/0xb4 lr: 00003fff865f442c sp: 3fffd9dce3e0 msr: 8000000102a03031 current = 0xc00000041f68b700 paca = 0xc00000000fb84800 softe: 0 irq_happened: 0x01 pid = 1721, comm = tm-signal-sigre Linux version 4.9.0-3-powerpc64le (debian-kernel@lists.debian.org) (gcc version 6.3.0 20170516 (Debian 6.3.0-18) ) #1 SMP Debian 4.9.30-2+deb9u2 (2017-06-26) WARNING: exception is not recoverable, can't continue The same problem happens on 32-bits signal handler, and the fix is very similar, if tm_recheckpoint() is not executed, then regs->msr[TS] should be zeroed. This patch also fixes a sparse warning related to lack of indentation when CONFIG_PPC_TRANSACTIONAL_MEM is set. Fixes: 2b0a576d15e0e ("powerpc: Add new transactional memory state to the signal context") CC: Stable <stable@vger.kernel.org> # 3.10+ Signed-off-by: Breno Leitao <leitao@debian.org> Tested-by: Michal Suchánek <msuchanek@suse.de> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-11-27 04:12:00 +08:00
if (!tm_restore)
if (do_setcontext(&rt_sf->uc, regs, 1))
goto bad;
/*
* It's not clear whether or why it is desirable to save the
* sigaltstack setting on signal delivery and restore it on
* signal return. But other architectures do this and we have
* always done it up until now so it is probably better not to
* change it. -- paulus
*/
#ifdef CONFIG_PPC64
if (compat_restore_altstack(&rt_sf->uc.uc_stack))
goto bad;
#else
if (restore_altstack(&rt_sf->uc.uc_stack))
goto bad;
#endif
[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>
2005-11-16 02:52:18 +08:00
set_thread_flag(TIF_RESTOREALL);
return 0;
bad:
signal_fault(current, regs, "sys_rt_sigreturn", rt_sf);
force_sig(SIGSEGV);
return 0;
}
#ifdef CONFIG_PPC32
SYSCALL_DEFINE3(debug_setcontext, struct ucontext __user *, ctx,
int, ndbg, struct sig_dbg_op __user *, dbg)
{
struct pt_regs *regs = current_pt_regs();
struct sig_dbg_op op;
int i;
unsigned long new_msr = regs->msr;
#ifdef CONFIG_PPC_ADV_DEBUG_REGS
unsigned long new_dbcr0 = current->thread.debug.dbcr0;
#endif
for (i=0; i<ndbg; i++) {
if (copy_from_user(&op, dbg + i, sizeof(op)))
return -EFAULT;
switch (op.dbg_type) {
case SIG_DBG_SINGLE_STEPPING:
#ifdef CONFIG_PPC_ADV_DEBUG_REGS
if (op.dbg_value) {
new_msr |= MSR_DE;
new_dbcr0 |= (DBCR0_IDM | DBCR0_IC);
} else {
new_dbcr0 &= ~DBCR0_IC;
if (!DBCR_ACTIVE_EVENTS(new_dbcr0,
current->thread.debug.dbcr1)) {
new_msr &= ~MSR_DE;
new_dbcr0 &= ~DBCR0_IDM;
}
}
#else
if (op.dbg_value)
new_msr |= MSR_SE;
else
new_msr &= ~MSR_SE;
#endif
break;
case SIG_DBG_BRANCH_TRACING:
#ifdef CONFIG_PPC_ADV_DEBUG_REGS
return -EINVAL;
#else
if (op.dbg_value)
new_msr |= MSR_BE;
else
new_msr &= ~MSR_BE;
#endif
break;
default:
return -EINVAL;
}
}
/* We wait until here to actually install the values in the
registers so if we fail in the above loop, it will not
affect the contents of these registers. After this point,
failure is a problem, anyway, and it's very unlikely unless
the user is really doing something wrong. */
regs_set_return_msr(regs, new_msr);
#ifdef CONFIG_PPC_ADV_DEBUG_REGS
current->thread.debug.dbcr0 = new_dbcr0;
#endif
Remove 'type' argument from access_ok() function Nobody has actually used the type (VERIFY_READ vs VERIFY_WRITE) argument of the user address range verification function since we got rid of the old racy i386-only code to walk page tables by hand. It existed because the original 80386 would not honor the write protect bit when in kernel mode, so you had to do COW by hand before doing any user access. But we haven't supported that in a long time, and these days the 'type' argument is a purely historical artifact. A discussion about extending 'user_access_begin()' to do the range checking resulted this patch, because there is no way we're going to move the old VERIFY_xyz interface to that model. And it's best done at the end of the merge window when I've done most of my merges, so let's just get this done once and for all. This patch was mostly done with a sed-script, with manual fix-ups for the cases that weren't of the trivial 'access_ok(VERIFY_xyz' form. There were a couple of notable cases: - csky still had the old "verify_area()" name as an alias. - the iter_iov code had magical hardcoded knowledge of the actual values of VERIFY_{READ,WRITE} (not that they mattered, since nothing really used it) - microblaze used the type argument for a debug printout but other than those oddities this should be a total no-op patch. I tried to fix up all architectures, did fairly extensive grepping for access_ok() uses, and the changes are trivial, but I may have missed something. Any missed conversion should be trivially fixable, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 10:57:57 +08:00
if (!access_ok(ctx, sizeof(*ctx)) ||
fault_in_readable((char __user *)ctx, sizeof(*ctx)))
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 (do_setcontext(ctx, regs, 1)) {
signal_fault(current, regs, "sys_debug_setcontext", ctx);
force_sig(SIGSEGV);
goto out;
}
/*
* It's not clear whether or why it is desirable to save the
* sigaltstack setting on signal delivery and restore it on
* signal return. But other architectures do this and we have
* always done it up until now so it is probably better not to
* change it. -- paulus
*/
restore_altstack(&ctx->uc_stack);
[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>
2005-11-16 02:52:18 +08:00
set_thread_flag(TIF_RESTOREALL);
out:
return 0;
}
#endif
/*
* Do a signal return; undo the signal stack.
*/
#ifdef CONFIG_PPC64
COMPAT_SYSCALL_DEFINE0(sigreturn)
#else
SYSCALL_DEFINE0(sigreturn)
#endif
{
struct pt_regs *regs = current_pt_regs();
struct sigframe __user *sf;
struct sigcontext __user *sc;
struct sigcontext sigctx;
struct mcontext __user *sr;
sigset_t set;
struct mcontext __user *mcp;
struct mcontext __user *tm_mcp = NULL;
unsigned long long msr_hi = 0;
/* 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>
2015-02-13 07:01:14 +08:00
current->restart_block.fn = do_no_restart_syscall;
sf = (struct sigframe __user *)(regs->gpr[1] + __SIGNAL_FRAMESIZE);
sc = &sf->sctx;
if (copy_from_user(&sigctx, sc, sizeof(sigctx)))
goto badframe;
#ifdef CONFIG_PPC64
/*
* Note that PPC32 puts the upper 32 bits of the sigmask in the
* unused part of the signal stackframe
*/
set.sig[0] = sigctx.oldmask + ((long)(sigctx._unused[3]) << 32);
#else
set.sig[0] = sigctx.oldmask;
set.sig[1] = sigctx._unused[3];
#endif
set_current_blocked(&set);
mcp = (struct mcontext __user *)&sf->mctx;
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
tm_mcp = (struct mcontext __user *)&sf->mctx_transact;
if (__get_user(msr_hi, &tm_mcp->mc_gregs[PT_MSR]))
goto badframe;
#endif
if (MSR_TM_ACTIVE(msr_hi<<32)) {
if (!cpu_has_feature(CPU_FTR_TM))
goto badframe;
if (restore_tm_user_regs(regs, mcp, tm_mcp))
goto badframe;
} else {
sr = (struct mcontext __user *)from_user_ptr(sigctx.regs);
if (restore_user_regs(regs, sr, 1)) {
signal_fault(current, regs, "sys_sigreturn", sr);
force_sig(SIGSEGV);
return 0;
}
}
[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>
2005-11-16 02:52:18 +08:00
set_thread_flag(TIF_RESTOREALL);
return 0;
badframe:
signal_fault(current, regs, "sys_sigreturn", sc);
force_sig(SIGSEGV);
return 0;
}