select GENERIC_GETTIMEOFDAY
select GENERIC_IDLE_POLL_SETUP
select GENERIC_IOREMAP
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index 7f31f3fb9c1d8..8731064631de0 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0-or-later
#include <linux/context_tracking.h>
+#include <linux/entry-common.h>
#include <linux/err.h>
#include <linux/compat.h>
#include <linux/rseq.h>
@@ -163,15 +164,10 @@ notrace unsigned long syscall_exit_prepare(unsigned long
r3,
unsigned long ret = 0;
bool is_not_scv = !IS_ENABLED(CONFIG_PPC_BOOK3S_64) || !scv;
- CT_WARN_ON(ct_state() == CT_STATE_USER);
-
kuap_assert_locked();
regs->result = r3;
- /* Check whether the syscall is issued inside a restartable sequence */
- rseq_syscall(regs);
-
ti_flags = read_thread_flags();
if (unlikely(r3 >= (unsigned long)-MAX_ERRNO) && is_not_scv) {
@@ -192,13 +188,27 @@ notrace unsigned long syscall_exit_prepare(unsigned long
r3,
}
if (unlikely(ti_flags & _TIF_SYSCALL_DOTRACE)) {
- do_syscall_trace_leave(regs);
ret |= _TIF_RESTOREALL;
}
- local_irq_disable();
- ret = interrupt_exit_user_prepare_main(ret, regs);
+
+ user_enter_irqoff();
+ if (!prep_irq_for_enabled_exit(true)) {
+ user_exit_irqoff();
+ local_irq_enable();
+ local_irq_disable();
+ goto again;
+ }
+
+ /* Restore user access locks last */
+ kuap_user_restore(regs);
+ if (unlikely((local_paca->generic_fw_flags & GFW_RESTORE_ALL) == GFW_RESTORE_ALL)) {
+ ret |= _TIF_RESTOREALL;
+ local_paca->generic_fw_flags &= ~GFW_RESTORE_ALL;
+ }
#ifdef CONFIG_PPC64
regs->exit_result = ret;
#endif
@@ -209,6 +219,7 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
#ifdef CONFIG_PPC64
notrace unsigned long syscall_exit_restart(unsigned long r3, struct pt_regs
*regs)
{
+ unsigned long ret = 0;
/*
* This is called when detecting a soft-pending interrupt as well as
* an alternate-return interrupt. So we can't just have the alternate
@@ -222,14 +233,23 @@ notrace unsigned long syscall_exit_restart(unsigned long
r3, struct pt_regs *reg
#ifdef CONFIG_PPC_BOOK3S_64
set_kuap(AMR_KUAP_BLOCKED);
#endif
+again:
+ syscall_exit_to_user_mode(regs);
- trace_hardirqs_off();
- user_exit_irqoff();
- account_cpu_user_entry();
+ user_enter_irqoff();
+ if (!prep_irq_for_enabled_exit(true)) {
+ user_exit_irqoff();
+ local_irq_enable();
+ local_irq_disable();
+ goto again;
+ }
- BUG_ON(!user_mode(regs));
+ if (unlikely((local_paca->generic_fw_flags & GFW_RESTORE_ALL) ==
GFW_RESTORE_ALL)) {
+ ret = _TIF_RESTOREALL;
+ local_paca->generic_fw_flags &= ~GFW_RESTORE_ALL;
+ }
- regs->exit_result = interrupt_exit_user_prepare_main(regs->exit_result, regs);
+ regs->exit_result |= ret;
return regs->exit_result;
}
diff --git a/arch/powerpc/kernel/ptrace/ptrace.c
b/arch/powerpc/kernel/ptrace/ptrace.c
index c6997df632873..2a2b0b94a3eaa 100644
--- a/arch/powerpc/kernel/ptrace/ptrace.c
+++ b/arch/powerpc/kernel/ptrace/ptrace.c
@@ -21,9 +21,6 @@
#include <asm/switch_to.h>
#include <asm/debug.h>
-#define CREATE_TRACE_POINTS
-#include <trace/events/syscalls.h>
-
#include "ptrace-decl.h"
/*
@@ -233,106 +230,6 @@ static int do_seccomp(struct pt_regs *regs)
static inline int do_seccomp(struct pt_regs *regs) { return 0; }
#endif /* CONFIG_SECCOMP */
-/**
- * do_syscall_trace_enter() - Do syscall tracing on kernel entry.
- * @regs: the pt_regs of the task to trace (current)
- *
- * Performs various types of tracing on syscall entry. This includes seccomp,
- * ptrace, syscall tracepoints and audit.
- *
- * The pt_regs are potentially visible to userspace via ptrace, so their
- * contents is ABI.
- *
- * One or more of the tracers may modify the contents of pt_regs, in particular
- * to modify arguments or even the syscall number itself.
- *
- * It's also possible that a tracer can choose to reject the system call. In
- * that case this function will return an illegal syscall number, and will put
- * an appropriate return value in regs->r3.
- *
- * Return: the (possibly changed) syscall number.
- */
-long do_syscall_trace_enter(struct pt_regs *regs)
-{
- u32 flags;
-
- flags = read_thread_flags() & (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE);
-
- if (flags) {
- int rc = ptrace_report_syscall_entry(regs);
-
- if (unlikely(flags & _TIF_SYSCALL_EMU)) {
- /*
- * A nonzero return code from
- * ptrace_report_syscall_entry() tells us to prevent
- * the syscall execution, but we are not going to
- * execute it anyway.
- *
- * Returning -1 will skip the syscall execution. We want
- * to avoid clobbering any registers, so we don't goto
- * the skip label below.
- */
- return -1;
- }
-
- if (rc) {
- /*
- * The tracer decided to abort the syscall. Note that
- * the tracer may also just change regs->gpr[0] to an
- * invalid syscall number, that is handled below on the
- * exit path.
- */
- goto skip;
- }
- }
-
- /* Run seccomp after ptrace; allow it to set gpr[3]. */
- if (do_seccomp(regs))
- return -1;
-
- /* Avoid trace and audit when syscall is invalid. */
- if (regs->gpr[0] >= NR_syscalls)
- goto skip;
-
- if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
- trace_sys_enter(regs, regs->gpr[0]);
-
- if (!is_32bit_task())
- audit_syscall_entry(regs->gpr[0], regs->gpr[3], regs->gpr[4],
- regs->gpr[5], regs->gpr[6]);
- else
- audit_syscall_entry(regs->gpr[0],
- regs->gpr[3] & 0xffffffff,
- regs->gpr[4] & 0xffffffff,
- regs->gpr[5] & 0xffffffff,
- regs->gpr[6] & 0xffffffff);
-
- /* Return the possibly modified but valid syscall number */
- return regs->gpr[0];
-
-skip:
- /*
- * If we are aborting explicitly, or if the syscall number is
- * now invalid, set the return value to -ENOSYS.
- */
- regs->gpr[3] = -ENOSYS;
- return -1;
-}
-
-void do_syscall_trace_leave(struct pt_regs *regs)
-{
- int step;
-
- audit_syscall_exit(regs);
-
- if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
- trace_sys_exit(regs, regs->result);
-
- step = test_thread_flag(TIF_SINGLESTEP);
- if (step || test_thread_flag(TIF_SYSCALL_TRACE))
- ptrace_report_syscall_exit(regs, step);
-}
-
void __init pt_regs_check(void);
/*
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index 719930cf4ae1f..8e1a1b26b5eae 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -6,6 +6,7 @@
* Extracted from signal_32.c and signal_64.c
*/
+#include <linux/entry-common.h>
#include <linux/resume_user_mode.h>
#include <linux/signal.h>
#include <linux/uprobes.h>
@@ -22,11 +23,6 @@
#include "signal.h"
-/* This will be removed */
-#ifdef CONFIG_GENERIC_ENTRY
-#include <linux/entry-common.h>
-#endif /* CONFIG_GENERIC_ENTRY */
-
#ifdef CONFIG_VSX
unsigned long copy_fpr_to_user(void __user *to,
struct task_struct *task)
@@ -374,11 +370,9 @@ void signal_fault(struct task_struct *tsk, struct pt_regs
*regs,
task_pid_nr(tsk), where, ptr, regs->nip,
regs->link);
}
-#ifdef CONFIG_GENERIC_ENTRY
void arch_do_signal_or_restart(struct pt_regs *regs)
{
BUG_ON(regs != current->thread.regs);
local_paca->generic_fw_flags |= GFW_RESTORE_ALL;
do_signal(current);
}
-#endif /* CONFIG_GENERIC_ENTRY */
diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c
index 9f03a6263fb41..66fd6ca4462b0 100644
--- a/arch/powerpc/kernel/syscall.c
+++ b/arch/powerpc/kernel/syscall.c
@@ -3,6 +3,7 @@
#include <linux/compat.h>
#include <linux/context_tracking.h>
#include <linux/randomize_kstack.h>
+#include <linux/entry-common.h>
#include <asm/interrupt.h>
#include <asm/kup.h>
@@ -21,121 +22,9 @@ notrace long system_call_exception(struct pt_regs *regs,
unsigned long r0)
kuap_lock();
add_random_kstack_offset();
+ r0 = syscall_enter_from_user_mode(regs, r0);
- if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
- BUG_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED);
-
- trace_hardirqs_off(); /* finish reconciling */
-
- CT_WARN_ON(ct_state() == CT_STATE_KERNEL);
- user_exit_irqoff();
-
- BUG_ON(regs_is_unrecoverable(regs));
- BUG_ON(!user_mode(regs));
- BUG_ON(regs_irqs_disabled(regs));
-
-#ifdef CONFIG_PPC_PKEY
- if (mmu_has_feature(MMU_FTR_PKEY)) {
- unsigned long amr, iamr;
- bool flush_needed = false;
- /*
- * When entering from userspace we mostly have the AMR/IAMR
- * different from kernel default values. Hence don't compare.
- */
- amr = mfspr(SPRN_AMR);
- iamr = mfspr(SPRN_IAMR);
- regs->amr = amr;
- regs->iamr = iamr;
- if (mmu_has_feature(MMU_FTR_KUAP)) {
- mtspr(SPRN_AMR, AMR_KUAP_BLOCKED);
- flush_needed = true;
- }
- if (mmu_has_feature(MMU_FTR_BOOK3S_KUEP)) {
- mtspr(SPRN_IAMR, AMR_KUEP_BLOCKED);
- flush_needed = true;
- }
- if (flush_needed)
- isync();
- } else
-#endif
- kuap_assert_locked();
-
- booke_restore_dbcr0();
-
- account_cpu_user_entry();
-
- account_stolen_time();
-
- /*
- * This is not required for the syscall exit path, but makes the
- * stack frame look nicer. If this was initialised in the first stack
- * frame, or if the unwinder was taught the first stack frame always
- * returns to user with IRQS_ENABLED, this store could be avoided!
- */
- irq_soft_mask_regs_set_state(regs, IRQS_ENABLED);
-
- /*
- * If system call is called with TM active, set _TIF_RESTOREALL to
- * prevent RFSCV being used to return to userspace, because POWER9
- * TM implementation has problems with this instruction returning to
- * transactional state. Final register values are not relevant because
- * the transaction will be aborted upon return anyway. Or in the case
- * of unsupported_scv SIGILL fault, the return state does not much
- * matter because it's an edge case.
- */
- if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) &&
- unlikely(MSR_TM_TRANSACTIONAL(regs->msr)))
- set_bits(_TIF_RESTOREALL, ¤t_thread_info()->flags);
-
- /*
- * If the system call was made with a transaction active, doom it and
- * return without performing the system call. Unless it was an
- * unsupported scv vector, in which case it's treated like an illegal
- * instruction.
- */
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
- if (unlikely(MSR_TM_TRANSACTIONAL(regs->msr)) &&
- !trap_is_unsupported_scv(regs)) {
- /* Enable TM in the kernel, and disable EE (for scv) */
- hard_irq_disable();
- mtmsr(mfmsr() | MSR_TM);
-
- /* tabort, this dooms the transaction, nothing else */
- asm volatile(".long 0x7c00071d | ((%0) << 16)"
- :: "r"(TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT));
-
- /*
- * Userspace will never see the return value. Execution will
- * resume after the tbegin. of the aborted transaction with the
- * checkpointed register state. A context switch could occur
- * or signal delivered to the process before resuming the
- * doomed transaction context, but that should all be handled
- * as expected.
- */
- return -ENOSYS;
- }
-#endif // CONFIG_PPC_TRANSACTIONAL_MEM
-
- local_irq_enable();
-
- if (unlikely(read_thread_flags() & _TIF_SYSCALL_DOTRACE)) {
- if (unlikely(trap_is_unsupported_scv(regs))) {
- /* Unsupported scv vector */
- _exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
- return regs->gpr[3];
- }
- /*
- * We use the return value of do_syscall_trace_enter() as the
- * syscall number. If the syscall was rejected for any reason
- * do_syscall_trace_enter() returns an invalid syscall number
- * and the test against NR_syscalls will fail and the return
- * value to be used is in regs->gpr[3].
- */
- r0 = do_syscall_trace_enter(regs);
- if (unlikely(r0 >= NR_syscalls))
- return regs->gpr[3];
-
- } else if (unlikely(r0 >= NR_syscalls)) {
+ if (unlikely(r0 >= NR_syscalls)) {
if (unlikely(trap_is_unsupported_scv(regs))) {
/* Unsupported scv vector */
_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
