Merge tag 'powerpc-5.14-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - A big series refactoring parts of our KVM code, and converting some
   to C.

 - Support for ARCH_HAS_SET_MEMORY, and ARCH_HAS_STRICT_MODULE_RWX on
   some CPUs.

 - Support for the Microwatt soft-core.

 - Optimisations to our interrupt return path on 64-bit.

 - Support for userspace access to the NX GZIP accelerator on PowerVM on
   Power10.

 - Enable KUAP and KUEP by default on 32-bit Book3S CPUs.

 - Other smaller features, fixes & cleanups.

Thanks to: Andy Shevchenko, Aneesh Kumar K.V, Arnd Bergmann, Athira
Rajeev, Baokun Li, Benjamin Herrenschmidt, Bharata B Rao, Christophe
Leroy, Daniel Axtens, Daniel Henrique Barboza, Finn Thain, Geoff Levand,
Haren Myneni, Jason Wang, Jiapeng Chong, Joel Stanley, Jordan Niethe,
Kajol Jain, Nathan Chancellor, Nathan Lynch, Naveen N. Rao, Nicholas
Piggin, Nick Desaulniers, Paul Mackerras, Russell Currey, Sathvika
Vasireddy, Shaokun Zhang, Stephen Rothwell, Sudeep Holla, Suraj Jitindar
Singh, Tom Rix, Vaibhav Jain, YueHaibing, Zhang Jianhua, and Zhen Lei.

* tag 'powerpc-5.14-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (218 commits)
  powerpc: Only build restart_table.c for 64s
  powerpc/64s: move ret_from_fork etc above __end_soft_masked
  powerpc/64s/interrupt: clean up interrupt return labels
  powerpc/64/interrupt: add missing kprobe annotations on interrupt exit symbols
  powerpc/64: enable MSR[EE] in irq replay pt_regs
  powerpc/64s/interrupt: preserve regs->softe for NMI interrupts
  powerpc/64s: add a table of implicit soft-masked addresses
  powerpc/64e: remove implicit soft-masking and interrupt exit restart logic
  powerpc/64e: fix CONFIG_RELOCATABLE build warnings
  powerpc/64s: fix hash page fault interrupt handler
  powerpc/4xx: Fix setup_kuep() on SMP
  powerpc/32s: Fix setup_{kuap/kuep}() on SMP
  powerpc/interrupt: Use names in check_return_regs_valid()
  powerpc/interrupt: Also use exit_must_hard_disable() on PPC32
  powerpc/sysfs: Replace sizeof(arr)/sizeof(arr[0]) with ARRAY_SIZE
  powerpc/ptrace: Refactor regs_set_return_{msr/ip}
  powerpc/ptrace: Move set_return_regs_changed() before regs_set_return_{msr/ip}
  powerpc/stacktrace: Fix spurious "stale" traces in raise_backtrace_ipi()
  powerpc/pseries/vas: Include irqdomain.h
  powerpc: mark local variables around longjmp as volatile
  ...

1 files changed, 70 insertions, 37 deletions

diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 8935c5696bce..185beb290580 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -96,7 +96,8 @@ static void check_if_tm_restore_required(struct task_struct *tsk)
 	if (tsk == current && tsk->thread.regs &&
 	    MSR_TM_ACTIVE(tsk->thread.regs->msr) &&
 	    !test_thread_flag(TIF_RESTORE_TM)) {
-		tsk->thread.ckpt_regs.msr = tsk->thread.regs->msr;
+		regs_set_return_msr(&tsk->thread.ckpt_regs,
+						tsk->thread.regs->msr);
 		set_thread_flag(TIF_RESTORE_TM);
 	}
 }
@@ -161,7 +162,7 @@ static void __giveup_fpu(struct task_struct *tsk)
 	msr &= ~(MSR_FP|MSR_FE0|MSR_FE1);
 	if (cpu_has_feature(CPU_FTR_VSX))
 		msr &= ~MSR_VSX;
-	tsk->thread.regs->msr = msr;
+	regs_set_return_msr(tsk->thread.regs, msr);
 }
 
 void giveup_fpu(struct task_struct *tsk)
@@ -244,7 +245,7 @@ static void __giveup_altivec(struct task_struct *tsk)
 	msr &= ~MSR_VEC;
 	if (cpu_has_feature(CPU_FTR_VSX))
 		msr &= ~MSR_VSX;
-	tsk->thread.regs->msr = msr;
+	regs_set_return_msr(tsk->thread.regs, msr);
 }
 
 void giveup_altivec(struct task_struct *tsk)
@@ -559,7 +560,7 @@ void notrace restore_math(struct pt_regs *regs)
 
 		msr_check_and_clear(new_msr);
 
-		regs->msr |= new_msr | fpexc_mode;
+		regs_set_return_msr(regs, regs->msr | new_msr | fpexc_mode);
 	}
 }
 #endif /* CONFIG_PPC_BOOK3S_64 */
@@ -1114,7 +1115,7 @@ void restore_tm_state(struct pt_regs *regs)
 #endif
 	restore_math(regs);
 
-	regs->msr |= msr_diff;
+	regs_set_return_msr(regs, regs->msr | msr_diff);
 }
 
 #else /* !CONFIG_PPC_TRANSACTIONAL_MEM */
@@ -1129,6 +1130,10 @@ static inline void save_sprs(struct thread_struct *t)
 	if (cpu_has_feature(CPU_FTR_ALTIVEC))
 		t->vrsave = mfspr(SPRN_VRSAVE);
 #endif
+#ifdef CONFIG_SPE
+	if (cpu_has_feature(CPU_FTR_SPE))
+		t->spefscr = mfspr(SPRN_SPEFSCR);
+#endif
 #ifdef CONFIG_PPC_BOOK3S_64
 	if (cpu_has_feature(CPU_FTR_DSCR))
 		t->dscr = mfspr(SPRN_DSCR);
@@ -1159,6 +1164,11 @@ static inline void restore_sprs(struct thread_struct *old_thread,
 	    old_thread->vrsave != new_thread->vrsave)
 		mtspr(SPRN_VRSAVE, new_thread->vrsave);
 #endif
+#ifdef CONFIG_SPE
+	if (cpu_has_feature(CPU_FTR_SPE) &&
+	    old_thread->spefscr != new_thread->spefscr)
+		mtspr(SPRN_SPEFSCR, new_thread->spefscr);
+#endif
 #ifdef CONFIG_PPC_BOOK3S_64
 	if (cpu_has_feature(CPU_FTR_DSCR)) {
 		u64 dscr = get_paca()->dscr_default;
@@ -1213,6 +1223,19 @@ struct task_struct *__switch_to(struct task_struct *prev,
 			__flush_tlb_pending(batch);
 		batch->active = 0;
 	}
+
+	/*
+	 * On POWER9 the copy-paste buffer can only paste into
+	 * foreign real addresses, so unprivileged processes can not
+	 * see the data or use it in any way unless they have
+	 * foreign real mappings. If the new process has the foreign
+	 * real address mappings, we must issue a cp_abort to clear
+	 * any state and prevent snooping, corruption or a covert
+	 * channel. ISA v3.1 supports paste into local memory.
+	 */
+	if (new->mm && (cpu_has_feature(CPU_FTR_ARCH_31) ||
+			atomic_read(&new->mm->context.vas_windows)))
+		asm volatile(PPC_CP_ABORT);
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
@@ -1248,43 +1271,48 @@ struct task_struct *__switch_to(struct task_struct *prev,
 	}
 
 	/*
-	 * Call restore_sprs() before calling _switch(). If we move it after
-	 * _switch() then we miss out on calling it for new tasks. The reason
-	 * for this is we manually create a stack frame for new tasks that
-	 * directly returns through ret_from_fork() or
+	 * Call restore_sprs() and set_return_regs_changed() before calling
+	 * _switch(). If we move it after _switch() then we miss out on calling
+	 * it for new tasks. The reason for this is we manually create a stack
+	 * frame for new tasks that directly returns through ret_from_fork() or
 	 * ret_from_kernel_thread(). See copy_thread() for details.
 	 */
 	restore_sprs(old_thread, new_thread);
 
+	set_return_regs_changed(); /* _switch changes stack (and regs) */
+
 #ifdef CONFIG_PPC32
 	kuap_assert_locked();
 #endif
 	last = _switch(old_thread, new_thread);
 
+	/*
+	 * Nothing after _switch will be run for newly created tasks,
+	 * because they switch directly to ret_from_fork/ret_from_kernel_thread
+	 * etc. Code added here should have a comment explaining why that is
+	 * okay.
+	 */
+
 #ifdef CONFIG_PPC_BOOK3S_64
+	/*
+	 * This applies to a process that was context switched while inside
+	 * arch_enter_lazy_mmu_mode(), to re-activate the batch that was
+	 * deactivated above, before _switch(). This will never be the case
+	 * for new tasks.
+	 */
 	if (current_thread_info()->local_flags & _TLF_LAZY_MMU) {
 		current_thread_info()->local_flags &= ~_TLF_LAZY_MMU;
 		batch = this_cpu_ptr(&ppc64_tlb_batch);
 		batch->active = 1;
 	}
 
-	if (current->thread.regs) {
+	/*
+	 * Math facilities are masked out of the child MSR in copy_thread.
+	 * A new task does not need to restore_math because it will
+	 * demand fault them.
+	 */
+	if (current->thread.regs)
 		restore_math(current->thread.regs);
-
-		/*
-		 * On POWER9 the copy-paste buffer can only paste into
-		 * foreign real addresses, so unprivileged processes can not
-		 * see the data or use it in any way unless they have
-		 * foreign real mappings. If the new process has the foreign
-		 * real address mappings, we must issue a cp_abort to clear
-		 * any state and prevent snooping, corruption or a covert
-		 * channel. ISA v3.1 supports paste into local memory.
-		 */
-		if (current->mm &&
-			(cpu_has_feature(CPU_FTR_ARCH_31) ||
-			atomic_read(&current->mm->context.vas_windows)))
-			asm volatile(PPC_CP_ABORT);
-	}
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
 	return last;
@@ -1736,6 +1764,9 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 #ifdef CONFIG_ALTIVEC
 	p->thread.vr_save_area = NULL;
 #endif
+#if defined(CONFIG_PPC_BOOK3S_32) && defined(CONFIG_PPC_KUAP)
+	p->thread.kuap = KUAP_NONE;
+#endif
 
 	setup_ksp_vsid(p, sp);
 
@@ -1838,13 +1869,14 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 			}
 			regs->gpr[2] = toc;
 		}
-		regs->nip = entry;
-		regs->msr = MSR_USER64;
+		regs_set_return_ip(regs, entry);
+		regs_set_return_msr(regs, MSR_USER64);
 	} else {
-		regs->nip = start;
 		regs->gpr[2] = 0;
-		regs->msr = MSR_USER32;
+		regs_set_return_ip(regs, start);
+		regs_set_return_msr(regs, MSR_USER32);
 	}
+
 #endif
 #ifdef CONFIG_VSX
 	current->thread.used_vsr = 0;
@@ -1875,7 +1907,6 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 	current->thread.tm_tfiar = 0;
 	current->thread.load_tm = 0;
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
-
 }
 EXPORT_SYMBOL(start_thread);
 
@@ -1923,9 +1954,10 @@ int set_fpexc_mode(struct task_struct *tsk, unsigned int val)
 	if (val > PR_FP_EXC_PRECISE)
 		return -EINVAL;
 	tsk->thread.fpexc_mode = __pack_fe01(val);
-	if (regs != NULL && (regs->msr & MSR_FP) != 0)
-		regs->msr = (regs->msr & ~(MSR_FE0|MSR_FE1))
-			| tsk->thread.fpexc_mode;
+	if (regs != NULL && (regs->msr & MSR_FP) != 0) {
+		regs_set_return_msr(regs, (regs->msr & ~(MSR_FE0|MSR_FE1))
+						| tsk->thread.fpexc_mode);
+	}
 	return 0;
 }
 
@@ -1971,9 +2003,9 @@ int set_endian(struct task_struct *tsk, unsigned int val)
 		return -EINVAL;
 
 	if (val == PR_ENDIAN_BIG)
-		regs->msr &= ~MSR_LE;
+		regs_set_return_msr(regs, regs->msr & ~MSR_LE);
 	else if (val == PR_ENDIAN_LITTLE || val == PR_ENDIAN_PPC_LITTLE)
-		regs->msr |= MSR_LE;
+		regs_set_return_msr(regs, regs->msr | MSR_LE);
 	else
 		return -EINVAL;
 
@@ -2121,8 +2153,9 @@ unsigned long get_wchan(struct task_struct *p)
 
 static int kstack_depth_to_print = CONFIG_PRINT_STACK_DEPTH;
 
-void show_stack(struct task_struct *tsk, unsigned long *stack,
-		const char *loglvl)
+void __no_sanitize_address show_stack(struct task_struct *tsk,
+				      unsigned long *stack,
+				      const char *loglvl)
 {
 	unsigned long sp, ip, lr, newsp;
 	int count = 0;