Merge tag 'powerpc-5.13-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - Enable KFENCE for 32-bit.

 - Implement EBPF for 32-bit.

 - Convert 32-bit to do interrupt entry/exit in C.

 - Convert 64-bit BookE to do interrupt entry/exit in C.

 - Changes to our signal handling code to use user_access_begin/end()
   more extensively.

 - Add support for time namespaces (CONFIG_TIME_NS)

 - A series of fixes that allow us to reenable STRICT_KERNEL_RWX.

 - Other smaller features, fixes & cleanups.

Thanks to Alexey Kardashevskiy, Andreas Schwab, Andrew Donnellan, Aneesh
Kumar K.V, Athira Rajeev, Bhaskar Chowdhury, Bixuan Cui, Cédric Le
Goater, Chen Huang, Chris Packham, Christophe Leroy, Christopher M.
Riedl, Colin Ian King, Dan Carpenter, Daniel Axtens, Daniel Henrique
Barboza, David Gibson, Davidlohr Bueso, Denis Efremov, dingsenjie,
Dmitry Safonov, Dominic DeMarco, Fabiano Rosas, Ganesh Goudar, Geert
Uytterhoeven, Geetika Moolchandani, Greg Kurz, Guenter Roeck, Haren
Myneni, He Ying, Jiapeng Chong, Jordan Niethe, Laurent Dufour, Lee
Jones, Leonardo Bras, Li Huafei, Madhavan Srinivasan, Mahesh Salgaonkar,
Masahiro Yamada, Nathan Chancellor, Nathan Lynch, Nicholas Piggin,
Oliver O'Halloran, Paul Menzel, Pu Lehui, Randy Dunlap, Ravi Bangoria,
Rosen Penev, Russell Currey, Santosh Sivaraj, Sebastian Andrzej Siewior,
Segher Boessenkool, Shivaprasad G Bhat, Srikar Dronamraju, Stephen
Rothwell, Thadeu Lima de Souza Cascardo, Thomas Gleixner, Tony Ambardar,
Tyrel Datwyler, Vaibhav Jain, Vincenzo Frascino, Xiongwei Song, Yang Li,
Yu Kuai, and Zhang Yunkai.

* tag 'powerpc-5.13-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (302 commits)
  powerpc/signal32: Fix erroneous SIGSEGV on RT signal return
  powerpc: Avoid clang uninitialized warning in __get_user_size_allowed
  powerpc/papr_scm: Mark nvdimm as unarmed if needed during probe
  powerpc/kvm: Fix build error when PPC_MEM_KEYS/PPC_PSERIES=n
  powerpc/kasan: Fix shadow start address with modules
  powerpc/kernel/iommu: Use largepool as a last resort when !largealloc
  powerpc/kernel/iommu: Align size for IOMMU_PAGE_SIZE() to save TCEs
  powerpc/44x: fix spelling mistake in Kconfig "varients" -> "variants"
  powerpc/iommu: Annotate nested lock for lockdep
  powerpc/iommu: Do not immediately panic when failed IOMMU table allocation
  powerpc/iommu: Allocate it_map by vmalloc
  selftests/powerpc: remove unneeded semicolon
  powerpc/64s: remove unneeded semicolon
  powerpc/eeh: remove unneeded semicolon
  powerpc/selftests: Add selftest to test concurrent perf/ptrace events
  powerpc/selftests/perf-hwbreak: Add testcases for 2nd DAWR
  powerpc/selftests/perf-hwbreak: Coalesce event creation code
  powerpc/selftests/ptrace-hwbreak: Add testcases for 2nd DAWR
  powerpc/configs: Add IBMVNIC to some 64-bit configs
  selftests/powerpc: Add uaccess flush test
  ...

1 files changed, 131 insertions, 42 deletions

diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index e8d09a841373..44cde2e129b8 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -2,6 +2,70 @@
 #ifndef _ASM_POWERPC_INTERRUPT_H
 #define _ASM_POWERPC_INTERRUPT_H
 
+/* BookE/4xx */
+#define INTERRUPT_CRITICAL_INPUT  0x100
+
+/* BookE */
+#define INTERRUPT_DEBUG           0xd00
+#ifdef CONFIG_BOOKE
+#define INTERRUPT_PERFMON         0x260
+#define INTERRUPT_DOORBELL        0x280
+#endif
+
+/* BookS/4xx/8xx */
+#define INTERRUPT_MACHINE_CHECK   0x200
+
+/* BookS/8xx */
+#define INTERRUPT_SYSTEM_RESET    0x100
+
+/* BookS */
+#define INTERRUPT_DATA_SEGMENT    0x380
+#define INTERRUPT_INST_SEGMENT    0x480
+#define INTERRUPT_TRACE           0xd00
+#define INTERRUPT_H_DATA_STORAGE  0xe00
+#define INTERRUPT_HMI			0xe60
+#define INTERRUPT_H_FAC_UNAVAIL   0xf80
+#ifdef CONFIG_PPC_BOOK3S
+#define INTERRUPT_DOORBELL        0xa00
+#define INTERRUPT_PERFMON         0xf00
+#define INTERRUPT_ALTIVEC_UNAVAIL	0xf20
+#endif
+
+/* BookE/BookS/4xx/8xx */
+#define INTERRUPT_DATA_STORAGE    0x300
+#define INTERRUPT_INST_STORAGE    0x400
+#define INTERRUPT_EXTERNAL		0x500
+#define INTERRUPT_ALIGNMENT       0x600
+#define INTERRUPT_PROGRAM         0x700
+#define INTERRUPT_SYSCALL         0xc00
+#define INTERRUPT_TRACE			0xd00
+
+/* BookE/BookS/44x */
+#define INTERRUPT_FP_UNAVAIL      0x800
+
+/* BookE/BookS/44x/8xx */
+#define INTERRUPT_DECREMENTER     0x900
+
+#ifndef INTERRUPT_PERFMON
+#define INTERRUPT_PERFMON         0x0
+#endif
+
+/* 8xx */
+#define INTERRUPT_SOFT_EMU_8xx		0x1000
+#define INTERRUPT_INST_TLB_MISS_8xx	0x1100
+#define INTERRUPT_DATA_TLB_MISS_8xx	0x1200
+#define INTERRUPT_INST_TLB_ERROR_8xx	0x1300
+#define INTERRUPT_DATA_TLB_ERROR_8xx	0x1400
+#define INTERRUPT_DATA_BREAKPOINT_8xx	0x1c00
+#define INTERRUPT_INST_BREAKPOINT_8xx	0x1d00
+
+/* 603 */
+#define INTERRUPT_INST_TLB_MISS_603		0x1000
+#define INTERRUPT_DATA_LOAD_TLB_MISS_603	0x1100
+#define INTERRUPT_DATA_STORE_TLB_MISS_603	0x1200
+
+#ifndef __ASSEMBLY__
+
 #include <linux/context_tracking.h>
 #include <linux/hardirq.h>
 #include <asm/cputime.h>
@@ -9,10 +73,18 @@
 #include <asm/kprobes.h>
 #include <asm/runlatch.h>
 
-struct interrupt_state {
-#ifdef CONFIG_PPC_BOOK3E_64
-	enum ctx_state ctx_state;
+static inline void nap_adjust_return(struct pt_regs *regs)
+{
+#ifdef CONFIG_PPC_970_NAP
+	if (unlikely(test_thread_local_flags(_TLF_NAPPING))) {
+		/* Can avoid a test-and-clear because NMIs do not call this */
+		clear_thread_local_flags(_TLF_NAPPING);
+		regs->nip = (unsigned long)power4_idle_nap_return;
+	}
 #endif
+}
+
+struct interrupt_state {
 };
 
 static inline void booke_restore_dbcr0(void)
@@ -29,10 +101,19 @@ static inline void booke_restore_dbcr0(void)
 
 static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
 {
-	/*
-	 * Book3E reconciles irq soft mask in asm
-	 */
-#ifdef CONFIG_PPC_BOOK3S_64
+#ifdef CONFIG_PPC32
+	if (!arch_irq_disabled_regs(regs))
+		trace_hardirqs_off();
+
+	if (user_mode(regs)) {
+		kuep_lock();
+		account_cpu_user_entry();
+	} else {
+		kuap_save_and_lock(regs);
+	}
+#endif
+
+#ifdef CONFIG_PPC64
 	if (irq_soft_mask_set_return(IRQS_ALL_DISABLED) == IRQS_ENABLED)
 		trace_hardirqs_off();
 	local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
@@ -48,16 +129,12 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup
 		 * CT_WARN_ON comes here via program_check_exception,
 		 * so avoid recursion.
 		 */
-		if (TRAP(regs) != 0x700)
+		if (TRAP(regs) != INTERRUPT_PROGRAM)
 			CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
 	}
 #endif
 
-#ifdef CONFIG_PPC_BOOK3E_64
-	state->ctx_state = exception_enter();
-	if (user_mode(regs))
-		account_cpu_user_entry();
-#endif
+	booke_restore_dbcr0();
 }
 
 /*
@@ -76,23 +153,8 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup
  */
 static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
 {
-#ifdef CONFIG_PPC_BOOK3E_64
-	exception_exit(state->ctx_state);
-#endif
-
-	/*
-	 * Book3S exits to user via interrupt_exit_user_prepare(), which does
-	 * context tracking, which is a cleaner way to handle PREEMPT=y
-	 * and avoid context entry/exit in e.g., preempt_schedule_irq()),
-	 * which is likely to be where the core code wants to end up.
-	 *
-	 * The above comment explains why we can't do the
-	 *
-	 *     if (user_mode(regs))
-	 *         user_exit_irqoff();
-	 *
-	 * sequence here.
-	 */
+	if (user_mode(regs))
+		kuep_unlock();
 }
 
 static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
@@ -109,24 +171,46 @@ static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct in
 
 static inline void interrupt_async_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
 {
+	/*
+	 * Adjust at exit so the main handler sees the true NIA. This must
+	 * come before irq_exit() because irq_exit can enable interrupts, and
+	 * if another interrupt is taken before nap_adjust_return has run
+	 * here, then that interrupt would return directly to idle nap return.
+	 */
+	nap_adjust_return(regs);
+
 	irq_exit();
 	interrupt_exit_prepare(regs, state);
 }
 
 struct interrupt_nmi_state {
 #ifdef CONFIG_PPC64
-#ifdef CONFIG_PPC_BOOK3S_64
 	u8 irq_soft_mask;
 	u8 irq_happened;
-#endif
 	u8 ftrace_enabled;
 #endif
 };
 
+static inline bool nmi_disables_ftrace(struct pt_regs *regs)
+{
+	/* Allow DEC and PMI to be traced when they are soft-NMI */
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) {
+		if (TRAP(regs) == INTERRUPT_DECREMENTER)
+		       return false;
+		if (TRAP(regs) == INTERRUPT_PERFMON)
+		       return false;
+	}
+	if (IS_ENABLED(CONFIG_PPC_BOOK3E)) {
+		if (TRAP(regs) == INTERRUPT_PERFMON)
+			return false;
+	}
+
+	return true;
+}
+
 static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct interrupt_nmi_state *state)
 {
 #ifdef CONFIG_PPC64
-#ifdef CONFIG_PPC_BOOK3S_64
 	state->irq_soft_mask = local_paca->irq_soft_mask;
 	state->irq_happened = local_paca->irq_happened;
 
@@ -139,9 +223,8 @@ static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct inte
 	local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
 
 	/* Don't do any per-CPU operations until interrupt state is fixed */
-#endif
-	/* Allow DEC and PMI to be traced when they are soft-NMI */
-	if (TRAP(regs) != 0x900 && TRAP(regs) != 0xf00 && TRAP(regs) != 0x260) {
+
+	if (nmi_disables_ftrace(regs)) {
 		state->ftrace_enabled = this_cpu_get_ftrace_enabled();
 		this_cpu_set_ftrace_enabled(0);
 	}
@@ -164,17 +247,20 @@ static inline void interrupt_nmi_exit_prepare(struct pt_regs *regs, struct inter
 			radix_enabled() || (mfmsr() & MSR_DR))
 		nmi_exit();
 
+	/*
+	 * nmi does not call nap_adjust_return because nmi should not create
+	 * new work to do (must use irq_work for that).
+	 */
+
 #ifdef CONFIG_PPC64
-	if (TRAP(regs) != 0x900 && TRAP(regs) != 0xf00 && TRAP(regs) != 0x260)
+	if (nmi_disables_ftrace(regs))
 		this_cpu_set_ftrace_enabled(state->ftrace_enabled);
 
-#ifdef CONFIG_PPC_BOOK3S_64
 	/* Check we didn't change the pending interrupt mask. */
 	WARN_ON_ONCE((state->irq_happened | PACA_IRQ_HARD_DIS) != local_paca->irq_happened);
 	local_paca->irq_happened = state->irq_happened;
 	local_paca->irq_soft_mask = state->irq_soft_mask;
 #endif
-#endif
 }
 
 /*
@@ -387,6 +473,7 @@ DECLARE_INTERRUPT_HANDLER(SMIException);
 DECLARE_INTERRUPT_HANDLER(handle_hmi_exception);
 DECLARE_INTERRUPT_HANDLER(unknown_exception);
 DECLARE_INTERRUPT_HANDLER_ASYNC(unknown_async_exception);
+DECLARE_INTERRUPT_HANDLER_NMI(unknown_nmi_exception);
 DECLARE_INTERRUPT_HANDLER(instruction_breakpoint_exception);
 DECLARE_INTERRUPT_HANDLER(RunModeException);
 DECLARE_INTERRUPT_HANDLER(single_step_exception);
@@ -410,7 +497,7 @@ DECLARE_INTERRUPT_HANDLER(altivec_assist_exception);
 DECLARE_INTERRUPT_HANDLER(CacheLockingException);
 DECLARE_INTERRUPT_HANDLER(SPEFloatingPointException);
 DECLARE_INTERRUPT_HANDLER(SPEFloatingPointRoundException);
-DECLARE_INTERRUPT_HANDLER(WatchdogException);
+DECLARE_INTERRUPT_HANDLER_NMI(WatchdogException);
 DECLARE_INTERRUPT_HANDLER(kernel_bad_stack);
 
 /* slb.c */
@@ -421,7 +508,7 @@ DECLARE_INTERRUPT_HANDLER(do_bad_slb_fault);
 DECLARE_INTERRUPT_HANDLER_RAW(do_hash_fault);
 
 /* fault.c */
-DECLARE_INTERRUPT_HANDLER_RET(do_page_fault);
+DECLARE_INTERRUPT_HANDLER(do_page_fault);
 DECLARE_INTERRUPT_HANDLER(do_bad_page_fault_segv);
 
 /* process.c */
@@ -436,7 +523,7 @@ DECLARE_INTERRUPT_HANDLER_NMI(hmi_exception_realmode);
 
 DECLARE_INTERRUPT_HANDLER_ASYNC(TAUException);
 
-void unrecoverable_exception(struct pt_regs *regs);
+void __noreturn unrecoverable_exception(struct pt_regs *regs);
 
 void replay_system_reset(void);
 void replay_soft_interrupts(void);
@@ -447,4 +534,6 @@ static inline void interrupt_cond_local_irq_enable(struct pt_regs *regs)
 		local_irq_enable();
 }
 
+#endif /* __ASSEMBLY__ */
+
 #endif /* _ASM_POWERPC_INTERRUPT_H */