Merge tag 'powerpc-5.15-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fixes from Michael Ellerman:

 - Fix crashes when scv (System Call Vectored) is used to make a syscall
   when a transaction is active, on Power9 or later.

 - Fix bad interactions between rfscv (Return-from scv) and Power9
   fake-suspend mode.

 - Fix crashes when handling machine checks in LPARs using the Hash MMU.

 - Partly revert a recent change to our XICS interrupt controller code,
   which broke the recently added Microwatt support.

Thanks to Cédric Le Goater, Eirik Fuller, Ganesh Goudar, Gustavo Romero,
Joel Stanley, Nicholas Piggin.

* tag 'powerpc-5.15-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  powerpc/xics: Set the IRQ chip data for the ICS native backend
  powerpc/mce: Fix access error in mce handler
  KVM: PPC: Book3S HV: Tolerate treclaim. in fake-suspend mode changing registers
  powerpc/64s: system call rfscv workaround for TM bugs
  selftests/powerpc: Add scv versions of the basic TM syscall tests
  powerpc/64s: system call scv tabort fix for corrupt irq soft-mask state

arch/powerpc/kernel/interrupt.c

@@ -18,6 +18,7 @@
 #include <asm/switch_to.h>
 #include <asm/syscall.h>
 #include <asm/time.h>
+#include <asm/tm.h>
 #include <asm/unistd.h>
 
 #if defined(CONFIG_PPC_ADV_DEBUG_REGS) && defined(CONFIG_PPC32)
@@ -136,6 +137,48 @@ notrace long system_call_exception(long r3, long r4, long r5,
 	 */
 	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)))
+		current_thread_info()->flags |= _TIF_RESTOREALL;
+
+	/*
+	 * 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(current_thread_info()->flags & _TIF_SYSCALL_DOTRACE)) {

arch/powerpc/kernel/interrupt_64.S

@@ -12,7 +12,6 @@
 #include <asm/mmu.h>
 #include <asm/ppc_asm.h>
 #include <asm/ptrace.h>
-#include <asm/tm.h>
 
 	.section	".toc","aw"
 SYS_CALL_TABLE:
@@ -55,12 +54,6 @@ COMPAT_SYS_CALL_TABLE:
 	.globl system_call_vectored_\name
 system_call_vectored_\name:
 _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name)
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-BEGIN_FTR_SECTION
-	extrdi.	r10, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */
-	bne	tabort_syscall
-END_FTR_SECTION_IFSET(CPU_FTR_TM)
-#endif
 	SCV_INTERRUPT_TO_KERNEL
 	mr	r10,r1
 	ld	r1,PACAKSAVE(r13)
@@ -247,12 +240,6 @@ _ASM_NOKPROBE_SYMBOL(system_call_common_real)
 	.globl system_call_common
 system_call_common:
 _ASM_NOKPROBE_SYMBOL(system_call_common)
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-BEGIN_FTR_SECTION
-	extrdi.	r10, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */
-	bne	tabort_syscall
-END_FTR_SECTION_IFSET(CPU_FTR_TM)
-#endif
 	mr	r10,r1
 	ld	r1,PACAKSAVE(r13)
 	std	r10,0(r1)
@@ -425,34 +412,6 @@ SOFT_MASK_TABLE(.Lsyscall_rst_start, 1b)
 RESTART_TABLE(.Lsyscall_rst_start, .Lsyscall_rst_end, syscall_restart)
 #endif
 
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-tabort_syscall:
-_ASM_NOKPROBE_SYMBOL(tabort_syscall)
-	/* Firstly we need to enable TM in the kernel */
-	mfmsr	r10
-	li	r9, 1
-	rldimi	r10, r9, MSR_TM_LG, 63-MSR_TM_LG
-	mtmsrd	r10, 0
-
-	/* tabort, this dooms the transaction, nothing else */
-	li	r9, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
-	TABORT(R9)
-
-	/*
-	 * Return directly to userspace. We have corrupted user register state,
-	 * but userspace will never see that register state. Execution will
-	 * resume after the tbegin of the aborted transaction with the
-	 * checkpointed register state.
-	 */
-	li	r9, MSR_RI
-	andc	r10, r10, r9
-	mtmsrd	r10, 1
-	mtspr	SPRN_SRR0, r11
-	mtspr	SPRN_SRR1, r12
-	RFI_TO_USER
-	b	.	/* prevent speculative execution */
-#endif
-
 	/*
 	 * If MSR EE/RI was never enabled, IRQs not reconciled, NVGPRs not
 	 * touched, no exit work created, then this can be used.

arch/powerpc/kernel/mce.c

@@ -249,6 +249,7 @@ void machine_check_queue_event(void)
 {
 	int index;
 	struct machine_check_event evt;
+	unsigned long msr;
 
 	if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
 		return;
@@ -262,8 +263,20 @@ void machine_check_queue_event(void)
 	memcpy(&local_paca->mce_info->mce_event_queue[index],
 	       &evt, sizeof(evt));
 
-	/* Queue irq work to process this event later. */
+	/*
+	 * Queue irq work to process this event later. Before
+	 * queuing the work enable translation for non radix LPAR,
+	 * as irq_work_queue may try to access memory outside RMO
+	 * region.
+	 */
+	if (!radix_enabled() && firmware_has_feature(FW_FEATURE_LPAR)) {
+		msr = mfmsr();
+		mtmsr(msr | MSR_IR | MSR_DR);
 		irq_work_queue(&mce_event_process_work);
+		mtmsr(msr);
+	} else {
+		irq_work_queue(&mce_event_process_work);
+	}
 }
 
 void mce_common_process_ue(struct pt_regs *regs,

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -2536,7 +2536,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_P9_TM_HV_ASSIST)
 	/* The following code handles the fake_suspend = 1 case */
 	mflr	r0
 	std	r0, PPC_LR_STKOFF(r1)
-	stdu	r1, -PPC_MIN_STKFRM(r1)
+	stdu	r1, -TM_FRAME_SIZE(r1)
 
 	/* Turn on TM. */
 	mfmsr	r8
@@ -2551,10 +2551,42 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG)
 	nop
 
+	/*
+	 * It's possible that treclaim. may modify registers, if we have lost
+	 * track of fake-suspend state in the guest due to it using rfscv.
+	 * Save and restore registers in case this occurs.
+	 */
+	mfspr	r3, SPRN_DSCR
+	mfspr	r4, SPRN_XER
+	mfspr	r5, SPRN_AMR
+	/* SPRN_TAR would need to be saved here if the kernel ever used it */
+	mfcr	r12
+	SAVE_NVGPRS(r1)
+	SAVE_GPR(2, r1)
+	SAVE_GPR(3, r1)
+	SAVE_GPR(4, r1)
+	SAVE_GPR(5, r1)
+	stw	r12, 8(r1)
+	std	r1, HSTATE_HOST_R1(r13)
+
 	/* We have to treclaim here because that's the only way to do S->N */
 	li	r3, TM_CAUSE_KVM_RESCHED
 	TRECLAIM(R3)
 
+	GET_PACA(r13)
+	ld	r1, HSTATE_HOST_R1(r13)
+	REST_GPR(2, r1)
+	REST_GPR(3, r1)
+	REST_GPR(4, r1)
+	REST_GPR(5, r1)
+	lwz	r12, 8(r1)
+	REST_NVGPRS(r1)
+	mtspr	SPRN_DSCR, r3
+	mtspr	SPRN_XER, r4
+	mtspr	SPRN_AMR, r5
+	mtcr	r12
+	HMT_MEDIUM
+
 	/*
 	 * We were in fake suspend, so we are not going to save the
 	 * register state as the guest checkpointed state (since
@@ -2582,7 +2614,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG)
 	std	r5, VCPU_TFHAR(r9)
 	std	r6, VCPU_TFIAR(r9)
 
-	addi	r1, r1, PPC_MIN_STKFRM
+	addi	r1, r1, TM_FRAME_SIZE
 	ld	r0, PPC_LR_STKOFF(r1)
 	mtlr	r0
 	blr

arch/powerpc/sysdev/xics/xics-common.c

@@ -348,9 +348,9 @@ static int xics_host_map(struct irq_domain *domain, unsigned int virq,
 	if (xics_ics->check(xics_ics, hwirq))
 		return -EINVAL;
 
-	/* No chip data for the XICS domain */
+	/* Let the ICS be the chip data for the XICS domain. For ICS native */
 	irq_domain_set_info(domain, virq, hwirq, xics_ics->chip,
-			    NULL, handle_fasteoi_irq, NULL, NULL);
+			    xics_ics, handle_fasteoi_irq, NULL, NULL);
 
 	return 0;
 }

tools/testing/selftests/powerpc/tm/tm-syscall-asm.S

 /* SPDX-License-Identifier: GPL-2.0 */
-#include <ppc-asm.h>
+#include <basic_asm.h>
 #include <asm/unistd.h>
 
 	.text
@@ -26,3 +26,38 @@ FUNC_START(getppid_tm_suspended)
 1:
 	li	r3, -1
 	blr
+
+
+.macro scv level
+	.long (0x44000001 | (\level) << 5)
+.endm
+
+FUNC_START(getppid_scv_tm_active)
+	PUSH_BASIC_STACK(0)
+	tbegin.
+	beq 1f
+	li	r0, __NR_getppid
+	scv	0
+	tend.
+	POP_BASIC_STACK(0)
+	blr
+1:
+	li	r3, -1
+	POP_BASIC_STACK(0)
+	blr
+
+FUNC_START(getppid_scv_tm_suspended)
+	PUSH_BASIC_STACK(0)
+	tbegin.
+	beq 1f
+	li	r0, __NR_getppid
+	tsuspend.
+	scv	0
+	tresume.
+	tend.
+	POP_BASIC_STACK(0)
+	blr
+1:
+	li	r3, -1
+	POP_BASIC_STACK(0)
+	blr

tools/testing/selftests/powerpc/tm/tm-syscall.c

@@ -19,23 +19,36 @@
 #include "utils.h"
 #include "tm.h"
 
+#ifndef PPC_FEATURE2_SCV
+#define PPC_FEATURE2_SCV               0x00100000 /* scv syscall */
+#endif
+
 extern int getppid_tm_active(void);
 extern int getppid_tm_suspended(void);
+extern int getppid_scv_tm_active(void);
+extern int getppid_scv_tm_suspended(void);
 
 unsigned retries = 0;
 
 #define TEST_DURATION 10 /* seconds */
 
-pid_t getppid_tm(bool suspend)
+pid_t getppid_tm(bool scv, bool suspend)
 {
 	int i;
 	pid_t pid;
 
 	for (i = 0; i < TM_RETRIES; i++) {
-		if (suspend)
+		if (suspend) {
+			if (scv)
+				pid = getppid_scv_tm_suspended();
+			else
 				pid = getppid_tm_suspended();
+		} else {
+			if (scv)
+				pid = getppid_scv_tm_active();
 			else
 				pid = getppid_tm_active();
+		}
 
 		if (pid >= 0)
 			return pid;
@@ -82,15 +95,24 @@ int tm_syscall(void)
 		 * Test a syscall within a suspended transaction and verify
 		 * that it succeeds.
 		 */
-		FAIL_IF(getppid_tm(true) == -1); /* Should succeed. */
+		FAIL_IF(getppid_tm(false, true) == -1); /* Should succeed. */
 
 		/*
 		 * Test a syscall within an active transaction and verify that
 		 * it fails with the correct failure code.
 		 */
-		FAIL_IF(getppid_tm(false) != -1);  /* Should fail... */
+		FAIL_IF(getppid_tm(false, false) != -1);  /* Should fail... */
+		FAIL_IF(!failure_is_persistent()); /* ...persistently... */
+		FAIL_IF(!failure_is_syscall());    /* ...with code syscall. */
+
+		/* Now do it all again with scv if it is available. */
+		if (have_hwcap2(PPC_FEATURE2_SCV)) {
+			FAIL_IF(getppid_tm(true, true) == -1); /* Should succeed. */
+			FAIL_IF(getppid_tm(true, false) != -1);  /* Should fail... */
 			FAIL_IF(!failure_is_persistent()); /* ...persistently... */
 			FAIL_IF(!failure_is_syscall());    /* ...with code syscall. */
+		}
+
 		gettimeofday(&now, 0);
 	}