Merge tag 'powerpc-4.12-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Highlights include:

   - Larger virtual address space on 64-bit server CPUs. By default we
     use a 128TB virtual address space, but a process can request access
     to the full 512TB by passing a hint to mmap().

   - Support for the new Power9 "XIVE" interrupt controller.

   - TLB flushing optimisations for the radix MMU on Power9.

   - Support for CAPI cards on Power9, using the "Coherent Accelerator
     Interface Architecture 2.0".

   - The ability to configure the mmap randomisation limits at build and
     runtime.

   - Several small fixes and cleanups to the kprobes code, as well as
     support for KPROBES_ON_FTRACE.

   - Major improvements to handling of system reset interrupts,
     correctly treating them as NMIs, giving them a dedicated stack and
     using a new hypervisor call to trigger them, all of which should
     aid debugging and robustness.

   - Many fixes and other minor enhancements.

  Thanks to: Alastair D'Silva, Alexey Kardashevskiy, Alistair Popple,
  Andrew Donnellan, Aneesh Kumar K.V, Anshuman Khandual, Anton
  Blanchard, Balbir Singh, Ben Hutchings, Benjamin Herrenschmidt,
  Bhupesh Sharma, Chris Packham, Christian Zigotzky, Christophe Leroy,
  Christophe Lombard, Daniel Axtens, David Gibson, Gautham R. Shenoy,
  Gavin Shan, Geert Uytterhoeven, Guilherme G. Piccoli, Hamish Martin,
  Hari Bathini, Kees Cook, Laurent Dufour, Madhavan Srinivasan, Mahesh J
  Salgaonkar, Mahesh Salgaonkar, Masami Hiramatsu, Matt Brown, Matthew
  R. Ochs, Michael Neuling, Naveen N. Rao, Nicholas Piggin, Oliver
  O'Halloran, Pan Xinhui, Paul Mackerras, Rashmica Gupta, Russell
  Currey, Sukadev Bhattiprolu, Thadeu Lima de Souza Cascardo, Tobin C.
  Harding, Tyrel Datwyler, Uma Krishnan, Vaibhav Jain, Vipin K Parashar,
  Yang Shi"

* tag 'powerpc-4.12-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (214 commits)
  powerpc/64s: Power9 has no LPCR[VRMASD] field so don't set it
  powerpc/powernv: Fix TCE kill on NVLink2
  powerpc/mm/radix: Drop support for CPUs without lockless tlbie
  powerpc/book3s/mce: Move add_taint() later in virtual mode
  powerpc/sysfs: Move #ifdef CONFIG_HOTPLUG_CPU out of the function body
  powerpc/smp: Document irq enable/disable after migrating IRQs
  powerpc/mpc52xx: Don't select user-visible RTAS_PROC
  powerpc/powernv: Document cxl dependency on special case in pnv_eeh_reset()
  powerpc/eeh: Clean up and document event handling functions
  powerpc/eeh: Avoid use after free in eeh_handle_special_event()
  cxl: Mask slice error interrupts after first occurrence
  cxl: Route eeh events to all drivers in cxl_pci_error_detected()
  cxl: Force context lock during EEH flow
  powerpc/64: Allow CONFIG_RELOCATABLE if COMPILE_TEST
  powerpc/xmon: Teach xmon oops about radix vectors
  powerpc/mm/hash: Fix off-by-one in comment about kernel contexts ids
  powerpc/pseries: Enable VFIO
  powerpc/powernv: Fix iommu table size calculation hook for small tables
  powerpc/powernv: Check kzalloc() return value in pnv_pci_table_alloc
  powerpc: Add arch/powerpc/tools directory
  ...

1 files changed, 87 insertions, 99 deletions

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 6353019966e6..a9312b52fe6f 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -116,9 +116,11 @@ EXC_VIRT_NONE(0x4000, 0x100)
 
 EXC_REAL_BEGIN(system_reset, 0x100, 0x100)
 	SET_SCRATCH0(r13)
-	GET_PACA(r13)
-	clrrdi	r13,r13,1 /* Last bit of HSPRG0 is set if waking from winkle */
-	EXCEPTION_PROLOG_PSERIES_PACA(PACA_EXGEN, system_reset_common, EXC_STD,
+	/*
+	 * MSR_RI is not enabled, because PACA_EXNMI and nmi stack is
+	 * being used, so a nested NMI exception would corrupt it.
+	 */
+	EXCEPTION_PROLOG_PSERIES_NORI(PACA_EXNMI, system_reset_common, EXC_STD,
 				 IDLETEST, 0x100)
 
 EXC_REAL_END(system_reset, 0x100, 0x100)
@@ -126,34 +128,37 @@ EXC_VIRT_NONE(0x4100, 0x100)
 
 #ifdef CONFIG_PPC_P7_NAP
 EXC_COMMON_BEGIN(system_reset_idle_common)
-BEGIN_FTR_SECTION
-	GET_PACA(r13) /* Restore HSPRG0 to get the winkle bit in r13 */
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
-	bl	pnv_restore_hyp_resource
+	b	pnv_powersave_wakeup
+#endif
 
-	li	r0,PNV_THREAD_RUNNING
-	stb	r0,PACA_THREAD_IDLE_STATE(r13)	/* Clear thread state */
+EXC_COMMON_BEGIN(system_reset_common)
+	/*
+	 * Increment paca->in_nmi then enable MSR_RI. SLB or MCE will be able
+	 * to recover, but nested NMI will notice in_nmi and not recover
+	 * because of the use of the NMI stack. in_nmi reentrancy is tested in
+	 * system_reset_exception.
+	 */
+	lhz	r10,PACA_IN_NMI(r13)
+	addi	r10,r10,1
+	sth	r10,PACA_IN_NMI(r13)
+	li	r10,MSR_RI
+	mtmsrd 	r10,1
 
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-	li	r0,KVM_HWTHREAD_IN_KERNEL
-	stb	r0,HSTATE_HWTHREAD_STATE(r13)
-	/* Order setting hwthread_state vs. testing hwthread_req */
-	sync
-	lbz	r0,HSTATE_HWTHREAD_REQ(r13)
-	cmpwi	r0,0
-	beq	1f
-	BRANCH_TO_KVM(r10, kvm_start_guest)
-1:
-#endif
+	mr	r10,r1
+	ld	r1,PACA_NMI_EMERG_SP(r13)
+	subi	r1,r1,INT_FRAME_SIZE
+	EXCEPTION_COMMON_NORET_STACK(PACA_EXNMI, 0x100,
+			system_reset, system_reset_exception,
+			ADD_NVGPRS;ADD_RECONCILE)
 
-	/* Return SRR1 from power7_nap() */
-	mfspr	r3,SPRN_SRR1
-	blt	cr3,2f
-	b	pnv_wakeup_loss
-2:	b	pnv_wakeup_noloss
-#endif
+	/*
+	 * The stack is no longer in use, decrement in_nmi.
+	 */
+	lhz	r10,PACA_IN_NMI(r13)
+	subi	r10,r10,1
+	sth	r10,PACA_IN_NMI(r13)
 
-EXC_COMMON(system_reset_common, 0x100, system_reset_exception)
+	b	ret_from_except
 
 #ifdef CONFIG_PPC_PSERIES
 /*
@@ -161,8 +166,9 @@ EXC_COMMON(system_reset_common, 0x100, system_reset_exception)
  */
 TRAMP_REAL_BEGIN(system_reset_fwnmi)
 	SET_SCRATCH0(r13)		/* save r13 */
-	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD,
-				 NOTEST, 0x100)
+	/* See comment at system_reset exception */
+	EXCEPTION_PROLOG_PSERIES_NORI(PACA_EXNMI, system_reset_common,
+						EXC_STD, NOTEST, 0x100)
 #endif /* CONFIG_PPC_PSERIES */
 
 
@@ -172,14 +178,6 @@ EXC_REAL_BEGIN(machine_check, 0x200, 0x100)
 	 * vector
 	 */
 	SET_SCRATCH0(r13)		/* save r13 */
-	/*
-	 * Running native on arch 2.06 or later, we may wakeup from winkle
-	 * inside machine check. If yes, then last bit of HSPRG0 would be set
-	 * to 1. Hence clear it unconditionally.
-	 */
-	GET_PACA(r13)
-	clrrdi	r13,r13,1
-	SET_PACA(r13)
 	EXCEPTION_PROLOG_0(PACA_EXMC)
 BEGIN_FTR_SECTION
 	b	machine_check_powernv_early
@@ -212,6 +210,12 @@ BEGIN_FTR_SECTION
 	 * NOTE: We are here with MSR_ME=0 (off), which means we risk a
 	 * checkstop if we get another machine check exception before we do
 	 * rfid with MSR_ME=1.
+	 *
+	 * This interrupt can wake directly from idle. If that is the case,
+	 * the machine check is handled then the idle wakeup code is called
+	 * to restore state. In that case, the POWER9 DD1 idle PACA workaround
+	 * is not applied in the early machine check code, which will cause
+	 * bugs.
 	 */
 	mr	r11,r1			/* Save r1 */
 	lhz	r10,PACA_IN_MCE(r13)
@@ -268,20 +272,11 @@ machine_check_fwnmi:
 machine_check_pSeries_0:
 	EXCEPTION_PROLOG_1(PACA_EXMC, KVMTEST_PR, 0x200)
 	/*
-	 * The following is essentially EXCEPTION_PROLOG_PSERIES_1 with the
-	 * difference that MSR_RI is not enabled, because PACA_EXMC is being
-	 * used, so nested machine check corrupts it. machine_check_common
-	 * enables MSR_RI.
+	 * MSR_RI is not enabled, because PACA_EXMC is being used, so a
+	 * nested machine check corrupts it. machine_check_common enables
+	 * MSR_RI.
 	 */
-	ld	r10,PACAKMSR(r13)
-	xori	r10,r10,MSR_RI
-	mfspr	r11,SPRN_SRR0
-	LOAD_HANDLER(r12, machine_check_common)
-	mtspr	SPRN_SRR0,r12
-	mfspr	r12,SPRN_SRR1
-	mtspr	SPRN_SRR1,r10
-	rfid
-	b	.	/* prevent speculative execution */
+	EXCEPTION_PROLOG_PSERIES_1_NORI(machine_check_common, EXC_STD)
 
 TRAMP_KVM_SKIP(PACA_EXMC, 0x200)
 
@@ -340,6 +335,37 @@ EXC_COMMON_BEGIN(machine_check_common)
 	/* restore original r1. */			\
 	ld	r1,GPR1(r1)
 
+#ifdef CONFIG_PPC_P7_NAP
+/*
+ * This is an idle wakeup. Low level machine check has already been
+ * done. Queue the event then call the idle code to do the wake up.
+ */
+EXC_COMMON_BEGIN(machine_check_idle_common)
+	bl	machine_check_queue_event
+
+	/*
+	 * We have not used any non-volatile GPRs here, and as a rule
+	 * most exception code including machine check does not.
+	 * Therefore PACA_NAPSTATELOST does not need to be set. Idle
+	 * wakeup will restore volatile registers.
+	 *
+	 * Load the original SRR1 into r3 for pnv_powersave_wakeup_mce.
+	 *
+	 * Then decrement MCE nesting after finishing with the stack.
+	 */
+	ld	r3,_MSR(r1)
+
+	lhz	r11,PACA_IN_MCE(r13)
+	subi	r11,r11,1
+	sth	r11,PACA_IN_MCE(r13)
+
+	/* Turn off the RI bit because SRR1 is used by idle wakeup code. */
+	/* Recoverability could be improved by reducing the use of SRR1. */
+	li	r11,0
+	mtmsrd	r11,1
+
+	b	pnv_powersave_wakeup_mce
+#endif
 	/*
 	 * Handle machine check early in real mode. We come here with
 	 * ME=1, MMU (IR=0 and DR=0) off and using MC emergency stack.
@@ -352,6 +378,7 @@ EXC_COMMON_BEGIN(machine_check_handle_early)
 	bl	machine_check_early
 	std	r3,RESULT(r1)	/* Save result */
 	ld	r12,_MSR(r1)
+
 #ifdef	CONFIG_PPC_P7_NAP
 	/*
 	 * Check if thread was in power saving mode. We come here when any
@@ -362,48 +389,14 @@ EXC_COMMON_BEGIN(machine_check_handle_early)
 	 *
 	 * Go back to nap/sleep/winkle mode again if (b) is true.
 	 */
-	rlwinm.	r11,r12,47-31,30,31	/* Was it in power saving mode? */
-	beq	4f			/* No, it wasn;t */
-	/* Thread was in power saving mode. Go back to nap again. */
-	cmpwi	r11,2
-	blt	3f
-	/* Supervisor/Hypervisor state loss */
-	li	r0,1
-	stb	r0,PACA_NAPSTATELOST(r13)
-3:	bl	machine_check_queue_event
-	MACHINE_CHECK_HANDLER_WINDUP
-	GET_PACA(r13)
-	ld	r1,PACAR1(r13)
-	/*
-	 * Check what idle state this CPU was in and go back to same mode
-	 * again.
-	 */
-	lbz	r3,PACA_THREAD_IDLE_STATE(r13)
-	cmpwi	r3,PNV_THREAD_NAP
-	bgt	10f
-	IDLE_STATE_ENTER_SEQ_NORET(PPC_NAP)
-	/* No return */
-10:
-	cmpwi	r3,PNV_THREAD_SLEEP
-	bgt	2f
-	IDLE_STATE_ENTER_SEQ_NORET(PPC_SLEEP)
-	/* No return */
-
-2:
-	/*
-	 * Go back to winkle. Please note that this thread was woken up in
-	 * machine check from winkle and have not restored the per-subcore
-	 * state. Hence before going back to winkle, set last bit of HSPRG0
-	 * to 1. This will make sure that if this thread gets woken up
-	 * again at reset vector 0x100 then it will get chance to restore
-	 * the subcore state.
-	 */
-	ori	r13,r13,1
-	SET_PACA(r13)
-	IDLE_STATE_ENTER_SEQ_NORET(PPC_WINKLE)
-	/* No return */
+	BEGIN_FTR_SECTION
+	rlwinm.	r11,r12,47-31,30,31
+	beq-	4f
+	BRANCH_TO_COMMON(r10, machine_check_idle_common)
 4:
+	END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
 #endif
+
 	/*
 	 * Check if we are coming from hypervisor userspace. If yes then we
 	 * continue in host kernel in V mode to deliver the MC event.
@@ -968,17 +961,12 @@ EXC_VIRT_NONE(0x4e60, 0x20)
 TRAMP_KVM_HV(PACA_EXGEN, 0xe60)
 TRAMP_REAL_BEGIN(hmi_exception_early)
 	EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_HV, 0xe60)
-	mr	r10,r1			/* Save r1			*/
-	ld	r1,PACAEMERGSP(r13)	/* Use emergency stack		*/
+	mr	r10,r1			/* Save r1 */
+	ld	r1,PACAEMERGSP(r13)	/* Use emergency stack for realmode */
 	subi	r1,r1,INT_FRAME_SIZE	/* alloc stack frame		*/
-	std	r9,_CCR(r1)		/* save CR in stackframe	*/
 	mfspr	r11,SPRN_HSRR0		/* Save HSRR0 */
-	std	r11,_NIP(r1)		/* save HSRR0 in stackframe	*/
-	mfspr	r12,SPRN_HSRR1		/* Save SRR1 */
-	std	r12,_MSR(r1)		/* save SRR1 in stackframe	*/
-	std	r10,0(r1)		/* make stack chain pointer	*/
-	std	r0,GPR0(r1)		/* save r0 in stackframe	*/
-	std	r10,GPR1(r1)		/* save r1 in stackframe	*/
+	mfspr	r12,SPRN_HSRR1		/* Save HSRR1 */
+	EXCEPTION_PROLOG_COMMON_1()
 	EXCEPTION_PROLOG_COMMON_2(PACA_EXGEN)
 	EXCEPTION_PROLOG_COMMON_3(0xe60)
 	addi	r3,r1,STACK_FRAME_OVERHEAD