Merge tag 'powerpc-4.19-1' of git://git.kernel.org/pub/scm/linux/kern…

…el/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Notable changes:

   - A fix for a bug in our page table fragment allocator, where a page
     table page could be freed and reallocated for something else while
     still in use, leading to memory corruption etc. The fix reuses
     pt_mm in struct page (x86 only) for a powerpc only refcount.

   - Fixes to our pkey support. Several are user-visible changes, but
     bring us in to line with x86 behaviour and/or fix outright bugs.
     Thanks to Florian Weimer for reporting many of these.

   - A series to improve the hvc driver & related OPAL console code,
     which have been seen to cause hardlockups at times. The hvc driver
     changes in particular have been in linux-next for ~month.

   - Increase our MAX_PHYSMEM_BITS to 128TB when SPARSEMEM_VMEMMAP=y.

   - Remove Power8 DD1 and Power9 DD1 support, neither chip should be in
     use anywhere other than as a paper weight.

   - An optimised memcmp implementation using Power7-or-later VMX
     instructions

   - Support for barrier_nospec on some NXP CPUs.

   - Support for flushing the count cache on context switch on some IBM
     CPUs (controlled by firmware), as a Spectre v2 mitigation.

   - A series to enhance the information we print on unhandled signals
     to bring it into line with other arches, including showing the
     offending VMA and dumping the instructions around the fault.

  Thanks to: Aaro Koskinen, Akshay Adiga, Alastair D'Silva, Alexey
  Kardashevskiy, Alexey Spirkov, Alistair Popple, Andrew Donnellan,
  Aneesh Kumar K.V, Anju T Sudhakar, Arnd Bergmann, Bartosz Golaszewski,
  Benjamin Herrenschmidt, Bharat Bhushan, Bjoern Noetel, Boqun Feng,
  Breno Leitao, Bryant G. Ly, Camelia Groza, Christophe Leroy, Christoph
  Hellwig, Cyril Bur, Dan Carpenter, Daniel Klamt, Darren Stevens, Dave
  Young, David Gibson, Diana Craciun, Finn Thain, Florian Weimer,
  Frederic Barrat, Gautham R. Shenoy, Geert Uytterhoeven, Geoff Levand,
  Guenter Roeck, Gustavo Romero, Haren Myneni, Hari Bathini, Joel
  Stanley, Jonathan Neuschäfer, Kees Cook, Madhavan Srinivasan, Mahesh
  Salgaonkar, Markus Elfring, Mathieu Malaterre, Mauro S. M. Rodrigues,
  Michael Hanselmann, Michael Neuling, Michael Schmitz, Mukesh Ojha,
  Murilo Opsfelder Araujo, Nicholas Piggin, Parth Y Shah, Paul
  Mackerras, Paul Menzel, Ram Pai, Randy Dunlap, Rashmica Gupta, Reza
  Arbab, Rodrigo R. Galvao, Russell Currey, Sam Bobroff, Scott Wood,
  Shilpasri G Bhat, Simon Guo, Souptick Joarder, Stan Johnson, Thiago
  Jung Bauermann, Tyrel Datwyler, Vaibhav Jain, Vasant Hegde, Venkat
  Rao, zhong jiang"

* tag 'powerpc-4.19-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (234 commits)
  powerpc/mm/book3s/radix: Add mapping statistics
  powerpc/uaccess: Enable get_user(u64, *p) on 32-bit
  powerpc/mm/hash: Remove unnecessary do { } while(0) loop
  powerpc/64s: move machine check SLB flushing to mm/slb.c
  powerpc/powernv/idle: Fix build error
  powerpc/mm/tlbflush: update the mmu_gather page size while iterating address range
  powerpc/mm: remove warning about ‘type’ being set
  powerpc/32: Include setup.h header file to fix warnings
  powerpc: Move `path` variable inside DEBUG_PROM
  powerpc/powermac: Make some functions static
  powerpc/powermac: Remove variable x that's never read
  cxl: remove a dead branch
  powerpc/powermac: Add missing include of header pmac.h
  powerpc/kexec: Use common error handling code in setup_new_fdt()
  powerpc/xmon: Add address lookup for percpu symbols
  powerpc/mm: remove huge_pte_offset_and_shift() prototype
  powerpc/lib: Use patch_site to patch copy_32 functions once cache is enabled
  powerpc/pseries: Fix endianness while restoring of r3 in MCE handler.
  powerpc/fadump: merge adjacent memory ranges to reduce PT_LOAD segements
  powerpc/fadump: handle crash memory ranges array index overflow
  ...

Documentation/ABI/testing/ppc-memtrace

@@ -13,10 +13,11 @@ Contact:	[email protected]
 Description:	Write an integer containing the size in bytes of the memory
 		you want removed from each NUMA node to this file - it must be
 		aligned to the memblock size. This amount of RAM will be removed
-		from the kernel mappings and the following debugfs files will be
-		created. This can only be successfully done once per boot. Once
-		memory is successfully removed from each node, the following
-		files are created.
+		from each NUMA node in the kernel mappings and the following
+		debugfs files will be created. Once memory is successfully
+		removed from each node, the following files are created. To
+		re-add memory to the kernel, echo 0 into this file (it will be
+		automatically onlined).
 
 What:		/sys/kernel/debug/powerpc/memtrace/<node-id>
 Date:		Aug 2017

Documentation/admin-guide/kernel-parameters.txt

@@ -2784,6 +2784,10 @@
 			nosmt=force: Force disable SMT, cannot be undone
 				     via the sysfs control file.
 
+	nospectre_v1	[PPC] Disable mitigations for Spectre Variant 1 (bounds
+			check bypass). With this option data leaks are possible
+			in the system.
+
 	nospectre_v2	[X86] Disable all mitigations for the Spectre variant 2
 			(indirect branch prediction) vulnerability. System may
 			allow data leaks with this option, which is equivalent

Documentation/hwmon/ibmpowernv

@@ -33,9 +33,48 @@ fanX_input		Measured RPM value.
 fanX_min		Threshold RPM for alert generation.
 fanX_fault		0: No fail condition
 			1: Failing fan
+
 tempX_input		Measured ambient temperature.
 tempX_max		Threshold ambient temperature for alert generation.
-inX_input		Measured power supply voltage
+tempX_highest		Historical maximum temperature
+tempX_lowest		Historical minimum temperature
+tempX_enable		Enable/disable all temperature sensors belonging to the
+			sub-group. In POWER9, this attribute corresponds to
+			each OCC. Using this attribute each OCC can be asked to
+			disable/enable all of its temperature sensors.
+			1: Enable
+			0: Disable
+
+inX_input		Measured power supply voltage (millivolt)
 inX_fault		0: No fail condition.
 			1: Failing power supply.
-power1_input		System power consumption (microWatt)
+inX_highest		Historical maximum voltage
+inX_lowest		Historical minimum voltage
+inX_enable		Enable/disable all voltage sensors belonging to the
+			sub-group. In POWER9, this attribute corresponds to
+			each OCC. Using this attribute each OCC can be asked to
+			disable/enable all of its voltage sensors.
+			1: Enable
+			0: Disable
+
+powerX_input		Power consumption (microWatt)
+powerX_input_highest	Historical maximum power
+powerX_input_lowest	Historical minimum power
+powerX_enable		Enable/disable all power sensors belonging to the
+			sub-group. In POWER9, this attribute corresponds to
+			each OCC. Using this attribute each OCC can be asked to
+			disable/enable all of its power sensors.
+			1: Enable
+			0: Disable
+
+currX_input		Measured current (milliampere)
+currX_highest		Historical maximum current
+currX_lowest		Historical minimum current
+currX_enable		Enable/disable all current sensors belonging to the
+			sub-group. In POWER9, this attribute corresponds to
+			each OCC. Using this attribute each OCC can be asked to
+			disable/enable all of its current sensors.
+			1: Enable
+			0: Disable
+
+energyX_input		Cumulative energy (microJoule)

Documentation/powerpc/DAWR-POWER9.txt

@@ -0,0 +1,58 @@
+DAWR issues on POWER9
+============================
+
+On POWER9 the DAWR can cause a checkstop if it points to cache
+inhibited (CI) memory. Currently Linux has no way to disinguish CI
+memory when configuring the DAWR, so (for now) the DAWR is disabled by
+this commit:
+
+    commit 9654153158d3e0684a1bdb76dbababdb7111d5a0
+    Author: Michael Neuling <[email protected]>
+    Date:   Tue Mar 27 15:37:24 2018 +1100
+    powerpc: Disable DAWR in the base POWER9 CPU features
+
+Technical Details:
+============================
+
+DAWR has 6 different ways of being set.
+1) ptrace
+2) h_set_mode(DAWR)
+3) h_set_dabr()
+4) kvmppc_set_one_reg()
+5) xmon
+
+For ptrace, we now advertise zero breakpoints on POWER9 via the
+PPC_PTRACE_GETHWDBGINFO call. This results in GDB falling back to
+software emulation of the watchpoint (which is slow).
+
+h_set_mode(DAWR) and h_set_dabr() will now return an error to the
+guest on a POWER9 host. Current Linux guests ignore this error, so
+they will silently not get the DAWR.
+
+kvmppc_set_one_reg() will store the value in the vcpu but won't
+actually set it on POWER9 hardware. This is done so we don't break
+migration from POWER8 to POWER9, at the cost of silently losing the
+DAWR on the migration.
+
+For xmon, the 'bd' command will return an error on P9.
+
+Consequences for users
+============================
+
+For GDB watchpoints (ie 'watch' command) on POWER9 bare metal , GDB
+will accept the command. Unfortunately since there is no hardware
+support for the watchpoint, GDB will software emulate the watchpoint
+making it run very slowly.
+
+The same will also be true for any guests started on a POWER9
+host. The watchpoint will fail and GDB will fall back to software
+emulation.
+
+If a guest is started on a POWER8 host, GDB will accept the watchpoint
+and configure the hardware to use the DAWR. This will run at full
+speed since it can use the hardware emulation. Unfortunately if this
+guest is migrated to a POWER9 host, the watchpoint will be lost on the
+POWER9. Loads and stores to the watchpoint locations will not be
+trapped in GDB. The watchpoint is remembered, so if the guest is
+migrated back to the POWER8 host, it will start working again.
+

Documentation/powerpc/transactional_memory.txt

@@ -198,3 +198,47 @@ presented).  The transaction cannot then be continued and will take the failure
 handler route.  Furthermore, the transactional 2nd register state will be
 inaccessible.  GDB can currently be used on programs using TM, but not sensibly
 in parts within transactions.
+
+POWER9
+======
+
+TM on POWER9 has issues with storing the complete register state. This
+is described in this commit:
+
+    commit 4bb3c7a0208fc13ca70598efd109901a7cd45ae7
+    Author: Paul Mackerras <[email protected]>
+    Date:   Wed Mar 21 21:32:01 2018 +1100
+    KVM: PPC: Book3S HV: Work around transactional memory bugs in POWER9
+
+To account for this different POWER9 chips have TM enabled in
+different ways.
+
+On POWER9N DD2.01 and below, TM is disabled. ie
+HWCAP2[PPC_FEATURE2_HTM] is not set.
+
+On POWER9N DD2.1 TM is configured by firmware to always abort a
+transaction when tm suspend occurs. So tsuspend will cause a
+transaction to be aborted and rolled back. Kernel exceptions will also
+cause the transaction to be aborted and rolled back and the exception
+will not occur. If userspace constructs a sigcontext that enables TM
+suspend, the sigcontext will be rejected by the kernel. This mode is
+advertised to users with HWCAP2[PPC_FEATURE2_HTM_NO_SUSPEND] set.
+HWCAP2[PPC_FEATURE2_HTM] is not set in this mode.
+
+On POWER9N DD2.2 and above, KVM and POWERVM emulate TM for guests (as
+described in commit 4bb3c7a0208f), hence TM is enabled for guests
+ie. HWCAP2[PPC_FEATURE2_HTM] is set for guest userspace. Guests that
+makes heavy use of TM suspend (tsuspend or kernel suspend) will result
+in traps into the hypervisor and hence will suffer a performance
+degradation. Host userspace has TM disabled
+ie. HWCAP2[PPC_FEATURE2_HTM] is not set. (although we make enable it
+at some point in the future if we bring the emulation into host
+userspace context switching).
+
+POWER9C DD1.2 and above are only available with POWERVM and hence
+Linux only runs as a guest. On these systems TM is emulated like on
+POWER9N DD2.2.
+
+Guest migration from POWER8 to POWER9 will work with POWER9N DD2.2 and
+POWER9C DD1.2. Since earlier POWER9 processors don't support TM
+emulation, migration from POWER8 to POWER9 is not supported there.

MAINTAINERS

@@ -813,11 +813,6 @@ S:	Supported
 F:	drivers/net/ethernet/amd/xgbe/
 F:	arch/arm64/boot/dts/amd/amd-seattle-xgbe*.dtsi
 
-AMS (Apple Motion Sensor) DRIVER
-M:	Michael Hanselmann <[email protected]>
-S:	Supported
-F:	drivers/macintosh/ams/
-
 ANALOG DEVICES INC AD5686 DRIVER
 M:	Stefan Popa <[email protected]>
 L:	[email protected]

arch/m68k/configs/mac_defconfig

@@ -366,7 +366,7 @@ CONFIG_TCM_PSCSI=m
 CONFIG_ADB=y
 CONFIG_ADB_MACII=y
 CONFIG_ADB_IOP=y
-CONFIG_ADB_PMU68K=y
+CONFIG_ADB_PMU=y
 CONFIG_ADB_CUDA=y
 CONFIG_INPUT_ADBHID=y
 CONFIG_MAC_EMUMOUSEBTN=y

arch/m68k/configs/multi_defconfig

@@ -400,7 +400,7 @@ CONFIG_TCM_PSCSI=m
 CONFIG_ADB=y
 CONFIG_ADB_MACII=y
 CONFIG_ADB_IOP=y
-CONFIG_ADB_PMU68K=y
+CONFIG_ADB_PMU=y
 CONFIG_ADB_CUDA=y
 CONFIG_INPUT_ADBHID=y
 CONFIG_MAC_EMUMOUSEBTN=y

arch/m68k/mac/config.c

@@ -889,7 +889,7 @@ static void __init mac_identify(void)
 #ifdef CONFIG_ADB_CUDA
 	find_via_cuda();
 #endif
-#ifdef CONFIG_ADB_PMU68K
+#ifdef CONFIG_ADB_PMU
 	find_via_pmu();
 #endif
 }

arch/m68k/mac/misc.c

@@ -90,7 +90,7 @@ static void cuda_write_pram(int offset, __u8 data)
 }
 #endif /* CONFIG_ADB_CUDA */
 
-#ifdef CONFIG_ADB_PMU68K
+#ifdef CONFIG_ADB_PMU
 static time64_t pmu_read_time(void)
 {
 	struct adb_request req;
@@ -142,7 +142,7 @@ static void pmu_write_pram(int offset, __u8 data)
 	while (!req.complete)
 		pmu_poll();
 }
-#endif /* CONFIG_ADB_PMU68K */
+#endif /* CONFIG_ADB_PMU */
 
 /*
  * VIA PRAM/RTC access routines
@@ -373,38 +373,6 @@ static void cuda_shutdown(void)
 }
 #endif /* CONFIG_ADB_CUDA */
 
-#ifdef CONFIG_ADB_PMU68K
-
-void pmu_restart(void)
-{
-	struct adb_request req;
-	if (pmu_request(&req, NULL,
-			2, PMU_SET_INTR_MASK, PMU_INT_ADB|PMU_INT_TICK) < 0)
-		return;
-	while (!req.complete)
-		pmu_poll();
-	if (pmu_request(&req, NULL, 1, PMU_RESET) < 0)
-		return;
-	while (!req.complete)
-		pmu_poll();
-}
-
-void pmu_shutdown(void)
-{
-	struct adb_request req;
-	if (pmu_request(&req, NULL,
-			2, PMU_SET_INTR_MASK, PMU_INT_ADB|PMU_INT_TICK) < 0)
-		return;
-	while (!req.complete)
-		pmu_poll();
-	if (pmu_request(&req, NULL, 5, PMU_SHUTDOWN, 'M', 'A', 'T', 'T') < 0)
-		return;
-	while (!req.complete)
-		pmu_poll();
-}
-
-#endif
-
 /*
  *-------------------------------------------------------------------
  * Below this point are the generic routines; they'll dispatch to the
@@ -429,7 +397,7 @@ void mac_pram_read(int offset, __u8 *buffer, int len)
 		func = cuda_read_pram;
 		break;
 #endif
-#ifdef CONFIG_ADB_PMU68K
+#ifdef CONFIG_ADB_PMU
 	case MAC_ADB_PB2:
 		func = pmu_read_pram;
 		break;
@@ -459,7 +427,7 @@ void mac_pram_write(int offset, __u8 *buffer, int len)
 		func = cuda_write_pram;
 		break;
 #endif
-#ifdef CONFIG_ADB_PMU68K
+#ifdef CONFIG_ADB_PMU
 	case MAC_ADB_PB2:
 		func = pmu_write_pram;
 		break;
@@ -483,9 +451,8 @@ void mac_poweroff(void)
 	           macintosh_config->adb_type == MAC_ADB_CUDA) {
 		cuda_shutdown();
 #endif
-#ifdef CONFIG_ADB_PMU68K
-	} else if (macintosh_config->adb_type == MAC_ADB_PB1
-		|| macintosh_config->adb_type == MAC_ADB_PB2) {
+#ifdef CONFIG_ADB_PMU
+	} else if (macintosh_config->adb_type == MAC_ADB_PB2) {
 		pmu_shutdown();
 #endif
 	}
@@ -525,9 +492,8 @@ void mac_reset(void)
 	           macintosh_config->adb_type == MAC_ADB_CUDA) {
 		cuda_restart();
 #endif
-#ifdef CONFIG_ADB_PMU68K
-	} else if (macintosh_config->adb_type == MAC_ADB_PB1
-		|| macintosh_config->adb_type == MAC_ADB_PB2) {
+#ifdef CONFIG_ADB_PMU
+	} else if (macintosh_config->adb_type == MAC_ADB_PB2) {
 		pmu_restart();
 #endif
 	} else if (CPU_IS_030) {
@@ -680,7 +646,7 @@ int mac_hwclk(int op, struct rtc_time *t)
 			now = cuda_read_time();
 			break;
 #endif
-#ifdef CONFIG_ADB_PMU68K
+#ifdef CONFIG_ADB_PMU
 		case MAC_ADB_PB2:
 			now = pmu_read_time();
 			break;
@@ -716,7 +682,7 @@ int mac_hwclk(int op, struct rtc_time *t)
 			cuda_write_time(now);
 			break;
 #endif
-#ifdef CONFIG_ADB_PMU68K
+#ifdef CONFIG_ADB_PMU
 		case MAC_ADB_PB2:
 			pmu_write_time(now);
 			break;

arch/powerpc/Kconfig

@@ -165,7 +165,7 @@ config PPC
 	select GENERIC_CLOCKEVENTS_BROADCAST	if SMP
 	select GENERIC_CMOS_UPDATE
 	select GENERIC_CPU_AUTOPROBE
-	select GENERIC_CPU_VULNERABILITIES	if PPC_BOOK3S_64
+	select GENERIC_CPU_VULNERABILITIES	if PPC_BARRIER_NOSPEC
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_SHOW_LEVEL
 	select GENERIC_SMP_IDLE_THREAD
@@ -197,6 +197,7 @@ config PPC
 	select HAVE_IOREMAP_PROT
 	select HAVE_IRQ_EXIT_ON_IRQ_STACK
 	select HAVE_KERNEL_GZIP
+	select HAVE_KERNEL_XZ			if PPC_BOOK3S
 	select HAVE_KPROBES
 	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_KRETPROBES
@@ -225,6 +226,7 @@ config PPC
 	select IRQ_DOMAIN
 	select IRQ_FORCED_THREADING
 	select MODULES_USE_ELF_RELA
+	select NEED_DMA_MAP_STATE		if PPC64 || NOT_COHERENT_CACHE
 	select NEED_SG_DMA_LENGTH
 	select NO_BOOTMEM
 	select OF
@@ -240,6 +242,11 @@ config PPC
 	# Please keep this list sorted alphabetically.
 	#
 
+config PPC_BARRIER_NOSPEC
+    bool
+    default y
+    depends on PPC_BOOK3S_64 || PPC_FSL_BOOK3E
+
 config GENERIC_CSUM
 	def_bool n
 
@@ -876,9 +883,6 @@ config ZONE_DMA
 	bool
 	default y
 
-config NEED_DMA_MAP_STATE
-	def_bool (PPC64 || NOT_COHERENT_CACHE)
-
 config GENERIC_ISA_DMA
 	bool
 	depends on ISA_DMA_API