powerpc fixes for 4.13 #5

Fixes for recently merged code:
  - a fix for the _PAGE_DEVMAP support, which was breaking KVM on Power9 radix
  - avoid a (harmless) lockdep warning in the early SMP code
  - return failure for some uses of dma_set_mask() rather than falling back to 32-bits
  - fix stack setup in watchdog soft_nmi_common() to use emergency stack
  - fix of_irq_to_resource() error check in of_fsl_spi_probe()
 
 Two fixes going to stable:
  - fix saving of Transactional Memory SPRs in core dump
  - fix __check_irq_replay missing decrementer interrupt
 
 And two misc:
  - fix 64-bit boot wrapper build with non-biarch compiler
  - work around a POWER9 PMU hang after state-loss idle
 
 Thanks to:
   Alistair Popple, Aneesh Kumar K.V, Cyril Bur, Gustavo Romero, Jose Ricardo
   Ziviani, Laurent Vivier, Nicholas Piggin, Oliver O'Halloran, Sergei Shtylyov,
   Suraj Jitindar Singh, Thomas Gleixner.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQIcBAABAgAGBQJZhEH/AAoJEFHr6jzI4aWA8GoP+wdtaBYZIElFMnPay/BY8lSQ
 MODF6FlaexdNuVFo5In2BnMAs12bIXDO69wMziqc+uZIA+vI3K7lqsi+8p1R38Ts
 FG5OFLzX/gx1ykoeDe0mC8GPUHGVBdMr6+rHzt/9M7PrQWApCoBJLakYIElOrN5B
 EiAxunwJQISKNQYYmyVhjMVFq8ydMHSgtR7JVDHTh1AoStaO9M5hoJegD4Dnytaf
 F0/0Y5U+NGGWwPIyDrjB4wE9L8NCk0JfvpBhjORMkFSpAOe4VhxZrAGDyaCzVKVh
 YkxSirVKuVwEmvV2prmq4SAJi61EMUEPx2WL7hRN3ol/dF+2lU9nl2lyL3yRnGPY
 9mtNHur07qoMqyXI8750ayTzbMG75aakJF2be9G+zwNc3Sw8dqJvs2PwpSVdnima
 jWmWnRikws4qmEOEBV6nxtWf8qYACHevyK7YzIHDU8SVXLjAkX/u6LZGHAfTQ8Xo
 jYcISpiA2ko8YnMR7yy9FZqs4KGqeOotMamgJRGUcSY/9Xn8WDIrtQ4tIuJtGjzW
 XFOFafZOzyt6s1dNz01C4hzP60J+/CxPNRxx6zWnbijY6puADu/Mv1g+ai3nYdKA
 e/CYt6O8tzooFHCHtVLUPgWA82heDwNtjmlnSikWTdT07KLRhP+0w9Qq8gBzztKT
 7B/vPMjCMPQaJrrnj6GX
 =Rdy8
 -----END PGP SIGNATURE-----

Merge tag 'powerpc-4.13-5' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fixes from Michael Ellerman:
 "Fixes for recently merged code:
   - a fix for the _PAGE_DEVMAP support, which was breaking KVM on
     Power9 radix
   - avoid a (harmless) lockdep warning in the early SMP code
   - return failure for some uses of dma_set_mask() rather than falling
     back to 32-bits
   - fix stack setup in watchdog soft_nmi_common() to use emergency
     stack
   - fix of_irq_to_resource() error check in of_fsl_spi_probe()

  Two fixes going to stable:
   - fix saving of Transactional Memory SPRs in core dump
   - fix __check_irq_replay missing decrementer interrupt

  And two misc:
   - fix 64-bit boot wrapper build with non-biarch compiler
   - work around a POWER9 PMU hang after state-loss idle

  Thanks to: Alistair Popple, Aneesh Kumar K.V, Cyril Bur, Gustavo
  Romero, Jose Ricardo Ziviani, Laurent Vivier, Nicholas Piggin, Oliver
  O'Halloran, Sergei Shtylyov, Suraj Jitindar Singh, Thomas Gleixner"

* tag 'powerpc-4.13-5' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  powerpc/64: Fix __check_irq_replay missing decrementer interrupt
  powerpc/perf: POWER9 PMU stops after idle workaround
  powerpc/83xx/mpc832x_rdb: fix of_irq_to_resource() error check
  powerpc/64s: Fix stack setup in watchdog soft_nmi_common()
  powerpc/powernv/pci: Return failure for some uses of dma_set_mask()
  powerpc/boot: Fix 64-bit boot wrapper build with non-biarch compiler
  powerpc/smp: Call smp_ops->setup_cpu() directly on the boot CPU
  powerpc/tm: Fix saving of TM SPRs in core dump
  powerpc/mm: Fix pmd/pte_devmap() on non-leaf entries

arch/powerpc/boot/Makefile

@@ -25,12 +25,20 @@ compress-$(CONFIG_KERNEL_XZ)   := CONFIG_KERNEL_XZ
 BOOTCFLAGS    := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
 		 -fno-strict-aliasing -Os -msoft-float -pipe \
 		 -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \
-		 -isystem $(shell $(CROSS32CC) -print-file-name=include) \
 		 -D$(compress-y)
 
+BOOTCC := $(CC)
 ifdef CONFIG_PPC64_BOOT_WRAPPER
 BOOTCFLAGS	+= -m64
+else
+BOOTCFLAGS	+= -m32
+ifdef CROSS32_COMPILE
+    BOOTCC := $(CROSS32_COMPILE)gcc
 endif
+endif
+
+BOOTCFLAGS	+= -isystem $(shell $(BOOTCC) -print-file-name=include)
+
 ifdef CONFIG_CPU_BIG_ENDIAN
 BOOTCFLAGS	+= -mbig-endian
 else
@@ -183,10 +191,10 @@ clean-files := $(zlib-) $(zlibheader-) $(zliblinuxheader-) \
 		empty.c zImage.coff.lds zImage.ps3.lds zImage.lds
 
 quiet_cmd_bootcc = BOOTCC  $@
-      cmd_bootcc = $(CROSS32CC) -Wp,-MD,$(depfile) $(BOOTCFLAGS) -c -o $@ $<
+      cmd_bootcc = $(BOOTCC) -Wp,-MD,$(depfile) $(BOOTCFLAGS) -c -o $@ $<
 
 quiet_cmd_bootas = BOOTAS  $@
-      cmd_bootas = $(CROSS32CC) -Wp,-MD,$(depfile) $(BOOTAFLAGS) -c -o $@ $<
+      cmd_bootas = $(BOOTCC) -Wp,-MD,$(depfile) $(BOOTAFLAGS) -c -o $@ $<
 
 quiet_cmd_bootar = BOOTAR  $@
       cmd_bootar = $(CROSS32AR) -cr$(KBUILD_ARFLAGS) $@.$$$$ $(filter-out FORCE,$^); mv $@.$$$$ $@

arch/powerpc/include/asm/book3s/64/pgtable.h

@@ -608,9 +608,17 @@ static inline pte_t pte_mkdevmap(pte_t pte)
 	return __pte(pte_val(pte) | _PAGE_SPECIAL|_PAGE_DEVMAP);
 }
 
+/*
+ * This is potentially called with a pmd as the argument, in which case it's not
+ * safe to check _PAGE_DEVMAP unless we also confirm that _PAGE_PTE is set.
+ * That's because the bit we use for _PAGE_DEVMAP is not reserved for software
+ * use in page directory entries (ie. non-ptes).
+ */
 static inline int pte_devmap(pte_t pte)
 {
-	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_DEVMAP));
+	u64 mask = cpu_to_be64(_PAGE_DEVMAP | _PAGE_PTE);
+
+	return (pte_raw(pte) & mask) == mask;
 }
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)

arch/powerpc/kernel/exceptions-64s.S

@@ -1325,10 +1325,18 @@ EXC_VIRT_NONE(0x5800, 0x100)
 	std	r10,PACA_EXGEN+EX_R13(r13);		\
 	EXCEPTION_PROLOG_PSERIES_1(soft_nmi_common, _H)
 
+/*
+ * Branch to soft_nmi_interrupt using the emergency stack. The emergency
+ * stack is one that is usable by maskable interrupts so long as MSR_EE
+ * remains off. It is used for recovery when something has corrupted the
+ * normal kernel stack, for example. The "soft NMI" must not use the process
+ * stack because we want irq disabled sections to avoid touching the stack
+ * at all (other than PMU interrupts), so use the emergency stack for this,
+ * and run it entirely with interrupts hard disabled.
+ */
 EXC_COMMON_BEGIN(soft_nmi_common)
 	mr	r10,r1
 	ld	r1,PACAEMERGSP(r13)
-	ld	r1,PACA_NMI_EMERG_SP(r13)
 	subi	r1,r1,INT_FRAME_SIZE
 	EXCEPTION_COMMON_NORET_STACK(PACA_EXGEN, 0x900,
 			system_reset, soft_nmi_interrupt,

arch/powerpc/kernel/idle_book3s.S

@@ -460,11 +460,17 @@ pnv_restore_hyp_resource_arch300:
 	/*
 	 * Workaround for POWER9, if we lost resources, the ERAT
 	 * might have been mixed up and needs flushing. We also need
-	 * to reload MMCR0 (see comment above).
+	 * to reload MMCR0 (see comment above). We also need to set
+	 * then clear bit 60 in MMCRA to ensure the PMU starts running.
 	 */
 	blt	cr3,1f
 	PPC_INVALIDATE_ERAT
 	ld	r1,PACAR1(r13)
+	mfspr	r4,SPRN_MMCRA
+	ori	r4,r4,(1 << (63-60))
+	mtspr	SPRN_MMCRA,r4
+	xori	r4,r4,(1 << (63-60))
+	mtspr	SPRN_MMCRA,r4
 	ld	r4,_MMCR0(r1)
 	mtspr	SPRN_MMCR0,r4
 1:

arch/powerpc/kernel/irq.c

@@ -145,6 +145,19 @@ notrace unsigned int __check_irq_replay(void)
 
 	/* Clear bit 0 which we wouldn't clear otherwise */
 	local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
+	if (happened & PACA_IRQ_HARD_DIS) {
+		/*
+		 * We may have missed a decrementer interrupt if hard disabled.
+		 * Check the decrementer register in case we had a rollover
+		 * while hard disabled.
+		 */
+		if (!(happened & PACA_IRQ_DEC)) {
+			if (decrementer_check_overflow()) {
+				local_paca->irq_happened |= PACA_IRQ_DEC;
+				happened |= PACA_IRQ_DEC;
+			}
+		}
+	}
 
 	/*
 	 * Force the delivery of pending soft-disabled interrupts on PS3.
@@ -170,7 +183,7 @@ notrace unsigned int __check_irq_replay(void)
 	 * in case we also had a rollover while hard disabled
 	 */
 	local_paca->irq_happened &= ~PACA_IRQ_DEC;
-	if ((happened & PACA_IRQ_DEC) || decrementer_check_overflow())
+	if (happened & PACA_IRQ_DEC)
 		return 0x900;
 
 	/* Finally check if an external interrupt happened */

arch/powerpc/kernel/ptrace.c

@@ -127,12 +127,19 @@ static void flush_tmregs_to_thread(struct task_struct *tsk)
 	 * If task is not current, it will have been flushed already to
 	 * it's thread_struct during __switch_to().
 	 *
-	 * A reclaim flushes ALL the state.
+	 * A reclaim flushes ALL the state or if not in TM save TM SPRs
+	 * in the appropriate thread structures from live.
 	 */
 
-	if (tsk == current && MSR_TM_SUSPENDED(mfmsr()))
-		tm_reclaim_current(TM_CAUSE_SIGNAL);
+	if (tsk != current)
+		return;
 
+	if (MSR_TM_SUSPENDED(mfmsr())) {
+		tm_reclaim_current(TM_CAUSE_SIGNAL);
+	} else {
+		tm_enable();
+		tm_save_sprs(&(tsk->thread));
+	}
 }
 #else
 static inline void flush_tmregs_to_thread(struct task_struct *tsk) { }

arch/powerpc/kernel/smp.c

@@ -1003,21 +1003,13 @@ static struct sched_domain_topology_level powerpc_topology[] = {
 	{ NULL, },
 };
 
-static __init long smp_setup_cpu_workfn(void *data __always_unused)
-{
-	smp_ops->setup_cpu(boot_cpuid);
-	return 0;
-}
-
 void __init smp_cpus_done(unsigned int max_cpus)
 {
 	/*
-	 * We want the setup_cpu() here to be called on the boot CPU, but
-	 * init might run on any CPU, so make sure it's invoked on the boot
-	 * CPU.
+	 * We are running pinned to the boot CPU, see rest_init().
 	 */
 	if (smp_ops && smp_ops->setup_cpu)
-		work_on_cpu_safe(boot_cpuid, smp_setup_cpu_workfn, NULL);
+		smp_ops->setup_cpu(boot_cpuid);
 
 	if (smp_ops && smp_ops->bringup_done)
 		smp_ops->bringup_done();

arch/powerpc/platforms/83xx/mpc832x_rdb.c

@@ -89,7 +89,7 @@ static int __init of_fsl_spi_probe(char *type, char *compatible, u32 sysclk,
 			goto err;
 
 		ret = of_irq_to_resource(np, 0, &res[1]);
-		if (!ret)
+		if (ret <= 0)
 			goto err;
 
 		pdev = platform_device_alloc("mpc83xx_spi", i);

arch/powerpc/platforms/powernv/pci-ioda.c

@@ -1852,6 +1852,14 @@ static int pnv_pci_ioda_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
 			/* 4GB offset bypasses 32-bit space */
 			set_dma_offset(&pdev->dev, (1ULL << 32));
 			set_dma_ops(&pdev->dev, &dma_direct_ops);
+		} else if (dma_mask >> 32 && dma_mask != DMA_BIT_MASK(64)) {
+			/*
+			 * Fail the request if a DMA mask between 32 and 64 bits
+			 * was requested but couldn't be fulfilled. Ideally we
+			 * would do this for 64-bits but historically we have
+			 * always fallen back to 32-bits.
+			 */
+			return -ENOMEM;
 		} else {
 			dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n");
 			set_dma_ops(&pdev->dev, &dma_iommu_ops);