Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel…

…/git/mpe/linux

Pull more powerpc updates from Michael Ellerman:
 "Here's some more updates for powerpc for 3.18.

  They are a bit late I know, though must are actually bug fixes.  In my
  defence I nearly cut the top of my finger off last weekend in a
  gruesome bike maintenance accident, so I spent a good part of the week
  waiting around for doctors.  True story, I can send photos if you like :)

  Probably the most interesting fix is the sys_call_table one, which
  enables syscall tracing for powerpc.  There's a fix for HMI handling
  for old firmware, more endian fixes for firmware interfaces, more EEH
  fixes, Anton fixed our routine that gets the current stack pointer,
  and a few other misc bits"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux: (22 commits)
  powerpc: Only do dynamic DMA zone limits on platforms that need it
  powerpc: sync pseries_le_defconfig with pseries_defconfig
  powerpc: Add printk levels to setup_system output
  powerpc/vphn: NUMA node code expects big-endian
  powerpc/msi: Use WARN_ON() in msi bitmap selftests
  powerpc/msi: Fix the msi bitmap alignment tests
  powerpc/eeh: Block CFG upon frozen Shiner adapter
  powerpc/eeh: Don't collect logs on PE with blocked config space
  powerpc/eeh: Block PCI config access upon frozen PE
  powerpc/pseries: Drop config requests in EEH accessors
  powerpc/powernv: Drop config requests in EEH accessors
  powerpc/eeh: Rename flag EEH_PE_RESET to EEH_PE_CFG_BLOCKED
  powerpc/eeh: Fix condition for isolated state
  powerpc/pseries: Make CPU hotplug path endian safe
  powerpc/pseries: Use dump_stack instead of show_stack
  powerpc: Rename __get_SP() to current_stack_pointer()
  powerpc: Reimplement __get_SP() as a function not a define
  powerpc/numa: Add ability to disable and debug topology updates
  powerpc/numa: check error return from proc_create
  powerpc/powernv: Fallback to old HMI handling behavior for old firmware
  ...

Documentation/kernel-parameters.txt

@@ -3465,6 +3465,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			e.g. base its process migration decisions on it.
 			Default is on.
 
+	topology_updates= [KNL, PPC, NUMA]
+			Format: {off}
+			Specify if the kernel should ignore (off)
+			topology updates sent by the hypervisor to this
+			LPAR.
+
 	tp720=		[HW,PS2]
 
 	tpm_suspend_pcr=[HW,TPM]

arch/powerpc/configs/pseries_le_defconfig

@@ -48,7 +48,6 @@ CONFIG_KEXEC=y
 CONFIG_IRQ_ALL_CPUS=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
-CONFIG_CMA=y
 CONFIG_PPC_64K_PAGES=y
 CONFIG_PPC_SUBPAGE_PROT=y
 CONFIG_SCHED_SMT=y
@@ -138,6 +137,7 @@ CONFIG_NETCONSOLE=y
 CONFIG_NETPOLL_TRAP=y
 CONFIG_TUN=m
 CONFIG_VIRTIO_NET=m
+CONFIG_VHOST_NET=m
 CONFIG_VORTEX=y
 CONFIG_ACENIC=m
 CONFIG_ACENIC_OMIT_TIGON_I=y
@@ -303,4 +303,9 @@ CONFIG_CRYPTO_LZO=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_DEV_NX=y
 CONFIG_CRYPTO_DEV_NX_ENCRYPT=m
+CONFIG_VIRTUALIZATION=y
+CONFIG_KVM_BOOK3S_64=m
+CONFIG_KVM_BOOK3S_64_HV=y
+CONFIG_TRANSPARENT_HUGEPAGE=y
+CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS=y
 CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y

arch/powerpc/include/asm/eeh.h

@@ -71,9 +71,10 @@ struct device_node;
 
 #define EEH_PE_ISOLATED		(1 << 0)	/* Isolated PE		*/
 #define EEH_PE_RECOVERING	(1 << 1)	/* Recovering PE	*/
-#define EEH_PE_RESET		(1 << 2)	/* PE reset in progress	*/
+#define EEH_PE_CFG_BLOCKED	(1 << 2)	/* Block config access	*/
 
 #define EEH_PE_KEEP		(1 << 8)	/* Keep PE on hotplug	*/
+#define EEH_PE_CFG_RESTRICTED	(1 << 9)	/* Block config on error */
 
 struct eeh_pe {
 	int type;			/* PE type: PHB/Bus/Device	*/

arch/powerpc/include/asm/perf_event.h

@@ -34,7 +34,7 @@
 	do {							\
 		(regs)->result = 0;				\
 		(regs)->nip = __ip;				\
-		(regs)->gpr[1] = *(unsigned long *)__get_SP();	\
+		(regs)->gpr[1] = current_stack_pointer();	\
 		asm volatile("mfmsr %0" : "=r" ((regs)->msr));	\
 	} while (0)
 #endif

arch/powerpc/include/asm/reg.h

@@ -1265,8 +1265,7 @@ static inline unsigned long mfvtb (void)
 
 #define proc_trap()	asm volatile("trap")
 
-#define __get_SP()	({unsigned long sp; \
-			asm volatile("mr %0,1": "=r" (sp)); sp;})
+extern unsigned long current_stack_pointer(void);
 
 extern unsigned long scom970_read(unsigned int address);
 extern void scom970_write(unsigned int address, unsigned long value);

arch/powerpc/include/asm/syscall.h

@@ -19,7 +19,7 @@
 
 /* ftrace syscalls requires exporting the sys_call_table */
 #ifdef CONFIG_FTRACE_SYSCALLS
-extern const unsigned long *sys_call_table;
+extern const unsigned long sys_call_table[];
 #endif /* CONFIG_FTRACE_SYSCALLS */
 
 static inline long syscall_get_nr(struct task_struct *task,

arch/powerpc/kernel/dma.c

@@ -53,9 +53,16 @@ void *dma_direct_alloc_coherent(struct device *dev, size_t size,
 #else
 	struct page *page;
 	int node = dev_to_node(dev);
+#ifdef CONFIG_FSL_SOC
 	u64 pfn = get_pfn_limit(dev);
 	int zone;
 
+	/*
+	 * This code should be OK on other platforms, but we have drivers that
+	 * don't set coherent_dma_mask. As a workaround we just ifdef it. This
+	 * whole routine needs some serious cleanup.
+	 */
+
 	zone = dma_pfn_limit_to_zone(pfn);
 	if (zone < 0) {
 		dev_err(dev, "%s: No suitable zone for pfn %#llx\n",
@@ -73,6 +80,7 @@ void *dma_direct_alloc_coherent(struct device *dev, size_t size,
 		break;
 #endif
 	};
+#endif /* CONFIG_FSL_SOC */
 
 	/* ignore region specifiers */
 	flag  &= ~(__GFP_HIGHMEM);

arch/powerpc/kernel/eeh.c

@@ -257,6 +257,13 @@ static void *eeh_dump_pe_log(void *data, void *flag)
 	struct eeh_dev *edev, *tmp;
 	size_t *plen = flag;
 
+	/* If the PE's config space is blocked, 0xFF's will be
+	 * returned. It's pointless to collect the log in this
+	 * case.
+	 */
+	if (pe->state & EEH_PE_CFG_BLOCKED)
+		return NULL;
+
 	eeh_pe_for_each_dev(pe, edev, tmp)
 		*plen += eeh_dump_dev_log(edev, pci_regs_buf + *plen,
 					  EEH_PCI_REGS_LOG_LEN - *plen);
@@ -673,18 +680,18 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat
 	switch (state) {
 	case pcie_deassert_reset:
 		eeh_ops->reset(pe, EEH_RESET_DEACTIVATE);
-		eeh_pe_state_clear(pe, EEH_PE_RESET);
+		eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
 		break;
 	case pcie_hot_reset:
-		eeh_pe_state_mark(pe, EEH_PE_RESET);
+		eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
 		eeh_ops->reset(pe, EEH_RESET_HOT);
 		break;
 	case pcie_warm_reset:
-		eeh_pe_state_mark(pe, EEH_PE_RESET);
+		eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
 		eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL);
 		break;
 	default:
-		eeh_pe_state_clear(pe, EEH_PE_RESET);
+		eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
 		return -EINVAL;
 	};
 
@@ -1523,7 +1530,7 @@ int eeh_pe_reset(struct eeh_pe *pe, int option)
 	switch (option) {
 	case EEH_RESET_DEACTIVATE:
 		ret = eeh_ops->reset(pe, option);
-		eeh_pe_state_clear(pe, EEH_PE_RESET);
+		eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
 		if (ret)
 			break;
 
@@ -1538,7 +1545,7 @@ int eeh_pe_reset(struct eeh_pe *pe, int option)
 		 */
 		eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE);
 
-		eeh_pe_state_mark(pe, EEH_PE_RESET);
+		eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
 		ret = eeh_ops->reset(pe, option);
 		break;
 	default:

arch/powerpc/kernel/eeh_driver.c

@@ -528,13 +528,13 @@ int eeh_pe_reset_and_recover(struct eeh_pe *pe)
 	eeh_pe_dev_traverse(pe, eeh_report_error, &result);
 
 	/* Issue reset */
-	eeh_pe_state_mark(pe, EEH_PE_RESET);
+	eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
 	ret = eeh_reset_pe(pe);
 	if (ret) {
-		eeh_pe_state_clear(pe, EEH_PE_RECOVERING | EEH_PE_RESET);
+		eeh_pe_state_clear(pe, EEH_PE_RECOVERING | EEH_PE_CFG_BLOCKED);
 		return ret;
 	}
-	eeh_pe_state_clear(pe, EEH_PE_RESET);
+	eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
 
 	/* Unfreeze the PE */
 	ret = eeh_clear_pe_frozen_state(pe, true);
@@ -601,10 +601,10 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 	 * config accesses. So we prefer to block them. However, controlled
 	 * PCI config accesses initiated from EEH itself are allowed.
 	 */
-	eeh_pe_state_mark(pe, EEH_PE_RESET);
+	eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
 	rc = eeh_reset_pe(pe);
 	if (rc) {
-		eeh_pe_state_clear(pe, EEH_PE_RESET);
+		eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
 		return rc;
 	}
 
@@ -613,7 +613,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 	/* Restore PE */
 	eeh_ops->configure_bridge(pe);
 	eeh_pe_restore_bars(pe);
-	eeh_pe_state_clear(pe, EEH_PE_RESET);
+	eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
 
 	/* Clear frozen state */
 	rc = eeh_clear_pe_frozen_state(pe, false);

arch/powerpc/kernel/eeh_pe.c

@@ -525,7 +525,7 @@ static void *__eeh_pe_state_mark(void *data, void *flag)
 	pe->state |= state;
 
 	/* Offline PCI devices if applicable */
-	if (state != EEH_PE_ISOLATED)
+	if (!(state & EEH_PE_ISOLATED))
 		return NULL;
 
 	eeh_pe_for_each_dev(pe, edev, tmp) {
@@ -534,6 +534,10 @@ static void *__eeh_pe_state_mark(void *data, void *flag)
 			pdev->error_state = pci_channel_io_frozen;
 	}
 
+	/* Block PCI config access if required */
+	if (pe->state & EEH_PE_CFG_RESTRICTED)
+		pe->state |= EEH_PE_CFG_BLOCKED;
+
 	return NULL;
 }
 
@@ -611,6 +615,10 @@ static void *__eeh_pe_state_clear(void *data, void *flag)
 		pdev->error_state = pci_channel_io_normal;
 	}
 
+	/* Unblock PCI config access if required */
+	if (pe->state & EEH_PE_CFG_RESTRICTED)
+		pe->state &= ~EEH_PE_CFG_BLOCKED;
+
 	return NULL;
 }
 

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

@@ -1270,11 +1270,6 @@ hmi_exception_early:
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	hmi_exception_realmode
 	/* Windup the stack. */
-	/* Clear MSR_RI before setting SRR0 and SRR1. */
-	li	r0,MSR_RI
-	mfmsr	r9			/* get MSR value */
-	andc	r9,r9,r0
-	mtmsrd	r9,1			/* Clear MSR_RI */
 	/* Move original HSRR0 and HSRR1 into the respective regs */
 	ld	r9,_MSR(r1)
 	mtspr	SPRN_HSRR1,r9

arch/powerpc/kernel/irq.c

@@ -466,7 +466,7 @@ static inline void check_stack_overflow(void)
 #ifdef CONFIG_DEBUG_STACKOVERFLOW
 	long sp;
 
-	sp = __get_SP() & (THREAD_SIZE-1);
+	sp = current_stack_pointer() & (THREAD_SIZE-1);
 
 	/* check for stack overflow: is there less than 2KB free? */
 	if (unlikely(sp < (sizeof(struct thread_info) + 2048))) {

arch/powerpc/kernel/misc.S

@@ -114,3 +114,7 @@ _GLOBAL(longjmp)
 	mtlr	r0
 	mr	r3,r4
 	blr
+
+_GLOBAL(current_stack_pointer)
+	PPC_LL	r3,0(r1)
+	blr

arch/powerpc/kernel/ppc_ksyms.c

@@ -41,3 +41,5 @@ EXPORT_SYMBOL(giveup_spe);
 #ifdef CONFIG_EPAPR_PARAVIRT
 EXPORT_SYMBOL(epapr_hypercall_start);
 #endif
+
+EXPORT_SYMBOL(current_stack_pointer);

arch/powerpc/kernel/process.c

@@ -1545,7 +1545,7 @@ void show_stack(struct task_struct *tsk, unsigned long *stack)
 		tsk = current;
 	if (sp == 0) {
 		if (tsk == current)
-			asm("mr %0,1" : "=r" (sp));
+			sp = current_stack_pointer();
 		else
 			sp = tsk->thread.ksp;
 	}

arch/powerpc/kernel/rtas_pci.c

@@ -66,6 +66,11 @@ int rtas_read_config(struct pci_dn *pdn, int where, int size, u32 *val)
 		return PCIBIOS_DEVICE_NOT_FOUND;
 	if (!config_access_valid(pdn, where))
 		return PCIBIOS_BAD_REGISTER_NUMBER;
+#ifdef CONFIG_EEH
+	if (pdn->edev && pdn->edev->pe &&
+	    (pdn->edev->pe->state & EEH_PE_CFG_BLOCKED))
+		return PCIBIOS_SET_FAILED;
+#endif
 
 	addr = rtas_config_addr(pdn->busno, pdn->devfn, where);
 	buid = pdn->phb->buid;
@@ -90,9 +95,6 @@ static int rtas_pci_read_config(struct pci_bus *bus,
 	struct device_node *busdn, *dn;
 	struct pci_dn *pdn;
 	bool found = false;
-#ifdef CONFIG_EEH
-	struct eeh_dev *edev;
-#endif
 	int ret;
 
 	/* Search only direct children of the bus */
@@ -109,11 +111,6 @@ static int rtas_pci_read_config(struct pci_bus *bus,
 
 	if (!found)
 		return PCIBIOS_DEVICE_NOT_FOUND;
-#ifdef CONFIG_EEH
-	edev = of_node_to_eeh_dev(dn);
-	if (edev && edev->pe && edev->pe->state & EEH_PE_RESET)
-		return PCIBIOS_DEVICE_NOT_FOUND;
-#endif
 
 	ret = rtas_read_config(pdn, where, size, val);
 	if (*val == EEH_IO_ERROR_VALUE(size) &&
@@ -132,6 +129,11 @@ int rtas_write_config(struct pci_dn *pdn, int where, int size, u32 val)
 		return PCIBIOS_DEVICE_NOT_FOUND;
 	if (!config_access_valid(pdn, where))
 		return PCIBIOS_BAD_REGISTER_NUMBER;
+#ifdef CONFIG_EEH
+	if (pdn->edev && pdn->edev->pe &&
+	    (pdn->edev->pe->state & EEH_PE_CFG_BLOCKED))
+		return PCIBIOS_SET_FAILED;
+#endif
 
 	addr = rtas_config_addr(pdn->busno, pdn->devfn, where);
 	buid = pdn->phb->buid;
@@ -155,10 +157,6 @@ static int rtas_pci_write_config(struct pci_bus *bus,
 	struct device_node *busdn, *dn;
 	struct pci_dn *pdn;
 	bool found = false;
-#ifdef CONFIG_EEH
-	struct eeh_dev *edev;
-#endif
-	int ret;
 
 	/* Search only direct children of the bus */
 	busdn = pci_bus_to_OF_node(bus);
@@ -173,14 +171,8 @@ static int rtas_pci_write_config(struct pci_bus *bus,
 
 	if (!found)
 		return PCIBIOS_DEVICE_NOT_FOUND;
-#ifdef CONFIG_EEH
-	edev = of_node_to_eeh_dev(dn);
-	if (edev && edev->pe && (edev->pe->state & EEH_PE_RESET))
-		return PCIBIOS_DEVICE_NOT_FOUND;
-#endif
-	ret = rtas_write_config(pdn, where, size, val);
 
-	return ret;
+	return rtas_write_config(pdn, where, size, val);
 }
 
 static struct pci_ops rtas_pci_ops = {

arch/powerpc/kernel/setup_64.c

@@ -522,36 +522,36 @@ void __init setup_system(void)
 	smp_release_cpus();
 #endif
 
-	printk("Starting Linux PPC64 %s\n", init_utsname()->version);
+	pr_info("Starting Linux PPC64 %s\n", init_utsname()->version);
 
-	printk("-----------------------------------------------------\n");
-	printk("ppc64_pft_size    = 0x%llx\n", ppc64_pft_size);
-	printk("phys_mem_size     = 0x%llx\n", memblock_phys_mem_size());
+	pr_info("-----------------------------------------------------\n");
+	pr_info("ppc64_pft_size    = 0x%llx\n", ppc64_pft_size);
+	pr_info("phys_mem_size     = 0x%llx\n", memblock_phys_mem_size());
 
 	if (ppc64_caches.dline_size != 0x80)
-		printk("dcache_line_size  = 0x%x\n", ppc64_caches.dline_size);
+		pr_info("dcache_line_size  = 0x%x\n", ppc64_caches.dline_size);
 	if (ppc64_caches.iline_size != 0x80)
-		printk("icache_line_size  = 0x%x\n", ppc64_caches.iline_size);
+		pr_info("icache_line_size  = 0x%x\n", ppc64_caches.iline_size);
 
-	printk("cpu_features      = 0x%016lx\n", cur_cpu_spec->cpu_features);
-	printk("  possible        = 0x%016lx\n", CPU_FTRS_POSSIBLE);
-	printk("  always          = 0x%016lx\n", CPU_FTRS_ALWAYS);
-	printk("cpu_user_features = 0x%08x 0x%08x\n", cur_cpu_spec->cpu_user_features,
+	pr_info("cpu_features      = 0x%016lx\n", cur_cpu_spec->cpu_features);
+	pr_info("  possible        = 0x%016lx\n", CPU_FTRS_POSSIBLE);
+	pr_info("  always          = 0x%016lx\n", CPU_FTRS_ALWAYS);
+	pr_info("cpu_user_features = 0x%08x 0x%08x\n", cur_cpu_spec->cpu_user_features,
 		cur_cpu_spec->cpu_user_features2);
-	printk("mmu_features      = 0x%08x\n", cur_cpu_spec->mmu_features);
-	printk("firmware_features = 0x%016lx\n", powerpc_firmware_features);
+	pr_info("mmu_features      = 0x%08x\n", cur_cpu_spec->mmu_features);
+	pr_info("firmware_features = 0x%016lx\n", powerpc_firmware_features);
 
 #ifdef CONFIG_PPC_STD_MMU_64
 	if (htab_address)
-		printk("htab_address      = 0x%p\n", htab_address);
+		pr_info("htab_address      = 0x%p\n", htab_address);
 
-	printk("htab_hash_mask    = 0x%lx\n", htab_hash_mask);
+	pr_info("htab_hash_mask    = 0x%lx\n", htab_hash_mask);
 #endif
 
 	if (PHYSICAL_START > 0)
-		printk("physical_start    = 0x%llx\n",
+		pr_info("physical_start    = 0x%llx\n",
 		       (unsigned long long)PHYSICAL_START);
-	printk("-----------------------------------------------------\n");
+	pr_info("-----------------------------------------------------\n");
 
 	DBG(" <- setup_system()\n");
 }