Merge tag 'powerpc-4.19-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fixes from Michael Ellerman:

 - An implementation for the newly added hv_ops->flush() for the OPAL
   hvc console driver backends, I forgot to apply this after merging the
   hvc driver changes before the merge window.

 - Enable all PCI bridges at boot on powernv, to avoid races when
   multiple children of a bridge try to enable it simultaneously. This
   is a workaround until the PCI core can be enhanced to fix the races.

 - A fix to query PowerVM for the correct system topology at boot before
   initialising sched domains, seen in some configurations to cause
   broken scheduling etc.

 - A fix for pte_access_permitted() on "nohash" platforms.

 - Two commits to fix SIGBUS when using remap_pfn_range() seen on Power9
   due to a workaround when using the nest MMU (GPUs, accelerators).

 - Another fix to the VFIO code used by KVM, the previous fix had some
   bugs which caused guests to not start in some configurations.

 - A handful of other minor fixes.

Thanks to: Aneesh Kumar K.V, Benjamin Herrenschmidt, Christophe Leroy,
Hari Bathini, Luke Dashjr, Mahesh Salgaonkar, Nicholas Piggin, Paul
Mackerras, Srikar Dronamraju.

* tag 'powerpc-4.19-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  powerpc/mce: Fix SLB rebolting during MCE recovery path.
  KVM: PPC: Book3S: Fix guest DMA when guest partially backed by THP pages
  powerpc/mm/radix: Only need the Nest MMU workaround for R -> RW transition
  powerpc/mm/books3s: Add new pte bit to mark pte temporarily invalid.
  powerpc/nohash: fix pte_access_permitted()
  powerpc/topology: Get topology for shared processors at boot
  powerpc64/ftrace: Include ftrace.h needed for enable/disable calls
  powerpc/powernv/pci: Work around races in PCI bridge enabling
  powerpc/fadump: cleanup crash memory ranges support
  powerpc/powernv: provide a console flush operation for opal hvc driver
  powerpc/traps: Avoid rate limit messages from show unhandled signals
  powerpc/64s: Fix PACA_IRQ_HARD_DIS accounting in idle_power4()

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

@@ -44,6 +44,16 @@
 
 #define _PAGE_PTE		0x4000000000000000UL	/* distinguishes PTEs from pointers */
 #define _PAGE_PRESENT		0x8000000000000000UL	/* pte contains a translation */
+/*
+ * We need to mark a pmd pte invalid while splitting. We can do that by clearing
+ * the _PAGE_PRESENT bit. But then that will be taken as a swap pte. In order to
+ * differentiate between two use a SW field when invalidating.
+ *
+ * We do that temporary invalidate for regular pte entry in ptep_set_access_flags
+ *
+ * This is used only when _PAGE_PRESENT is cleared.
+ */
+#define _PAGE_INVALID		_RPAGE_SW0
 
 /*
  * Top and bottom bits of RPN which can be used by hash
@@ -568,7 +578,13 @@ static inline pte_t pte_clear_savedwrite(pte_t pte)
 
 static inline int pte_present(pte_t pte)
 {
-	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT));
+	/*
+	 * A pte is considerent present if _PAGE_PRESENT is set.
+	 * We also need to consider the pte present which is marked
+	 * invalid during ptep_set_access_flags. Hence we look for _PAGE_INVALID
+	 * if we find _PAGE_PRESENT cleared.
+	 */
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_INVALID));
 }
 
 #ifdef CONFIG_PPC_MEM_KEYS

arch/powerpc/include/asm/nohash/pgtable.h

@@ -51,17 +51,14 @@ static inline int pte_present(pte_t pte)
 #define pte_access_permitted pte_access_permitted
 static inline bool pte_access_permitted(pte_t pte, bool write)
 {
-	unsigned long pteval = pte_val(pte);
 	/*
 	 * A read-only access is controlled by _PAGE_USER bit.
 	 * We have _PAGE_READ set for WRITE and EXECUTE
 	 */
-	unsigned long need_pte_bits = _PAGE_PRESENT | _PAGE_USER;
-
-	if (write)
-		need_pte_bits |= _PAGE_WRITE;
+	if (!pte_present(pte) || !pte_user(pte) || !pte_read(pte))
+		return false;
 
-	if ((pteval & need_pte_bits) != need_pte_bits)
+	if (write && !pte_write(pte))
 		return false;
 
 	return true;

arch/powerpc/include/asm/opal.h

@@ -308,6 +308,7 @@ extern void opal_configure_cores(void);
 extern int opal_get_chars(uint32_t vtermno, char *buf, int count);
 extern int opal_put_chars(uint32_t vtermno, const char *buf, int total_len);
 extern int opal_put_chars_atomic(uint32_t vtermno, const char *buf, int total_len);
+extern int opal_flush_chars(uint32_t vtermno, bool wait);
 extern int opal_flush_console(uint32_t vtermno);
 
 extern void hvc_opal_init_early(void);

arch/powerpc/include/asm/topology.h

@@ -92,6 +92,7 @@ extern int stop_topology_update(void);
 extern int prrn_is_enabled(void);
 extern int find_and_online_cpu_nid(int cpu);
 extern int timed_topology_update(int nsecs);
+extern void __init shared_proc_topology_init(void);
 #else
 static inline int start_topology_update(void)
 {
@@ -113,6 +114,10 @@ static inline int timed_topology_update(int nsecs)
 {
 	return 0;
 }
+
+#ifdef CONFIG_SMP
+static inline void shared_proc_topology_init(void) {}
+#endif
 #endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */
 
 #include <asm-generic/topology.h>

arch/powerpc/kernel/fadump.c

@@ -34,6 +34,7 @@
 #include <linux/crash_dump.h>
 #include <linux/kobject.h>
 #include <linux/sysfs.h>
+#include <linux/slab.h>
 
 #include <asm/debugfs.h>
 #include <asm/page.h>
@@ -1019,13 +1020,6 @@ static int fadump_setup_crash_memory_ranges(void)
 	pr_debug("Setup crash memory ranges.\n");
 	crash_mem_ranges = 0;
 
-	/* allocate memory for crash memory ranges for the first time */
-	if (!max_crash_mem_ranges) {
-		ret = allocate_crash_memory_ranges();
-		if (ret)
-			return ret;
-	}
-
 	/*
 	 * add the first memory chunk (RMA_START through boot_memory_size) as
 	 * a separate memory chunk. The reason is, at the time crash firmware

arch/powerpc/kernel/idle_power4.S

@@ -32,6 +32,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_CAN_NAP)
 	cmpwi	0,r4,0
 	beqlr
 
+	/* This sequence is similar to prep_irq_for_idle() */
+
 	/* Hard disable interrupts */
 	mfmsr	r7
 	rldicl	r0,r7,48,1
@@ -41,10 +43,15 @@ END_FTR_SECTION_IFCLR(CPU_FTR_CAN_NAP)
 	/* Check if something happened while soft-disabled */
 	lbz	r0,PACAIRQHAPPENED(r13)
 	cmpwi	cr0,r0,0
-	bnelr
+	bne-	2f
 
-	/* Soft-enable interrupts */
+	/*
+	 * Soft-enable interrupts. This will make power4_fixup_nap return
+	 * to our caller with interrupts enabled (soft and hard). The caller
+	 * can cope with either interrupts disabled or enabled upon return.
+	 */
 #ifdef CONFIG_TRACE_IRQFLAGS
+	/* Tell the tracer interrupts are on, because idle responds to them. */
 	mflr	r0
 	std	r0,16(r1)
 	stdu    r1,-128(r1)
@@ -73,3 +80,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	isync
 	b	1b
 
+2:	/* Return if an interrupt had happened while soft disabled */
+	/* Set the HARD_DIS flag because interrupts are now hard disabled */
+	ori	r0,r0,PACA_IRQ_HARD_DIS
+	stb	r0,PACAIRQHAPPENED(r13)
+	blr

arch/powerpc/kernel/smp.c

@@ -1160,6 +1160,11 @@ void __init smp_cpus_done(unsigned int max_cpus)
 	if (smp_ops && smp_ops->bringup_done)
 		smp_ops->bringup_done();
 
+	/*
+	 * On a shared LPAR, associativity needs to be requested.
+	 * Hence, get numa topology before dumping cpu topology
+	 */
+	shared_proc_topology_init();
 	dump_numa_cpu_topology();
 
 	/*

arch/powerpc/kernel/traps.c

@@ -315,22 +315,21 @@ void user_single_step_siginfo(struct task_struct *tsk,
 	info->si_addr = (void __user *)regs->nip;
 }
 
-static bool show_unhandled_signals_ratelimited(void)
+static void show_signal_msg(int signr, struct pt_regs *regs, int code,
+			    unsigned long addr)
 {
 	static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL,
 				      DEFAULT_RATELIMIT_BURST);
-	return show_unhandled_signals && __ratelimit(&rs);
-}
 
-static void show_signal_msg(int signr, struct pt_regs *regs, int code,
-			    unsigned long addr)
-{
-	if (!show_unhandled_signals_ratelimited())
+	if (!show_unhandled_signals)
 		return;
 
 	if (!unhandled_signal(current, signr))
 		return;
 
+	if (!__ratelimit(&rs))
+		return;
+
 	pr_info("%s[%d]: %s (%d) at %lx nip %lx lr %lx code %x",
 		current->comm, current->pid, signame(signr), signr,
 		addr, regs->nip, regs->link, code);

arch/powerpc/kvm/book3s_hv.c

@@ -46,6 +46,7 @@
 #include <linux/compiler.h>
 #include <linux/of.h>
 
+#include <asm/ftrace.h>
 #include <asm/reg.h>
 #include <asm/ppc-opcode.h>
 #include <asm/asm-prototypes.h>

arch/powerpc/mm/mmu_context_iommu.c

@@ -129,6 +129,7 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 	long i, j, ret = 0, locked_entries = 0;
 	unsigned int pageshift;
 	unsigned long flags;
+	unsigned long cur_ua;
 	struct page *page = NULL;
 
 	mutex_lock(&mem_list_mutex);
@@ -177,7 +178,8 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 	}
 
 	for (i = 0; i < entries; ++i) {
-		if (1 != get_user_pages_fast(ua + (i << PAGE_SHIFT),
+		cur_ua = ua + (i << PAGE_SHIFT);
+		if (1 != get_user_pages_fast(cur_ua,
 					1/* pages */, 1/* iswrite */, &page)) {
 			ret = -EFAULT;
 			for (j = 0; j < i; ++j)
@@ -196,7 +198,7 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 		if (is_migrate_cma_page(page)) {
 			if (mm_iommu_move_page_from_cma(page))
 				goto populate;
-			if (1 != get_user_pages_fast(ua + (i << PAGE_SHIFT),
+			if (1 != get_user_pages_fast(cur_ua,
 						1/* pages */, 1/* iswrite */,
 						&page)) {
 				ret = -EFAULT;
@@ -210,20 +212,21 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 		}
 populate:
 		pageshift = PAGE_SHIFT;
-		if (PageCompound(page)) {
+		if (mem->pageshift > PAGE_SHIFT && PageCompound(page)) {
 			pte_t *pte;
 			struct page *head = compound_head(page);
 			unsigned int compshift = compound_order(head);
+			unsigned int pteshift;
 
 			local_irq_save(flags); /* disables as well */
-			pte = find_linux_pte(mm->pgd, ua, NULL, &pageshift);
-			local_irq_restore(flags);
+			pte = find_linux_pte(mm->pgd, cur_ua, NULL, &pteshift);
 
 			/* Double check it is still the same pinned page */
 			if (pte && pte_page(*pte) == head &&
-					pageshift == compshift)
-				pageshift = max_t(unsigned int, pageshift,
+			    pteshift == compshift + PAGE_SHIFT)
+				pageshift = max_t(unsigned int, pteshift,
 						PAGE_SHIFT);
+			local_irq_restore(flags);
 		}
 		mem->pageshift = min(mem->pageshift, pageshift);
 		mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;

arch/powerpc/mm/numa.c

@@ -1078,7 +1078,6 @@ static int prrn_enabled;
 static void reset_topology_timer(void);
 static int topology_timer_secs = 1;
 static int topology_inited;
-static int topology_update_needed;
 
 /*
  * Change polling interval for associativity changes.
@@ -1306,11 +1305,8 @@ int numa_update_cpu_topology(bool cpus_locked)
 	struct device *dev;
 	int weight, new_nid, i = 0;
 
-	if (!prrn_enabled && !vphn_enabled) {
-		if (!topology_inited)
-			topology_update_needed = 1;
+	if (!prrn_enabled && !vphn_enabled && topology_inited)
 		return 0;
-	}
 
 	weight = cpumask_weight(&cpu_associativity_changes_mask);
 	if (!weight)
@@ -1423,7 +1419,6 @@ int numa_update_cpu_topology(bool cpus_locked)
 
 out:
 	kfree(updates);
-	topology_update_needed = 0;
 	return changed;
 }
 
@@ -1551,6 +1546,15 @@ int prrn_is_enabled(void)
 	return prrn_enabled;
 }
 
+void __init shared_proc_topology_init(void)
+{
+	if (lppaca_shared_proc(get_lppaca())) {
+		bitmap_fill(cpumask_bits(&cpu_associativity_changes_mask),
+			    nr_cpumask_bits);
+		numa_update_cpu_topology(false);
+	}
+}
+
 static int topology_read(struct seq_file *file, void *v)
 {
 	if (vphn_enabled || prrn_enabled)
@@ -1608,10 +1612,6 @@ static int topology_update_init(void)
 		return -ENOMEM;
 
 	topology_inited = 1;
-	if (topology_update_needed)
-		bitmap_fill(cpumask_bits(&cpu_associativity_changes_mask),
-					nr_cpumask_bits);
-
 	return 0;
 }
 device_initcall(topology_update_init);

arch/powerpc/mm/pgtable-radix.c

@@ -1045,20 +1045,22 @@ void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep,
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_ACCESSED |
 					      _PAGE_RW | _PAGE_EXEC);
+
+	unsigned long change = pte_val(entry) ^ pte_val(*ptep);
 	/*
 	 * To avoid NMMU hang while relaxing access, we need mark
 	 * the pte invalid in between.
 	 */
-	if (atomic_read(&mm->context.copros) > 0) {
+	if ((change & _PAGE_RW) && atomic_read(&mm->context.copros) > 0) {
 		unsigned long old_pte, new_pte;
 
-		old_pte = __radix_pte_update(ptep, ~0, 0);
+		old_pte = __radix_pte_update(ptep, _PAGE_PRESENT, _PAGE_INVALID);
 		/*
 		 * new value of pte
 		 */
 		new_pte = old_pte | set;
 		radix__flush_tlb_page_psize(mm, address, psize);
-		__radix_pte_update(ptep, 0, new_pte);
+		__radix_pte_update(ptep, _PAGE_INVALID, new_pte);
 	} else {
 		__radix_pte_update(ptep, 0, set);
 		/*

arch/powerpc/mm/slb.c

@@ -70,7 +70,7 @@ static inline void slb_shadow_update(unsigned long ea, int ssize,
 
 static inline void slb_shadow_clear(enum slb_index index)
 {
-	WRITE_ONCE(get_slb_shadow()->save_area[index].esid, 0);
+	WRITE_ONCE(get_slb_shadow()->save_area[index].esid, cpu_to_be64(index));
 }
 
 static inline void create_shadowed_slbe(unsigned long ea, int ssize,

arch/powerpc/platforms/powernv/opal.c

@@ -370,12 +370,8 @@ static int __opal_put_chars(uint32_t vtermno, const char *data, int total_len, b
 	olen = cpu_to_be64(total_len);
 	rc = opal_console_write(vtermno, &olen, data);
 	if (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
-		if (rc == OPAL_BUSY_EVENT) {
-			mdelay(OPAL_BUSY_DELAY_MS);
+		if (rc == OPAL_BUSY_EVENT)
 			opal_poll_events(NULL);
-		} else if (rc == OPAL_BUSY_EVENT) {
-			mdelay(OPAL_BUSY_DELAY_MS);
-		}
 		written = -EAGAIN;
 		goto out;
 	}
@@ -401,15 +397,6 @@ static int __opal_put_chars(uint32_t vtermno, const char *data, int total_len, b
 	if (atomic)
 		spin_unlock_irqrestore(&opal_write_lock, flags);
 
-	/* In the -EAGAIN case, callers loop, so we have to flush the console
-	 * here in case they have interrupts off (and we don't want to wait
-	 * for async flushing if we can make immediate progress here). If
-	 * necessary the API could be made entirely non-flushing if the
-	 * callers had a ->flush API to use.
-	 */
-	if (written == -EAGAIN)
-		opal_flush_console(vtermno);
-
 	return written;
 }
 
@@ -429,40 +416,74 @@ int opal_put_chars_atomic(uint32_t vtermno, const char *data, int total_len)
 	return __opal_put_chars(vtermno, data, total_len, true);
 }
 
-int opal_flush_console(uint32_t vtermno)
+static s64 __opal_flush_console(uint32_t vtermno)
 {
 	s64 rc;
 
 	if (!opal_check_token(OPAL_CONSOLE_FLUSH)) {
 		__be64 evt;
 
-		WARN_ONCE(1, "opal: OPAL_CONSOLE_FLUSH missing.\n");
 		/*
 		 * If OPAL_CONSOLE_FLUSH is not implemented in the firmware,
 		 * the console can still be flushed by calling the polling
 		 * function while it has OPAL_EVENT_CONSOLE_OUTPUT events.
 		 */
-		do {
-			opal_poll_events(&evt);
-		} while (be64_to_cpu(evt) & OPAL_EVENT_CONSOLE_OUTPUT);
+		WARN_ONCE(1, "opal: OPAL_CONSOLE_FLUSH missing.\n");
 
+		opal_poll_events(&evt);
+		if (!(be64_to_cpu(evt) & OPAL_EVENT_CONSOLE_OUTPUT))
 			return OPAL_SUCCESS;
-	}
+		return OPAL_BUSY;
 
-	do  {
-		rc = OPAL_BUSY;
-		while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+	} else {
 		rc = opal_console_flush(vtermno);
 		if (rc == OPAL_BUSY_EVENT) {
-				mdelay(OPAL_BUSY_DELAY_MS);
 			opal_poll_events(NULL);
-			} else if (rc == OPAL_BUSY) {
-				mdelay(OPAL_BUSY_DELAY_MS);
+			rc = OPAL_BUSY;
 		}
+		return rc;
+	}
+
+}
+
+/*
+ * opal_flush_console spins until the console is flushed
+ */
+int opal_flush_console(uint32_t vtermno)
+{
+	for (;;) {
+		s64 rc = __opal_flush_console(vtermno);
+
+		if (rc == OPAL_BUSY || rc == OPAL_PARTIAL) {
+			mdelay(1);
+			continue;
 		}
-	} while (rc == OPAL_PARTIAL); /* More to flush */
 
 		return opal_error_code(rc);
+	}
+}
+
+/*
+ * opal_flush_chars is an hvc interface that sleeps until the console is
+ * flushed if wait, otherwise it will return -EBUSY if the console has data,
+ * -EAGAIN if it has data and some of it was flushed.
+ */
+int opal_flush_chars(uint32_t vtermno, bool wait)
+{
+	for (;;) {
+		s64 rc = __opal_flush_console(vtermno);
+
+		if (rc == OPAL_BUSY || rc == OPAL_PARTIAL) {
+			if (wait) {
+				msleep(OPAL_BUSY_DELAY_MS);
+				continue;
+			}
+			if (rc == OPAL_PARTIAL)
+				return -EAGAIN;
+		}
+
+		return opal_error_code(rc);
+	}
 }
 
 static int opal_recover_mce(struct pt_regs *regs,

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

@@ -3228,12 +3228,49 @@ static void pnv_pci_ioda_create_dbgfs(void)
 #endif /* CONFIG_DEBUG_FS */
 }
 
+static void pnv_pci_enable_bridge(struct pci_bus *bus)
+{
+	struct pci_dev *dev = bus->self;
+	struct pci_bus *child;
+
+	/* Empty bus ? bail */
+	if (list_empty(&bus->devices))
+		return;
+
+	/*
+	 * If there's a bridge associated with that bus enable it. This works
+	 * around races in the generic code if the enabling is done during
+	 * parallel probing. This can be removed once those races have been
+	 * fixed.
+	 */
+	if (dev) {
+		int rc = pci_enable_device(dev);
+		if (rc)
+			pci_err(dev, "Error enabling bridge (%d)\n", rc);
+		pci_set_master(dev);
+	}
+
+	/* Perform the same to child busses */
+	list_for_each_entry(child, &bus->children, node)
+		pnv_pci_enable_bridge(child);
+}
+
+static void pnv_pci_enable_bridges(void)
+{
+	struct pci_controller *hose;
+
+	list_for_each_entry(hose, &hose_list, list_node)
+		pnv_pci_enable_bridge(hose->bus);
+}
+
 static void pnv_pci_ioda_fixup(void)
 {
 	pnv_pci_ioda_setup_PEs();
 	pnv_pci_ioda_setup_iommu_api();
 	pnv_pci_ioda_create_dbgfs();
 
+	pnv_pci_enable_bridges();
+
 #ifdef CONFIG_EEH
 	pnv_eeh_post_init();
 #endif

drivers/tty/hvc/hvc_opal.c

@@ -52,6 +52,7 @@ static u32 hvc_opal_boot_termno;
 static const struct hv_ops hvc_opal_raw_ops = {
 	.get_chars = opal_get_chars,
 	.put_chars = opal_put_chars,
+	.flush = opal_flush_chars,
 	.notifier_add = notifier_add_irq,
 	.notifier_del = notifier_del_irq,
 	.notifier_hangup = notifier_hangup_irq,
@@ -141,6 +142,7 @@ static int hvc_opal_hvsi_tiocmset(struct hvc_struct *hp, unsigned int set,
 static const struct hv_ops hvc_opal_hvsi_ops = {
 	.get_chars = hvc_opal_hvsi_get_chars,
 	.put_chars = hvc_opal_hvsi_put_chars,
+	.flush = opal_flush_chars,
 	.notifier_add = hvc_opal_hvsi_open,
 	.notifier_del = hvc_opal_hvsi_close,
 	.notifier_hangup = hvc_opal_hvsi_hangup,