Merge tag 'v4.20-rc5' into x86/cleanups, to sync up the tree

Signed-off-by: Ingo Molnar <mingo@kernel.org>

6 files changed, 37 insertions, 112 deletions

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index e996e8e744cb..750f46ad018a 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -10,7 +10,6 @@
 #include <xen/xen.h>
 #include <xen/features.h>
 #include <xen/page.h>
-#include <xen/interface/memory.h>
 
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
@@ -346,80 +345,3 @@ void xen_arch_unregister_cpu(int num)
 }
 EXPORT_SYMBOL(xen_arch_unregister_cpu);
 #endif
-
-#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
-void __init arch_xen_balloon_init(struct resource *hostmem_resource)
-{
-	struct xen_memory_map memmap;
-	int rc;
-	unsigned int i, last_guest_ram;
-	phys_addr_t max_addr = PFN_PHYS(max_pfn);
-	struct e820_table *xen_e820_table;
-	const struct e820_entry *entry;
-	struct resource *res;
-
-	if (!xen_initial_domain())
-		return;
-
-	xen_e820_table = kmalloc(sizeof(*xen_e820_table), GFP_KERNEL);
-	if (!xen_e820_table)
-		return;
-
-	memmap.nr_entries = ARRAY_SIZE(xen_e820_table->entries);
-	set_xen_guest_handle(memmap.buffer, xen_e820_table->entries);
-	rc = HYPERVISOR_memory_op(XENMEM_machine_memory_map, &memmap);
-	if (rc) {
-		pr_warn("%s: Can't read host e820 (%d)\n", __func__, rc);
-		goto out;
-	}
-
-	last_guest_ram = 0;
-	for (i = 0; i < memmap.nr_entries; i++) {
-		if (xen_e820_table->entries[i].addr >= max_addr)
-			break;
-		if (xen_e820_table->entries[i].type == E820_TYPE_RAM)
-			last_guest_ram = i;
-	}
-
-	entry = &xen_e820_table->entries[last_guest_ram];
-	if (max_addr >= entry->addr + entry->size)
-		goto out; /* No unallocated host RAM. */
-
-	hostmem_resource->start = max_addr;
-	hostmem_resource->end = entry->addr + entry->size;
-
-	/*
-	 * Mark non-RAM regions between the end of dom0 RAM and end of host RAM
-	 * as unavailable. The rest of that region can be used for hotplug-based
-	 * ballooning.
-	 */
-	for (; i < memmap.nr_entries; i++) {
-		entry = &xen_e820_table->entries[i];
-
-		if (entry->type == E820_TYPE_RAM)
-			continue;
-
-		if (entry->addr >= hostmem_resource->end)
-			break;
-
-		res = kzalloc(sizeof(*res), GFP_KERNEL);
-		if (!res)
-			goto out;
-
-		res->name = "Unavailable host RAM";
-		res->start = entry->addr;
-		res->end = (entry->addr + entry->size < hostmem_resource->end) ?
-			    entry->addr + entry->size : hostmem_resource->end;
-		rc = insert_resource(hostmem_resource, res);
-		if (rc) {
-			pr_warn("%s: Can't insert [%llx - %llx) (%d)\n",
-				__func__, res->start, res->end, rc);
-			kfree(res);
-			goto  out;
-		}
-	}
-
- out:
-	kfree(xen_e820_table);
-}
-#endif /* CONFIG_XEN_BALLOON_MEMORY_HOTPLUG */
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 0d7b3ae4960b..a5d7ed125337 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1905,7 +1905,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	init_top_pgt[0] = __pgd(0);
 
 	/* Pre-constructed entries are in pfn, so convert to mfn */
-	/* L4[272] -> level3_ident_pgt  */
+	/* L4[273] -> level3_ident_pgt  */
 	/* L4[511] -> level3_kernel_pgt */
 	convert_pfn_mfn(init_top_pgt);
 
@@ -1925,8 +1925,8 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	addr[0] = (unsigned long)pgd;
 	addr[1] = (unsigned long)l3;
 	addr[2] = (unsigned long)l2;
-	/* Graft it onto L4[272][0]. Note that we creating an aliasing problem:
-	 * Both L4[272][0] and L4[511][510] have entries that point to the same
+	/* Graft it onto L4[273][0]. Note that we creating an aliasing problem:
+	 * Both L4[273][0] and L4[511][510] have entries that point to the same
 	 * L2 (PMD) tables. Meaning that if you modify it in __va space
 	 * it will be also modified in the __ka space! (But if you just
 	 * modify the PMD table to point to other PTE's or none, then you
diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c
index 2bce7958ce8b..0766a08bdf45 100644
--- a/arch/x86/xen/multicalls.c
+++ b/arch/x86/xen/multicalls.c
@@ -69,6 +69,11 @@ void xen_mc_flush(void)
 
 	trace_xen_mc_flush(b->mcidx, b->argidx, b->cbidx);
 
+#if MC_DEBUG
+	memcpy(b->debug, b->entries,
+	       b->mcidx * sizeof(struct multicall_entry));
+#endif
+
 	switch (b->mcidx) {
 	case 0:
 		/* no-op */
@@ -87,32 +92,34 @@ void xen_mc_flush(void)
 		break;
 
 	default:
-#if MC_DEBUG
-		memcpy(b->debug, b->entries,
-		       b->mcidx * sizeof(struct multicall_entry));
-#endif
-
 		if (HYPERVISOR_multicall(b->entries, b->mcidx) != 0)
 			BUG();
 		for (i = 0; i < b->mcidx; i++)
 			if (b->entries[i].result < 0)
 				ret++;
+	}
 
+	if (WARN_ON(ret)) {
+		pr_err("%d of %d multicall(s) failed: cpu %d\n",
+		       ret, b->mcidx, smp_processor_id());
+		for (i = 0; i < b->mcidx; i++) {
+			if (b->entries[i].result < 0) {
 #if MC_DEBUG
-		if (ret) {
-			printk(KERN_ERR "%d multicall(s) failed: cpu %d\n",
-			       ret, smp_processor_id());
-			dump_stack();
-			for (i = 0; i < b->mcidx; i++) {
-				printk(KERN_DEBUG "  call %2d/%d: op=%lu arg=[%lx] result=%ld\t%pF\n",
-				       i+1, b->mcidx,
+				pr_err("  call %2d: op=%lu arg=[%lx] result=%ld\t%pF\n",
+				       i + 1,
 				       b->debug[i].op,
 				       b->debug[i].args[0],
 				       b->entries[i].result,
 				       b->caller[i]);
+#else
+				pr_err("  call %2d: op=%lu arg=[%lx] result=%ld\n",
+				       i + 1,
+				       b->entries[i].op,
+				       b->entries[i].args[0],
+				       b->entries[i].result);
+#endif
 			}
 		}
-#endif
 	}
 
 	b->mcidx = 0;
@@ -126,8 +133,6 @@ void xen_mc_flush(void)
 	b->cbidx = 0;
 
 	local_irq_restore(flags);
-
-	WARN_ON(ret);
 }
 
 struct multicall_space __xen_mc_entry(size_t args)
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index b06731705529..055e37e43541 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -656,8 +656,7 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 
 	/*
 	 * The interface requires atomic updates on p2m elements.
-	 * xen_safe_write_ulong() is using __put_user which does an atomic
-	 * store via asm().
+	 * xen_safe_write_ulong() is using an atomic store via asm().
 	 */
 	if (likely(!xen_safe_write_ulong(xen_p2m_addr + pfn, mfn)))
 		return true;
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 1163e33121fb..075ed47993bb 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -808,6 +808,7 @@ char * __init xen_memory_setup(void)
 	addr = xen_e820_table.entries[0].addr;
 	size = xen_e820_table.entries[0].size;
 	while (i < xen_e820_table.nr_entries) {
+		bool discard = false;
 
 		chunk_size = size;
 		type = xen_e820_table.entries[i].type;
@@ -823,10 +824,11 @@ char * __init xen_memory_setup(void)
 				xen_add_extra_mem(pfn_s, n_pfns);
 				xen_max_p2m_pfn = pfn_s + n_pfns;
 			} else
-				type = E820_TYPE_UNUSABLE;
+				discard = true;
 		}
 
-		xen_align_and_add_e820_region(addr, chunk_size, type);
+		if (!discard)
+			xen_align_and_add_e820_region(addr, chunk_size, type);
 
 		addr += chunk_size;
 		size -= chunk_size;
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 441c88262169..3776122c87cc 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -3,24 +3,21 @@
  * Split spinlock implementation out into its own file, so it can be
  * compiled in a FTRACE-compatible way.
  */
-#include <linux/kernel_stat.h>
+#include <linux/kernel.h>
 #include <linux/spinlock.h>
-#include <linux/debugfs.h>
-#include <linux/log2.h>
-#include <linux/gfp.h>
 #include <linux/slab.h>
+#include <linux/atomic.h>
 
 #include <asm/paravirt.h>
 #include <asm/qspinlock.h>
 
-#include <xen/interface/xen.h>
 #include <xen/events.h>
 
 #include "xen-ops.h"
-#include "debugfs.h"
 
 static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
 static DEFINE_PER_CPU(char *, irq_name);
+static DEFINE_PER_CPU(atomic_t, xen_qlock_wait_nest);
 static bool xen_pvspin = true;
 
 static void xen_qlock_kick(int cpu)
@@ -39,25 +36,25 @@ static void xen_qlock_kick(int cpu)
  */
 static void xen_qlock_wait(u8 *byte, u8 val)
 {
-	unsigned long flags;
 	int irq = __this_cpu_read(lock_kicker_irq);
+	atomic_t *nest_cnt = this_cpu_ptr(&xen_qlock_wait_nest);
 
 	/* If kicker interrupts not initialized yet, just spin */
 	if (irq == -1 || in_nmi())
 		return;
 
-	/* Guard against reentry. */
-	local_irq_save(flags);
+	/* Detect reentry. */
+	atomic_inc(nest_cnt);
 
-	/* If irq pending already clear it. */
-	if (xen_test_irq_pending(irq)) {
+	/* If irq pending already and no nested call clear it. */
+	if (atomic_read(nest_cnt) == 1 && xen_test_irq_pending(irq)) {
 		xen_clear_irq_pending(irq);
 	} else if (READ_ONCE(*byte) == val) {
 		/* Block until irq becomes pending (or a spurious wakeup) */
 		xen_poll_irq(irq);
 	}
 
-	local_irq_restore(flags);
+	atomic_dec(nest_cnt);
 }
 
 static irqreturn_t dummy_handler(int irq, void *dev_id)