Merge branch 'perf/core' into perf/uprobes

Merge in latest upstream (and the latest perf development tree),
to prepare for tooling changes, and also to pick up v3.4 MM
changes that the uprobes code needs to take care of.

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

1 files changed, 144 insertions, 55 deletions

diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index fb072754bc1..e88300d8e80 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -64,9 +64,28 @@
 #include <asm/apic.h>
 
 #define __apicdebuginit(type) static type __init
+
 #define for_each_irq_pin(entry, head) \
 	for (entry = head; entry; entry = entry->next)
 
+static void		__init __ioapic_init_mappings(void);
+
+static unsigned int	__io_apic_read  (unsigned int apic, unsigned int reg);
+static void		__io_apic_write (unsigned int apic, unsigned int reg, unsigned int val);
+static void		__io_apic_modify(unsigned int apic, unsigned int reg, unsigned int val);
+
+static struct io_apic_ops io_apic_ops = {
+	.init	= __ioapic_init_mappings,
+	.read	= __io_apic_read,
+	.write	= __io_apic_write,
+	.modify = __io_apic_modify,
+};
+
+void __init set_io_apic_ops(const struct io_apic_ops *ops)
+{
+	io_apic_ops = *ops;
+}
+
 /*
  *      Is the SiS APIC rmw bug present ?
  *      -1 = don't know, 0 = no, 1 = yes
@@ -294,6 +313,22 @@ static void free_irq_at(unsigned int at, struct irq_cfg *cfg)
 	irq_free_desc(at);
 }
 
+static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
+{
+	return io_apic_ops.read(apic, reg);
+}
+
+static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
+{
+	io_apic_ops.write(apic, reg, value);
+}
+
+static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
+{
+	io_apic_ops.modify(apic, reg, value);
+}
+
+
 struct io_apic {
 	unsigned int index;
 	unsigned int unused[3];
@@ -314,16 +349,17 @@ static inline void io_apic_eoi(unsigned int apic, unsigned int vector)
 	writel(vector, &io_apic->eoi);
 }
 
-static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
+static unsigned int __io_apic_read(unsigned int apic, unsigned int reg)
 {
 	struct io_apic __iomem *io_apic = io_apic_base(apic);
 	writel(reg, &io_apic->index);
 	return readl(&io_apic->data);
 }
 
-static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
+static void __io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
 {
 	struct io_apic __iomem *io_apic = io_apic_base(apic);
+
 	writel(reg, &io_apic->index);
 	writel(value, &io_apic->data);
 }
@@ -334,7 +370,7 @@ static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned i
  *
  * Older SiS APIC requires we rewrite the index register
  */
-static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
+static void __io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
 {
 	struct io_apic __iomem *io_apic = io_apic_base(apic);
 
@@ -377,6 +413,7 @@ static struct IO_APIC_route_entry __ioapic_read_entry(int apic, int pin)
 
 	eu.w1 = io_apic_read(apic, 0x10 + 2 * pin);
 	eu.w2 = io_apic_read(apic, 0x11 + 2 * pin);
+
 	return eu.entry;
 }
 
@@ -384,9 +421,11 @@ static struct IO_APIC_route_entry ioapic_read_entry(int apic, int pin)
 {
 	union entry_union eu;
 	unsigned long flags;
+
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	eu.entry = __ioapic_read_entry(apic, pin);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
+
 	return eu.entry;
 }
 
@@ -396,8 +435,7 @@ static struct IO_APIC_route_entry ioapic_read_entry(int apic, int pin)
  * the interrupt, and we need to make sure the entry is fully populated
  * before that happens.
  */
-static void
-__ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
+static void __ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
 {
 	union entry_union eu = {{0, 0}};
 
@@ -409,6 +447,7 @@ __ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
 static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
 {
 	unsigned long flags;
+
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	__ioapic_write_entry(apic, pin, e);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
@@ -435,8 +474,7 @@ static void ioapic_mask_entry(int apic, int pin)
  * shared ISA-space IRQs, so we have to support them. We are super
  * fast in the common case, and fast for shared ISA-space IRQs.
  */
-static int
-__add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
+static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
 {
 	struct irq_pin_list **last, *entry;
 
@@ -521,6 +559,7 @@ static void io_apic_sync(struct irq_pin_list *entry)
 	 * a dummy read from the IO-APIC
 	 */
 	struct io_apic __iomem *io_apic;
+
 	io_apic = io_apic_base(entry->apic);
 	readl(&io_apic->data);
 }
@@ -2512,21 +2551,73 @@ static void ack_apic_edge(struct irq_data *data)
 
 atomic_t irq_mis_count;
 
-static void ack_apic_level(struct irq_data *data)
-{
-	struct irq_cfg *cfg = data->chip_data;
-	int i, do_unmask_irq = 0, irq = data->irq;
-	unsigned long v;
-
-	irq_complete_move(cfg);
 #ifdef CONFIG_GENERIC_PENDING_IRQ
+static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg)
+{
 	/* If we are moving the irq we need to mask it */
 	if (unlikely(irqd_is_setaffinity_pending(data))) {
-		do_unmask_irq = 1;
 		mask_ioapic(cfg);
+		return true;
 	}
+	return false;
+}
+
+static inline void ioapic_irqd_unmask(struct irq_data *data,
+				      struct irq_cfg *cfg, bool masked)
+{
+	if (unlikely(masked)) {
+		/* Only migrate the irq if the ack has been received.
+		 *
+		 * On rare occasions the broadcast level triggered ack gets
+		 * delayed going to ioapics, and if we reprogram the
+		 * vector while Remote IRR is still set the irq will never
+		 * fire again.
+		 *
+		 * To prevent this scenario we read the Remote IRR bit
+		 * of the ioapic.  This has two effects.
+		 * - On any sane system the read of the ioapic will
+		 *   flush writes (and acks) going to the ioapic from
+		 *   this cpu.
+		 * - We get to see if the ACK has actually been delivered.
+		 *
+		 * Based on failed experiments of reprogramming the
+		 * ioapic entry from outside of irq context starting
+		 * with masking the ioapic entry and then polling until
+		 * Remote IRR was clear before reprogramming the
+		 * ioapic I don't trust the Remote IRR bit to be
+		 * completey accurate.
+		 *
+		 * However there appears to be no other way to plug
+		 * this race, so if the Remote IRR bit is not
+		 * accurate and is causing problems then it is a hardware bug
+		 * and you can go talk to the chipset vendor about it.
+		 */
+		if (!io_apic_level_ack_pending(cfg))
+			irq_move_masked_irq(data);
+		unmask_ioapic(cfg);
+	}
+}
+#else
+static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg)
+{
+	return false;
+}
+static inline void ioapic_irqd_unmask(struct irq_data *data,
+				      struct irq_cfg *cfg, bool masked)
+{
+}
 #endif
 
+static void ack_apic_level(struct irq_data *data)
+{
+	struct irq_cfg *cfg = data->chip_data;
+	int i, irq = data->irq;
+	unsigned long v;
+	bool masked;
+
+	irq_complete_move(cfg);
+	masked = ioapic_irqd_mask(data, cfg);
+
 	/*
 	 * It appears there is an erratum which affects at least version 0x11
 	 * of I/O APIC (that's the 82093AA and cores integrated into various
@@ -2581,38 +2672,7 @@ static void ack_apic_level(struct irq_data *data)
 		eoi_ioapic_irq(irq, cfg);
 	}
 
-	/* Now we can move and renable the irq */
-	if (unlikely(do_unmask_irq)) {
-		/* Only migrate the irq if the ack has been received.
-		 *
-		 * On rare occasions the broadcast level triggered ack gets
-		 * delayed going to ioapics, and if we reprogram the
-		 * vector while Remote IRR is still set the irq will never
-		 * fire again.
-		 *
-		 * To prevent this scenario we read the Remote IRR bit
-		 * of the ioapic.  This has two effects.
-		 * - On any sane system the read of the ioapic will
-		 *   flush writes (and acks) going to the ioapic from
-		 *   this cpu.
-		 * - We get to see if the ACK has actually been delivered.
-		 *
-		 * Based on failed experiments of reprogramming the
-		 * ioapic entry from outside of irq context starting
-		 * with masking the ioapic entry and then polling until
-		 * Remote IRR was clear before reprogramming the
-		 * ioapic I don't trust the Remote IRR bit to be
-		 * completey accurate.
-		 *
-		 * However there appears to be no other way to plug
-		 * this race, so if the Remote IRR bit is not
-		 * accurate and is causing problems then it is a hardware bug
-		 * and you can go talk to the chipset vendor about it.
-		 */
-		if (!io_apic_level_ack_pending(cfg))
-			irq_move_masked_irq(data);
-		unmask_ioapic(cfg);
-	}
+	ioapic_irqd_unmask(data, cfg, masked);
 }
 
 #ifdef CONFIG_IRQ_REMAP
@@ -3873,6 +3933,11 @@ static struct resource * __init ioapic_setup_resources(int nr_ioapics)
 
 void __init ioapic_and_gsi_init(void)
 {
+	io_apic_ops.init();
+}
+
+static void __init __ioapic_init_mappings(void)
+{
 	unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
 	struct resource *ioapic_res;
 	int i;
@@ -3967,18 +4032,36 @@ int mp_find_ioapic_pin(int ioapic, u32 gsi)
 static __init int bad_ioapic(unsigned long address)
 {
 	if (nr_ioapics >= MAX_IO_APICS) {
-		printk(KERN_WARNING "WARNING: Max # of I/O APICs (%d) exceeded "
-		       "(found %d), skipping\n", MAX_IO_APICS, nr_ioapics);
+		pr_warn("WARNING: Max # of I/O APICs (%d) exceeded (found %d), skipping\n",
+			MAX_IO_APICS, nr_ioapics);
 		return 1;
 	}
 	if (!address) {
-		printk(KERN_WARNING "WARNING: Bogus (zero) I/O APIC address"
-		       " found in table, skipping!\n");
+		pr_warn("WARNING: Bogus (zero) I/O APIC address found in table, skipping!\n");
 		return 1;
 	}
 	return 0;
 }
 
+static __init int bad_ioapic_register(int idx)
+{
+	union IO_APIC_reg_00 reg_00;
+	union IO_APIC_reg_01 reg_01;
+	union IO_APIC_reg_02 reg_02;
+
+	reg_00.raw = io_apic_read(idx, 0);
+	reg_01.raw = io_apic_read(idx, 1);
+	reg_02.raw = io_apic_read(idx, 2);
+
+	if (reg_00.raw == -1 && reg_01.raw == -1 && reg_02.raw == -1) {
+		pr_warn("I/O APIC 0x%x registers return all ones, skipping!\n",
+			mpc_ioapic_addr(idx));
+		return 1;
+	}
+
+	return 0;
+}
+
 void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
 {
 	int idx = 0;
@@ -3995,6 +4078,12 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
 	ioapics[idx].mp_config.apicaddr = address;
 
 	set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address);
+
+	if (bad_ioapic_register(idx)) {
+		clear_fixmap(FIX_IO_APIC_BASE_0 + idx);
+		return;
+	}
+
 	ioapics[idx].mp_config.apicid = io_apic_unique_id(id);
 	ioapics[idx].mp_config.apicver = io_apic_get_version(idx);
 
@@ -4015,10 +4104,10 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
 	if (gsi_cfg->gsi_end >= gsi_top)
 		gsi_top = gsi_cfg->gsi_end + 1;
 
-	printk(KERN_INFO "IOAPIC[%d]: apic_id %d, version %d, address 0x%x, "
-	       "GSI %d-%d\n", idx, mpc_ioapic_id(idx),
-	       mpc_ioapic_ver(idx), mpc_ioapic_addr(idx),
-	       gsi_cfg->gsi_base, gsi_cfg->gsi_end);
+	pr_info("IOAPIC[%d]: apic_id %d, version %d, address 0x%x, GSI %d-%d\n",
+		idx, mpc_ioapic_id(idx),
+		mpc_ioapic_ver(idx), mpc_ioapic_addr(idx),
+		gsi_cfg->gsi_base, gsi_cfg->gsi_end);
 
 	nr_ioapics++;
 }