AHCI: Support multiple MSIs

Take advantage of multiple MSIs implementation on x86 - on
systems with IRQ remapping AHCI ports not only get assigned
separate MSI vectors - but also separate IRQs. As result,
interrupts generated by different ports could be serviced on
different CPUs rather than on a single one.

In cases when number of allocated MSIs is less than requested
the Sharing Last MSI mode does not get used, no matter
implemented in hardware or not. Instead, the driver assumes the
advantage of multiple MSIs is negated and falls back to the
single MSI mode as if MRSM bit was set (some Intel chips
implement this strategy anyway - MRSM bit gets set even if the
number of allocated MSIs exceeds the number of implemented ports).

Signed-off-by: Alexander Gordeev <agordeev@redhat.com>
Acked-by: Jeff Garzik <jgarzik@redhat.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Matthew Wilcox <willy@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/15bf7ee314dd55f21ec7d2a01c47613cd8190a7c.1353324359.git.agordeev@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

3 files changed, 207 insertions, 10 deletions

diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 49791273256..495aeed2677 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -1061,6 +1061,86 @@ static inline void ahci_gtf_filter_workaround(struct ata_host *host)
 {}
 #endif
 
+int ahci_init_interrupts(struct pci_dev *pdev, struct ahci_host_priv *hpriv)
+{
+	int rc;
+	unsigned int maxvec;
+
+	if (!(hpriv->flags & AHCI_HFLAG_NO_MSI)) {
+		rc = pci_enable_msi_block_auto(pdev, &maxvec);
+		if (rc > 0) {
+			if ((rc == maxvec) || (rc == 1))
+				return rc;
+			/*
+			 * Assume that advantage of multipe MSIs is negated,
+			 * so fallback to single MSI mode to save resources
+			 */
+			pci_disable_msi(pdev);
+			if (!pci_enable_msi(pdev))
+				return 1;
+		}
+	}
+
+	pci_intx(pdev, 1);
+	return 0;
+}
+
+/**
+ *	ahci_host_activate - start AHCI host, request IRQs and register it
+ *	@host: target ATA host
+ *	@irq: base IRQ number to request
+ *	@n_msis: number of MSIs allocated for this host
+ *	@irq_handler: irq_handler used when requesting IRQs
+ *	@irq_flags: irq_flags used when requesting IRQs
+ *
+ *	Similar to ata_host_activate, but requests IRQs according to AHCI-1.1
+ *	when multiple MSIs were allocated. That is one MSI per port, starting
+ *	from @irq.
+ *
+ *	LOCKING:
+ *	Inherited from calling layer (may sleep).
+ *
+ *	RETURNS:
+ *	0 on success, -errno otherwise.
+ */
+int ahci_host_activate(struct ata_host *host, int irq, unsigned int n_msis)
+{
+	int i, rc;
+
+	/* Sharing Last Message among several ports is not supported */
+	if (n_msis < host->n_ports)
+		return -EINVAL;
+
+	rc = ata_host_start(host);
+	if (rc)
+		return rc;
+
+	for (i = 0; i < host->n_ports; i++) {
+		rc = devm_request_threaded_irq(host->dev,
+			irq + i, ahci_hw_interrupt, ahci_thread_fn, IRQF_SHARED,
+			dev_driver_string(host->dev), host->ports[i]);
+		if (rc)
+			goto out_free_irqs;
+	}
+
+	for (i = 0; i < host->n_ports; i++)
+		ata_port_desc(host->ports[i], "irq %d", irq + i);
+
+	rc = ata_host_register(host, &ahci_sht);
+	if (rc)
+		goto out_free_all_irqs;
+
+	return 0;
+
+out_free_all_irqs:
+	i = host->n_ports;
+out_free_irqs:
+	for (i--; i >= 0; i--)
+		devm_free_irq(host->dev, irq + i, host->ports[i]);
+
+	return rc;
+}
+
 static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	unsigned int board_id = ent->driver_data;
@@ -1069,7 +1149,7 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct device *dev = &pdev->dev;
 	struct ahci_host_priv *hpriv;
 	struct ata_host *host;
-	int n_ports, i, rc;
+	int n_ports, n_msis, i, rc;
 	int ahci_pci_bar = AHCI_PCI_BAR_STANDARD;
 
 	VPRINTK("ENTER\n");
@@ -1156,11 +1236,12 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (ahci_sb600_enable_64bit(pdev))
 		hpriv->flags &= ~AHCI_HFLAG_32BIT_ONLY;
 
-	if ((hpriv->flags & AHCI_HFLAG_NO_MSI) || pci_enable_msi(pdev))
-		pci_intx(pdev, 1);
-
 	hpriv->mmio = pcim_iomap_table(pdev)[ahci_pci_bar];
 
+	n_msis = ahci_init_interrupts(pdev, hpriv);
+	if (n_msis > 1)
+		hpriv->flags |= AHCI_HFLAG_MULTI_MSI;
+
 	/* save initial config */
 	ahci_pci_save_initial_config(pdev, hpriv);
 
@@ -1256,6 +1337,10 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	ahci_pci_print_info(host);
 
 	pci_set_master(pdev);
+
+	if (hpriv->flags & AHCI_HFLAG_MULTI_MSI)
+		return ahci_host_activate(host, pdev->irq, n_msis);
+
 	return ata_host_activate(host, pdev->irq, ahci_interrupt, IRQF_SHARED,
 				 &ahci_sht);
 }
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index 9be471200a0..b830e6c9fe4 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -231,6 +231,7 @@ enum {
 	AHCI_HFLAG_DELAY_ENGINE		= (1 << 15), /* do not start engine on
 						        port start (wait until
 						        error-handling stage) */
+	AHCI_HFLAG_MULTI_MSI		= (1 << 16), /* multiple PCI MSIs */
 
 	/* ap->flags bits */
 
@@ -297,6 +298,8 @@ struct ahci_port_priv {
 	unsigned int		ncq_saw_d2h:1;
 	unsigned int		ncq_saw_dmas:1;
 	unsigned int		ncq_saw_sdb:1;
+	u32			intr_status;	/* interrupts to handle */
+	spinlock_t		lock;		/* protects parent ata_port */
 	u32 			intr_mask;	/* interrupts to enable */
 	bool			fbs_supported;	/* set iff FBS is supported */
 	bool			fbs_enabled;	/* set iff FBS is enabled */
@@ -359,7 +362,10 @@ void ahci_set_em_messages(struct ahci_host_priv *hpriv,
 			  struct ata_port_info *pi);
 int ahci_reset_em(struct ata_host *host);
 irqreturn_t ahci_interrupt(int irq, void *dev_instance);
+irqreturn_t ahci_hw_interrupt(int irq, void *dev_instance);
+irqreturn_t ahci_thread_fn(int irq, void *dev_instance);
 void ahci_print_info(struct ata_host *host, const char *scc_s);
+int ahci_host_activate(struct ata_host *host, int irq, unsigned int n_msis);
 
 static inline void __iomem *__ahci_port_base(struct ata_host *host,
 					     unsigned int port_no)
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index 6cd7805e47c..34c82167b96 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -1655,19 +1655,16 @@ static void ahci_error_intr(struct ata_port *ap, u32 irq_stat)
 		ata_port_abort(ap);
 }
 
-static void ahci_port_intr(struct ata_port *ap)
+static void ahci_handle_port_interrupt(struct ata_port *ap,
+				       void __iomem *port_mmio, u32 status)
 {
-	void __iomem *port_mmio = ahci_port_base(ap);
 	struct ata_eh_info *ehi = &ap->link.eh_info;
 	struct ahci_port_priv *pp = ap->private_data;
 	struct ahci_host_priv *hpriv = ap->host->private_data;
 	int resetting = !!(ap->pflags & ATA_PFLAG_RESETTING);
-	u32 status, qc_active = 0;
+	u32 qc_active = 0;
 	int rc;
 
-	status = readl(port_mmio + PORT_IRQ_STAT);
-	writel(status, port_mmio + PORT_IRQ_STAT);
-
 	/* ignore BAD_PMP while resetting */
 	if (unlikely(resetting))
 		status &= ~PORT_IRQ_BAD_PMP;
@@ -1743,6 +1740,107 @@ static void ahci_port_intr(struct ata_port *ap)
 	}
 }
 
+void ahci_port_intr(struct ata_port *ap)
+{
+	void __iomem *port_mmio = ahci_port_base(ap);
+	u32 status;
+
+	status = readl(port_mmio + PORT_IRQ_STAT);
+	writel(status, port_mmio + PORT_IRQ_STAT);
+
+	ahci_handle_port_interrupt(ap, port_mmio, status);
+}
+
+irqreturn_t ahci_thread_fn(int irq, void *dev_instance)
+{
+	struct ata_port *ap = dev_instance;
+	struct ahci_port_priv *pp = ap->private_data;
+	void __iomem *port_mmio = ahci_port_base(ap);
+	unsigned long flags;
+	u32 status;
+
+	spin_lock_irqsave(&ap->host->lock, flags);
+	status = pp->intr_status;
+	if (status)
+		pp->intr_status = 0;
+	spin_unlock_irqrestore(&ap->host->lock, flags);
+
+	spin_lock_bh(ap->lock);
+	ahci_handle_port_interrupt(ap, port_mmio, status);
+	spin_unlock_bh(ap->lock);
+
+	return IRQ_HANDLED;
+}
+EXPORT_SYMBOL_GPL(ahci_thread_fn);
+
+void ahci_hw_port_interrupt(struct ata_port *ap)
+{
+	void __iomem *port_mmio = ahci_port_base(ap);
+	struct ahci_port_priv *pp = ap->private_data;
+	u32 status;
+
+	status = readl(port_mmio + PORT_IRQ_STAT);
+	writel(status, port_mmio + PORT_IRQ_STAT);
+
+	pp->intr_status |= status;
+}
+
+irqreturn_t ahci_hw_interrupt(int irq, void *dev_instance)
+{
+	struct ata_port *ap_this = dev_instance;
+	struct ahci_port_priv *pp = ap_this->private_data;
+	struct ata_host *host = ap_this->host;
+	struct ahci_host_priv *hpriv = host->private_data;
+	void __iomem *mmio = hpriv->mmio;
+	unsigned int i;
+	u32 irq_stat, irq_masked;
+
+	VPRINTK("ENTER\n");
+
+	spin_lock(&host->lock);
+
+	irq_stat = readl(mmio + HOST_IRQ_STAT);
+
+	if (!irq_stat) {
+		u32 status = pp->intr_status;
+
+		spin_unlock(&host->lock);
+
+		VPRINTK("EXIT\n");
+
+		return status ? IRQ_WAKE_THREAD : IRQ_NONE;
+	}
+
+	irq_masked = irq_stat & hpriv->port_map;
+
+	for (i = 0; i < host->n_ports; i++) {
+		struct ata_port *ap;
+
+		if (!(irq_masked & (1 << i)))
+			continue;
+
+		ap = host->ports[i];
+		if (ap) {
+			ahci_hw_port_interrupt(ap);
+			VPRINTK("port %u\n", i);
+		} else {
+			VPRINTK("port %u (no irq)\n", i);
+			if (ata_ratelimit())
+				dev_warn(host->dev,
+					 "interrupt on disabled port %u\n", i);
+		}
+	}
+
+	writel(irq_stat, mmio + HOST_IRQ_STAT);
+
+	spin_unlock(&host->lock);
+
+	VPRINTK("EXIT\n");
+
+	return IRQ_WAKE_THREAD;
+}
+EXPORT_SYMBOL_GPL(ahci_hw_interrupt);
+
 irqreturn_t ahci_interrupt(int irq, void *dev_instance)
 {
 	struct ata_host *host = dev_instance;
@@ -2196,6 +2294,14 @@ static int ahci_port_start(struct ata_port *ap)
 	 */
 	pp->intr_mask = DEF_PORT_IRQ;
 
+	/*
+	 * Switch to per-port locking in case each port has its own MSI vector.
+	 */
+	if ((hpriv->flags & AHCI_HFLAG_MULTI_MSI)) {
+		spin_lock_init(&pp->lock);
+		ap->lock = &pp->lock;
+	}
+
 	ap->private_data = pp;
 
 	/* engage engines, captain */