PCI MSI: Add support for multiple MSI

Add the new API pci_enable_msi_block() to allow drivers to
request multiple MSI and reimplement pci_enable_msi in terms of
pci_enable_msi_block.  Ensure that the architecture back ends don't
have to know about multiple MSI.

Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>

7 files changed, 116 insertions, 41 deletions

diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt
index 1c02431f1d1a..9494f6dc38eb 100644
--- a/Documentation/PCI/MSI-HOWTO.txt
+++ b/Documentation/PCI/MSI-HOWTO.txt
@@ -94,15 +94,48 @@ This function should be called before the driver calls request_irq()
 since enabling MSIs disables the pin-based IRQ and the driver will not
 receive interrupts on the old interrupt.
 
-4.2.2 pci_disable_msi
+4.2.2 pci_enable_msi_block
+
+int pci_enable_msi_block(struct pci_dev *dev, int count)
+
+This variation on the above call allows a device driver to request multiple
+MSIs.  The MSI specification only allows interrupts to be allocated in
+powers of two, up to a maximum of 2^5 (32).
+
+If this function returns 0, it has succeeded in allocating at least as many
+interrupts as the driver requested (it may have allocated more in order
+to satisfy the power-of-two requirement).  In this case, the function
+enables MSI on this device and updates dev->irq to be the lowest of
+the new interrupts assigned to it.  The other interrupts assigned to
+the device are in the range dev->irq to dev->irq + count - 1.
+
+If this function returns a negative number, it indicates an error and
+the driver should not attempt to request any more MSI interrupts for
+this device.  If this function returns a positive number, it will be
+less than 'count' and indicate the number of interrupts that could have
+been allocated.  In neither case will the irq value have been
+updated, nor will the device have been switched into MSI mode.
+
+The device driver must decide what action to take if
+pci_enable_msi_block() returns a value less than the number asked for.
+Some devices can make use of fewer interrupts than the maximum they
+request; in this case the driver should call pci_enable_msi_block()
+again.  Note that it is not guaranteed to succeed, even when the
+'count' has been reduced to the value returned from a previous call to
+pci_enable_msi_block().  This is because there are multiple constraints
+on the number of vectors that can be allocated; pci_enable_msi_block()
+will return as soon as it finds any constraint that doesn't allow the
+call to succeed.
+
+4.2.3 pci_disable_msi
 
 void pci_disable_msi(struct pci_dev *dev)
 
-This function should be used to undo the effect of pci_enable_msi().
-Calling it restores dev->irq to the pin-based interrupt number and frees
-the previously allocated message signaled interrupt(s).  The interrupt
-may subsequently be assigned to another device, so drivers should not
-cache the value of dev->irq.
+This function should be used to undo the effect of pci_enable_msi() or
+pci_enable_msi_block().  Calling it restores dev->irq to the pin-based
+interrupt number and frees the previously allocated message signaled
+interrupt(s).  The interrupt may subsequently be assigned to another
+device, so drivers should not cache the value of dev->irq.
 
 A device driver must always call free_irq() on the interrupt(s)
 for which it has called request_irq() before calling this function.
diff --git a/arch/powerpc/kernel/msi.c b/arch/powerpc/kernel/msi.c
index 3bb7d3dd28be..0c16e2a854e5 100644
--- a/arch/powerpc/kernel/msi.c
+++ b/arch/powerpc/kernel/msi.c
@@ -19,6 +19,10 @@ int arch_msi_check_device(struct pci_dev* dev, int nvec, int type)
                 return -ENOSYS;
         }
 
+        /* PowerPC doesn't support multiple MSI yet */
+        if (type == PCI_CAP_ID_MSI && nvec > 1)
+                return 1;
+
         if (ppc_md.msi_check_device) {
                 pr_debug("msi: Using platform check routine.\n");
                 return ppc_md.msi_check_device(dev, nvec, type);
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index bc7ac4da90d7..a09549a6321b 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -3510,6 +3510,10 @@ int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
         int index = 0;
 #endif
 
+        /* x86 doesn't support multiple MSI yet */
+        if (type == PCI_CAP_ID_MSI && nvec > 1)
+                return 1;
+
         irq_want = nr_irqs_gsi;
         sub_handle = 0;
         list_for_each_entry(msidesc, &dev->msi_list, list) {
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index adcc78242571..6f2e6295e773 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -40,6 +40,13 @@ int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
         struct msi_desc *entry;
         int ret;
 
+        /*
+         * If an architecture wants to support multiple MSI, it needs to
+         * override arch_setup_msi_irqs()
+         */
+        if (type == PCI_CAP_ID_MSI && nvec > 1)
+                return 1;
+
         list_for_each_entry(entry, &dev->msi_list, list) {
                 ret = arch_setup_msi_irq(dev, entry);
                 if (ret < 0)
@@ -58,8 +65,12 @@ void arch_teardown_msi_irqs(struct pci_dev *dev)
         struct msi_desc *entry;
 
         list_for_each_entry(entry, &dev->msi_list, list) {
-                if (entry->irq != 0)
-                        arch_teardown_msi_irq(entry->irq);
+                int i, nvec;
+                if (entry->irq == 0)
+                        continue;
+                nvec = 1 << entry->msi_attrib.multiple;
+                for (i = 0; i < nvec; i++)
+                        arch_teardown_msi_irq(entry->irq + i);
         }
 }
 #endif
@@ -163,7 +174,8 @@ static void msi_set_mask_bit(unsigned irq, u32 flag)
                 msix_mask_irq(desc, flag);
                 readl(desc->mask_base);         /* Flush write to device */
         } else {
-                msi_mask_irq(desc, 1, flag);
+                unsigned offset = irq - desc->dev->irq;
+                msi_mask_irq(desc, 1 << offset, flag << offset);
         }
 }
 
@@ -229,6 +241,12 @@ void write_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
         } else {
                 struct pci_dev *dev = entry->dev;
                 int pos = entry->msi_attrib.pos;
+                u16 msgctl;
+
+                pci_read_config_word(dev, msi_control_reg(pos), &msgctl);
+                msgctl &= ~PCI_MSI_FLAGS_QSIZE;
+                msgctl |= entry->msi_attrib.multiple << 4;
+                pci_write_config_word(dev, msi_control_reg(pos), msgctl);
 
                 pci_write_config_dword(dev, msi_lower_address_reg(pos),
                                         msg->address_lo);
@@ -291,7 +309,7 @@ static void __pci_restore_msi_state(struct pci_dev *dev)
         pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &control);
         msi_mask_irq(entry, msi_capable_mask(control), entry->masked);
         control &= ~PCI_MSI_FLAGS_QSIZE;
-        control |= PCI_MSI_FLAGS_ENABLE;
+        control |= (entry->msi_attrib.multiple << 4) | PCI_MSI_FLAGS_ENABLE;
         pci_write_config_word(dev, pos + PCI_MSI_FLAGS, control);
 }
 
@@ -332,13 +350,15 @@ EXPORT_SYMBOL_GPL(pci_restore_msi_state);
 /**
  * msi_capability_init - configure device's MSI capability structure
  * @dev: pointer to the pci_dev data structure of MSI device function
+ * @nvec: number of interrupts to allocate
  *
- * Setup the MSI capability structure of device function with a single
- * MSI irq, regardless of device function is capable of handling
- * multiple messages. A return of zero indicates the successful setup
- * of an entry zero with the new MSI irq or non-zero for otherwise.
- **/
-static int msi_capability_init(struct pci_dev *dev)
+ * Setup the MSI capability structure of the device with the requested
+ * number of interrupts.  A return value of zero indicates the successful
+ * setup of an entry with the new MSI irq.  A negative return value indicates
+ * an error, and a positive return value indicates the number of interrupts
+ * which could have been allocated.
+ */
+static int msi_capability_init(struct pci_dev *dev, int nvec)
 {
         struct msi_desc *entry;
         int pos, ret;
@@ -371,7 +391,7 @@ static int msi_capability_init(struct pci_dev *dev)
         list_add_tail(&entry->list, &dev->msi_list);
 
         /* Configure MSI capability structure */
-        ret = arch_setup_msi_irqs(dev, 1, PCI_CAP_ID_MSI);
+        ret = arch_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSI);
         if (ret) {
                 msi_free_irqs(dev);
                 return ret;
@@ -524,35 +544,48 @@ static int pci_msi_check_device(struct pci_dev* dev, int nvec, int type)
 }
 
 /**
- * pci_enable_msi - configure device's MSI capability structure
- * @dev: pointer to the pci_dev data structure of MSI device function
+ * pci_enable_msi_block - configure device's MSI capability structure
+ * @dev: device to configure
+ * @nvec: number of interrupts to configure
  *
- * Setup the MSI capability structure of device function with
- * a single MSI irq upon its software driver call to request for
- * MSI mode enabled on its hardware device function. A return of zero
- * indicates the successful setup of an entry zero with the new MSI
- * irq or non-zero for otherwise.
- **/
-int pci_enable_msi(struct pci_dev* dev)
+ * Allocate IRQs for a device with the MSI capability.
+ * This function returns a negative errno if an error occurs.  If it
+ * is unable to allocate the number of interrupts requested, it returns
+ * the number of interrupts it might be able to allocate.  If it successfully
+ * allocates at least the number of interrupts requested, it returns 0 and
+ * updates the @dev's irq member to the lowest new interrupt number; the
+ * other interrupt numbers allocated to this device are consecutive.
+ */
+int pci_enable_msi_block(struct pci_dev *dev, unsigned int nvec)
 {
-        int status;
+        int status, pos, maxvec;
+        u16 msgctl;
+
+        pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
+        if (!pos)
+                return -EINVAL;
+        pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl);
+        maxvec = 1 << ((msgctl & PCI_MSI_FLAGS_QMASK) >> 1);
+        if (nvec > maxvec)
+                return maxvec;
 
-        status = pci_msi_check_device(dev, 1, PCI_CAP_ID_MSI);
+        status = pci_msi_check_device(dev, nvec, PCI_CAP_ID_MSI);
         if (status)
                 return status;
 
         WARN_ON(!!dev->msi_enabled);
 
-        /* Check whether driver already requested for MSI-X irqs */
+        /* Check whether driver already requested MSI-X irqs */
         if (dev->msix_enabled) {
                 dev_info(&dev->dev, "can't enable MSI "
                          "(MSI-X already enabled)\n");
                 return -EINVAL;
         }
-        status = msi_capability_init(dev);
+
+        status = msi_capability_init(dev, nvec);
         return status;
 }
-EXPORT_SYMBOL(pci_enable_msi);
+EXPORT_SYMBOL(pci_enable_msi_block);
 
 void pci_msi_shutdown(struct pci_dev *dev)
 {
@@ -599,8 +632,12 @@ static int msi_free_irqs(struct pci_dev* dev)
         struct msi_desc *entry, *tmp;
 
         list_for_each_entry(entry, &dev->msi_list, list) {
-                if (entry->irq)
-                        BUG_ON(irq_has_action(entry->irq));
+                int i, nvec;
+                if (!entry->irq)
+                        continue;
+                nvec = 1 << entry->msi_attrib.multiple;
+                for (i = 0; i < nvec; i++)
+                        BUG_ON(irq_has_action(entry->irq + i));
         }
 
         arch_teardown_msi_irqs(dev);
diff --git a/drivers/pci/msi.h b/drivers/pci/msi.h
index 3898f5237144..71f4df2ef654 100644
--- a/drivers/pci/msi.h
+++ b/drivers/pci/msi.h
@@ -20,14 +20,8 @@
 #define msi_mask_bits_reg(base, is64bit) \
         ( (is64bit == 1) ? base+PCI_MSI_MASK_BIT : base+PCI_MSI_MASK_BIT-4)
 #define msi_disable(control)            control &= ~PCI_MSI_FLAGS_ENABLE
-#define multi_msi_capable(control) \
-        (1 << ((control & PCI_MSI_FLAGS_QMASK) >> 1))
-#define multi_msi_enable(control, num) \
-        control |= (((num >> 1) << 4) & PCI_MSI_FLAGS_QSIZE);
 #define is_64bit_address(control)       (!!(control & PCI_MSI_FLAGS_64BIT))
 #define is_mask_bit_support(control)    (!!(control & PCI_MSI_FLAGS_MASKBIT))
-#define msi_enable(control, num) multi_msi_enable(control, num); \
-        control |= PCI_MSI_FLAGS_ENABLE
 
 #define msix_table_offset_reg(base)     (base + 0x04)
 #define msix_pba_offset_reg(base)       (base + 0x08)
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 37c1bbe546e5..6991ab5b24d1 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -21,6 +21,7 @@ extern void write_msi_msg(unsigned int irq, struct msi_msg *msg);
 struct msi_desc {
         struct {
                 __u8    is_msix : 1;
+                __u8    multiple: 3;    /* log2 number of messages */
                 __u8    maskbit : 1;    /* mask-pending bit supported ?   */
                 __u8    is_64   : 1;    /* Address size: 0=32bit 1=64bit  */
                 __u8    pos;            /* Location of the msi capability */
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 7baf2a5db12a..1f6c5ddaae36 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -789,7 +789,7 @@ struct msix_entry {
 
 
 #ifndef CONFIG_PCI_MSI
-static inline int pci_enable_msi(struct pci_dev *dev)
+static inline int pci_enable_msi_block(struct pci_dev *dev, unsigned int nvec)
 {
         return -1;
 }
@@ -824,7 +824,7 @@ static inline int pci_msi_enabled(void)
         return 0;
 }
 #else
-extern int pci_enable_msi(struct pci_dev *dev);
+extern int pci_enable_msi_block(struct pci_dev *dev, unsigned int nvec);
 extern void pci_msi_shutdown(struct pci_dev *dev);
 extern void pci_disable_msi(struct pci_dev *dev);
 extern int pci_msix_table_size(struct pci_dev *dev);
@@ -846,6 +846,8 @@ static inline int pcie_aspm_enabled(void)
 extern int pcie_aspm_enabled(void);
 #endif
 
+#define pci_enable_msi(pdev)    pci_enable_msi_block(pdev, 1)
+
 #ifdef CONFIG_HT_IRQ
 /* The functions a driver should call */
 int  ht_create_irq(struct pci_dev *dev, int idx);