From d1ac1d2622e8f0fd2a25127a8649d135b54db8a9 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Mon, 30 Dec 2013 08:28:13 +0100 Subject: PCI/MSI: Add pci_msi_vec_count() Device drivers can use this interface to obtain the maximum number of MSI interrupts the device supports and use that number, e.g., in a subsequent call to pci_enable_msi_block(). Signed-off-by: Alexander Gordeev Signed-off-by: Bjorn Helgaas Reviewed-by: Tejun Heo --- drivers/pci/msi.c | 41 +++++++++++++++++++++++++++++++++-------- 1 file changed, 33 insertions(+), 8 deletions(-) (limited to 'drivers/pci/msi.c') diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index ce0d4eb91a22..ba6d0a9bdd39 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -842,6 +842,31 @@ static int pci_msi_check_device(struct pci_dev *dev, int nvec, int type) return 0; } +/** + * pci_msi_vec_count - Return the number of MSI vectors a device can send + * @dev: device to report about + * + * This function returns the number of MSI vectors a device requested via + * Multiple Message Capable register. It returns a negative errno if the + * device is not capable sending MSI interrupts. Otherwise, the call succeeds + * and returns a power of two, up to a maximum of 2^5 (32), according to the + * MSI specification. + **/ +int pci_msi_vec_count(struct pci_dev *dev) +{ + int ret; + u16 msgctl; + + if (!dev->msi_cap) + return -EINVAL; + + pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &msgctl); + ret = 1 << ((msgctl & PCI_MSI_FLAGS_QMASK) >> 1); + + return ret; +} +EXPORT_SYMBOL(pci_msi_vec_count); + /** * pci_enable_msi_block - configure device's MSI capability structure * @dev: device to configure @@ -858,13 +883,13 @@ static int pci_msi_check_device(struct pci_dev *dev, int nvec, int type) int pci_enable_msi_block(struct pci_dev *dev, int nvec) { int status, maxvec; - u16 msgctl; - if (!dev->msi_cap || dev->current_state != PCI_D0) + if (dev->current_state != PCI_D0) return -EINVAL; - pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &msgctl); - maxvec = 1 << ((msgctl & PCI_MSI_FLAGS_QMASK) >> 1); + maxvec = pci_msi_vec_count(dev); + if (maxvec < 0) + return maxvec; if (nvec > maxvec) return maxvec; @@ -889,13 +914,13 @@ EXPORT_SYMBOL(pci_enable_msi_block); int pci_enable_msi_block_auto(struct pci_dev *dev, int *maxvec) { int ret, nvec; - u16 msgctl; - if (!dev->msi_cap || dev->current_state != PCI_D0) + if (dev->current_state != PCI_D0) return -EINVAL; - pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &msgctl); - ret = 1 << ((msgctl & PCI_MSI_FLAGS_QMASK) >> 1); + ret = pci_msi_vec_count(dev); + if (ret < 0) + return ret; if (maxvec) *maxvec = ret; -- cgit v1.2.3-59-g8ed1b From 7b92b4f61ec49cb1a5813298f35258bd7ecd3667 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Mon, 30 Dec 2013 08:28:14 +0100 Subject: PCI/MSI: Remove pci_enable_msi_block_auto() The new pci_msi_vec_count() interface makes pci_enable_msi_block_auto() superfluous. Drivers can use pci_msi_vec_count() to learn the maximum number of MSIs supported by the device, and then call pci_enable_msi_block(). pci_enable_msi_block_auto() was introduced recently, and its only user is the AHCI driver, which is also updated by this change. Signed-off-by: Alexander Gordeev Signed-off-by: Bjorn Helgaas Acked-by: Tejun Heo --- Documentation/PCI/MSI-HOWTO.txt | 39 +++++----------------------- drivers/ata/ahci.c | 56 +++++++++++++++++++++++++---------------- drivers/pci/msi.c | 25 ------------------ include/linux/pci.h | 7 ------ 4 files changed, 41 insertions(+), 86 deletions(-) (limited to 'drivers/pci/msi.c') diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt index a8b41788dfde..aa4ad987510d 100644 --- a/Documentation/PCI/MSI-HOWTO.txt +++ b/Documentation/PCI/MSI-HOWTO.txt @@ -127,49 +127,22 @@ on the number of vectors that can be allocated; pci_enable_msi_block() returns as soon as it finds any constraint that doesn't allow the call to succeed. -4.2.3 pci_enable_msi_block_auto - -int pci_enable_msi_block_auto(struct pci_dev *dev, int *count) - -This variation on pci_enable_msi() call allows a device driver to request -the maximum possible number of 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 a positive number, it indicates that it has -succeeded and the returned value is the number of allocated interrupts. 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 + returned -value - 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 the device driver needs to know the number of interrupts the device -supports it can pass the pointer count where that number is stored. The -device driver must decide what action to take if pci_enable_msi_block_auto() -succeeds, but returns a value less than the number of interrupts supported. -If the device driver does not need to know the number of interrupts -supported, it can set the pointer count to NULL. - -4.2.4 pci_disable_msi +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() or -pci_enable_msi_block() or pci_enable_msi_block_auto(). 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. +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. Before calling this function, a device driver must always call free_irq() on any interrupt for which it previously called request_irq(). Failure to do so results in a BUG_ON(), leaving the device with MSI enabled and thus leaking its vector. -4.2.5 pci_msi_vec_count +4.2.4 pci_msi_vec_count int pci_msi_vec_count(struct pci_dev *dev) diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index e2903d03180e..8516f4d47893 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -1095,26 +1095,40 @@ 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 ahci_init_interrupts(struct pci_dev *pdev, unsigned int n_ports, + struct ahci_host_priv *hpriv) { - int rc; - unsigned int maxvec; + int rc, nvec; - 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; - } - } + if (hpriv->flags & AHCI_HFLAG_NO_MSI) + goto intx; + + rc = pci_msi_vec_count(pdev); + if (rc < 0) + goto intx; + + /* + * If number of MSIs is less than number of ports then Sharing Last + * Message mode could be enforced. In this case assume that advantage + * of multipe MSIs is negated and use single MSI mode instead. + */ + if (rc < n_ports) + goto single_msi; + + nvec = rc; + rc = pci_enable_msi_block(pdev, nvec); + if (rc) + goto intx; + return nvec; + +single_msi: + rc = pci_enable_msi(pdev); + if (rc) + goto intx; + return 1; + +intx: pci_intx(pdev, 1); return 0; } @@ -1281,10 +1295,6 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) 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); @@ -1339,6 +1349,10 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) */ n_ports = max(ahci_nr_ports(hpriv->cap), fls(hpriv->port_map)); + n_msis = ahci_init_interrupts(pdev, n_ports, hpriv); + if (n_msis > 1) + hpriv->flags |= AHCI_HFLAG_MULTI_MSI; + host = ata_host_alloc_pinfo(&pdev->dev, ppi, n_ports); if (!host) return -ENOMEM; diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index ba6d0a9bdd39..76507ab13beb 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -911,31 +911,6 @@ int pci_enable_msi_block(struct pci_dev *dev, int nvec) } EXPORT_SYMBOL(pci_enable_msi_block); -int pci_enable_msi_block_auto(struct pci_dev *dev, int *maxvec) -{ - int ret, nvec; - - if (dev->current_state != PCI_D0) - return -EINVAL; - - ret = pci_msi_vec_count(dev); - if (ret < 0) - return ret; - - if (maxvec) - *maxvec = ret; - - do { - nvec = ret; - ret = pci_enable_msi_block(dev, nvec); - } while (ret > 0); - - if (ret < 0) - return ret; - return nvec; -} -EXPORT_SYMBOL(pci_enable_msi_block_auto); - void pci_msi_shutdown(struct pci_dev *dev) { struct msi_desc *desc; diff --git a/include/linux/pci.h b/include/linux/pci.h index 6691de093f1c..86dcf006adcc 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1164,12 +1164,6 @@ static inline int pci_enable_msi_block(struct pci_dev *dev, int nvec) return -ENOSYS; } -static inline int -pci_enable_msi_block_auto(struct pci_dev *dev, int *maxvec) -{ - return -ENOSYS; -} - static inline void pci_msi_shutdown(struct pci_dev *dev) { } static inline void pci_disable_msi(struct pci_dev *dev) @@ -1202,7 +1196,6 @@ static inline int pci_msi_enabled(void) #else int pci_msi_vec_count(struct pci_dev *dev); int pci_enable_msi_block(struct pci_dev *dev, int nvec); -int pci_enable_msi_block_auto(struct pci_dev *dev, int *maxvec); void pci_msi_shutdown(struct pci_dev *dev); void pci_disable_msi(struct pci_dev *dev); int pci_msix_table_size(struct pci_dev *dev); -- cgit v1.2.3-59-g8ed1b From ff1aa430a2fa43189e89c7ddd559f0bee2298288 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Mon, 30 Dec 2013 08:28:15 +0100 Subject: PCI/MSI: Add pci_msix_vec_count() This creates an MSI-X counterpart for pci_msi_vec_count(). Device drivers can use this function to obtain maximum number of MSI-X interrupts the device supports and use that number in a subsequent call to pci_enable_msix(). pci_msix_vec_count() supersedes pci_msix_table_size() and returns a negative errno if device does not support MSI-X interrupts. After this update, callers must always check the returned value. The only user of pci_msix_table_size() was the PCI-Express port driver, which is also updated by this change. Signed-off-by: Alexander Gordeev Signed-off-by: Bjorn Helgaas Reviewed-by: Tejun Heo --- Documentation/PCI/MSI-HOWTO.txt | 13 +++++++++++++ drivers/pci/msi.c | 18 +++++++++++++----- drivers/pci/pcie/portdrv_core.c | 7 ++++--- include/linux/pci.h | 6 +++--- 4 files changed, 33 insertions(+), 11 deletions(-) (limited to 'drivers/pci/msi.c') diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt index aa4ad987510d..b58f4a4d14bb 100644 --- a/Documentation/PCI/MSI-HOWTO.txt +++ b/Documentation/PCI/MSI-HOWTO.txt @@ -243,6 +243,19 @@ MSI-X Table. This address is mapped by the PCI subsystem, and should not be accessed directly by the device driver. If the driver wishes to mask or unmask an interrupt, it should call disable_irq() / enable_irq(). +4.3.4 pci_msix_vec_count + +int pci_msix_vec_count(struct pci_dev *dev) + +This function could be used to retrieve number of entries in the device +MSI-X table. + +If this function returns a negative number, it indicates the device is +not capable of sending MSI-Xs. + +If this function returns a positive number, it indicates the maximum +number of MSI-X interrupt vectors that could be allocated. + 4.4 Handling devices implementing both MSI and MSI-X capabilities If a device implements both MSI and MSI-X capabilities, it can diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 76507ab13beb..bd18ecf74c55 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -948,19 +948,25 @@ void pci_disable_msi(struct pci_dev *dev) EXPORT_SYMBOL(pci_disable_msi); /** - * pci_msix_table_size - return the number of device's MSI-X table entries + * pci_msix_vec_count - return the number of device's MSI-X table entries * @dev: pointer to the pci_dev data structure of MSI-X device function - */ -int pci_msix_table_size(struct pci_dev *dev) + + * This function returns the number of device's MSI-X table entries and + * therefore the number of MSI-X vectors device is capable of sending. + * It returns a negative errno if the device is not capable of sending MSI-X + * interrupts. + **/ +int pci_msix_vec_count(struct pci_dev *dev) { u16 control; if (!dev->msix_cap) - return 0; + return -EINVAL; pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control); return msix_table_size(control); } +EXPORT_SYMBOL(pci_msix_vec_count); /** * pci_enable_msix - configure device's MSI-X capability structure @@ -989,7 +995,9 @@ int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec) if (status) return status; - nr_entries = pci_msix_table_size(dev); + nr_entries = pci_msix_vec_count(dev); + if (nr_entries < 0) + return nr_entries; if (nvec > nr_entries) return nr_entries; diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c index 0b6e76604068..4ab719826dd7 100644 --- a/drivers/pci/pcie/portdrv_core.c +++ b/drivers/pci/pcie/portdrv_core.c @@ -79,9 +79,10 @@ static int pcie_port_enable_msix(struct pci_dev *dev, int *vectors, int mask) u16 reg16; u32 reg32; - nr_entries = pci_msix_table_size(dev); - if (!nr_entries) - return -EINVAL; + nr_entries = pci_msix_vec_count(dev); + if (nr_entries < 0) + return nr_entries; + BUG_ON(!nr_entries); if (nr_entries > PCIE_PORT_MAX_MSIX_ENTRIES) nr_entries = PCIE_PORT_MAX_MSIX_ENTRIES; diff --git a/include/linux/pci.h b/include/linux/pci.h index 86dcf006adcc..cf6125ba649d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1169,9 +1169,9 @@ static inline void pci_msi_shutdown(struct pci_dev *dev) static inline void pci_disable_msi(struct pci_dev *dev) { } -static inline int pci_msix_table_size(struct pci_dev *dev) +static inline int pci_msix_vec_count(struct pci_dev *dev) { - return 0; + return -ENOSYS; } static inline int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec) @@ -1198,7 +1198,7 @@ int pci_msi_vec_count(struct pci_dev *dev); int pci_enable_msi_block(struct pci_dev *dev, int nvec); void pci_msi_shutdown(struct pci_dev *dev); void pci_disable_msi(struct pci_dev *dev); -int pci_msix_table_size(struct pci_dev *dev); +int pci_msix_vec_count(struct pci_dev *dev); int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec); void pci_msix_shutdown(struct pci_dev *dev); void pci_disable_msix(struct pci_dev *dev); -- cgit v1.2.3-59-g8ed1b From 302a2523c277bea0bbe8340312b09507905849ed Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Mon, 30 Dec 2013 08:28:16 +0100 Subject: PCI/MSI: Add pci_enable_msi_range() and pci_enable_msix_range() This adds pci_enable_msi_range(), which supersedes the pci_enable_msi() and pci_enable_msi_block() MSI interfaces. It also adds pci_enable_msix_range(), which supersedes the pci_enable_msix() MSI-X interface. The old interfaces have three categories of return values: negative: failure; caller should not retry positive: failure; value indicates number of interrupts that *could* have been allocated, and caller may retry with a smaller request zero: success; at least as many interrupts allocated as requested It is error-prone to handle these three cases correctly in drivers. The new functions return either a negative error code or a number of successfully allocated MSI/MSI-X interrupts, which is expected to lead to clearer device driver code. pci_enable_msi(), pci_enable_msi_block() and pci_enable_msix() still exist unchanged, but are deprecated and may be removed after callers are updated. [bhelgaas: tweak changelog] Suggested-by: Ben Hutchings Signed-off-by: Alexander Gordeev Signed-off-by: Bjorn Helgaas Reviewed-by: Tejun Heo --- Documentation/PCI/MSI-HOWTO.txt | 261 ++++++++++++++++++++++++++++------------ drivers/pci/msi.c | 74 ++++++++++++ include/linux/pci.h | 14 +++ 3 files changed, 274 insertions(+), 75 deletions(-) (limited to 'drivers/pci/msi.c') diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt index b58f4a4d14bb..a8d01005f480 100644 --- a/Documentation/PCI/MSI-HOWTO.txt +++ b/Documentation/PCI/MSI-HOWTO.txt @@ -82,67 +82,97 @@ Most of the hard work is done for the driver in the PCI layer. It simply has to request that the PCI layer set up the MSI capability for this device. -4.2.1 pci_enable_msi +4.2.1 pci_enable_msi_range -int pci_enable_msi(struct pci_dev *dev) +int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec) -A successful call allocates ONE interrupt to the device, regardless -of how many MSIs the device supports. The device is switched from -pin-based interrupt mode to MSI mode. The dev->irq number is changed -to a new number which represents the message signaled interrupt; -consequently, this function should be called before the driver calls -request_irq(), because an MSI is delivered via a vector that is -different from the vector of a pin-based interrupt. +This function allows a device driver to request any number of MSI +interrupts within specified range from 'minvec' to 'maxvec'. -4.2.2 pci_enable_msi_block +If this function returns a positive number it indicates the number of +MSI interrupts that have been successfully allocated. In this case +the device is switched from pin-based interrupt mode to MSI mode 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 + returned value - 1. Device driver can use the returned +number of successfully allocated MSI interrupts to further allocate +and initialize device resources. -int pci_enable_msi_block(struct pci_dev *dev, int count) +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. -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). +This function should be called before the driver calls request_irq(), +because MSI interrupts are delivered via vectors that are different +from the vector of a pin-based interrupt. -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. +It is ideal if drivers can cope with a variable number of MSI interrupts; +there are many reasons why the platform may not be able to provide the +exact number that a driver asks for. -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 is -less than 'count' and indicates the number of interrupts that could have -been allocated. In neither case is the irq value updated or the device -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 requested. -For instance, the driver could still make use of fewer interrupts; -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() -returns as soon as it finds any constraint that doesn't allow the -call to succeed. - -4.2.3 pci_disable_msi +There could be devices that can not operate with just any number of MSI +interrupts within a range. See chapter 4.3.1.3 to get the idea how to +handle such devices for MSI-X - the same logic applies to MSI. + +4.2.1.1 Maximum possible number of MSI interrupts + +The typical usage of MSI interrupts is to allocate as many vectors as +possible, likely up to the limit returned by pci_msi_vec_count() function: + +static int foo_driver_enable_msi(struct pci_dev *pdev, int nvec) +{ + return pci_enable_msi_range(pdev, 1, nvec); +} + +Note the value of 'minvec' parameter is 1. As 'minvec' is inclusive, +the value of 0 would be meaningless and could result in error. + +Some devices have a minimal limit on number of MSI interrupts. +In this case the function could look like this: + +static int foo_driver_enable_msi(struct pci_dev *pdev, int nvec) +{ + return pci_enable_msi_range(pdev, FOO_DRIVER_MINIMUM_NVEC, nvec); +} + +4.2.1.2 Exact number of MSI interrupts + +If a driver is unable or unwilling to deal with a variable number of MSI +interrupts it could request a particular number of interrupts by passing +that number to pci_enable_msi_range() function as both 'minvec' and 'maxvec' +parameters: + +static int foo_driver_enable_msi(struct pci_dev *pdev, int nvec) +{ + return pci_enable_msi_range(pdev, nvec, nvec); +} + +4.2.1.3 Single MSI mode + +The most notorious example of the request type described above is +enabling the single MSI mode for a device. It could be done by passing +two 1s as 'minvec' and 'maxvec': + +static int foo_driver_enable_single_msi(struct pci_dev *pdev) +{ + return pci_enable_msi_range(pdev, 1, 1); +} + +4.2.2 pci_disable_msi void pci_disable_msi(struct pci_dev *dev) -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. +This function should be used to undo the effect of pci_enable_msi_range(). +Calling it restores dev->irq to the pin-based interrupt number and frees +the previously allocated MSIs. The interrupts may subsequently be assigned +to another device, so drivers should not cache the value of dev->irq. Before calling this function, a device driver must always call free_irq() on any interrupt for which it previously called request_irq(). Failure to do so results in a BUG_ON(), leaving the device with MSI enabled and thus leaking its vector. -4.2.4 pci_msi_vec_count +4.2.3 pci_msi_vec_count int pci_msi_vec_count(struct pci_dev *dev) @@ -176,26 +206,31 @@ in each element of the array to indicate for which entries the kernel should assign interrupts; it is invalid to fill in two entries with the same number. -4.3.1 pci_enable_msix +4.3.1 pci_enable_msix_range -int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec) +int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, + int minvec, int maxvec) -Calling this function asks the PCI subsystem to allocate 'nvec' MSIs. +Calling this function asks the PCI subsystem to allocate any number of +MSI-X interrupts within specified range from 'minvec' to 'maxvec'. The 'entries' argument is a pointer to an array of msix_entry structs -which should be at least 'nvec' entries in size. On success, the -device is switched into MSI-X mode and the function returns 0. -The 'vector' member in each entry is populated with the interrupt number; +which should be at least 'maxvec' entries in size. + +On success, the device is switched into MSI-X mode and the function +returns the number of MSI-X interrupts that have been successfully +allocated. In this case the 'vector' member in entries numbered from +0 to the returned value - 1 is populated with the interrupt number; the driver should then call request_irq() for each 'vector' that it decides to use. The device driver is responsible for keeping track of the interrupts assigned to the MSI-X vectors so it can free them again later. +Device driver can use the returned number of successfully allocated MSI-X +interrupts to further allocate and initialize device resources. If this function returns a negative number, it indicates an error and the driver should not attempt to allocate any more MSI-X interrupts for -this device. If it returns a positive number, it indicates the maximum -number of interrupt vectors that could have been allocated. See example -below. +this device. -This function, in contrast with pci_enable_msi(), does not adjust +This function, in contrast with pci_enable_msi_range(), does not adjust dev->irq. The device will not generate interrupts for this interrupt number once MSI-X is enabled. @@ -206,28 +241,103 @@ It is ideal if drivers can cope with a variable number of MSI-X interrupts; there are many reasons why the platform may not be able to provide the exact number that a driver asks for. -A request loop to achieve that might look like: +There could be devices that can not operate with just any number of MSI-X +interrupts within a range. E.g., an network adapter might need let's say +four vectors per each queue it provides. Therefore, a number of MSI-X +interrupts allocated should be a multiple of four. In this case interface +pci_enable_msix_range() can not be used alone to request MSI-X interrupts +(since it can allocate any number within the range, without any notion of +the multiple of four) and the device driver should master a custom logic +to request the required number of MSI-X interrupts. + +4.3.1.1 Maximum possible number of MSI-X interrupts + +The typical usage of MSI-X interrupts is to allocate as many vectors as +possible, likely up to the limit returned by pci_msix_vec_count() function: + +static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec) +{ + return pci_enable_msi_range(adapter->pdev, adapter->msix_entries, + 1, nvec); +} + +Note the value of 'minvec' parameter is 1. As 'minvec' is inclusive, +the value of 0 would be meaningless and could result in error. + +Some devices have a minimal limit on number of MSI-X interrupts. +In this case the function could look like this: static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec) { - while (nvec >= FOO_DRIVER_MINIMUM_NVEC) { - rc = pci_enable_msix(adapter->pdev, - adapter->msix_entries, nvec); - if (rc > 0) - nvec = rc; - else - return rc; + return pci_enable_msi_range(adapter->pdev, adapter->msix_entries, + FOO_DRIVER_MINIMUM_NVEC, nvec); +} + +4.3.1.2 Exact number of MSI-X interrupts + +If a driver is unable or unwilling to deal with a variable number of MSI-X +interrupts it could request a particular number of interrupts by passing +that number to pci_enable_msix_range() function as both 'minvec' and 'maxvec' +parameters: + +static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec) +{ + return pci_enable_msi_range(adapter->pdev, adapter->msix_entries, + nvec, nvec); +} + +4.3.1.3 Specific requirements to the number of MSI-X interrupts + +As noted above, there could be devices that can not operate with just any +number of MSI-X interrupts within a range. E.g., let's assume a device that +is only capable sending the number of MSI-X interrupts which is a power of +two. A routine that enables MSI-X mode for such device might look like this: + +/* + * Assume 'minvec' and 'maxvec' are non-zero + */ +static int foo_driver_enable_msix(struct foo_adapter *adapter, + int minvec, int maxvec) +{ + int rc; + + minvec = roundup_pow_of_two(minvec); + maxvec = rounddown_pow_of_two(maxvec); + + if (minvec > maxvec) + return -ERANGE; + +retry: + rc = pci_enable_msix_range(adapter->pdev, adapter->msix_entries, + maxvec, maxvec); + /* + * -ENOSPC is the only error code allowed to be analized + */ + if (rc == -ENOSPC) { + if (maxvec == 1) + return -ENOSPC; + + maxvec /= 2; + + if (minvec > maxvec) + return -ENOSPC; + + goto retry; } - return -ENOSPC; + return rc; } +Note how pci_enable_msix_range() return value is analized for a fallback - +any error code other than -ENOSPC indicates a fatal error and should not +be retried. + 4.3.2 pci_disable_msix void pci_disable_msix(struct pci_dev *dev) -This function should be used to undo the effect of pci_enable_msix(). It frees -the previously allocated message signaled interrupts. The interrupts may +This function should be used to undo the effect of pci_enable_msix_range(). +It frees the previously allocated MSI-X interrupts. The interrupts may subsequently be assigned to another device, so drivers should not cache the value of the 'vector' elements over a call to pci_disable_msix(). @@ -261,13 +371,14 @@ number of MSI-X interrupt vectors that could be allocated. If a device implements both MSI and MSI-X capabilities, it can run in either MSI mode or MSI-X mode, but not both simultaneously. This is a requirement of the PCI spec, and it is enforced by the -PCI layer. Calling pci_enable_msi() when MSI-X is already enabled or -pci_enable_msix() when MSI is already enabled results in an error. -If a device driver wishes to switch between MSI and MSI-X at runtime, -it must first quiesce the device, then switch it back to pin-interrupt -mode, before calling pci_enable_msi() or pci_enable_msix() and resuming -operation. This is not expected to be a common operation but may be -useful for debugging or testing during development. +PCI layer. Calling pci_enable_msi_range() when MSI-X is already +enabled or pci_enable_msix_range() when MSI is already enabled +results in an error. If a device driver wishes to switch between MSI +and MSI-X at runtime, it must first quiesce the device, then switch +it back to pin-interrupt mode, before calling pci_enable_msi_range() +or pci_enable_msix_range() and resuming operation. This is not expected +to be a common operation but may be useful for debugging or testing +during development. 4.5 Considerations when using MSIs @@ -382,5 +493,5 @@ or disabled (0). If 0 is found in any of the msi_bus files belonging to bridges between the PCI root and the device, MSIs are disabled. It is also worth checking the device driver to see whether it supports MSIs. -For example, it may contain calls to pci_enable_msi(), pci_enable_msix() or -pci_enable_msi_block(). +For example, it may contain calls to pci_enable_msi_range() or +pci_enable_msix_range(). diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index bd18ecf74c55..e6bd8e57d92d 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -1102,3 +1102,77 @@ void pci_msi_init_pci_dev(struct pci_dev *dev) if (dev->msix_cap) msix_set_enable(dev, 0); } + +/** + * pci_enable_msi_range - configure device's MSI capability structure + * @dev: device to configure + * @minvec: minimal number of interrupts to configure + * @maxvec: maximum number of interrupts to configure + * + * This function tries to allocate a maximum possible number of interrupts in a + * range between @minvec and @maxvec. It returns a negative errno if an error + * occurs. If it succeeds, it returns the actual number of interrupts allocated + * 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_range(struct pci_dev *dev, int minvec, int maxvec) +{ + int nvec = maxvec; + int rc; + + if (maxvec < minvec) + return -ERANGE; + + do { + rc = pci_enable_msi_block(dev, nvec); + if (rc < 0) { + return rc; + } else if (rc > 0) { + if (rc < minvec) + return -ENOSPC; + nvec = rc; + } + } while (rc); + + return nvec; +} +EXPORT_SYMBOL(pci_enable_msi_range); + +/** + * pci_enable_msix_range - configure device's MSI-X capability structure + * @dev: pointer to the pci_dev data structure of MSI-X device function + * @entries: pointer to an array of MSI-X entries + * @minvec: minimum number of MSI-X irqs requested + * @maxvec: maximum number of MSI-X irqs requested + * + * Setup the MSI-X capability structure of device function with a maximum + * possible number of interrupts in the range between @minvec and @maxvec + * upon its software driver call to request for MSI-X mode enabled on its + * hardware device function. It returns a negative errno if an error occurs. + * If it succeeds, it returns the actual number of interrupts allocated and + * indicates the successful configuration of MSI-X capability structure + * with new allocated MSI-X interrupts. + **/ +int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, + int minvec, int maxvec) +{ + int nvec = maxvec; + int rc; + + if (maxvec < minvec) + return -ERANGE; + + do { + rc = pci_enable_msix(dev, entries, nvec); + if (rc < 0) { + return rc; + } else if (rc > 0) { + if (rc < minvec) + return -ENOSPC; + nvec = rc; + } + } while (rc); + + return nvec; +} +EXPORT_SYMBOL(pci_enable_msix_range); diff --git a/include/linux/pci.h b/include/linux/pci.h index cf6125ba649d..6e32a2820126 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1193,6 +1193,17 @@ static inline int pci_msi_enabled(void) { return 0; } + +static inline int pci_enable_msi_range(struct pci_dev *dev, int minvec, + int maxvec) +{ + return -ENOSYS; +} +static inline int pci_enable_msix_range(struct pci_dev *dev, + struct msix_entry *entries, int minvec, int maxvec) +{ + return -ENOSYS; +} #else int pci_msi_vec_count(struct pci_dev *dev); int pci_enable_msi_block(struct pci_dev *dev, int nvec); @@ -1205,6 +1216,9 @@ void pci_disable_msix(struct pci_dev *dev); void msi_remove_pci_irq_vectors(struct pci_dev *dev); void pci_restore_msi_state(struct pci_dev *dev); int pci_msi_enabled(void); +int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec); +int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, + int minvec, int maxvec); #endif #ifdef CONFIG_PCIEPORTBUS -- cgit v1.2.3-59-g8ed1b