diff options
106 files changed, 3428 insertions, 1655 deletions
diff --git a/Documentation/ABI/testing/sysfs-bus-pci b/Documentation/ABI/testing/sysfs-bus-pci index 6bf68053e4b..25be3250f7d 100644 --- a/Documentation/ABI/testing/sysfs-bus-pci +++ b/Documentation/ABI/testing/sysfs-bus-pci @@ -84,6 +84,16 @@ Description: from this part of the device tree. Depends on CONFIG_HOTPLUG. +What: /sys/bus/pci/devices/.../reset +Date: July 2009 +Contact: Michael S. Tsirkin <mst@redhat.com> +Description: + Some devices allow an individual function to be reset + without affecting other functions in the same device. + For devices that have this support, a file named reset + will be present in sysfs. Writing 1 to this file + will perform reset. + What: /sys/bus/pci/devices/.../vpd Date: February 2008 Contact: Ben Hutchings <bhutchings@solarflare.com> diff --git a/Documentation/PCI/pci-error-recovery.txt b/Documentation/PCI/pci-error-recovery.txt index 6650af43252..e83f2ea7641 100644 --- a/Documentation/PCI/pci-error-recovery.txt +++ b/Documentation/PCI/pci-error-recovery.txt @@ -4,15 +4,17 @@ February 2, 2006 Current document maintainer: - Linas Vepstas <linas@austin.ibm.com> + Linas Vepstas <linasvepstas@gmail.com> + updated by Richard Lary <rlary@us.ibm.com> + and Mike Mason <mmlnx@us.ibm.com> on 27-Jul-2009 Many PCI bus controllers are able to detect a variety of hardware PCI errors on the bus, such as parity errors on the data and address busses, as well as SERR and PERR errors. Some of the more advanced chipsets are able to deal with these errors; these include PCI-E chipsets, -and the PCI-host bridges found on IBM Power4 and Power5-based pSeries -boxes. A typical action taken is to disconnect the affected device, +and the PCI-host bridges found on IBM Power4, Power5 and Power6-based +pSeries boxes. A typical action taken is to disconnect the affected device, halting all I/O to it. The goal of a disconnection is to avoid system corruption; for example, to halt system memory corruption due to DMA's to "wild" addresses. Typically, a reconnection mechanism is also @@ -37,10 +39,11 @@ is forced by the need to handle multi-function devices, that is, devices that have multiple device drivers associated with them. In the first stage, each driver is allowed to indicate what type of reset it desires, the choices being a simple re-enabling of I/O -or requesting a hard reset (a full electrical #RST of the PCI card). -If any driver requests a full reset, that is what will be done. +or requesting a slot reset. -After a full reset and/or a re-enabling of I/O, all drivers are +If any driver requests a slot reset, that is what will be done. + +After a reset and/or a re-enabling of I/O, all drivers are again notified, so that they may then perform any device setup/config that may be required. After these have all completed, a final "resume normal operations" event is sent out. @@ -101,7 +104,7 @@ if it implements any, it must implement error_detected(). If a callback is not implemented, the corresponding feature is considered unsupported. For example, if mmio_enabled() and resume() aren't there, then it is assumed that the driver is not doing any direct recovery and requires -a reset. If link_reset() is not implemented, the card is assumed as +a slot reset. If link_reset() is not implemented, the card is assumed to not care about link resets. Typically a driver will want to know about a slot_reset(). @@ -111,7 +114,7 @@ sequence described below. STEP 0: Error Event ------------------- -PCI bus error is detect by the PCI hardware. On powerpc, the slot +A PCI bus error is detected by the PCI hardware. On powerpc, the slot is isolated, in that all I/O is blocked: all reads return 0xffffffff, all writes are ignored. @@ -139,7 +142,7 @@ The driver must return one of the following result codes: a chance to extract some diagnostic information (see mmio_enable, below). - PCI_ERS_RESULT_NEED_RESET: - Driver returns this if it can't recover without a hard + Driver returns this if it can't recover without a slot reset. - PCI_ERS_RESULT_DISCONNECT: Driver returns this if it doesn't want to recover at all. @@ -169,11 +172,11 @@ is STEP 6 (Permanent Failure). >>> The current powerpc implementation doesn't much care if the device >>> attempts I/O at this point, or not. I/O's will fail, returning ->>> a value of 0xff on read, and writes will be dropped. If the device ->>> driver attempts more than 10K I/O's to a frozen adapter, it will ->>> assume that the device driver has gone into an infinite loop, and ->>> it will panic the kernel. There doesn't seem to be any other ->>> way of stopping a device driver that insists on spinning on I/O. +>>> a value of 0xff on read, and writes will be dropped. If more than +>>> EEH_MAX_FAILS I/O's are attempted to a frozen adapter, EEH +>>> assumes that the device driver has gone into an infinite loop +>>> and prints an error to syslog. A reboot is then required to +>>> get the device working again. STEP 2: MMIO Enabled ------------------- @@ -182,15 +185,14 @@ DMA), and then calls the mmio_enabled() callback on all affected device drivers. This is the "early recovery" call. IOs are allowed again, but DMA is -not (hrm... to be discussed, I prefer not), with some restrictions. This -is NOT a callback for the driver to start operations again, only to -peek/poke at the device, extract diagnostic information, if any, and -eventually do things like trigger a device local reset or some such, -but not restart operations. This is callback is made if all drivers on -a segment agree that they can try to recover and if no automatic link reset -was performed by the HW. If the platform can't just re-enable IOs without -a slot reset or a link reset, it wont call this callback, and instead -will have gone directly to STEP 3 (Link Reset) or STEP 4 (Slot Reset) +not, with some restrictions. This is NOT a callback for the driver to +start operations again, only to peek/poke at the device, extract diagnostic +information, if any, and eventually do things like trigger a device local +reset or some such, but not restart operations. This callback is made if +all drivers on a segment agree that they can try to recover and if no automatic +link reset was performed by the HW. If the platform can't just re-enable IOs +without a slot reset or a link reset, it will not call this callback, and +instead will have gone directly to STEP 3 (Link Reset) or STEP 4 (Slot Reset) >>> The following is proposed; no platform implements this yet: >>> Proposal: All I/O's should be done _synchronously_ from within @@ -228,9 +230,6 @@ proceeds to either STEP3 (Link Reset) or to STEP 5 (Resume Operations). If any driver returned PCI_ERS_RESULT_NEED_RESET, then the platform proceeds to STEP 4 (Slot Reset) ->>> The current powerpc implementation does not implement this callback. - - STEP 3: Link Reset ------------------ The platform resets the link, and then calls the link_reset() callback @@ -253,16 +252,33 @@ The platform then proceeds to either STEP 4 (Slot Reset) or STEP 5 >>> The current powerpc implementation does not implement this callback. - STEP 4: Slot Reset ------------------ -The platform performs a soft or hard reset of the device, and then -calls the slot_reset() callback. -A soft reset consists of asserting the adapter #RST line and then +In response to a return value of PCI_ERS_RESULT_NEED_RESET, the +the platform will peform a slot reset on the requesting PCI device(s). +The actual steps taken by a platform to perform a slot reset +will be platform-dependent. Upon completion of slot reset, the +platform will call the device slot_reset() callback. + +Powerpc platforms implement two levels of slot reset: +soft reset(default) and fundamental(optional) reset. + +Powerpc soft reset consists of asserting the adapter #RST line and then restoring the PCI BAR's and PCI configuration header to a state that is equivalent to what it would be after a fresh system power-on followed by power-on BIOS/system firmware initialization. +Soft reset is also known as hot-reset. + +Powerpc fundamental reset is supported by PCI Express cards only +and results in device's state machines, hardware logic, port states and +configuration registers to initialize to their default conditions. + +For most PCI devices, a soft reset will be sufficient for recovery. +Optional fundamental reset is provided to support a limited number +of PCI Express PCI devices for which a soft reset is not sufficient +for recovery. + If the platform supports PCI hotplug, then the reset might be performed by toggling the slot electrical power off/on. @@ -274,10 +290,12 @@ may result in hung devices, kernel panics, or silent data corruption. This call gives drivers the chance to re-initialize the hardware (re-download firmware, etc.). At this point, the driver may assume -that he card is in a fresh state and is fully functional. In -particular, interrupt generation should work normally. +that the card is in a fresh state and is fully functional. The slot +is unfrozen and the driver has full access to PCI config space, +memory mapped I/O space and DMA. Interrupts (Legacy, MSI, or MSI-X) +will also be available. -Drivers should not yet restart normal I/O processing operations +Drivers should not restart normal I/O processing operations at this point. If all device drivers report success on this callback, the platform will call resume() to complete the sequence, and let the driver restart normal I/O processing. @@ -302,11 +320,21 @@ driver performs device init only from PCI function 0: - PCI_ERS_RESULT_DISCONNECT Same as above. +Drivers for PCI Express cards that require a fundamental reset must +set the needs_freset bit in the pci_dev structure in their probe function. +For example, the QLogic qla2xxx driver sets the needs_freset bit for certain +PCI card types: + ++ /* Set EEH reset type to fundamental if required by hba */ ++ if (IS_QLA24XX(ha) || IS_QLA25XX(ha) || IS_QLA81XX(ha)) ++ pdev->needs_freset = 1; ++ + Platform proceeds either to STEP 5 (Resume Operations) or STEP 6 (Permanent Failure). ->>> The current powerpc implementation does not currently try a ->>> power-cycle reset if the driver returned PCI_ERS_RESULT_DISCONNECT. +>>> The current powerpc implementation does not try a power-cycle +>>> reset if the driver returned PCI_ERS_RESULT_DISCONNECT. >>> However, it probably should. @@ -348,7 +376,7 @@ software errors. Conclusion; General Remarks --------------------------- -The way those callbacks are called is platform policy. A platform with +The way the callbacks are called is platform policy. A platform with no slot reset capability may want to just "ignore" drivers that can't recover (disconnect them) and try to let other cards on the same segment recover. Keep in mind that in most real life cases, though, there will @@ -361,8 +389,8 @@ That is, the recovery API only requires that: - There is no guarantee that interrupt delivery can proceed from any device on the segment starting from the error detection and until the -resume callback is sent, at which point interrupts are expected to be -fully operational. +slot_reset callback is called, at which point interrupts are expected +to be fully operational. - There is no guarantee that interrupt delivery is stopped, that is, a driver that gets an interrupt after detecting an error, or that detects @@ -381,16 +409,23 @@ anyway :) >>> Implementation details for the powerpc platform are discussed in >>> the file Documentation/powerpc/eeh-pci-error-recovery.txt ->>> As of this writing, there are six device drivers with patches ->>> implementing error recovery. Not all of these patches are in +>>> As of this writing, there is a growing list of device drivers with +>>> patches implementing error recovery. Not all of these patches are in >>> mainline yet. These may be used as "examples": >>> ->>> drivers/scsi/ipr.c ->>> drivers/scsi/sym53cxx_2 +>>> drivers/scsi/ipr +>>> drivers/scsi/sym53c8xx_2 +>>> drivers/scsi/qla2xxx +>>> drivers/scsi/lpfc +>>> drivers/next/bnx2.c >>> drivers/next/e100.c >>> drivers/net/e1000 +>>> drivers/net/e1000e >>> drivers/net/ixgb +>>> drivers/net/ixgbe +>>> drivers/net/cxgb3 >>> drivers/net/s2io.c +>>> drivers/net/qlge The End ------- diff --git a/Documentation/vgaarbiter.txt b/Documentation/vgaarbiter.txt new file mode 100644 index 00000000000..987f9b0a5ec --- /dev/null +++ b/Documentation/vgaarbiter.txt @@ -0,0 +1,194 @@ + +VGA Arbiter +=========== + +Graphic devices are accessed through ranges in I/O or memory space. While most +modern devices allow relocation of such ranges, some "Legacy" VGA devices +implemented on PCI will typically have the same "hard-decoded" addresses as +they did on ISA. For more details see "PCI Bus Binding to IEEE Std 1275-1994 +Standard for Boot (Initialization Configuration) Firmware Revision 2.1" +Section 7, Legacy Devices. + +The Resource Access Control (RAC) module inside the X server [0] existed for +the legacy VGA arbitration task (besides other bus management tasks) when more +than one legacy device co-exists on the same machine. But the problem happens +when these devices are trying to be accessed by different userspace clients +(e.g. two server in parallel). Their address assignments conflict. Moreover, +ideally, being an userspace application, it is not the role of the the X +server to control bus resources. Therefore an arbitration scheme outside of +the X server is needed to control the sharing of these resources. This +document introduces the operation of the VGA arbiter implemented for Linux +kernel. + +---------------------------------------------------------------------------- + +I. Details and Theory of Operation + I.1 vgaarb + I.2 libpciaccess + I.3 xf86VGAArbiter (X server implementation) +II. Credits +III.References + + +I. Details and Theory of Operation +================================== + +I.1 vgaarb +---------- + +The vgaarb is a module of the Linux Kernel. When it is initially loaded, it +scans all PCI devices and adds the VGA ones inside the arbitration. The +arbiter then enables/disables the decoding on different devices of the VGA +legacy instructions. Device which do not want/need to use the arbiter may +explicitly tell it by calling vga_set_legacy_decoding(). + +The kernel exports a char device interface (/dev/vga_arbiter) to the clients, +which has the following semantics: + + open : open user instance of the arbiter. By default, it's attached to + the default VGA device of the system. + + close : close user instance. Release locks made by the user + + read : return a string indicating the status of the target like: + + "<card_ID>,decodes=<io_state>,owns=<io_state>,locks=<io_state> (ic,mc)" + + An IO state string is of the form {io,mem,io+mem,none}, mc and + ic are respectively mem and io lock counts (for debugging/ + diagnostic only). "decodes" indicate what the card currently + decodes, "owns" indicates what is currently enabled on it, and + "locks" indicates what is locked by this card. If the card is + unplugged, we get "invalid" then for card_ID and an -ENODEV + error is returned for any command until a new card is targeted. + + + write : write a command to the arbiter. List of commands: + + target <card_ID> : switch target to card <card_ID> (see below) + lock <io_state> : acquires locks on target ("none" is an invalid io_state) + trylock <io_state> : non-blocking acquire locks on target (returns EBUSY if + unsuccessful) + unlock <io_state> : release locks on target + unlock all : release all locks on target held by this user (not + implemented yet) + decodes <io_state> : set the legacy decoding attributes for the card + + poll : event if something changes on any card (not just the + target) + + card_ID is of the form "PCI:domain:bus:dev.fn". It can be set to "default" + to go back to the system default card (TODO: not implemented yet). Currently, + only PCI is supported as a prefix, but the userland API may support other bus + types in the future, even if the current kernel implementation doesn't. + +Note about locks: + +The driver keeps track of which user has which locks on which card. It +supports stacking, like the kernel one. This complexifies the implementation +a bit, but makes the arbiter more tolerant to user space problems and able +to properly cleanup in all cases when a process dies. +Currently, a max of 16 cards can have locks simultaneously issued from +user space for a given user (file descriptor instance) of the arbiter. + +In the case of devices hot-{un,}plugged, there is a hook - pci_notify() - to +notify them being added/removed in the system and automatically added/removed +in the arbiter. + +There's also a in-kernel API of the arbiter in the case of DRM, vgacon and +others which may use the arbiter. + + +I.2 libpciaccess +---------------- + +To use the vga arbiter char device it was implemented an API inside the +libpciaccess library. One fieldd was added to struct pci_device (each device +on the system): + + /* the type of resource decoded by the device */ + int vgaarb_rsrc; + +Besides it, in pci_system were added: + + int vgaarb_fd; + int vga_count; + struct pci_device *vga_target; + struct pci_device *vga_default_dev; + + +The vga_count is usually need to keep informed how many cards are being +arbitrated, so for instance if there's only one then it can totally escape the +scheme. + + +These functions below acquire VGA resources for the given card and mark those +resources as locked. If the resources requested are "normal" (and not legacy) +resources, the arbiter will first check whether the card is doing legacy +decoding for that type of resource. If yes, the lock is "converted" into a +legacy resource lock. The arbiter will first look for all VGA cards that +might conflict and disable their IOs and/or Memory access, including VGA +forwarding on P2P bridges if necessary, so that the requested resources can +be used. Then, the card is marked as locking these resources and the IO and/or +Memory access is enabled on the card (including VGA forwarding on parent +P2P bridges if any). In the case of vga_arb_lock(), the function will block +if some conflicting card is already locking one of the required resources (or +any resource on a different bus segment, since P2P bridges don't differentiate +VGA memory and IO afaik). If the card already owns the resources, the function +succeeds. vga_arb_trylock() will return (-EBUSY) instead of blocking. Nested +calls are supported (a per-resource counter is maintained). + + +Set the target device of this client. + int pci_device_vgaarb_set_target (struct pci_device *dev); + + +For instance, in x86 if two devices on the same bus want to lock different +resources, both will succeed (lock). If devices are in different buses and +trying to lock different resources, only the first who tried succeeds. + int pci_device_vgaarb_lock (void); + int pci_device_vgaarb_trylock (void); + +Unlock resources of device. + int pci_device_vgaarb_unlock (void); + +Indicates to the arbiter if the card decodes legacy VGA IOs, legacy VGA +Memory, both, or none. All cards default to both, the card driver (fbdev for +example) should tell the arbiter if it has disabled legacy decoding, so the +card can be left out of the arbitration process (and can be safe to take +interrupts at any time. + int pci_device_vgaarb_decodes (int new_vgaarb_rsrc); + +Connects to the arbiter device, allocates the struct + int pci_device_vgaarb_init (void); + +Close the connection + void pci_device_vgaarb_fini (void); + + +I.3 xf86VGAArbiter (X server implementation) +-------------------------------------------- + +(TODO) + +X server basically wraps all the functions that touch VGA registers somehow. + + +II. Credits +=========== + +Benjamin Herrenschmidt (IBM?) started this work when he discussed such design +with the Xorg community in 2005 [1, 2]. In the end of 2007, Paulo Zanoni and +Tiago Vignatti (both of C3SL/Federal University of Paraná) proceeded his work +enhancing the kernel code to adapt as a kernel module and also did the +implementation of the user space side [3]. Now (2009) Tiago Vignatti and Dave +Airlie finally put this work in shape and queued to Jesse Barnes' PCI tree. + + +III. References +============== + +[0] http://cgit.freedesktop.org/xorg/xserver/commit/?id=4b42448a2388d40f257774fbffdccaea87bd0347 +[1] http://lists.freedesktop.org/archives/xorg/2005-March/006663.html +[2] http://lists.freedesktop.org/archives/xorg/2005-March/006745.html +[3] http://lists.freedesktop.org/archives/xorg/2007-October/029507.html diff --git a/arch/alpha/include/asm/pci.h b/arch/alpha/include/asm/pci.h index d22ace99d13..dd8dcabf160 100644 --- a/arch/alpha/include/asm/pci.h +++ b/arch/alpha/include/asm/pci.h @@ -52,7 +52,6 @@ struct pci_controller { bus numbers. */ #define pcibios_assign_all_busses() 1 -#define pcibios_scan_all_fns(a, b) 0 #define PCIBIOS_MIN_IO alpha_mv.min_io_address #define PCIBIOS_MIN_MEM alpha_mv.min_mem_address diff --git a/arch/arm/include/asm/pci.h b/arch/arm/include/asm/pci.h index 0abf386ba3d..226cddd2fb6 100644 --- a/arch/arm/include/asm/pci.h +++ b/arch/arm/include/asm/pci.h @@ -6,8 +6,6 @@ #include <mach/hardware.h> /* for PCIBIOS_MIN_* */ -#define pcibios_scan_all_fns(a, b) 0 - #ifdef CONFIG_PCI_HOST_ITE8152 /* ITE bridge requires setting latency timer to avoid early bus access termination by PIC bus mater devices diff --git a/arch/frv/mb93090-mb00/pci-frv.c b/arch/frv/mb93090-mb00/pci-frv.c index 43d67534c71..566bdeb499d 100644 --- a/arch/frv/mb93090-mb00/pci-frv.c +++ b/arch/frv/mb93090-mb00/pci-frv.c @@ -86,7 +86,7 @@ static void __init pcibios_allocate_bus_resources(struct list_head *bus_list) struct pci_bus *bus; struct pci_dev *dev; int idx; - struct resource *r, *pr; + struct resource *r; /* Depth-First Search on bus tree */ for (ln=bus_list->next; ln != bus_list; ln=ln->next) { @@ -96,8 +96,7 @@ static void __init pcibios_allocate_bus_resources(struct list_head *bus_list) r = &dev->resource[idx]; if (!r->start) continue; - pr = pci_find_parent_resource(dev, r); - if (!pr || request_resource(pr, r) < 0) + if (pci_claim_resource(dev, idx) < 0) printk(KERN_ERR "PCI: Cannot allocate resource region %d of bridge %s\n", idx, pci_name(dev)); } } @@ -110,7 +109,7 @@ static void __init pcibios_allocate_resources(int pass) struct pci_dev *dev = NULL; int idx, disabled; u16 command; - struct resource *r, *pr; + struct resource *r; for_each_pci_dev(dev) { pci_read_config_word(dev, PCI_COMMAND, &command); @@ -127,8 +126,7 @@ static void __init pcibios_allocate_resources(int pass) if (pass == disabled) { DBG("PCI: Resource %08lx-%08lx (f=%lx, d=%d, p=%d)\n", r->start, r->end, r->flags, disabled, pass); - pr = pci_find_parent_resource(dev, r); - if (!pr || request_resource(pr, r) < 0) { + if (pci_claim_resource(dev, idx) < 0) { printk(KERN_ERR "PCI: Cannot allocate resource region %d of device %s\n", idx, pci_name(dev)); /* We'll assign a new address later */ r->end -= r->start; diff --git a/arch/h8300/include/asm/pci.h b/arch/h8300/include/asm/pci.h index 97389b35aa3..cc9762091c0 100644 --- a/arch/h8300/include/asm/pci.h +++ b/arch/h8300/include/asm/pci.h @@ -8,7 +8,6 @@ */ #define pcibios_assign_all_busses() 0 -#define pcibios_scan_all_fns(a, b) 0 static inline void pcibios_set_master(struct pci_dev *dev) { diff --git a/arch/ia64/include/asm/pci.h b/arch/ia64/include/asm/pci.h index fcfca56bb85..55281aabe5f 100644 --- a/arch/ia64/include/asm/pci.h +++ b/arch/ia64/include/asm/pci.h @@ -17,7 +17,6 @@ * loader. */ #define pcibios_assign_all_busses() 0 -#define pcibios_scan_all_fns(a, b) 0 #define PCIBIOS_MIN_IO 0x1000 #define PCIBIOS_MIN_MEM 0x10000000 @@ -135,7 +134,18 @@ extern void pcibios_resource_to_bus(struct pci_dev *dev, extern void pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res, struct pci_bus_region *region); -#define pcibios_scan_all_fns(a, b) 0 +static inline struct resource * +pcibios_select_root(struct pci_dev *pdev, struct resource *res) +{ + struct resource *root = NULL; + + if (res->flags & IORESOURCE_IO) + root = &ioport_resource; + if (res->flags & IORESOURCE_MEM) + root = &iomem_resource; + + return root; +} #define HAVE_ARCH_PCI_GET_LEGACY_IDE_IRQ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel) diff --git a/arch/mips/include/asm/pci.h b/arch/mips/include/asm/pci.h index a68d111e55e..5ebf82572ec 100644 --- a/arch/mips/include/asm/pci.h +++ b/arch/mips/include/asm/pci.h @@ -65,8 +65,6 @@ extern int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin); extern unsigned int pcibios_assign_all_busses(void); -#define pcibios_scan_all_fns(a, b) 0 - extern unsigned long PCIBIOS_MIN_IO; extern unsigned long PCIBIOS_MIN_MEM; diff --git a/arch/mn10300/include/asm/pci.h b/arch/mn10300/include/asm/pci.h index 19aecc90f7a..6095a28561d 100644 --- a/arch/mn10300/include/asm/pci.h +++ b/arch/mn10300/include/asm/pci.h @@ -101,7 +101,18 @@ extern void pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res, struct pci_bus_region *region); -#define pcibios_scan_all_fns(a, b) 0 +static inline struct resource * +pcibios_select_root(struct pci_dev *pdev, struct resource *res) +{ + struct resource *root = NULL; + + if (res->flags & IORESOURCE_IO) + root = &ioport_resource; + if (res->flags & IORESOURCE_MEM) + root = &iomem_resource; + + return root; +} static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel) { diff --git a/arch/parisc/include/asm/pci.h b/arch/parisc/include/asm/pci.h index 7d842d699df..64c7aa590ae 100644 --- a/arch/parisc/include/asm/pci.h +++ b/arch/parisc/include/asm/pci.h @@ -233,7 +233,6 @@ static inline void pcibios_register_hba(struct pci_hba_data *x) * rp7420/8420 boxes and then revisit this issue. */ #define pcibios_assign_all_busses() (1) -#define pcibios_scan_all_fns(a, b) (0) #define PCIBIOS_MIN_IO 0x10 #define PCIBIOS_MIN_MEM 0x1000 /* NBPG - but pci/setup-res.c dies */ diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h index 7aca4839387..b5ea626eea2 100644 --- a/arch/powerpc/include/asm/pci.h +++ b/arch/powerpc/include/asm/pci.h @@ -45,7 +45,6 @@ struct pci_dev; */ #define pcibios_assign_all_busses() \ (ppc_pci_has_flag(PPC_PCI_REASSIGN_ALL_BUS)) -#define pcibios_scan_all_fns(a, b) 0 static inline void pcibios_set_master(struct pci_dev *dev) { diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index 72c31bcb7aa..7311fdfb9bf 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -139,6 +139,7 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, dev->dev.bus = &pci_bus_type; dev->devfn = devfn; dev->multifunction = 0; /* maybe a lie? */ + dev->needs_freset = 0; /* pcie fundamental reset required */ dev->vendor = get_int_prop(node, "vendor-id", 0xffff); dev->device = get_int_prop(node, "device-id", 0xffff); diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c index 989d6462c15..ccd8dd03b8c 100644 --- a/arch/powerpc/platforms/pseries/eeh.c +++ b/arch/powerpc/platforms/pseries/eeh.c @@ -744,7 +744,15 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat static void __rtas_set_slot_reset(struct pci_dn *pdn) { - rtas_pci_slot_reset (pdn, 1); + struct pci_dev *dev = pdn->pcidev; + + /* Determine type of EEH reset required by device, + * default hot reset or fundamental reset + */ + if (dev->needs_freset) + rtas_pci_slot_reset(pdn, 3); + else + rtas_pci_slot_reset(pdn, 1); /* The PCI bus requires that the reset be held high for at least * a 100 milliseconds. We wait a bit longer 'just in case'. */ diff --git a/arch/sh/include/asm/pci.h b/arch/sh/include/asm/pci.h index d3633f513eb..4163950cd1c 100644 --- a/arch/sh/include/asm/pci.h +++ b/arch/sh/include/asm/pci.h @@ -10,7 +10,6 @@ or architectures with incomplete PCI setup by the loader */ #define pcibios_assign_all_busses() 1 -#define pcibios_scan_all_fns(a, b) 0 /* * A board can define one or more PCI channels that represent built-in (or diff --git a/arch/sparc/include/asm/pci_32.h b/arch/sparc/include/asm/pci_32.h index ac0e8369fd9..e769f668a4b 100644 --- a/arch/sparc/include/asm/pci_32.h +++ b/arch/sparc/include/asm/pci_32.h @@ -10,7 +10,6 @@ * or architectures with incomplete PCI setup by the loader. */ #define pcibios_assign_all_busses() 0 -#define pcibios_scan_all_fns(a, b) 0 #define PCIBIOS_MIN_IO 0UL #define PCIBIOS_MIN_MEM 0UL diff --git a/arch/sparc/include/asm/pci_64.h b/arch/sparc/include/asm/pci_64.h index 5cc9f6aa549..b63e51c3c3e 100644 --- a/arch/sparc/include/asm/pci_64.h +++ b/arch/sparc/include/asm/pci_64.h @@ -10,7 +10,6 @@ * or architectures with incomplete PCI setup by the loader. */ #define pcibios_assign_all_busses() 0 -#define pcibios_scan_all_fns(a, b) 0 #define PCIBIOS_MIN_IO 0UL #define PCIBIOS_MIN_MEM 0UL diff --git a/arch/um/include/asm/pci.h b/arch/um/include/asm/pci.h index 59923199cdc..b44cf59ede1 100644 --- a/arch/um/include/asm/pci.h +++ b/arch/um/include/asm/pci.h @@ -2,6 +2,5 @@ #define __UM_PCI_H #define PCI_DMA_BUS_IS_PHYS (1) -#define pcibios_scan_all_fns(a, b) 0 #endif diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 1ff685ca221..f76a162c082 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -48,7 +48,6 @@ extern unsigned int pcibios_assign_all_busses(void); #else #define pcibios_assign_all_busses() 0 #endif -#define pcibios_scan_all_fns(a, b) 0 extern unsigned long pci_mem_start; #define PCIBIOS_MIN_IO 0x1000 diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index d71c8655905..64b838eac18 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -225,10 +225,8 @@ static __init int iommu_setup(char *p) if (!strncmp(p, "soft", 4)) swiotlb = 1; #endif - if (!strncmp(p, "pt", 2)) { + if (!strncmp(p, "pt", 2)) iommu_pass_through = 1; - return 1; - } gart_parse_options(p); diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index af71d06624b..6c3b2c6fd77 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -508,7 +508,7 @@ static void __init quirk_amd_nb_node(struct pci_dev *dev) pci_read_config_dword(nb_ht, 0x60, &val); set_dev_node(&dev->dev, val & 7); - pci_dev_put(dev); + pci_dev_put(nb_ht); } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB, diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c index 3ffa10df20b..572ee9782f2 100644 --- a/arch/x86/pci/amd_bus.c +++ b/arch/x86/pci/amd_bus.c @@ -15,63 +15,6 @@ * also get peer root bus resource for io,mmio */ -#ifdef CONFIG_NUMA - -#define BUS_NR 256 - -#ifdef CONFIG_X86_64 - -static int mp_bus_to_node[BUS_NR]; - -void set_mp_bus_to_node(int busnum, int node) -{ - if (busnum >= 0 && busnum < BUS_NR) - mp_bus_to_node[busnum] = node; -} - -int get_mp_bus_to_node(int busnum) -{ - int node = -1; - - if (busnum < 0 || busnum > (BUS_NR - 1)) - return node; - - node = mp_bus_to_node[busnum]; - - /* - * let numa_node_id to decide it later in dma_alloc_pages - * if there is no ram on that node - */ - if (node != -1 && !node_online(node)) - node = -1; - - return node; -} - -#else /* CONFIG_X86_32 */ - -static unsigned char mp_bus_to_node[BUS_NR]; - -void set_mp_bus_to_node(int busnum, int node) -{ - if (busnum >= 0 && busnum < BUS_NR) - mp_bus_to_node[busnum] = (unsigned char) node; -} - -int get_mp_bus_to_node(int busnum) -{ - int node; - - if (busnum < 0 || busnum > (BUS_NR - 1)) - return 0; - node = mp_bus_to_node[busnum]; - return node; -} - -#endif /* CONFIG_X86_32 */ - -#endif /* CONFIG_NUMA */ - #ifdef CONFIG_X86_64 /* @@ -301,11 +244,6 @@ static int __init early_fill_mp_bus_info(void) u64 val; u32 address; -#ifdef CONFIG_NUMA - for (i = 0; i < BUS_NR; i++) - mp_bus_to_node[i] = -1; -#endif - if (!early_pci_allowed()) return -1; @@ -346,7 +284,7 @@ static int __init early_fill_mp_bus_info(void) node = (reg >> 4) & 0x07; #ifdef CONFIG_NUMA for (j = min_bus; j <= max_bus; j++) - mp_bus_to_node[j] = (unsigned char) node; + set_mp_bus_to_node(j, node); #endif link = (reg >> 8) & 0x03; diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 2202b6257b8..5db96d4304d 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -600,3 +600,72 @@ struct pci_bus * __devinit pci_scan_bus_with_sysdata(int busno) { return pci_scan_bus_on_node(busno, &pci_root_ops, -1); } + +/* + * NUMA info for PCI busses + * + * Early arch code is responsible for filling in reasonable values here. + * A node id of "-1" means "use current node". In other words, if a bus + * has a -1 node id, it's not tightly coupled to any particular chunk + * of memory (as is the case on some Nehalem systems). + */ +#ifdef CONFIG_NUMA + +#define BUS_NR 256 + +#ifdef CONFIG_X86_64 + +static int mp_bus_to_node[BUS_NR] = { + [0 ... BUS_NR - 1] = -1 +}; + +void set_mp_bus_to_node(int busnum, int node) +{ + if (busnum >= 0 && busnum < BUS_NR) + mp_bus_to_node[busnum] = node; +} + +int get_mp_bus_to_node(int busnum) +{ + int node = -1; + + if (busnum < 0 || busnum > (BUS_NR - 1)) + return node; + + node = mp_bus_to_node[busnum]; + + /* + * let numa_node_id to decide it later in dma_alloc_pages + * if there is no ram on that node + */ + if (node != -1 && !node_online(node)) + node = -1; + + return node; +} + +#else /* CONFIG_X86_32 */ + +static unsigned char mp_bus_to_node[BUS_NR] = { + [0 ... BUS_NR - 1] = -1 +}; + +void set_mp_bus_to_node(int busnum, int node) +{ + if (busnum >= 0 && busnum < BUS_NR) + mp_bus_to_node[busnum] = (unsigned char) node; +} + +int get_mp_bus_to_node(int busnum) +{ + int node; + + if (busnum < 0 || busnum > (BUS_NR - 1)) + return 0; + node = mp_bus_to_node[busnum]; + return node; +} + +#endif /* CONFIG_X86_32 */ + +#endif /* CONFIG_NUMA */ diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c index 55b5b90c2a4..31b961c2f22 100644 --- a/drivers/acpi/pci_root.c +++ b/drivers/acpi/pci_root.c @@ -61,20 +61,6 @@ static struct acpi_driver acpi_pci_root_driver = { }, }; -struct acpi_pci_root { - struct list_head node; - struct acpi_device *device; - struct pci_bus *bus; - u16 segment; - u8 bus_nr; - - u32 osc_support_set; /* _OSC state of support bits */ - u32 osc_control_set; /* _OSC state of control bits */ - u32 osc_control_qry; /* the latest _OSC query result */ - - u32 osc_queried:1; /* has _OSC control been queried? */ -}; - static LIST_HEAD(acpi_pci_roots); static struct acpi_pci_driver *sub_driver; @@ -317,7 +303,7 @@ static acpi_status acpi_pci_osc_support(struct acpi_pci_root *root, u32 flags) return status; } -static struct acpi_pci_root *acpi_pci_find_root(acpi_handle handle) +struct acpi_pci_root *acpi_pci_find_root(acpi_handle handle) { struct acpi_pci_root *root; @@ -327,6 +313,7 @@ static struct acpi_pci_root *acpi_pci_find_root(acpi_handle handle) } return NULL; } +EXPORT_SYMBOL_GPL(acpi_pci_find_root); struct acpi_handle_node { struct list_head node; diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index d74365d4a6e..5a09bf392ec 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -44,6 +44,8 @@ #include <acpi/acpi_bus.h> #include <acpi/acpi_drivers.h> +#include "sleep.h" + #define _COMPONENT ACPI_POWER_COMPONENT ACPI_MODULE_NAME("power"); #define ACPI_POWER_CLASS "power_resource" @@ -361,17 +363,15 @@ int acpi_device_sleep_wake(struct acpi_device *dev, */ int acpi_enable_wakeup_device_power(struct acpi_device *dev, int sleep_state) { - int i, err; + int i, err = 0; if (!dev || !dev->wakeup.flags.valid) return -EINVAL; - /* - * Do not execute the code below twice in a row without calling - * acpi_disable_wakeup_device_power() in between for the same device - */ - if (dev->wakeup.flags.prepared) - return 0; + mutex_lock(&acpi_device_lock); + + if (dev->wakeup.prepare_count++) + goto out; /* Open power resource */ for (i = 0; i < dev->wakeup.resources.count; i++) { @@ -379,7 +379,8 @@ int acpi_enable_wakeup_device_power(struct acpi_device *dev, int sleep_state) if (ret) { printk(KERN_ERR PREFIX "Transition power state\n"); dev->wakeup.flags.valid = 0; - return -ENODEV; + err = -ENODEV; + goto err_out; } } @@ -388,9 +389,13 @@ int acpi_enable_wakeup_device_power(struct acpi_device *dev, int sleep_state) * in arbitrary power state afterwards. */ err = acpi_device_sleep_wake(dev, 1, sleep_state, 3); - if (!err) - dev->wakeup.flags.prepared = 1; + err_out: + if (err) + dev->wakeup.prepare_count = 0; + + out: + mutex_unlock(&acpi_device_lock); return err; } @@ -402,35 +407,42 @@ int acpi_enable_wakeup_device_power(struct acpi_device *dev, int sleep_state) */ int acpi_disable_wakeup_device_power(struct acpi_device *dev) { - int i, ret; + int i, err = 0; if (!dev || !dev->wakeup.flags.valid) return -EINVAL; + mutex_lock(&acpi_device_lock); + + if (--dev->wakeup.prepare_count > 0) + goto out; + /* - * Do not execute the code below twice in a row without calling - * acpi_enable_wakeup_device_power() in between for the same device + * Executing the code below even if prepare_count is already zero when + * the function is called may be useful, for example for initialisation. */ - if (!dev->wakeup.flags.prepared) - return 0; + if (dev->wakeup.prepare_count < 0) + dev->wakeup.prepare_count = 0; - dev->wakeup.flags.prepared = 0; - - ret = acpi_device_sleep_wake(dev, 0, 0, 0); - if (ret) - return ret; + err = acpi_device_sleep_wake(dev, 0, 0, 0); + if (err) + goto out; /* Close power resource */ for (i = 0; i < dev->wakeup.resources.count; i++) { - ret = acpi_power_off_device(dev->wakeup.resources.handles[i], dev); + int ret = acpi_power_off_device( + dev->wakeup.resources.handles[i], dev); if (ret) { printk(KERN_ERR PREFIX "Transition power state\n"); dev->wakeup.flags.valid = 0; - return -ENODEV; + err = -ENODEV; + goto out; } } - return ret; + out: + mutex_unlock(&acpi_device_lock); + return err; } /* -------------------------------------------------------------------------- diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 781435d7e36..318b1ea7a5b 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -781,6 +781,7 @@ static int acpi_bus_get_wakeup_device_flags(struct acpi_device *device) kfree(buffer.pointer); device->wakeup.flags.valid = 1; + device->wakeup.prepare_count = 0; /* Call _PSW/_DSW object to disable its ability to wake the sleeping * system for the ACPI device with the _PRW object. * The _PSW object is depreciated in ACPI 3.0 and is replaced by _DSW. diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 42159a28f43..feece693d77 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -689,19 +689,25 @@ int acpi_pm_device_sleep_wake(struct device *dev, bool enable) { acpi_handle handle; struct acpi_device *adev; + int error; - if (!device_may_wakeup(dev)) + if (!device_can_wakeup(dev)) return -EINVAL; handle = DEVICE_ACPI_HANDLE(dev); if (!handle || ACPI_FAILURE(acpi_bus_get_device(handle, &adev))) { - printk(KERN_DEBUG "ACPI handle has no context!\n"); + dev_dbg(dev, "ACPI handle has no context in %s!\n", __func__); return -ENODEV; } - return enable ? + error = enable ? acpi_enable_wakeup_device_power(adev, acpi_target_sleep_state) : acpi_disable_wakeup_device_power(adev); + if (!error) + dev_info(dev, "wake-up capability %s by ACPI\n", + enable ? "enabled" : "disabled"); + + return error; } #endif diff --git a/drivers/acpi/wakeup.c b/drivers/acpi/wakeup.c index 88725dcdf8b..e0ee0c036f5 100644 --- a/drivers/acpi/wakeup.c +++ b/drivers/acpi/wakeup.c @@ -68,7 +68,7 @@ void acpi_enable_wakeup_device(u8 sleep_state) /* If users want to disable run-wake GPE, * we only disable it for wake and leave it for runtime */ - if ((!dev->wakeup.state.enabled && !dev->wakeup.flags.prepared) + if ((!dev->wakeup.state.enabled && !dev->wakeup.prepare_count) || sleep_state > (u32) dev->wakeup.sleep_state) { if (dev->wakeup.flags.run_wake) { /* set_gpe_type will disable GPE, leave it like that */ @@ -100,7 +100,7 @@ void acpi_disable_wakeup_device(u8 sleep_state) if (!dev->wakeup.flags.valid) continue; - if ((!dev->wakeup.state.enabled && !dev->wakeup.flags.prepared) + if ((!dev->wakeup.state.enabled && !dev->wakeup.prepare_count) || sleep_state > (u32) dev->wakeup.sleep_state) { if (dev->wakeup.flags.run_wake) { acpi_set_gpe_type(dev->wakeup.gpe_device, diff --git a/drivers/bluetooth/dtl1_cs.c b/drivers/bluetooth/dtl1_cs.c index 2cc7b3266ea..b881a9cd874 100644 --- a/drivers/bluetooth/dtl1_cs.c +++ b/drivers/bluetooth/dtl1_cs.c @@ -618,7 +618,7 @@ static int dtl1_config(struct pcmcia_device *link) /* Look for a generic full-sized window */ link->io.NumPorts1 = 8; - if (!pcmcia_loop_config(link, dtl1_confcheck, NULL)) + if (pcmcia_loop_config(link, dtl1_confcheck, NULL) < 0) goto failed; i = pcmcia_request_irq(link, &link->irq); diff --git a/drivers/gpu/Makefile b/drivers/gpu/Makefile index de566cf0414..30879df3dae 100644 --- a/drivers/gpu/Makefile +++ b/drivers/gpu/Makefile @@ -1 +1 @@ -obj-y += drm/ +obj-y += drm/ vga/ diff --git a/drivers/gpu/vga/Kconfig b/drivers/gpu/vga/Kconfig new file mode 100644 index 00000000000..790e675b13e --- /dev/null +++ b/drivers/gpu/vga/Kconfig @@ -0,0 +1,10 @@ +config VGA_ARB + bool "VGA Arbitration" if EMBEDDED + default y + depends on PCI + help + Some "legacy" VGA devices implemented on PCI typically have the same + hard-decoded addresses as they did on ISA. When multiple PCI devices + are accessed at same time they need some kind of coordination. Please + see Documentation/vgaarbiter.txt for more details. Select this to + enable VGA arbiter. diff --git a/drivers/gpu/vga/Makefile b/drivers/gpu/vga/Makefile new file mode 100644 index 00000000000..7cc8c1ed645 --- /dev/null +++ b/drivers/gpu/vga/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_VGA_ARB) += vgaarb.o diff --git a/drivers/gpu/vga/vgaarb.c b/drivers/gpu/vga/vgaarb.c new file mode 100644 index 00000000000..1ac0c93603c --- /dev/null +++ b/drivers/gpu/vga/vgaarb.c @@ -0,0 +1,1205 @@ +/* + * vgaarb.c + * + * (C) Copyright 2005 Benjamin Herrenschmidt <benh@kernel.crashing.org> + * (C) Copyright 2007 Paulo R. Zanoni <przanoni@gmail.com> + * (C) Copyright 2007, 2009 Tiago Vignatti <vignatti@freedesktop.org> + * + * Implements the VGA arbitration. For details refer to + * Documentation/vgaarbiter.txt + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/pci.h> +#include <linux/errno.h> +#include <linux/init.h> +#include <linux/list.h> +#include <linux/sched.h> +#include <linux/wait.h> +#include <linux/spinlock.h> +#include <linux/poll.h> +#include <linux/miscdevice.h> + +#include <linux/uaccess.h> + +#include <linux/vgaarb.h> + +static void vga_arbiter_notify_clients(void); +/* + * We keep a list of all vga devices in the system to speed + * up the various operations of the arbiter + */ +struct vga_device { + struct list_head list; + struct pci_dev *pdev; + unsigned int decodes; /* what does it decodes */ + unsigned int owns; /* what does it owns */ + unsigned int locks; /* what does it locks */ + unsigned int io_lock_cnt; /* legacy IO lock count */ + unsigned int mem_lock_cnt; /* legacy MEM lock count */ + unsigned int io_norm_cnt; /* normal IO count */ + unsigned int mem_norm_cnt; /* normal MEM count */ + + /* allow IRQ enable/disable hook */ + void *cookie; + void (*irq_set_state)(void *cookie, bool enable); + unsigned int (*set_vga_decode)(void *cookie, bool decode); +}; + +static LIST_HEAD(vga_list); +static int vga_count, vga_decode_count; +static bool vga_arbiter_used; +static DEFINE_SPINLOCK(vga_lock); +static DECLARE_WAIT_QUEUE_HEAD(vga_wait_queue); + + +static const char *vga_iostate_to_str(unsigned int iostate) +{ + /* Ignore VGA_RSRC_IO and VGA_RSRC_MEM */ + iostate &= VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM; + switch (iostate) { + case VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM: + return "io+mem"; + case VGA_RSRC_LEGACY_IO: + return "io"; + case VGA_RSRC_LEGACY_MEM: + return "mem"; + } + return "none"; +} + +static int vga_str_to_iostate(char *buf, int str_size, int *io_state) +{ + /* we could in theory hand out locks on IO and mem + * separately to userspace but it can cause deadlocks */ + if (strncmp(buf, "none", 4) == 0) { + *io_state = VGA_RSRC_NONE; + return 1; + } + + /* XXX We're not chekcing the str_size! */ + if (strncmp(buf, "io+mem", 6) == 0) + goto both; + else if (strncmp(buf, "io", 2) == 0) + goto both; + else if (strncmp(buf, "mem", 3) == 0) + goto both; + return 0; +both: + *io_state = VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM; + return 1; +} + +#ifndef __ARCH_HAS_VGA_DEFAULT_DEVICE +/* this is only used a cookie - it should not be dereferenced */ +static struct pci_dev *vga_default; +#endif + +static void vga_arb_device_card_gone(struct pci_dev *pdev); + +/* Find somebody in our list */ +static struct vga_device *vgadev_find(struct pci_dev *pdev) +{ + struct vga_device *vgadev; + + list_for_each_entry(vgadev, &vga_list, list) + if (pdev == vgadev->pdev) + return vgadev; + return NULL; +} + +/* Returns the default VGA device (vgacon's babe) */ +#ifndef __ARCH_HAS_VGA_DEFAULT_DEVICE +struct pci_dev *vga_default_device(void) +{ + return vga_default; +} +#endif + +static inline void vga_irq_set_state(struct vga_device *vgadev, bool state) +{ + if (vgadev->irq_set_state) + vgadev->irq_set_state(vgadev->cookie, state); +} + + +/* If we don't ever use VGA arb we should avoid + turning off anything anywhere due to old X servers getting + confused about the boot device not being VGA */ +static void vga_check_first_use(void) +{ + /* we should inform all GPUs in the system that + * VGA arb has occured and to try and disable resources + * if they can */ + if (!vga_arbiter_used) { + vga_arbiter_used = true; + vga_arbiter_notify_clients(); + } +} + +static struct vga_device *__vga_tryget(struct vga_device *vgadev, + unsigned int rsrc) +{ + unsigned int wants, legacy_wants, match; + struct vga_device *conflict; + unsigned int pci_bits; + /* Account for "normal" resources to lock. If we decode the legacy, + * counterpart, we need to request it as well + */ + if ((rsrc & VGA_RSRC_NORMAL_IO) && + (vgadev->decodes & VGA_RSRC_LEGACY_IO)) + rsrc |= VGA_RSRC_LEGACY_IO; + if ((rsrc & VGA_RSRC_NORMAL_MEM) && + (vgadev->decodes & VGA_RSRC_LEGACY_MEM)) + rsrc |= VGA_RSRC_LEGACY_MEM; + + pr_devel("%s: %d\n", __func__, rsrc); + pr_devel("%s: owns: %d\n", __func__, vgadev->owns); + + /* Check what resources we need to acquire */ + wants = rsrc & ~vgadev->owns; + + /* We already own everything, just mark locked & bye bye */ + if (wants == 0) + goto lock_them; + + /* We don't need to request a legacy resource, we just enable + * appropriate decoding and go + */ + legacy_wants = wants & VGA_RSRC_LEGACY_MASK; + if (legacy_wants == 0) + goto enable_them; + + /* Ok, we don't, let's find out how we need to kick off */ + list_for_each_entry(conflict, &vga_list, list) { + unsigned int lwants = legacy_wants; + unsigned int change_bridge = 0; + + /* Don't conflict with myself */ + if (vgadev == conflict) + continue; + + /* Check if the architecture allows a conflict between those + * 2 devices or if they are on separate domains + */ + if (!vga_conflicts(vgadev->pdev, conflict->pdev)) + continue; + + /* We have a possible conflict. before we go further, we must + * check if we sit on the same bus as the conflicting device. + * if we don't, then we must tie both IO and MEM resources + * together since there is only a single bit controlling + * VGA forwarding on P2P bridges + */ + if (vgadev->pdev->bus != conflict->pdev->bus) { + change_bridge = 1; + lwants = VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM; + } + + /* Check if the guy has a lock on the resource. If he does, + * return the conflicting entry + */ + if (conflict->locks & lwants) + return conflict; + + /* Ok, now check if he owns the resource we want. We don't need + * to check "decodes" since it should be impossible to own + * own legacy resources you don't decode unless I have a bug + * in this code... + */ + WARN_ON(conflict->owns & ~conflict->decodes); + match = lwants & conflict->owns; + if (!match) + continue; + + /* looks like he doesn't have a lock, we can steal + * them from him + */ + vga_irq_set_state(conflict, false); + + pci_bits = 0; + if (lwants & (VGA_RSRC_LEGACY_MEM|VGA_RSRC_NORMAL_MEM)) + pci_bits |= PCI_COMMAND_MEMORY; + if (lwants & (VGA_RSRC_LEGACY_IO|VGA_RSRC_NORMAL_IO)) + pci_bits |= PCI_COMMAND_IO; + + pci_set_vga_state(conflict->pdev, false, pci_bits, + change_bridge); + conflict->owns &= ~lwants; + /* If he also owned non-legacy, that is no longer the case */ + if (lwants & VGA_RSRC_LEGACY_MEM) + conflict->owns &= ~VGA_RSRC_NORMAL_MEM; + if (lwants & VGA_RSRC_LEGACY_IO) + conflict->owns &= ~VGA_RSRC_NORMAL_IO; + } + +enable_them: + /* ok dude, we got it, everybody conflicting has been disabled, let's + * enable us. Make sure we don't mark a bit in "owns" that we don't + * also have in "decodes". We can lock resources we don't decode but + * not own them. + */ + pci_bits = 0; + if (wants & (VGA_RSRC_LEGACY_MEM|VGA_RSRC_NORMAL_MEM)) + pci_bits |= PCI_COMMAND_MEMORY; + if (wants & (VGA_RSRC_LEGACY_IO|VGA_RSRC_NORMAL_IO)) + pci_bits |= PCI_COMMAND_IO; + pci_set_vga_state(vgadev->pdev, true, pci_bits, !!(wants & VGA_RSRC_LEGACY_MASK)); + + vga_irq_set_state(vgadev, true); + vgadev->owns |= (wants & vgadev->decodes); +lock_them: + vgadev->locks |= (rsrc & VGA_RSRC_LEGACY_MASK); + if (rsrc & VGA_RSRC_LEGACY_IO) + vgadev->io_lock_cnt++; + if (rsrc & VGA_RSRC_LEGACY_MEM) + vgadev->mem_lock_cnt++; + if (rsrc & VGA_RSRC_NORMAL_IO) + vgadev->io_norm_cnt++; + if (rsrc & VGA_RSRC_NORMAL_MEM) + vgadev->mem_norm_cnt++; + + return NULL; +} + +static void __vga_put(struct vga_device *vgadev, unsigned int rsrc) +{ + unsigned int old_locks = vgadev->locks; + + pr_devel("%s\n", __func__); + + /* Update our counters, and account for equivalent legacy resources + * if we decode them + */ + if ((rsrc & VGA_RSRC_NORMAL_IO) && vgadev->io_norm_cnt > 0) { + vgadev->io_norm_cnt--; + if (vgadev->decodes & VGA_RSRC_LEGACY_IO) + rsrc |= VGA_RSRC_LEGACY_IO; + } + if ((rsrc & VGA_RSRC_NORMAL_MEM) && vgadev->mem_norm_cnt > 0) { + vgadev->mem_norm_cnt--; + if (vgadev->decodes & VGA_RSRC_LEGACY_MEM) + rsrc |= VGA_RSRC_LEGACY_MEM; + } + if ((rsrc & VGA_RSRC_LEGACY_IO) && vgadev->io_lock_cnt > 0) + vgadev->io_lock_cnt--; + if ((rsrc & VGA_RSRC_LEGACY_MEM) && vgadev->mem_lock_cnt > 0) + vgadev->mem_lock_cnt--; + + /* Just clear lock bits, we do lazy operations so we don't really + * have to bother about anything else at this point + */ + if (vgadev->io_lock_cnt == 0) + vgadev->locks &= ~VGA_RSRC_LEGACY_IO; + if (vgadev->mem_lock_cnt == 0) + vgadev->locks &= ~VGA_RSRC_LEGACY_MEM; + + /* Kick the wait queue in case somebody was waiting if we actually + * released something + */ + if (old_locks != vgadev->locks) + wake_up_all(&vga_wait_queue); +} + +int vga_get(struct pci_dev *pdev, unsigned int rsrc, int interruptible) +{ + struct vga_device *vgadev, *conflict; + unsigned long flags; + wait_queue_t wait; + int rc = 0; + + vga_check_first_use(); + /* The one who calls us should check for this, but lets be sure... */ + if (pdev == NULL) + pdev = vga_default_device(); + if (pdev == NULL) + return 0; + + for (;;) { + spin_lock_irqsave(&vga_lock, flags); + vgadev = vgadev_find(pdev); + if (vgadev == NULL) { + spin_unlock_irqrestore(&vga_lock, flags); + rc = -ENODEV; + break; + } + conflict = __vga_tryget(vgadev, rsrc); + spin_unlock_irqrestore(&vga_lock, flags); + if (conflict == NULL) + break; + + + /* We have a conflict, we wait until somebody kicks the + * work queue. Currently we have one work queue that we + * kick each time some resources are released, but it would + * be fairly easy to have a per device one so that we only + * need to attach to the conflicting device + */ + init_waitqueue_entry(&wait, current); + add_wait_queue(&vga_wait_queue, &wait); + set_current_state(interruptible ? + TASK_INTERRUPTIBLE : + TASK_UNINTERRUPTIBLE); + if (signal_pending(current)) { + rc = -EINTR; + break; + } + schedule(); + remove_wait_queue(&vga_wait_queue, &wait); + set_current_state(TASK_RUNNING); + } + return rc; +} +EXPORT_SYMBOL(vga_get); + +int vga_tryget(struct pci_dev *pdev, unsigned int rsrc) +{ + struct vga_device *vgadev; + unsigned long flags; + int rc = 0; + + vga_check_first_use(); + + /* The one who calls us should check for this, but lets be sure... */ + if (pdev == NULL) + pdev = vga_default_device(); + if (pdev == NULL) + return 0; + spin_lock_irqsave(&vga_lock, flags); + vgadev = vgadev_find(pdev); + if (vgadev == NULL) { + rc = -ENODEV; + goto bail; + } + if (__vga_tryget(vgadev, rsrc)) + rc = -EBUSY; +bail: + spin_unlock_irqrestore(&vga_lock, flags); + return rc; +} +EXPORT_SYMBOL(vga_tryget); + +void vga_put(struct pci_dev *pdev, unsigned int rsrc) +{ + struct vga_device *vgadev; + unsigned long flags; + + /* The one who calls us should check for this, but lets be sure... */ + if (pdev == NULL) + pdev = vga_default_device(); + if (pdev == NULL) + return; + spin_lock_irqsave(&vga_lock, flags); + vgadev = vgadev_find(pdev); + if (vgadev == NULL) + goto bail; + __vga_put(vgadev, rsrc); +bail: + spin_unlock_irqrestore(&vga_lock, flags); +} +EXPORT_SYMBOL(vga_put); + +/* + * Currently, we assume that the "initial" setup of the system is + * not sane, that is we come up with conflicting devices and let + * the arbiter's client decides if devices decodes or not legacy + * things. + */ +static bool vga_arbiter_add_pci_device(struct pci_dev *pdev) +{ + struct vga_device *vgadev; + unsigned long flags; + struct pci_bus *bus; + struct pci_dev *bridge; + u16 cmd; + + /* Only deal with VGA class devices */ + if ((pdev->class >> 8) != PCI_CLASS_DISPLAY_VGA) + return false; + + /* Allocate structure */ + vgadev = kmalloc(sizeof(struct vga_device), GFP_KERNEL); + if (vgadev == NULL) { + pr_err("vgaarb: failed to allocate pci device\n"); + /* What to do on allocation failure ? For now, let's + * just do nothing, I'm not sure there is anything saner + * to be done + */ + return false; + } + + memset(vgadev, 0, sizeof(*vgadev)); + + /* Take lock & check for duplicates */ + spin_lock_irqsave(&vga_lock, flags); + if (vgadev_find(pdev) != NULL) { + BUG_ON(1); + goto fail; + } + vgadev->pdev = pdev; + + /* By default, assume we decode everything */ + vgadev->decodes = VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM | + VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM; + + /* by default mark it as decoding */ + vga_decode_count++; + /* Mark that we "own" resources based on our enables, we will + * clear that below if the bridge isn't forwarding + */ + pci_read_config_word(pdev, PCI_COMMAND, &cmd); + if (cmd & PCI_COMMAND_IO) + vgadev->owns |= VGA_RSRC_LEGACY_IO; + if (cmd & PCI_COMMAND_MEMORY) + vgadev->owns |= VGA_RSRC_LEGACY_MEM; + + /* Check if VGA cycles can get down to us */ + bus = pdev->bus; + while (bus) { + bridge = bus->self; + if (bridge) { + u16 l; + pci_read_config_word(bridge, PCI_BRIDGE_CONTROL, + &l); + if (!(l & PCI_BRIDGE_CTL_VGA)) { + vgadev->owns = 0; + break; + } + } + bus = bus->parent; + } + + /* Deal with VGA default device. Use first enabled one + * by default if arch doesn't have it's own hook + */ +#ifndef __ARCH_HAS_VGA_DEFAULT_DEVICE + if (vga_default == NULL && + ((vgadev->owns & VGA_RSRC_LEGACY_MASK) == VGA_RSRC_LEGACY_MASK)) + vga_default = pci_dev_get(pdev); +#endif + + /* Add to the list */ + list_add(&vgadev->list, &vga_list); + vga_count++; + pr_info("vgaarb: device added: PCI:%s,decodes=%s,owns=%s,locks=%s\n", + pci_name(pdev), + vga_iostate_to_str(vgadev->decodes), + vga_iostate_to_str(vgadev->owns), + vga_iostate_to_str(vgadev->locks)); + + spin_unlock_irqrestore(&vga_lock, flags); + return true; +fail: + spin_unlock_irqrestore(&vga_lock, flags); + kfree(vgadev); + return false; +} + +static bool vga_arbiter_del_pci_device(struct pci_dev *pdev) +{ + struct vga_device *vgadev; + unsigned long flags; + bool ret = true; + + spin_lock_irqsave(&vga_lock, flags); + vgadev = vgadev_find(pdev); + if (vgadev == NULL) { + ret = false; + goto bail; + } + + if (vga_default == pdev) { + pci_dev_put(vga_default); + vga_default = NULL; + } + + if (vgadev->decodes & (VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM)) + vga_decode_count--; + + /* Remove entry from list */ + list_del(&vgadev->list); + vga_count--; + /* Notify userland driver that the device is gone so it discards + * it's copies of the pci_dev pointer + */ + vga_arb_device_card_gone(pdev); + + /* Wake up all possible waiters */ + wake_up_all(&vga_wait_queue); +bail: + spin_unlock_irqrestore(&vga_lock, flags); + kfree(vgadev); + return ret; +} + +/* this is called with the lock */ +static inline void vga_update_device_decodes(struct vga_device *vgadev, + int new_decodes) +{ + int old_decodes; + struct vga_device *new_vgadev, *conflict; + + old_decodes = vgadev->decodes; + vgadev->decodes = new_decodes; + + pr_info("vgaarb: device changed decodes: PCI:%s,olddecodes=%s,decodes=%s:owns=%s\n", + pci_name(vgadev->pdev), + vga_iostate_to_str(old_decodes), + vga_iostate_to_str(vgadev->decodes), + vga_iostate_to_str(vgadev->owns)); + + + /* if we own the decodes we should move them along to + another card */ + if ((vgadev->owns & old_decodes) && (vga_count > 1)) { + /* set us to own nothing */ + vgadev->owns &= ~old_decodes; + list_for_each_entry(new_vgadev, &vga_list, list) { + if ((new_vgadev != vgadev) && + (new_vgadev->decodes & VGA_RSRC_LEGACY_MASK)) { + pr_info("vgaarb: transferring owner from PCI:%s to PCI:%s\n", pci_name(vgadev->pdev), pci_name(new_vgadev->pdev)); + conflict = __vga_tryget(new_vgadev, VGA_RSRC_LEGACY_MASK); + if (!conflict) + __vga_put(new_vgadev, VGA_RSRC_LEGACY_MASK); + break; + } + } + } + + /* change decodes counter */ + if (old_decodes != new_decodes) { + if (new_decodes & (VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM)) + vga_decode_count++; + else + vga_decode_count--; + } +} + +void __vga_set_legacy_decoding(struct pci_dev *pdev, unsigned int decodes, bool userspace) +{ + struct vga_device *vgadev; + unsigned long flags; + + decodes &= VGA_RSRC_LEGACY_MASK; + + spin_lock_irqsave(&vga_lock, flags); + vgadev = vgadev_find(pdev); + if (vgadev == NULL) + goto bail; + + /* don't let userspace futz with kernel driver decodes */ + if (userspace && vgadev->set_vga_decode) + goto bail; + + /* update the device decodes + counter */ + vga_update_device_decodes(vgadev, decodes); + + /* XXX if somebody is going from "doesn't decode" to "decodes" state + * here, additional care must be taken as we may have pending owner + * ship of non-legacy region ... + */ +bail: + spin_unlock_irqrestore(&vga_lock, flags); +} + +void vga_set_legacy_decoding(struct pci_dev *pdev, unsigned int decodes) +{ + __vga_set_legacy_decoding(pdev, decodes, false); +} +EXPORT_SYMBOL(vga_set_legacy_decoding); + +/* call with NULL to unregister */ +int vga_client_register(struct pci_dev *pdev, void *cookie, + void (*irq_set_state)(void *cookie, bool state), + unsigned int (*set_vga_decode)(void *cookie, bool decode)) +{ + int ret = -1; + struct vga_device *vgadev; + unsigned long flags; + + spin_lock_irqsave(&vga_lock, flags); + vgadev = vgadev_find(pdev); + if (!vgadev) + goto bail; + + vgadev->irq_set_state = irq_set_state; + vgadev->set_vga_decode = set_vga_decode; + vgadev->cookie = cookie; + ret = 0; + +bail: + spin_unlock_irqrestore(&vga_lock, flags); + return ret; + +} +EXPORT_SYMBOL(vga_client_register); + +/* + * Char driver implementation + * + * Semantics is: + * + * open : open user instance of the arbitrer. by default, it's + * attached to the default VGA device of the system. + * + * close : close user instance, release locks + * + * read : return a string indicating the status of the target. + * an IO state string is of the form {io,mem,io+mem,none}, + * mc and ic are respectively mem and io lock counts (for + * debugging/diagnostic only). "decodes" indicate what the + * card currently decodes, "owns" indicates what is currently + * enabled on it, and "locks" indicates what is locked by this + * card. If the card is unplugged, we get "invalid" then for + * card_ID and an -ENODEV error is returned for any command + * until a new card is targeted + * + * "<card_ID>,decodes=<io_state>,owns=<io_state>,locks=<io_state> (ic,mc)" + * + * write : write a command to the arbiter. List of commands is: + * + * target <card_ID> : switch target to card <card_ID> (see below) + * lock <io_state> : acquires locks on target ("none" is invalid io_state) + * trylock <io_state> : non-blocking acquire locks on target + * unlock <io_state> : release locks on target + * unlock all : release all locks on target held by this user + * decodes <io_state> : set the legacy decoding attributes for the card + * + * poll : event if something change on any card (not just the target) + * + * card_ID is of the form "PCI:domain:bus:dev.fn". It can be set to "default" + * to go back to the system default card (TODO: not implemented yet). + * Currently, only PCI is supported as a prefix, but the userland API may + * support other bus types in the future, even if the current kernel + * implementation doesn't. + * + * Note about locks: + * + * The driver keeps track of which user has what locks on which card. It + * supports stacking, like the kernel one. This complexifies the implementation + * a bit, but makes the arbiter more tolerant to userspace problems and able + * to properly cleanup in all cases when a process dies. + * Currently, a max of 16 cards simultaneously can have locks issued from + * userspace for a given user (file descriptor instance) of the arbiter. + * + * If the device is hot-unplugged, there is a hook inside the module to notify + * they being added/removed in the system and automatically added/removed in + * the arbiter. + */ + +#define MAX_USER_CARDS 16 +#define PCI_INVALID_CARD ((struct pci_dev *)-1UL) + +/* + * Each user has an array of these, tracking which cards have locks + */ +struct vga_arb_user_card { + struct pci_dev *pdev; + unsigned int mem_cnt; + unsigned int io_cnt; +}; + +struct vga_arb_private { + struct list_head list; + struct pci_dev *target; + struct vga_arb_user_card cards[MAX_USER_CARDS]; + spinlock_t lock; +}; + +static LIST_HEAD(vga_user_list); +static DEFINE_SPINLOCK(vga_user_lock); + + +/* + * This function gets a string in the format: "PCI:domain:bus:dev.fn" and + * returns the respective values. If the string is not in this format, + * it returns 0. + */ +static int vga_pci_str_to_vars(char *buf, int count, unsigned int *domain, + unsigned int *bus, unsigned int *devfn) +{ + int n; + unsigned int slot, func; + + + n = sscanf(buf, "PCI:%x:%x:%x.%x", domain, bus, &slot, &func); + if (n != 4) + return 0; + + *devfn = PCI_DEVFN(slot, func); + + return 1; +} + +static ssize_t vga_arb_read(struct file *file, char __user * buf, + size_t count, loff_t *ppos) +{ + struct vga_arb_private *priv = file->private_data; + struct vga_device *vgadev; + struct pci_dev *pdev; + unsigned long flags; + size_t len; + int rc; + char *lbuf; + + lbuf = kmalloc(1024, GFP_KERNEL); + if (lbuf == NULL) + return -ENOMEM; + + /* Shields against vga_arb_device_card_gone (pci_dev going + * away), and allows access to vga list + */ + spin_lock_irqsave(&vga_lock, flags); + + /* If we are targetting the default, use it */ + pdev = priv->target; + if (pdev == NULL || pdev == PCI_INVALID_CARD) { + spin_unlock_irqrestore(&vga_lock, flags); + len = sprintf(lbuf, "invalid"); + goto done; + } + + /* Find card vgadev structure */ + vgadev = vgadev_find(pdev); + if (vgadev == NULL) { + /* Wow, it's not in the list, that shouldn't happen, + * let's fix us up and return invalid card + */ + if (pdev == priv->target) + vga_arb_device_card_gone(pdev); + spin_unlock_irqrestore(&vga_lock, flags); + len = sprintf(lbuf, "invalid"); + goto done; + } + + /* Fill the buffer with infos */ + len = snprintf(lbuf, 1024, + "count:%d,PCI:%s,decodes=%s,owns=%s,locks=%s(%d:%d)\n", + vga_decode_count, pci_name(pdev), + vga_iostate_to_str(vgadev->decodes), + vga_iostate_to_str(vgadev->owns), + vga_iostate_to_str(vgadev->locks), + vgadev->io_lock_cnt, vgadev->mem_lock_cnt); + + spin_unlock_irqrestore(&vga_lock, flags); +done: + + /* Copy that to user */ + if (len > count) + len = count; + rc = copy_to_user(buf, lbuf, len); + kfree(lbuf); + if (rc) + return -EFAULT; + return len; +} + +/* + * TODO: To avoid parsing inside kernel and to improve the speed we may + * consider use ioctl here + */ +static ssize_t vga_arb_write(struct file *file, const char __user * buf, + size_t count, loff_t *ppos) +{ + struct vga_arb_private *priv = file->private_data; + struct vga_arb_user_card *uc = NULL; + struct pci_dev *pdev; + + unsigned int io_state; + + char *kbuf, *curr_pos; + size_t remaining = count; + + int ret_val; + int i; + + + kbuf = kmalloc(count + 1, GFP_KERNEL); + if (!kbuf) + return -ENOMEM; + + if (copy_from_user(kbuf, buf, count)) { + kfree(kbuf); + return -EFAULT; + } + curr_pos = kbuf; + kbuf[count] = '\0'; /* Just to make sure... */ + + if (strncmp(curr_pos, "lock ", 5) == 0) { + curr_pos += 5; + remaining -= 5; + + pr_devel("client 0x%p called 'lock'\n", priv); + + if (!vga_str_to_iostate(curr_pos, remaining, &io_state)) { + ret_val = -EPROTO; + goto done; + } + if (io_state == VGA_RSRC_NONE) { + ret_val = -EPROTO; + goto done; + } + + pdev = priv->target; + if (priv->target == NULL) { + ret_val = -ENODEV; + goto done; + } + + vga_get_uninterruptible(pdev, io_state); + + /* Update the client's locks lists... */ + for (i = 0; i < MAX_USER_CARDS; i++) { + if (priv->cards[i].pdev == pdev) { + if (io_state & VGA_RSRC_LEGACY_IO) + priv->cards[i].io_cnt++; + if (io_state & VGA_RSRC_LEGACY_MEM) + priv->cards[i].mem_cnt++; + break; + } + } + + ret_val = count; + goto done; + } else if (strncmp(curr_pos, "unlock ", 7) == 0) { + curr_pos += 7; + remaining -= 7; + + pr_devel("client 0x%p called 'unlock'\n", priv); + + if (strncmp(curr_pos, "all", 3) == 0) + io_state = VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM; + else { + if (!vga_str_to_iostate + (curr_pos, remaining, &io_state)) { + ret_val = -EPROTO; + goto done; + } + /* TODO: Add this? + if (io_state == VGA_RSRC_NONE) { + ret_val = -EPROTO; + goto done; + } + */ + } + + pdev = priv->target; + if (priv->target == NULL) { + ret_val = -ENODEV; + goto done; + } + for (i = 0; i < MAX_USER_CARDS; i++) { + if (priv->cards[i].pdev == pdev) + uc = &priv->cards[i]; + } + + if (!uc) + return -EINVAL; + + if (io_state & VGA_RSRC_LEGACY_IO && uc->io_cnt == 0) + return -EINVAL; + + if (io_state & VGA_RSRC_LEGACY_MEM && uc->mem_cnt == 0) + return -EINVAL; + + vga_put(pdev, io_state); + + if (io_state & VGA_RSRC_LEGACY_IO) + uc->io_cnt--; + if (io_state & VGA_RSRC_LEGACY_MEM) + uc->mem_cnt--; + + ret_val = count; + goto done; + } else if (strncmp(curr_pos, "trylock ", 8) == 0) { + curr_pos += 8; + remaining -= 8; + + pr_devel("client 0x%p called 'trylock'\n", priv); + + if (!vga_str_to_iostate(curr_pos, remaining, &io_state)) { + ret_val = -EPROTO; + goto done; + } + /* TODO: Add this? + if (io_state == VGA_RSRC_NONE) { + ret_val = -EPROTO; + goto done; + } + */ + + pdev = priv->target; + if (priv->target == NULL) { + ret_val = -ENODEV; + goto done; + } + + if (vga_tryget(pdev, io_state)) { + /* Update the client's locks lists... */ + for (i = 0; i < MAX_USER_CARDS; i++) { + if (priv->cards[i].pdev == pdev) { + if (io_state & VGA_RSRC_LEGACY_IO) + priv->cards[i].io_cnt++; + if (io_state & VGA_RSRC_LEGACY_MEM) + priv->cards[i].mem_cnt++; + break; + } + } + ret_val = count; + goto done; + } else { + ret_val = -EBUSY; + goto done; + } + + } else if (strncmp(curr_pos, "target ", 7) == 0) { + unsigned int domain, bus, devfn; + struct vga_device *vgadev; + + curr_pos += 7; + remaining -= 7; + pr_devel("client 0x%p called 'target'\n", priv); + /* if target is default */ + if (!strncmp(buf, "default", 7)) + pdev = pci_dev_get(vga_default_device()); + else { + if (!vga_pci_str_to_vars(curr_pos, remaining, + &domain, &bus, &devfn)) { + ret_val = -EPROTO; + goto done; + } + + pdev = pci_get_bus_and_slot(bus, devfn); + if (!pdev) { + pr_info("vgaarb: invalid PCI address!\n"); + ret_val = -ENODEV; + goto done; + } + } + + vgadev = vgadev_find(pdev); + if (vgadev == NULL) { + pr_info("vgaarb: this pci device is not a vga device\n"); + pci_dev_put(pdev); + ret_val = -ENODEV; + goto done; + } + + priv->target = pdev; + for (i = 0; i < MAX_USER_CARDS; i++) { + if (priv->cards[i].pdev == pdev) + break; + if (priv->cards[i].pdev == NULL) { + priv->cards[i].pdev = pdev; + priv->cards[i].io_cnt = 0; + priv->cards[i].mem_cnt = 0; + break; + } + } + if (i == MAX_USER_CARDS) { + pr_err("vgaarb: maximum user cards number reached!\n"); + pci_dev_put(pdev); + /* XXX: which value to return? */ + ret_val = -ENOMEM; + goto done; + } + + ret_val = count; + pci_dev_put(pdev); + goto done; + + + } else if (strncmp(curr_pos, "decodes ", 8) == 0) { + curr_pos += 8; + remaining -= 8; + pr_devel("vgaarb: client 0x%p called 'decodes'\n", priv); + + if (!vga_str_to_iostate(curr_pos, remaining, &io_state)) { + ret_val = -EPROTO; + goto done; + } + pdev = priv->target; + if (priv->target == NULL) { + ret_val = -ENODEV; + goto done; + } + + __vga_set_legacy_decoding(pdev, io_state, true); + ret_val = count; + goto done; + } + /* If we got here, the message written is not part of the protocol! */ + kfree(kbuf); + return -EPROTO; + +done: + kfree(kbuf); + return ret_val; +} + +static unsigned int vga_arb_fpoll(struct file *file, poll_table * wait) +{ + struct vga_arb_private *priv = file->private_data; + + pr_devel("%s\n", __func__); + + if (priv == NULL) + return -ENODEV; + poll_wait(file, &vga_wait_queue, wait); + return POLLIN; +} + +static int vga_arb_open(struct inode *inode, struct file *file) +{ + struct vga_arb_private *priv; + unsigned long flags; + + pr_devel("%s\n", __func__); + + priv = kmalloc(sizeof(struct vga_arb_private), GFP_KERNEL); + if (priv == NULL) + return -ENOMEM; + memset(priv, 0, sizeof(*priv)); + spin_lock_init(&priv->lock); + file->private_data = priv; + + spin_lock_irqsave(&vga_user_lock, flags); + list_add(&priv->list, &vga_user_list); + spin_unlock_irqrestore(&vga_user_lock, flags); + + /* Set the client' lists of locks */ + priv->target = vga_default_device(); /* Maybe this is still null! */ + priv->cards[0].pdev = priv->target; + priv->cards[0].io_cnt = 0; + priv->cards[0].mem_cnt = 0; + + + return 0; +} + +static int vga_arb_release(struct inode *inode, struct file *file) +{ + struct vga_arb_private *priv = file->private_data; + struct vga_arb_user_card *uc; + unsigned long flags; + int i; + + pr_devel("%s\n", __func__); + + if (priv == NULL) + return -ENODEV; + + spin_lock_irqsave(&vga_user_lock, flags); + list_del(&priv->list); + for (i = 0; i < MAX_USER_CARDS; i++) { + uc = &priv->cards[i]; + if (uc->pdev == NULL) + continue; + pr_devel("uc->io_cnt == %d, uc->mem_cnt == %d\n", + uc->io_cnt, uc->mem_cnt); + while (uc->io_cnt--) + vga_put(uc->pdev, VGA_RSRC_LEGACY_IO); + while (uc->mem_cnt--) + vga_put(uc->pdev, VGA_RSRC_LEGACY_MEM); + } + spin_unlock_irqrestore(&vga_user_lock, flags); + + kfree(priv); + + return 0; +} + +static void vga_arb_device_card_gone(struct pci_dev *pdev) +{ +} + +/* + * callback any registered clients to let them know we have a + * change in VGA cards + */ +static void vga_arbiter_notify_clients(void) +{ + struct vga_device *vgadev; + unsigned long flags; + uint32_t new_decodes; + bool new_state; + + if (!vga_arbiter_used) + return; + + spin_lock_irqsave(&vga_lock, flags); + list_for_each_entry(vgadev, &vga_list, list) { + if (vga_count > 1) + new_state = false; + else + new_state = true; + if (vgadev->set_vga_decode) { + new_decodes = vgadev->set_vga_decode(vgadev->cookie, new_state); + vga_update_device_decodes(vgadev, new_decodes); + } + } + spin_unlock_irqrestore(&vga_lock, flags); +} + +static int pci_notify(struct notifier_block *nb, unsigned long action, + void *data) +{ + struct device *dev = data; + struct pci_dev *pdev = to_pci_dev(dev); + bool notify = false; + + pr_devel("%s\n", __func__); + + /* For now we're only intereted in devices added and removed. I didn't + * test this thing here, so someone needs to double check for the + * cases of hotplugable vga cards. */ + if (action == BUS_NOTIFY_ADD_DEVICE) + notify = vga_arbiter_add_pci_device(pdev); + else if (action == BUS_NOTIFY_DEL_DEVICE) + notify = vga_arbiter_del_pci_device(pdev); + + if (notify) + vga_arbiter_notify_clients(); + return 0; +} + +static struct notifier_block pci_notifier = { + .notifier_call = pci_notify, +}; + +static const struct file_operations vga_arb_device_fops = { + .read = vga_arb_read, + .write = vga_arb_write, + .poll = vga_arb_fpoll, + .open = vga_arb_open, + .release = vga_arb_release, +}; + +static struct miscdevice vga_arb_device = { + MISC_DYNAMIC_MINOR, "vga_arbiter", &vga_arb_device_fops +}; + +static int __init vga_arb_device_init(void) +{ + int rc; + struct pci_dev *pdev; + + rc = misc_register(&vga_arb_device); + if (rc < 0) + pr_err("vgaarb: error %d registering device\n", rc); + + bus_register_notifier(&pci_bus_type, &pci_notifier); + + /* We add all pci devices satisfying vga class in the arbiter by + * default */ + pdev = NULL; + while ((pdev = + pci_get_subsys(PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, + PCI_ANY_ID, pdev)) != NULL) + vga_arbiter_add_pci_device(pdev); + + pr_info("vgaarb: loaded\n"); + return rc; +} +subsys_initcall(vga_arb_device_init); diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile index 1ebd6b4c743..4a7f11d8f43 100644 --- a/drivers/pci/Makefile +++ b/drivers/pci/Makefile @@ -8,6 +8,9 @@ obj-y += access.o bus.o probe.o remove.o pci.o quirks.o \ obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_SYSFS) += slot.o +obj-$(CONFIG_PCI_LEGACY) += legacy.o +CFLAGS_legacy.o += -Wno-deprecated-declarations + # Build PCI Express stuff if needed obj-$(CONFIG_PCIEPORTBUS) += pcie/ diff --git a/drivers/pci/hotplug/Makefile b/drivers/pci/hotplug/Makefile index 2aa117c8cd8..3625b094bf7 100644 --- a/drivers/pci/hotplug/Makefile +++ b/drivers/pci/hotplug/Makefile @@ -22,7 +22,7 @@ obj-$(CONFIG_HOTPLUG_PCI_SGI) += sgi_hotplug.o # Link this last so it doesn't claim devices that have a real hotplug driver obj-$(CONFIG_HOTPLUG_PCI_FAKE) += fakephp.o -pci_hotplug-objs := pci_hotplug_core.o +pci_hotplug-objs := pci_hotplug_core.o pcihp_slot.o ifdef CONFIG_HOTPLUG_PCI_CPCI pci_hotplug-objs += cpci_hotplug_core.o \ diff --git a/drivers/pci/hotplug/acpi_pcihp.c b/drivers/pci/hotplug/acpi_pcihp.c index eb159587d0b..a73028ec52e 100644 --- a/drivers/pci/hotplug/acpi_pcihp.c +++ b/drivers/pci/hotplug/acpi_pcihp.c @@ -41,7 +41,6 @@ #define warn(format, arg...) printk(KERN_WARNING "%s: " format , MY_NAME , ## arg) #define METHOD_NAME__SUN "_SUN" -#define METHOD_NAME__HPP "_HPP" #define METHOD_NAME_OSHP "OSHP" static int debug_acpi; @@ -215,80 +214,41 @@ acpi_run_hpx(acpi_handle handle, struct hotplug_params *hpx) static acpi_status acpi_run_hpp(acpi_handle handle, struct hotplug_params *hpp) { - acpi_status status; - u8 nui[4]; - struct acpi_buffer ret_buf = { 0, NULL}; - struct acpi_buffer string = { ACPI_ALLOCATE_BUFFER, NULL }; - union acpi_object *ext_obj, *package; - int i, len = 0; - - acpi_get_name(handle, ACPI_FULL_PATHNAME, &string); + acpi_status status; + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + union acpi_object *package, *fields; + int i; - /* Clear the return buffer with zeros */ memset(hpp, 0, sizeof(struct hotplug_params)); - /* get _hpp */ - status = acpi_evaluate_object(handle, METHOD_NAME__HPP, NULL, &ret_buf); - switch (status) { - case AE_BUFFER_OVERFLOW: - ret_buf.pointer = kmalloc (ret_buf.length, GFP_KERNEL); - if (!ret_buf.pointer) { - printk(KERN_ERR "%s:%s alloc for _HPP fail\n", - __func__, (char *)string.pointer); - kfree(string.pointer); - return AE_NO_MEMORY; - } - status = acpi_evaluate_object(handle, METHOD_NAME__HPP, - NULL, &ret_buf); - if (ACPI_SUCCESS(status)) - break; - default: - if (ACPI_FAILURE(status)) { - pr_debug("%s:%s _HPP fail=0x%x\n", __func__, - (char *)string.pointer, status); - kfree(string.pointer); - return status; - } - } + status = acpi_evaluate_object(handle, "_HPP", NULL, &buffer); + if (ACPI_FAILURE(status)) + return status; - ext_obj = (union acpi_object *) ret_buf.pointer; - if (ext_obj->type != ACPI_TYPE_PACKAGE) { - printk(KERN_ERR "%s:%s _HPP obj not a package\n", __func__, - (char *)string.pointer); + package = (union acpi_object *) buffer.pointer; + if (package->type != ACPI_TYPE_PACKAGE || + package->package.count != 4) { status = AE_ERROR; - goto free_and_return; + goto exit; } - len = ext_obj->package.count; - package = (union acpi_object *) ret_buf.pointer; - for ( i = 0; (i < len) || (i < 4); i++) { - ext_obj = (union acpi_object *) &package->package.elements[i]; - switch (ext_obj->type) { - case ACPI_TYPE_INTEGER: - nui[i] = (u8)ext_obj->integer.value; - break; - default: - printk(KERN_ERR "%s:%s _HPP obj type incorrect\n", - __func__, (char *)string.pointer); + fields = package->package.elements; + for (i = 0; i < 4; i++) { + if (fields[i].type != ACPI_TYPE_INTEGER) { status = AE_ERROR; - goto free_and_return; + goto exit; } } hpp->t0 = &hpp->type0_data; - hpp->t0->cache_line_size = nui[0]; - hpp->t0->latency_timer = nui[1]; - hpp->t0->enable_serr = nui[2]; - hpp->t0->enable_perr = nui[3]; - - pr_debug(" _HPP: cache_line_size=0x%x\n", hpp->t0->cache_line_size); - pr_debug(" _HPP: latency timer =0x%x\n", hpp->t0->latency_timer); - pr_debug(" _HPP: enable SERR =0x%x\n", hpp->t0->enable_serr); - pr_debug(" _HPP: enable PERR =0x%x\n", hpp->t0->enable_perr); + hpp->t0->revision = 1; + hpp->t0->cache_line_size = fields[0].integer.value; + hpp->t0->latency_timer = fields[1].integer.value; + hpp->t0->enable_serr = fields[2].integer.value; + hpp->t0->enable_perr = fields[3].integer.value; -free_and_return: - kfree(string.pointer); - kfree(ret_buf.pointer); +exit: + kfree(buffer.pointer); return status; } @@ -322,20 +282,19 @@ static acpi_status acpi_run_oshp(acpi_handle handle) return status; } -/* acpi_get_hp_params_from_firmware +/* pci_get_hp_params * - * @bus - the pci_bus of the bus on which the device is newly added + * @dev - the pci_dev for which we want parameters * @hpp - allocated by the caller */ -acpi_status acpi_get_hp_params_from_firmware(struct pci_bus *bus, - struct hotplug_params *hpp) +int pci_get_hp_params(struct pci_dev *dev, struct hotplug_params *hpp) { - acpi_status status = AE_NOT_FOUND; + acpi_status status; acpi_handle handle, phandle; struct pci_bus *pbus; handle = NULL; - for (pbus = bus; pbus; pbus = pbus->parent) { + for (pbus = dev->bus; pbus; pbus = pbus->parent) { handle = acpi_pci_get_bridge_handle(pbus); if (handle) break; @@ -345,15 +304,15 @@ acpi_status acpi_get_hp_params_from_firmware(struct pci_bus *bus, * _HPP settings apply to all child buses, until another _HPP is * encountered. If we don't find an _HPP for the input pci dev, * look for it in the parent device scope since that would apply to - * this pci dev. If we don't find any _HPP, use hardcoded defaults + * this pci dev. */ while (handle) { status = acpi_run_hpx(handle, hpp); if (ACPI_SUCCESS(status)) - break; + return 0; status = acpi_run_hpp(handle, hpp); if (ACPI_SUCCESS(status)) - break; + return 0; if (acpi_is_root_bridge(handle)) break; status = acpi_get_parent(handle, &phandle); @@ -361,9 +320,9 @@ acpi_status acpi_get_hp_params_from_firmware(struct pci_bus *bus, break; handle = phandle; } - return status; + return -ENODEV; } -EXPORT_SYMBOL_GPL(acpi_get_hp_params_from_firmware); +EXPORT_SYMBOL_GPL(pci_get_hp_params); /** * acpi_get_hp_hw_control_from_firmware @@ -500,18 +459,18 @@ check_hotplug(acpi_handle handle, u32 lvl, void *context, void **rv) /** * acpi_pci_detect_ejectable - check if the PCI bus has ejectable slots - * @pbus - PCI bus to scan + * @handle - handle of the PCI bus to scan * * Returns 1 if the PCI bus has ACPI based ejectable slots, 0 otherwise. */ -int acpi_pci_detect_ejectable(struct pci_bus *pbus) +int acpi_pci_detect_ejectable(acpi_handle handle) { - acpi_handle handle; int found = 0; - if (!(handle = acpi_pci_get_bridge_handle(pbus))) - return 0; - acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, (u32)1, + if (!handle) + return found; + + acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, 1, check_hotplug, (void *)&found, NULL); return found; } diff --git a/drivers/pci/hotplug/acpiphp.h b/drivers/pci/hotplug/acpiphp.h index e68d5f20ffb..7d938df7920 100644 --- a/drivers/pci/hotplug/acpiphp.h +++ b/drivers/pci/hotplug/acpiphp.h @@ -91,9 +91,6 @@ struct acpiphp_bridge { /* PCI-to-PCI bridge device */ struct pci_dev *pci_dev; - /* ACPI 2.0 _HPP parameters */ - struct hotplug_params hpp; - spinlock_t res_lock; }; diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 0cb0f830a99..58d25a163a8 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -59,7 +59,7 @@ static DEFINE_SPINLOCK(ioapic_list_lock); static void handle_hotplug_event_bridge (acpi_handle, u32, void *); static void acpiphp_sanitize_bus(struct pci_bus *bus); -static void acpiphp_set_hpp_values(acpi_handle handle, struct pci_bus *bus); +static void acpiphp_set_hpp_values(struct pci_bus *bus); static void handle_hotplug_event_func(acpi_handle handle, u32 type, void *context); /* callback routine to check for the existence of a pci dock device */ @@ -261,51 +261,21 @@ register_slot(acpi_handle handle, u32 lvl, void *context, void **rv) /* see if it's worth looking at this bridge */ -static int detect_ejectable_slots(struct pci_bus *pbus) +static int detect_ejectable_slots(acpi_handle handle) { - int found = acpi_pci_detect_ejectable(pbus); + int found = acpi_pci_detect_ejectable(handle); if (!found) { - acpi_handle bridge_handle = acpi_pci_get_bridge_handle(pbus); - if (!bridge_handle) - return 0; - acpi_walk_namespace(ACPI_TYPE_DEVICE, bridge_handle, (u32)1, + acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, (u32)1, is_pci_dock_device, (void *)&found, NULL); } return found; } - -/* decode ACPI 2.0 _HPP hot plug parameters */ -static void decode_hpp(struct acpiphp_bridge *bridge) -{ - acpi_status status; - - status = acpi_get_hp_params_from_firmware(bridge->pci_bus, &bridge->hpp); - if (ACPI_FAILURE(status) || - !bridge->hpp.t0 || (bridge->hpp.t0->revision > 1)) { - /* use default numbers */ - printk(KERN_WARNING - "%s: Could not get hotplug parameters. Use defaults\n", - __func__); - bridge->hpp.t0 = &bridge->hpp.type0_data; - bridge->hpp.t0->revision = 0; - bridge->hpp.t0->cache_line_size = 0x10; - bridge->hpp.t0->latency_timer = 0x40; - bridge->hpp.t0->enable_serr = 0; - bridge->hpp.t0->enable_perr = 0; - } -} - - - /* initialize miscellaneous stuff for both root and PCI-to-PCI bridge */ static void init_bridge_misc(struct acpiphp_bridge *bridge) { acpi_status status; - /* decode ACPI 2.0 _HPP (hot plug parameters) */ - decode_hpp(bridge); - /* must be added to the list prior to calling register_slot */ list_add(&bridge->list, &bridge_list); @@ -399,9 +369,10 @@ static inline void config_p2p_bridge_flags(struct acpiphp_bridge *bridge) /* allocate and initialize host bridge data structure */ -static void add_host_bridge(acpi_handle *handle, struct pci_bus *pci_bus) +static void add_host_bridge(acpi_handle *handle) { struct acpiphp_bridge *bridge; + struct acpi_pci_root *root = acpi_pci_find_root(handle); bridge = kzalloc(sizeof(struct acpiphp_bridge), GFP_KERNEL); if (bridge == NULL) @@ -410,7 +381,7 @@ static void add_host_bridge(acpi_handle *handle, struct pci_bus *pci_bus) bridge->type = BRIDGE_TYPE_HOST; bridge->handle = handle; - bridge->pci_bus = pci_bus; + bridge->pci_bus = root->bus; spin_lock_init(&bridge->res_lock); @@ -419,7 +390,7 @@ static void add_host_bridge(acpi_handle *handle, struct pci_bus *pci_bus) /* allocate and initialize PCI-to-PCI bridge data structure */ -static void add_p2p_bridge(acpi_handle *handle, struct pci_dev *pci_dev) +static void add_p2p_bridge(acpi_handle *handle) { struct acpiphp_bridge *bridge; @@ -433,8 +404,8 @@ static void add_p2p_bridge(acpi_handle *handle, struct pci_dev *pci_dev) bridge->handle = handle; config_p2p_bridge_flags(bridge); - bridge->pci_dev = pci_dev_get(pci_dev); - bridge->pci_bus = pci_dev->subordinate; + bridge->pci_dev = acpi_get_pci_dev(handle); + bridge->pci_bus = bridge->pci_dev->subordinate; if (!bridge->pci_bus) { err("This is not a PCI-to-PCI bridge!\n"); goto err; @@ -451,7 +422,7 @@ static void add_p2p_bridge(acpi_handle *handle, struct pci_dev *pci_dev) init_bridge_misc(bridge); return; err: - pci_dev_put(pci_dev); + pci_dev_put(bridge->pci_dev); kfree(bridge); return; } @@ -462,39 +433,21 @@ static acpi_status find_p2p_bridge(acpi_handle handle, u32 lvl, void *context, void **rv) { acpi_status status; - acpi_handle dummy_handle; - unsigned long long tmp; - int device, function; struct pci_dev *dev; - struct pci_bus *pci_bus = context; - - status = acpi_get_handle(handle, "_ADR", &dummy_handle); - if (ACPI_FAILURE(status)) - return AE_OK; /* continue */ - - status = acpi_evaluate_integer(handle, "_ADR", NULL, &tmp); - if (ACPI_FAILURE(status)) { - dbg("%s: _ADR evaluation failure\n", __func__); - return AE_OK; - } - - device = (tmp >> 16) & 0xffff; - function = tmp & 0xffff; - - dev = pci_get_slot(pci_bus, PCI_DEVFN(device, function)); + dev = acpi_get_pci_dev(handle); if (!dev || !dev->subordinate) goto out; /* check if this bridge has ejectable slots */ - if ((detect_ejectable_slots(dev->subordinate) > 0)) { + if ((detect_ejectable_slots(handle) > 0)) { dbg("found PCI-to-PCI bridge at PCI %s\n", pci_name(dev)); - add_p2p_bridge(handle, dev); + add_p2p_bridge(handle); } /* search P2P bridges under this p2p bridge */ status = acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, (u32)1, - find_p2p_bridge, dev->subordinate, NULL); + find_p2p_bridge, NULL, NULL); if (ACPI_FAILURE(status)) warn("find_p2p_bridge failed (error code = 0x%x)\n", status); @@ -509,9 +462,7 @@ static int add_bridge(acpi_handle handle) { acpi_status status; unsigned long long tmp; - int seg, bus; acpi_handle dummy_handle; - struct pci_bus *pci_bus; /* if the bridge doesn't have _STA, we assume it is always there */ status = acpi_get_handle(handle, "_STA", &dummy_handle); @@ -526,36 +477,15 @@ static int add_bridge(acpi_handle handle) return 0; } - /* get PCI segment number */ - status = acpi_evaluate_integer(handle, "_SEG", NULL, &tmp); - - seg = ACPI_SUCCESS(status) ? tmp : 0; - - /* get PCI bus number */ - status = acpi_evaluate_integer(handle, "_BBN", NULL, &tmp); - - if (ACPI_SUCCESS(status)) { - bus = tmp; - } else { - warn("can't get bus number, assuming 0\n"); - bus = 0; - } - - pci_bus = pci_find_bus(seg, bus); - if (!pci_bus) { - err("Can't find bus %04x:%02x\n", seg, bus); - return 0; - } - /* check if this bridge has ejectable slots */ - if (detect_ejectable_slots(pci_bus) > 0) { + if (detect_ejectable_slots(handle) > 0) { dbg("found PCI host-bus bridge with hot-pluggable slots\n"); - add_host_bridge(handle, pci_bus); + add_host_bridge(handle); } /* search P2P bridges under this host bridge */ status = acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, (u32)1, - find_p2p_bridge, pci_bus, NULL); + find_p2p_bridge, NULL, NULL); if (ACPI_FAILURE(status)) warn("find_p2p_bridge failed (error code = 0x%x)\n", status); @@ -1083,7 +1013,7 @@ static int __ref enable_device(struct acpiphp_slot *slot) pci_bus_assign_resources(bus); acpiphp_sanitize_bus(bus); - acpiphp_set_hpp_values(slot->bridge->handle, bus); + acpiphp_set_hpp_values(bus); list_for_each_entry(func, &slot->funcs, sibling) acpiphp_configure_ioapics(func->handle); pci_enable_bridges(bus); @@ -1294,70 +1224,12 @@ static int acpiphp_check_bridge(struct acpiphp_bridge *bridge) return retval; } -static void program_hpp(struct pci_dev *dev, struct acpiphp_bridge *bridge) +static void acpiphp_set_hpp_values(struct pci_bus *bus) { - u16 pci_cmd, pci_bctl; - struct pci_dev *cdev; - - /* Program hpp values for this device */ - if (!(dev->hdr_type == PCI_HEADER_TYPE_NORMAL || - (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE && - (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI))) - return; - - if ((dev->class >> 8) == PCI_CLASS_BRIDGE_HOST) - return; - - pci_write_config_byte(dev, PCI_CACHE_LINE_SIZE, - bridge->hpp.t0->cache_line_size); - pci_write_config_byte(dev, PCI_LATENCY_TIMER, - bridge->hpp.t0->latency_timer); - pci_read_config_word(dev, PCI_COMMAND, &pci_cmd); - if (bridge->hpp.t0->enable_serr) - pci_cmd |= PCI_COMMAND_SERR; - else - pci_cmd &= ~PCI_COMMAND_SERR; - if (bridge->hpp.t0->enable_perr) - pci_cmd |= PCI_COMMAND_PARITY; - else - pci_cmd &= ~PCI_COMMAND_PARITY; - pci_write_config_word(dev, PCI_COMMAND, pci_cmd); - - /* Program bridge control value and child devices */ - if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) { - pci_write_config_byte(dev, PCI_SEC_LATENCY_TIMER, - bridge->hpp.t0->latency_timer); - pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &pci_bctl); - if (bridge->hpp.t0->enable_serr) - pci_bctl |= PCI_BRIDGE_CTL_SERR; - else - pci_bctl &= ~PCI_BRIDGE_CTL_SERR; - if (bridge->hpp.t0->enable_perr) - pci_bctl |= PCI_BRIDGE_CTL_PARITY; - else - pci_bctl &= ~PCI_BRIDGE_CTL_PARITY; - pci_write_config_word(dev, PCI_BRIDGE_CONTROL, pci_bctl); - if (dev->subordinate) { - list_for_each_entry(cdev, &dev->subordinate->devices, - bus_list) - program_hpp(cdev, bridge); - } - } -} - -static void acpiphp_set_hpp_values(acpi_handle handle, struct pci_bus *bus) -{ - struct acpiphp_bridge bridge; struct pci_dev *dev; - memset(&bridge, 0, sizeof(bridge)); - bridge.handle = handle; - bridge.pci_bus = bus; - bridge.pci_dev = bus->self; - decode_hpp(&bridge); list_for_each_entry(dev, &bus->devices, bus_list) - program_hpp(dev, &bridge); - + pci_configure_slot(dev); } /* @@ -1387,24 +1259,23 @@ static void acpiphp_sanitize_bus(struct pci_bus *bus) /* Program resources in newly inserted bridge */ static int acpiphp_configure_bridge (acpi_handle handle) { - struct pci_dev *dev; struct pci_bus *bus; - dev = acpi_get_pci_dev(handle); - if (!dev) { - err("cannot get PCI domain and bus number for bridge\n"); - return -EINVAL; + if (acpi_is_root_bridge(handle)) { + struct acpi_pci_root *root = acpi_pci_find_root(handle); + bus = root->bus; + } else { + struct pci_dev *pdev = acpi_get_pci_dev(handle); + bus = pdev->subordinate; + pci_dev_put(pdev); } - bus = dev->bus; - pci_bus_size_bridges(bus); pci_bus_assign_resources(bus); acpiphp_sanitize_bus(bus); - acpiphp_set_hpp_values(handle, bus); + acpiphp_set_hpp_values(bus); pci_enable_bridges(bus); acpiphp_configure_ioapics(handle); - pci_dev_put(dev); return 0; } diff --git a/drivers/pci/hotplug/pci_hotplug_core.c b/drivers/pci/hotplug/pci_hotplug_core.c index 5c5043f239c..0325d989bb4 100644 --- a/drivers/pci/hotplug/pci_hotplug_core.c +++ b/drivers/pci/hotplug/pci_hotplug_core.c @@ -86,7 +86,8 @@ static char *pci_bus_speed_strings[] = { "66 MHz PCIX 533", /* 0x11 */ "100 MHz PCIX 533", /* 0x12 */ "133 MHz PCIX 533", /* 0x13 */ - "25 GBps PCI-E", /* 0x14 */ + "2.5 GT/s PCI-E", /* 0x14 */ + "5.0 GT/s PCI-E", /* 0x15 */ }; #ifdef CONFIG_HOTPLUG_PCI_CPCI diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h index e6cf096498b..36faa9a8e18 100644 --- a/drivers/pci/hotplug/pciehp.h +++ b/drivers/pci/hotplug/pciehp.h @@ -237,17 +237,8 @@ static inline int pciehp_get_hp_hw_control_from_firmware(struct pci_dev *dev) return retval; return pciehp_acpi_slot_detection_check(dev); } - -static inline int pciehp_get_hp_params_from_firmware(struct pci_dev *dev, - struct hotplug_params *hpp) -{ - if (ACPI_FAILURE(acpi_get_hp_params_from_firmware(dev->bus, hpp))) - return -ENODEV; - return 0; -} #else #define pciehp_firmware_init() do {} while (0) #define pciehp_get_hp_hw_control_from_firmware(dev) 0 -#define pciehp_get_hp_params_from_firmware(dev, hpp) (-ENODEV) #endif /* CONFIG_ACPI */ #endif /* _PCIEHP_H */ diff --git a/drivers/pci/hotplug/pciehp_acpi.c b/drivers/pci/hotplug/pciehp_acpi.c index 96048010e7d..7163e6a6cfa 100644 --- a/drivers/pci/hotplug/pciehp_acpi.c +++ b/drivers/pci/hotplug/pciehp_acpi.c @@ -47,7 +47,7 @@ int pciehp_acpi_slot_detection_check(struct pci_dev *dev) { if (slot_detection_mode != PCIEHP_DETECT_ACPI) return 0; - if (acpi_pci_detect_ejectable(dev->subordinate)) + if (acpi_pci_detect_ejectable(DEVICE_ACPI_HANDLE(&dev->dev))) return 0; return -ENODEV; } @@ -76,9 +76,9 @@ static int __init dummy_probe(struct pcie_device *dev) { int pos; u32 slot_cap; + acpi_handle handle; struct slot *slot, *tmp; struct pci_dev *pdev = dev->port; - struct pci_bus *pbus = pdev->subordinate; /* Note: pciehp_detect_mode != PCIEHP_DETECT_ACPI here */ if (pciehp_get_hp_hw_control_from_firmware(pdev)) return -ENODEV; @@ -94,7 +94,8 @@ static int __init dummy_probe(struct pcie_device *dev) dup_slot_id++; } list_add_tail(&slot->slot_list, &dummy_slots); - if (!acpi_slot_detected && acpi_pci_detect_ejectable(pbus)) + handle = DEVICE_ACPI_HANDLE(&pdev->dev); + if (!acpi_slot_detected && acpi_pci_detect_ejectable(handle)) acpi_slot_detected = 1; return -ENODEV; /* dummy driver always returns error */ } diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c index 8aab8edf123..b97cb4c3e0f 100644 --- a/drivers/pci/hotplug/pciehp_ctrl.c +++ b/drivers/pci/hotplug/pciehp_ctrl.c @@ -246,11 +246,6 @@ static int board_added(struct slot *p_slot) goto err_exit; } - /* - * Some PCI Express root ports require fixup after hot-plug operation. - */ - if (pcie_mch_quirk) - pci_fixup_device(pci_fixup_final, ctrl->pci_dev); if (PWR_LED(ctrl)) p_slot->hpc_ops->green_led_on(p_slot); diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c index 52813257e5b..271f917b6f2 100644 --- a/drivers/pci/hotplug/pciehp_hpc.c +++ b/drivers/pci/hotplug/pciehp_hpc.c @@ -693,7 +693,10 @@ static int hpc_get_max_lnk_speed(struct slot *slot, enum pci_bus_speed *value) switch (lnk_cap & 0x000F) { case 1: - lnk_speed = PCIE_2PT5GB; + lnk_speed = PCIE_2_5GB; + break; + case 2: + lnk_speed = PCIE_5_0GB; break; default: lnk_speed = PCIE_LNK_SPEED_UNKNOWN; @@ -772,7 +775,10 @@ static int hpc_get_cur_lnk_speed(struct slot *slot, enum pci_bus_speed *value) switch (lnk_status & PCI_EXP_LNKSTA_CLS) { case 1: - lnk_speed = PCIE_2PT5GB; + lnk_speed = PCIE_2_5GB; + break; + case 2: + lnk_speed = PCIE_5_0GB; break; default: lnk_speed = PCIE_LNK_SPEED_UNKNOWN; diff --git a/drivers/pci/hotplug/pciehp_pci.c b/drivers/pci/hotplug/pciehp_pci.c index 10f9566ccee..02e24d63b3e 100644 --- a/drivers/pci/hotplug/pciehp_pci.c +++ b/drivers/pci/hotplug/pciehp_pci.c @@ -34,136 +34,6 @@ #include "../pci.h" #include "pciehp.h" -static void program_hpp_type0(struct pci_dev *dev, struct hpp_type0 *hpp) -{ - u16 pci_cmd, pci_bctl; - - if (hpp->revision > 1) { - warn("Rev.%d type0 record not supported\n", hpp->revision); - return; - } - - pci_write_config_byte(dev, PCI_CACHE_LINE_SIZE, hpp->cache_line_size); - pci_write_config_byte(dev, PCI_LATENCY_TIMER, hpp->latency_timer); - pci_read_config_word(dev, PCI_COMMAND, &pci_cmd); - if (hpp->enable_serr) - pci_cmd |= PCI_COMMAND_SERR; - else - pci_cmd &= ~PCI_COMMAND_SERR; - if (hpp->enable_perr) - pci_cmd |= PCI_COMMAND_PARITY; - else - pci_cmd &= ~PCI_COMMAND_PARITY; - pci_write_config_word(dev, PCI_COMMAND, pci_cmd); - - /* Program bridge control value */ - if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) { - pci_write_config_byte(dev, PCI_SEC_LATENCY_TIMER, - hpp->latency_timer); - pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &pci_bctl); - if (hpp->enable_serr) - pci_bctl |= PCI_BRIDGE_CTL_SERR; - else - pci_bctl &= ~PCI_BRIDGE_CTL_SERR; - if (hpp->enable_perr) - pci_bctl |= PCI_BRIDGE_CTL_PARITY; - else - pci_bctl &= ~PCI_BRIDGE_CTL_PARITY; - pci_write_config_word(dev, PCI_BRIDGE_CONTROL, pci_bctl); - } -} - -static void program_hpp_type2(struct pci_dev *dev, struct hpp_type2 *hpp) -{ - int pos; - u16 reg16; - u32 reg32; - - if (hpp->revision > 1) { - warn("Rev.%d type2 record not supported\n", hpp->revision); - return; - } - - /* Find PCI Express capability */ - pos = pci_find_capability(dev, PCI_CAP_ID_EXP); - if (!pos) - return; - - /* Initialize Device Control Register */ - pci_read_config_word(dev, pos + PCI_EXP_DEVCTL, ®16); - reg16 = (reg16 & hpp->pci_exp_devctl_and) | hpp->pci_exp_devctl_or; - pci_write_config_word(dev, pos + PCI_EXP_DEVCTL, reg16); - - /* Initialize Link Control Register */ - if (dev->subordinate) { - pci_read_config_word(dev, pos + PCI_EXP_LNKCTL, ®16); - reg16 = (reg16 & hpp->pci_exp_lnkctl_and) - | hpp->pci_exp_lnkctl_or; - pci_write_config_word(dev, pos + PCI_EXP_LNKCTL, reg16); - } - - /* Find Advanced Error Reporting Enhanced Capability */ - pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); - if (!pos) - return; - - /* Initialize Uncorrectable Error Mask Register */ - pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, ®32); - reg32 = (reg32 & hpp->unc_err_mask_and) | hpp->unc_err_mask_or; - pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, reg32); - - /* Initialize Uncorrectable Error Severity Register */ - pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, ®32); - reg32 = (reg32 & hpp->unc_err_sever_and) | hpp->unc_err_sever_or; - pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, reg32); - - /* Initialize Correctable Error Mask Register */ - pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK, ®32); - reg32 = (reg32 & hpp->cor_err_mask_and) | hpp->cor_err_mask_or; - pci_write_config_dword(dev, pos + PCI_ERR_COR_MASK, reg32); - - /* Initialize Advanced Error Capabilities and Control Register */ - pci_read_config_dword(dev, pos + PCI_ERR_CAP, ®32); - reg32 = (reg32 & hpp->adv_err_cap_and) | hpp->adv_err_cap_or; - pci_write_config_dword(dev, pos + PCI_ERR_CAP, reg32); - - /* - * FIXME: The following two registers are not supported yet. - * - * o Secondary Uncorrectable Error Severity Register - * o Secondary Uncorrectable Error Mask Register - */ -} - -static void program_fw_provided_values(struct pci_dev *dev) -{ - struct pci_dev *cdev; - struct hotplug_params hpp; - - /* Program hpp values for this device */ - if (!(dev->hdr_type == PCI_HEADER_TYPE_NORMAL || - (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE && - (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI))) - return; - - if (pciehp_get_hp_params_from_firmware(dev, &hpp)) { - warn("Could not get hotplug parameters\n"); - return; - } - - if (hpp.t2) - program_hpp_type2(dev, hpp.t2); - if (hpp.t0) - program_hpp_type0(dev, hpp.t0); - - /* Program child devices */ - if (dev->subordinate) { - list_for_each_entry(cdev, &dev->subordinate->devices, - bus_list) - program_fw_provided_values(cdev); - } -} - static int __ref pciehp_add_bridge(struct pci_dev *dev) { struct pci_bus *parent = dev->bus; @@ -226,7 +96,7 @@ int pciehp_configure_device(struct slot *p_slot) (dev->hdr_type == PCI_HEADER_TYPE_CARDBUS)) { pciehp_add_bridge(dev); } - program_fw_provided_values(dev); + pci_configure_slot(dev); pci_dev_put(dev); } @@ -285,11 +155,6 @@ int pciehp_unconfigure_device(struct slot *p_slot) } pci_dev_put(temp); } - /* - * Some PCI Express root ports require fixup after hot-plug operation. - */ - if (pcie_mch_quirk) - pci_fixup_device(pci_fixup_final, p_slot->ctrl->pci_dev); return rc; } diff --git a/drivers/pci/hotplug/pcihp_slot.c b/drivers/pci/hotplug/pcihp_slot.c new file mode 100644 index 00000000000..cc8ec3aa41a --- /dev/null +++ b/drivers/pci/hotplug/pcihp_slot.c @@ -0,0 +1,187 @@ +/* + * Copyright (C) 1995,2001 Compaq Computer Corporation + * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com) + * Copyright (C) 2001 IBM Corp. + * Copyright (C) 2003-2004 Intel Corporation + * (c) Copyright 2009 Hewlett-Packard Development Company, L.P. + * + * All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or (at + * your option) any later version. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for more + * details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +#include <linux/pci.h> +#include <linux/pci_hotplug.h> + +static struct hpp_type0 pci_default_type0 = { + .revision = 1, + .cache_line_size = 8, + .latency_timer = 0x40, + .enable_serr = 0, + .enable_perr = 0, +}; + +static void program_hpp_type0(struct pci_dev *dev, struct hpp_type0 *hpp) +{ + u16 pci_cmd, pci_bctl; + + if (!hpp) { + /* + * Perhaps we *should* use default settings for PCIe, but + * pciehp didn't, so we won't either. + */ + if (dev->is_pcie) + return; + dev_info(&dev->dev, "using default PCI settings\n"); + hpp = &pci_default_type0; + } + + if (hpp->revision > 1) { + dev_warn(&dev->dev, + "PCI settings rev %d not supported; using defaults\n", + hpp->revision); + hpp = &pci_default_type0; + } + + pci_write_config_byte(dev, PCI_CACHE_LINE_SIZE, hpp->cache_line_size); + pci_write_config_byte(dev, PCI_LATENCY_TIMER, hpp->latency_timer); + pci_read_config_word(dev, PCI_COMMAND, &pci_cmd); + if (hpp->enable_serr) + pci_cmd |= PCI_COMMAND_SERR; + else + pci_cmd &= ~PCI_COMMAND_SERR; + if (hpp->enable_perr) + pci_cmd |= PCI_COMMAND_PARITY; + else + pci_cmd &= ~PCI_COMMAND_PARITY; + pci_write_config_word(dev, PCI_COMMAND, pci_cmd); + + /* Program bridge control value */ + if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) { + pci_write_config_byte(dev, PCI_SEC_LATENCY_TIMER, + hpp->latency_timer); + pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &pci_bctl); + if (hpp->enable_serr) + pci_bctl |= PCI_BRIDGE_CTL_SERR; + else + pci_bctl &= ~PCI_BRIDGE_CTL_SERR; + if (hpp->enable_perr) + pci_bctl |= PCI_BRIDGE_CTL_PARITY; + else + pci_bctl &= ~PCI_BRIDGE_CTL_PARITY; + pci_write_config_word(dev, PCI_BRIDGE_CONTROL, pci_bctl); + } +} + +static void program_hpp_type1(struct pci_dev *dev, struct hpp_type1 *hpp) +{ + if (hpp) + dev_warn(&dev->dev, "PCI-X settings not supported\n"); +} + +static void program_hpp_type2(struct pci_dev *dev, struct hpp_type2 *hpp) +{ + int pos; + u16 reg16; + u32 reg32; + + if (!hpp) + return; + + /* Find PCI Express capability */ + pos = pci_find_capability(dev, PCI_CAP_ID_EXP); + if (!pos) + return; + + if (hpp->revision > 1) { + dev_warn(&dev->dev, "PCIe settings rev %d not supported\n", + hpp->revision); + return; + } + + /* Initialize Device Control Register */ + pci_read_config_word(dev, pos + PCI_EXP_DEVCTL, ®16); + reg16 = (reg16 & hpp->pci_exp_devctl_and) | hpp->pci_exp_devctl_or; + pci_write_config_word(dev, pos + PCI_EXP_DEVCTL, reg16); + + /* Initialize Link Control Register */ + if (dev->subordinate) { + pci_read_config_word(dev, pos + PCI_EXP_LNKCTL, ®16); + reg16 = (reg16 & hpp->pci_exp_lnkctl_and) + | hpp->pci_exp_lnkctl_or; + pci_write_config_word(dev, pos + PCI_EXP_LNKCTL, reg16); + } + + /* Find Advanced Error Reporting Enhanced Capability */ + pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); + if (!pos) + return; + + /* Initialize Uncorrectable Error Mask Register */ + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, ®32); + reg32 = (reg32 & hpp->unc_err_mask_and) | hpp->unc_err_mask_or; + pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, reg32); + + /* Initialize Uncorrectable Error Severity Register */ + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, ®32); + reg32 = (reg32 & hpp->unc_err_sever_and) | hpp->unc_err_sever_or; + pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, reg32); + + /* Initialize Correctable Error Mask Register */ + pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK, ®32); + reg32 = (reg32 & hpp->cor_err_mask_and) | hpp->cor_err_mask_or; + pci_write_config_dword(dev, pos + PCI_ERR_COR_MASK, reg32); + + /* Initialize Advanced Error Capabilities and Control Register */ + pci_read_config_dword(dev, pos + PCI_ERR_CAP, ®32); + reg32 = (reg32 & hpp->adv_err_cap_and) | hpp->adv_err_cap_or; + pci_write_config_dword(dev, pos + PCI_ERR_CAP, reg32); + + /* + * FIXME: The following two registers are not supported yet. + * + * o Secondary Uncorrectable Error Severity Register + * o Secondary Uncorrectable Error Mask Register + */ +} + +void pci_configure_slot(struct pci_dev *dev) +{ + struct pci_dev *cdev; + struct hotplug_params hpp; + int ret; + + if (!(dev->hdr_type == PCI_HEADER_TYPE_NORMAL || + (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE && + (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI))) + return; + + memset(&hpp, 0, sizeof(hpp)); + ret = pci_get_hp_params(dev, &hpp); + if (ret) + dev_warn(&dev->dev, "no hotplug settings from platform\n"); + + program_hpp_type2(dev, hpp.t2); + program_hpp_type1(dev, hpp.t1); + program_hpp_type0(dev, hpp.t0); + + if (dev->subordinate) { + list_for_each_entry(cdev, &dev->subordinate->devices, + bus_list) + pci_configure_slot(cdev); + } +} +EXPORT_SYMBOL_GPL(pci_configure_slot); diff --git a/drivers/pci/hotplug/shpchp.h b/drivers/pci/hotplug/shpchp.h index 974e924ca96..bd588eb8e92 100644 --- a/drivers/pci/hotplug/shpchp.h +++ b/drivers/pci/hotplug/shpchp.h @@ -188,21 +188,12 @@ static inline const char *slot_name(struct slot *slot) #ifdef CONFIG_ACPI #include <linux/pci-acpi.h> -static inline int get_hp_params_from_firmware(struct pci_dev *dev, - struct hotplug_params *hpp) -{ - if (ACPI_FAILURE(acpi_get_hp_params_from_firmware(dev->bus, hpp))) - return -ENODEV; - return 0; -} - static inline int get_hp_hw_control_from_firmware(struct pci_dev *dev) { u32 flags = OSC_SHPC_NATIVE_HP_CONTROL; return acpi_get_hp_hw_control_from_firmware(dev, flags); } #else -#define get_hp_params_from_firmware(dev, hpp) (-ENODEV) #define get_hp_hw_control_from_firmware(dev) (0) #endif diff --git a/drivers/pci/hotplug/shpchp_pci.c b/drivers/pci/hotplug/shpchp_pci.c index aa315e52529..8c3d3219f22 100644 --- a/drivers/pci/hotplug/shpchp_pci.c +++ b/drivers/pci/hotplug/shpchp_pci.c @@ -34,66 +34,6 @@ #include "../pci.h" #include "shpchp.h" -static void program_fw_provided_values(struct pci_dev *dev) -{ - u16 pci_cmd, pci_bctl; - struct pci_dev *cdev; - struct hotplug_params hpp; - - /* Program hpp values for this device */ - if (!(dev->hdr_type == PCI_HEADER_TYPE_NORMAL || - (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE && - (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI))) - return; - - /* use default values if we can't get them from firmware */ - if (get_hp_params_from_firmware(dev, &hpp) || - !hpp.t0 || (hpp.t0->revision > 1)) { - warn("Could not get hotplug parameters. Use defaults\n"); - hpp.t0 = &hpp.type0_data; - hpp.t0->revision = 0; - hpp.t0->cache_line_size = 8; - hpp.t0->latency_timer = 0x40; - hpp.t0->enable_serr = 0; - hpp.t0->enable_perr = 0; - } - - pci_write_config_byte(dev, - PCI_CACHE_LINE_SIZE, hpp.t0->cache_line_size); - pci_write_config_byte(dev, PCI_LATENCY_TIMER, hpp.t0->latency_timer); - pci_read_config_word(dev, PCI_COMMAND, &pci_cmd); - if (hpp.t0->enable_serr) - pci_cmd |= PCI_COMMAND_SERR; - else - pci_cmd &= ~PCI_COMMAND_SERR; - if (hpp.t0->enable_perr) - pci_cmd |= PCI_COMMAND_PARITY; - else - pci_cmd &= ~PCI_COMMAND_PARITY; - pci_write_config_word(dev, PCI_COMMAND, pci_cmd); - - /* Program bridge control value and child devices */ - if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) { - pci_write_config_byte(dev, PCI_SEC_LATENCY_TIMER, - hpp.t0->latency_timer); - pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &pci_bctl); - if (hpp.t0->enable_serr) - pci_bctl |= PCI_BRIDGE_CTL_SERR; - else - pci_bctl &= ~PCI_BRIDGE_CTL_SERR; - if (hpp.t0->enable_perr) - pci_bctl |= PCI_BRIDGE_CTL_PARITY; - else - pci_bctl &= ~PCI_BRIDGE_CTL_PARITY; - pci_write_config_word(dev, PCI_BRIDGE_CONTROL, pci_bctl); - if (dev->subordinate) { - list_for_each_entry(cdev, &dev->subordinate->devices, - bus_list) - program_fw_provided_values(cdev); - } - } -} - int __ref shpchp_configure_device(struct slot *p_slot) { struct pci_dev *dev; @@ -153,7 +93,7 @@ int __ref shpchp_configure_device(struct slot *p_slot) child->subordinate = pci_do_scan_bus(child); pci_bus_size_bridges(child); } - program_fw_provided_values(dev); + pci_configure_slot(dev); pci_dev_put(dev); } diff --git a/drivers/pci/legacy.c b/drivers/pci/legacy.c new file mode 100644 index 00000000000..871f65c1593 --- /dev/null +++ b/drivers/pci/legacy.c @@ -0,0 +1,34 @@ +#include <linux/init.h> +#include <linux/pci.h> +#include <linux/module.h> +#include <linux/interrupt.h> +#include "pci.h" + +/** + * pci_find_device - begin or continue searching for a PCI device by vendor/device id + * @vendor: PCI vendor id to match, or %PCI_ANY_ID to match all vendor ids + * @device: PCI device id to match, or %PCI_ANY_ID to match all device ids + * @from: Previous PCI device found in search, or %NULL for new search. + * + * Iterates through the list of known PCI devices. If a PCI device is found + * with a matching @vendor and @device, a pointer to its device structure is + * returned. Otherwise, %NULL is returned. + * A new search is initiated by passing %NULL as the @from argument. + * Otherwise if @from is not %NULL, searches continue from next device + * on the global list. + * + * NOTE: Do not use this function any more; use pci_get_device() instead, as + * the PCI device returned by this function can disappear at any moment in + * time. + */ +struct pci_dev *pci_find_device(unsigned int vendor, unsigned int device, + struct pci_dev *from) +{ + struct pci_dev *pdev; + + pci_dev_get(from); + pdev = pci_get_subsys(vendor, device, PCI_ANY_ID, PCI_ANY_ID, from); + pci_dev_put(pdev); + return pdev; +} +EXPORT_SYMBOL(pci_find_device); diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index d986afb7032..f9cf3173b23 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -16,9 +16,8 @@ #include <linux/proc_fs.h> #include <linux/msi.h> #include <linux/smp.h> - -#include <asm/errno.h> -#include <asm/io.h> +#include <linux/errno.h> +#include <linux/io.h> #include "pci.h" #include "msi.h" @@ -272,7 +271,30 @@ void write_msi_msg(unsigned int irq, struct msi_msg *msg) write_msi_msg_desc(desc, msg); } -static int msi_free_irqs(struct pci_dev* dev); +static void free_msi_irqs(struct pci_dev *dev) +{ + struct msi_desc *entry, *tmp; + + list_for_each_entry(entry, &dev->msi_list, list) { + 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); + + list_for_each_entry_safe(entry, tmp, &dev->msi_list, list) { + if (entry->msi_attrib.is_msix) { + if (list_is_last(&entry->list, &dev->msi_list)) + iounmap(entry->mask_base); + } + list_del(&entry->list); + kfree(entry); + } +} static struct msi_desc *alloc_msi_entry(struct pci_dev *dev) { @@ -324,7 +346,7 @@ static void __pci_restore_msix_state(struct pci_dev *dev) if (!dev->msix_enabled) return; BUG_ON(list_empty(&dev->msi_list)); - entry = list_entry(dev->msi_list.next, struct msi_desc, list); + entry = list_first_entry(&dev->msi_list, struct msi_desc, list); pos = entry->msi_attrib.pos; pci_read_config_word(dev, pos + PCI_MSIX_FLAGS, &control); @@ -367,7 +389,7 @@ static int msi_capability_init(struct pci_dev *dev, int nvec) u16 control; unsigned mask; - pos = pci_find_capability(dev, PCI_CAP_ID_MSI); + pos = pci_find_capability(dev, PCI_CAP_ID_MSI); msi_set_enable(dev, pos, 0); /* Disable MSI during set up */ pci_read_config_word(dev, msi_control_reg(pos), &control); @@ -376,12 +398,12 @@ static int msi_capability_init(struct pci_dev *dev, int nvec) if (!entry) return -ENOMEM; - entry->msi_attrib.is_msix = 0; - entry->msi_attrib.is_64 = is_64bit_address(control); - entry->msi_attrib.entry_nr = 0; - entry->msi_attrib.maskbit = is_mask_bit_support(control); - entry->msi_attrib.default_irq = dev->irq; /* Save IOAPIC IRQ */ - entry->msi_attrib.pos = pos; + entry->msi_attrib.is_msix = 0; + entry->msi_attrib.is_64 = is_64bit_address(control); + entry->msi_attrib.entry_nr = 0; + entry->msi_attrib.maskbit = is_mask_bit_support(control); + entry->msi_attrib.default_irq = dev->irq; /* Save IOAPIC IRQ */ + entry->msi_attrib.pos = pos; entry->mask_pos = msi_mask_reg(pos, entry->msi_attrib.is_64); /* All MSIs are unmasked by default, Mask them all */ @@ -396,7 +418,7 @@ static int msi_capability_init(struct pci_dev *dev, int nvec) ret = arch_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSI); if (ret) { msi_mask_irq(entry, mask, ~mask); - msi_free_irqs(dev); + free_msi_irqs(dev); return ret; } @@ -409,44 +431,27 @@ static int msi_capability_init(struct pci_dev *dev, int nvec) return 0; } -/** - * msix_capability_init - configure device's MSI-X capability - * @dev: pointer to the pci_dev data structure of MSI-X device function - * @entries: pointer to an array of struct msix_entry entries - * @nvec: number of @entries - * - * Setup the MSI-X capability structure of device function with a - * single MSI-X irq. A return of zero indicates the successful setup of - * requested MSI-X entries with allocated irqs or non-zero for otherwise. - **/ -static int msix_capability_init(struct pci_dev *dev, - struct msix_entry *entries, int nvec) +static void __iomem *msix_map_region(struct pci_dev *dev, unsigned pos, + unsigned nr_entries) { - struct msi_desc *entry; - int pos, i, j, nr_entries, ret; unsigned long phys_addr; u32 table_offset; - u16 control; u8 bir; - void __iomem *base; - pos = pci_find_capability(dev, PCI_CAP_ID_MSIX); - pci_read_config_word(dev, pos + PCI_MSIX_FLAGS, &control); - - /* Ensure MSI-X is disabled while it is set up */ - control &= ~PCI_MSIX_FLAGS_ENABLE; - pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control); - - /* Request & Map MSI-X table region */ - nr_entries = multi_msix_capable(control); - - pci_read_config_dword(dev, msix_table_offset_reg(pos), &table_offset); + pci_read_config_dword(dev, msix_table_offset_reg(pos), &table_offset); bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK); table_offset &= ~PCI_MSIX_FLAGS_BIRMASK; - phys_addr = pci_resource_start (dev, bir) + table_offset; - base = ioremap_nocache(phys_addr, nr_entries * PCI_MSIX_ENTRY_SIZE); - if (base == NULL) - return -ENOMEM; + phys_addr = pci_resource_start(dev, bir) + table_offset; + + return ioremap_nocache(phys_addr, nr_entries * PCI_MSIX_ENTRY_SIZE); +} + +static int msix_setup_entries(struct pci_dev *dev, unsigned pos, + void __iomem *base, struct msix_entry *entries, + int nvec) +{ + struct msi_desc *entry; + int i; for (i = 0; i < nvec; i++) { entry = alloc_msi_entry(dev); @@ -454,41 +459,78 @@ static int msix_capability_init(struct pci_dev *dev, if (!i) iounmap(base); else - msi_free_irqs(dev); + free_msi_irqs(dev); /* No enough memory. Don't try again */ return -ENOMEM; } - j = entries[i].entry; - entry->msi_attrib.is_msix = 1; - entry->msi_attrib.is_64 = 1; - entry->msi_attrib.entry_nr = j; - entry->msi_attrib.default_irq = dev->irq; - entry->msi_attrib.pos = pos; - entry->mask_base = base; + entry->msi_attrib.is_msix = 1; + entry->msi_attrib.is_64 = 1; + entry->msi_attrib.entry_nr = entries[i].entry; + entry->msi_attrib.default_irq = dev->irq; + entry->msi_attrib.pos = pos; + entry->mask_base = base; list_add_tail(&entry->list, &dev->msi_list); } - ret = arch_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSIX); - if (ret < 0) { - /* If we had some success report the number of irqs - * we succeeded in setting up. */ - int avail = 0; - list_for_each_entry(entry, &dev->msi_list, list) { - if (entry->irq != 0) { - avail++; - } - } + return 0; +} - if (avail != 0) - ret = avail; +static void msix_program_entries(struct pci_dev *dev, + struct msix_entry *entries) +{ + struct msi_desc *entry; + int i = 0; + + list_for_each_entry(entry, &dev->msi_list, list) { + int offset = entries[i].entry * PCI_MSIX_ENTRY_SIZE + + PCI_MSIX_ENTRY_VECTOR_CTRL; + + entries[i].vector = entry->irq; + set_irq_msi(entry->irq, entry); + entry->masked = readl(entry->mask_base + offset); + msix_mask_irq(entry, 1); + i++; } +} - if (ret) { - msi_free_irqs(dev); +/** + * msix_capability_init - configure device's MSI-X capability + * @dev: pointer to the pci_dev data structure of MSI-X device function + * @entries: pointer to an array of struct msix_entry entries + * @nvec: number of @entries + * + * Setup the MSI-X capability structure of device function with a + * single MSI-X irq. A return of zero indicates the successful setup of + * requested MSI-X entries with allocated irqs or non-zero for otherwise. + **/ +static int msix_capability_init(struct pci_dev *dev, + struct msix_entry *entries, int nvec) +{ + int pos, ret; + u16 control; + void __iomem *base; + + pos = pci_find_capability(dev, PCI_CAP_ID_MSIX); + pci_read_config_word(dev, pos + PCI_MSIX_FLAGS, &control); + + /* Ensure MSI-X is disabled while it is set up */ + control &= ~PCI_MSIX_FLAGS_ENABLE; + pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control); + + /* Request & Map MSI-X table region */ + base = msix_map_region(dev, pos, multi_msix_capable(control)); + if (!base) + return -ENOMEM; + + ret = msix_setup_entries(dev, pos, base, entries, nvec); + if (ret) return ret; - } + + ret = arch_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSIX); + if (ret) + goto error; /* * Some devices require MSI-X to be enabled before we can touch the @@ -498,16 +540,7 @@ static int msix_capability_init(struct pci_dev *dev, control |= PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE; pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control); - i = 0; - list_for_each_entry(entry, &dev->msi_list, list) { - entries[i].vector = entry->irq; - set_irq_msi(entry->irq, entry); - j = entries[i].entry; - entry->masked = readl(base + j * PCI_MSIX_ENTRY_SIZE + - PCI_MSIX_ENTRY_VECTOR_CTRL); - msix_mask_irq(entry, 1); - i++; - } + msix_program_entries(dev, entries); /* Set MSI-X enabled bits and unmask the function */ pci_intx_for_msi(dev, 0); @@ -517,6 +550,27 @@ static int msix_capability_init(struct pci_dev *dev, pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control); return 0; + +error: + if (ret < 0) { + /* + * If we had some success, report the number of irqs + * we succeeded in setting up. + */ + struct msi_desc *entry; + int avail = 0; + + list_for_each_entry(entry, &dev->msi_list, list) { + if (entry->irq != 0) + avail++; + } + if (avail != 0) + ret = avail; + } + + free_msi_irqs(dev); + + return ret; } /** @@ -529,7 +583,7 @@ static int msix_capability_init(struct pci_dev *dev, * to determine if MSI/-X are supported for the device. If MSI/-X is * supported return 0, else return an error code. **/ -static int pci_msi_check_device(struct pci_dev* dev, int nvec, int type) +static int pci_msi_check_device(struct pci_dev *dev, int nvec, int type) { struct pci_bus *bus; int ret; @@ -546,8 +600,9 @@ static int pci_msi_check_device(struct pci_dev* dev, int nvec, int type) if (nvec < 1) return -ERANGE; - /* Any bridge which does NOT route MSI transactions from it's - * secondary bus to it's primary bus must set NO_MSI flag on + /* + * Any bridge which does NOT route MSI transactions from its + * secondary bus to its primary bus must set NO_MSI flag on * the secondary pci_bus. * We expect only arch-specific PCI host bus controller driver * or quirks for specific PCI bridges to be setting NO_MSI. @@ -638,50 +693,16 @@ void pci_msi_shutdown(struct pci_dev *dev) dev->irq = desc->msi_attrib.default_irq; } -void pci_disable_msi(struct pci_dev* dev) +void pci_disable_msi(struct pci_dev *dev) { - struct msi_desc *entry; - if (!pci_msi_enable || !dev || !dev->msi_enabled) return; pci_msi_shutdown(dev); - - entry = list_entry(dev->msi_list.next, struct msi_desc, list); - if (entry->msi_attrib.is_msix) - return; - - msi_free_irqs(dev); + free_msi_irqs(dev); } EXPORT_SYMBOL(pci_disable_msi); -static int msi_free_irqs(struct pci_dev* dev) -{ - struct msi_desc *entry, *tmp; - - list_for_each_entry(entry, &dev->msi_list, list) { - 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); - - list_for_each_entry_safe(entry, tmp, &dev->msi_list, list) { - if (entry->msi_attrib.is_msix) { - if (list_is_last(&entry->list, &dev->msi_list)) - iounmap(entry->mask_base); - } - list_del(&entry->list); - kfree(entry); - } - - return 0; -} - /** * pci_msix_table_size - return the number of device's MSI-X table entries * @dev: pointer to the pci_dev data structure of MSI-X device function @@ -714,13 +735,13 @@ int pci_msix_table_size(struct pci_dev *dev) * of irqs or MSI-X vectors available. Driver should use the returned value to * re-send its request. **/ -int pci_enable_msix(struct pci_dev* dev, struct msix_entry *entries, int nvec) +int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec) { int status, nr_entries; int i, j; if (!entries) - return -EINVAL; + return -EINVAL; status = pci_msi_check_device(dev, nvec, PCI_CAP_ID_MSIX); if (status) @@ -742,7 +763,7 @@ int pci_enable_msix(struct pci_dev* dev, struct msix_entry *entries, int nvec) WARN_ON(!!dev->msix_enabled); /* Check whether driver already requested for MSI irq */ - if (dev->msi_enabled) { + if (dev->msi_enabled) { dev_info(&dev->dev, "can't enable MSI-X " "(MSI IRQ already assigned)\n"); return -EINVAL; @@ -752,12 +773,7 @@ int pci_enable_msix(struct pci_dev* dev, struct msix_entry *entries, int nvec) } EXPORT_SYMBOL(pci_enable_msix); -static void msix_free_all_irqs(struct pci_dev *dev) -{ - msi_free_irqs(dev); -} - -void pci_msix_shutdown(struct pci_dev* dev) +void pci_msix_shutdown(struct pci_dev *dev) { struct msi_desc *entry; @@ -774,14 +790,14 @@ void pci_msix_shutdown(struct pci_dev* dev) pci_intx_for_msi(dev, 1); dev->msix_enabled = 0; } -void pci_disable_msix(struct pci_dev* dev) + +void pci_disable_msix(struct pci_dev *dev) { if (!pci_msi_enable || !dev || !dev->msix_enabled) return; pci_msix_shutdown(dev); - - msix_free_all_irqs(dev); + free_msi_irqs(dev); } EXPORT_SYMBOL(pci_disable_msix); @@ -794,16 +810,13 @@ EXPORT_SYMBOL(pci_disable_msix); * allocated for this device function, are reclaimed to unused state, * which may be used later on. **/ -void msi_remove_pci_irq_vectors(struct pci_dev* dev) +void msi_remove_pci_irq_vectors(struct pci_dev *dev) { if (!pci_msi_enable || !dev) - return; - - if (dev->msi_enabled) - msi_free_irqs(dev); + return; - if (dev->msix_enabled) - msix_free_all_irqs(dev); + if (dev->msi_enabled || dev->msix_enabled) + free_msi_irqs(dev); } void pci_no_msi(void) diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index ea15b053745..33317df4769 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -109,15 +109,32 @@ static bool acpi_pci_can_wakeup(struct pci_dev *dev) return handle ? acpi_bus_can_wakeup(handle) : false; } +static void acpi_pci_propagate_wakeup_enable(struct pci_bus *bus, bool enable) +{ + while (bus->parent) { + struct pci_dev *bridge = bus->self; + int ret; + + ret = acpi_pm_device_sleep_wake(&bridge->dev, enable); + if (!ret || bridge->is_pcie) + return; + bus = bus->parent; + } + + /* We have reached the root bus. */ + if (bus->bridge) + acpi_pm_device_sleep_wake(bus->bridge, enable); +} + static int acpi_pci_sleep_wake(struct pci_dev *dev, bool enable) { - int error = acpi_pm_device_sleep_wake(&dev->dev, enable); + if (acpi_pci_can_wakeup(dev)) + return acpi_pm_device_sleep_wake(&dev->dev, enable); - if (!error) - dev_printk(KERN_INFO, &dev->dev, - "wake-up capability %s by ACPI\n", - enable ? "enabled" : "disabled"); - return error; + if (!dev->is_pcie) + acpi_pci_propagate_wakeup_enable(dev->bus, enable); + + return 0; } static struct pci_platform_pm_ops acpi_pci_platform_pm = { diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index a7eb7277b10..e5d47be3c6d 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -19,37 +19,98 @@ #include <linux/cpu.h> #include "pci.h" -/* - * Dynamic device IDs are disabled for !CONFIG_HOTPLUG - */ - struct pci_dynid { struct list_head node; struct pci_device_id id; }; -#ifdef CONFIG_HOTPLUG +/** + * pci_add_dynid - add a new PCI device ID to this driver and re-probe devices + * @drv: target pci driver + * @vendor: PCI vendor ID + * @device: PCI device ID + * @subvendor: PCI subvendor ID + * @subdevice: PCI subdevice ID + * @class: PCI class + * @class_mask: PCI class mask + * @driver_data: private driver data + * + * Adds a new dynamic pci device ID to this driver and causes the + * driver to probe for all devices again. @drv must have been + * registered prior to calling this function. + * + * CONTEXT: + * Does GFP_KERNEL allocation. + * + * RETURNS: + * 0 on success, -errno on failure. + */ +int pci_add_dynid(struct pci_driver *drv, + unsigned int vendor, unsigned int device, + unsigned int subvendor, unsigned int subdevice, + unsigned int class, unsigned int class_mask, + unsigned long driver_data) +{ + struct pci_dynid *dynid; + int retval; + + dynid = kzalloc(sizeof(*dynid), GFP_KERNEL); + if (!dynid) + return -ENOMEM; + + dynid->id.vendor = vendor; + dynid->id.device = device; + dynid->id.subvendor = subvendor; + dynid->id.subdevice = subdevice; + dynid->id.class = class; + dynid->id.class_mask = class_mask; + dynid->id.driver_data = driver_data; + + spin_lock(&drv->dynids.lock); + list_add_tail(&dynid->node, &drv->dynids.list); + spin_unlock(&drv->dynids.lock); + + get_driver(&drv->driver); + retval = driver_attach(&drv->driver); + put_driver(&drv->driver); + + return retval; +} + +static void pci_free_dynids(struct pci_driver *drv) +{ + struct pci_dynid *dynid, *n; + spin_lock(&drv->dynids.lock); + list_for_each_entry_safe(dynid, n, &drv->dynids.list, node) { + list_del(&dynid->node); + kfree(dynid); + } + spin_unlock(&drv->dynids.lock); +} + +/* + * Dynamic device ID manipulation via sysfs is disabled for !CONFIG_HOTPLUG + */ +#ifdef CONFIG_HOTPLUG /** - * store_new_id - add a new PCI device ID to this driver and re-probe devices + * store_new_id - sysfs frontend to pci_add_dynid() * @driver: target device driver * @buf: buffer for scanning device ID data * @count: input size * - * Adds a new dynamic pci device ID to this driver, - * and causes the driver to probe for all devices again. + * Allow PCI IDs to be added to an existing driver via sysfs. */ static ssize_t store_new_id(struct device_driver *driver, const char *buf, size_t count) { - struct pci_dynid *dynid; struct pci_driver *pdrv = to_pci_driver(driver); const struct pci_device_id *ids = pdrv->id_table; __u32 vendor, device, subvendor=PCI_ANY_ID, subdevice=PCI_ANY_ID, class=0, class_mask=0; unsigned long driver_data=0; int fields=0; - int retval=0; + int retval; fields = sscanf(buf, "%x %x %x %x %x %x %lx", &vendor, &device, &subvendor, &subdevice, @@ -72,27 +133,8 @@ store_new_id(struct device_driver *driver, const char *buf, size_t count) return retval; } - dynid = kzalloc(sizeof(*dynid), GFP_KERNEL); - if (!dynid) - return -ENOMEM; - - dynid->id.vendor = vendor; - dynid->id.device = device; - dynid->id.subvendor = subvendor; - dynid->id.subdevice = subdevice; - dynid->id.class = class; - dynid->id.class_mask = class_mask; - dynid->id.driver_data = driver_data; - - spin_lock(&pdrv->dynids.lock); - list_add_tail(&dynid->node, &pdrv->dynids.list); - spin_unlock(&pdrv->dynids.lock); - - if (get_driver(&pdrv->driver)) { - retval = driver_attach(&pdrv->driver); - put_driver(&pdrv->driver); - } - + retval = pci_add_dynid(pdrv, vendor, device, subvendor, subdevice, + class, class_mask, driver_data); if (retval) return retval; return count; @@ -145,19 +187,6 @@ store_remove_id(struct device_driver *driver, const char *buf, size_t count) } static DRIVER_ATTR(remove_id, S_IWUSR, NULL, store_remove_id); -static void -pci_free_dynids(struct pci_driver *drv) -{ - struct pci_dynid *dynid, *n; - - spin_lock(&drv->dynids.lock); - list_for_each_entry_safe(dynid, n, &drv->dynids.list, node) { - list_del(&dynid->node); - kfree(dynid); - } - spin_unlock(&drv->dynids.lock); -} - static int pci_create_newid_file(struct pci_driver *drv) { @@ -186,7 +215,6 @@ static void pci_remove_removeid_file(struct pci_driver *drv) driver_remove_file(&drv->driver, &driver_attr_remove_id); } #else /* !CONFIG_HOTPLUG */ -static inline void pci_free_dynids(struct pci_driver *drv) {} static inline int pci_create_newid_file(struct pci_driver *drv) { return 0; @@ -417,8 +445,6 @@ static int pci_legacy_suspend(struct device *dev, pm_message_t state) struct pci_dev * pci_dev = to_pci_dev(dev); struct pci_driver * drv = pci_dev->driver; - pci_dev->state_saved = false; - if (drv && drv->suspend) { pci_power_t prev = pci_dev->current_state; int error; @@ -514,7 +540,6 @@ static int pci_restore_standard_config(struct pci_dev *pci_dev) static void pci_pm_default_resume_noirq(struct pci_dev *pci_dev) { pci_restore_standard_config(pci_dev); - pci_dev->state_saved = false; pci_fixup_device(pci_fixup_resume_early, pci_dev); } @@ -580,8 +605,6 @@ static int pci_pm_suspend(struct device *dev) if (pci_has_legacy_pm_support(pci_dev)) return pci_legacy_suspend(dev, PMSG_SUSPEND); - pci_dev->state_saved = false; - if (!pm) { pci_pm_default_suspend(pci_dev); goto Fixup; @@ -694,7 +717,7 @@ static int pci_pm_resume(struct device *dev) pci_pm_reenable_device(pci_dev); } - return 0; + return error; } #else /* !CONFIG_SUSPEND */ @@ -716,8 +739,6 @@ static int pci_pm_freeze(struct device *dev) if (pci_has_legacy_pm_support(pci_dev)) return pci_legacy_suspend(dev, PMSG_FREEZE); - pci_dev->state_saved = false; - if (!pm) { pci_pm_default_suspend(pci_dev); return 0; @@ -793,6 +814,8 @@ static int pci_pm_thaw(struct device *dev) pci_pm_reenable_device(pci_dev); } + pci_dev->state_saved = false; + return error; } @@ -804,8 +827,6 @@ static int pci_pm_poweroff(struct device *dev) if (pci_has_legacy_pm_support(pci_dev)) return pci_legacy_suspend(dev, PMSG_HIBERNATE); - pci_dev->state_saved = false; - if (!pm) { pci_pm_default_suspend(pci_dev); goto Fixup; @@ -1106,6 +1127,7 @@ static int __init pci_driver_init(void) postcore_initcall(pci_driver_init); +EXPORT_SYMBOL_GPL(pci_add_dynid); EXPORT_SYMBOL(pci_match_id); EXPORT_SYMBOL(__pci_register_driver); EXPORT_SYMBOL(pci_unregister_driver); diff --git a/drivers/pci/pci-stub.c b/drivers/pci/pci-stub.c index 74fbec0bf6c..f7b68ca6cc9 100644 --- a/drivers/pci/pci-stub.c +++ b/drivers/pci/pci-stub.c @@ -19,8 +19,16 @@ #include <linux/module.h> #include <linux/pci.h> +static char ids[1024] __initdata; + +module_param_string(ids, ids, sizeof(ids), 0); +MODULE_PARM_DESC(ids, "Initial PCI IDs to add to the stub driver, format is " + "\"vendor:device[:subvendor[:subdevice[:class[:class_mask]]]]\"" + " and multiple comma separated entries can be specified"); + static int pci_stub_probe(struct pci_dev *dev, const struct pci_device_id *id) { + dev_printk(KERN_INFO, &dev->dev, "claimed by stub\n"); return 0; } @@ -32,7 +40,42 @@ static struct pci_driver stub_driver = { static int __init pci_stub_init(void) { - return pci_register_driver(&stub_driver); + char *p, *id; + int rc; + + rc = pci_register_driver(&stub_driver); + if (rc) + return rc; + + /* add ids specified in the module parameter */ + p = ids; + while ((id = strsep(&p, ","))) { + unsigned int vendor, device, subvendor = PCI_ANY_ID, + subdevice = PCI_ANY_ID, class=0, class_mask=0; + int fields; + + fields = sscanf(id, "%x:%x:%x:%x:%x:%x", + &vendor, &device, &subvendor, &subdevice, + &class, &class_mask); + + if (fields < 2) { + printk(KERN_WARNING + "pci-stub: invalid id string \"%s\"\n", id); + continue; + } + + printk(KERN_INFO + "pci-stub: add %04X:%04X sub=%04X:%04X cls=%08X/%08X\n", + vendor, device, subvendor, subdevice, class, class_mask); + + rc = pci_add_dynid(&stub_driver, vendor, device, + subvendor, subdevice, class, class_mask, 0); + if (rc) + printk(KERN_WARNING + "pci-stub: failed to add dynamic id (%d)\n", rc); + } + + return 0; } static void __exit pci_stub_exit(void) diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 85ebd02a64a..0f6382f090e 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -916,6 +916,24 @@ int __attribute__ ((weak)) pcibios_add_platform_entries(struct pci_dev *dev) return 0; } +static ssize_t reset_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) +{ + struct pci_dev *pdev = to_pci_dev(dev); + unsigned long val; + ssize_t result = strict_strtoul(buf, 0, &val); + + if (result < 0) + return result; + + if (val != 1) + return -EINVAL; + return pci_reset_function(pdev); +} + +static struct device_attribute reset_attr = __ATTR(reset, 0200, NULL, reset_store); + static int pci_create_capabilities_sysfs(struct pci_dev *dev) { int retval; @@ -943,7 +961,22 @@ static int pci_create_capabilities_sysfs(struct pci_dev *dev) /* Active State Power Management */ pcie_aspm_create_sysfs_dev_files(dev); + if (!pci_probe_reset_function(dev)) { + retval = device_create_file(&dev->dev, &reset_attr); + if (retval) + goto error; + dev->reset_fn = 1; + } return 0; + +error: + pcie_aspm_remove_sysfs_dev_files(dev); + if (dev->vpd && dev->vpd->attr) { + sysfs_remove_bin_file(&dev->dev.kobj, dev->vpd->attr); + kfree(dev->vpd->attr); + } + + return retval; } int __must_check pci_create_sysfs_dev_files (struct pci_dev *pdev) @@ -1037,6 +1070,10 @@ static void pci_remove_capabilities_sysfs(struct pci_dev *dev) } pcie_aspm_remove_sysfs_dev_files(dev); + if (dev->reset_fn) { + device_remove_file(&dev->dev, &reset_attr); + dev->reset_fn = 0; + } } /** diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 7b70312181d..6edecff0b41 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -41,6 +41,12 @@ int pci_domains_supported = 1; unsigned long pci_cardbus_io_size = DEFAULT_CARDBUS_IO_SIZE; unsigned long pci_cardbus_mem_size = DEFAULT_CARDBUS_MEM_SIZE; +#define DEFAULT_HOTPLUG_IO_SIZE (256) +#define DEFAULT_HOTPLUG_MEM_SIZE (2*1024*1024) +/* pci=hpmemsize=nnM,hpiosize=nn can override this */ +unsigned long pci_hotplug_io_size = DEFAULT_HOTPLUG_IO_SIZE; +unsigned long pci_hotplug_mem_size = DEFAULT_HOTPLUG_MEM_SIZE; + /** * pci_bus_max_busnr - returns maximum PCI bus number of given bus' children * @bus: pointer to PCI bus structure to search @@ -848,6 +854,7 @@ pci_restore_state(struct pci_dev *dev) if (!dev->state_saved) return 0; + /* PCI Express register must be restored first */ pci_restore_pcie_state(dev); @@ -869,6 +876,8 @@ pci_restore_state(struct pci_dev *dev) pci_restore_msi_state(dev); pci_restore_iov_state(dev); + dev->state_saved = false; + return 0; } @@ -1214,30 +1223,40 @@ void pci_pme_active(struct pci_dev *dev, bool enable) */ int pci_enable_wake(struct pci_dev *dev, pci_power_t state, bool enable) { - int error = 0; - bool pme_done = false; + int ret = 0; if (enable && !device_may_wakeup(&dev->dev)) return -EINVAL; + /* Don't do the same thing twice in a row for one device. */ + if (!!enable == !!dev->wakeup_prepared) + return 0; + /* * According to "PCI System Architecture" 4th ed. by Tom Shanley & Don * Anderson we should be doing PME# wake enable followed by ACPI wake * enable. To disable wake-up we call the platform first, for symmetry. */ - if (!enable && platform_pci_can_wakeup(dev)) - error = platform_pci_sleep_wake(dev, false); - - if (!enable || pci_pme_capable(dev, state)) { - pci_pme_active(dev, enable); - pme_done = true; - } + if (enable) { + int error; - if (enable && platform_pci_can_wakeup(dev)) + if (pci_pme_capable(dev, state)) + pci_pme_active(dev, true); + else + ret = 1; error = platform_pci_sleep_wake(dev, true); + if (ret) + ret = error; + if (!ret) + dev->wakeup_prepared = true; + } else { + platform_pci_sleep_wake(dev, false); + pci_pme_active(dev, false); + dev->wakeup_prepared = false; + } - return pme_done ? 0 : error; + return ret; } /** @@ -1356,6 +1375,7 @@ void pci_pm_init(struct pci_dev *dev) int pm; u16 pmc; + dev->wakeup_prepared = false; dev->pm_cap = 0; /* find PCI PM capability in list */ @@ -2262,6 +2282,22 @@ int __pci_reset_function(struct pci_dev *dev) EXPORT_SYMBOL_GPL(__pci_reset_function); /** + * pci_probe_reset_function - check whether the device can be safely reset + * @dev: PCI device to reset + * + * Some devices allow an individual function to be reset without affecting + * other functions in the same device. The PCI device must be responsive + * to PCI config space in order to use this function. + * + * Returns 0 if the device function can be reset or negative if the + * device doesn't support resetting a single function. + */ +int pci_probe_reset_function(struct pci_dev *dev) +{ + return pci_dev_reset(dev, 1); +} + +/** * pci_reset_function - quiesce and reset a PCI device function * @dev: PCI device to reset * @@ -2504,6 +2540,50 @@ int pci_resource_bar(struct pci_dev *dev, int resno, enum pci_bar_type *type) return 0; } +/** + * pci_set_vga_state - set VGA decode state on device and parents if requested + * @dev the PCI device + * @decode - true = enable decoding, false = disable decoding + * @command_bits PCI_COMMAND_IO and/or PCI_COMMAND_MEMORY + * @change_bridge - traverse ancestors and change bridges + */ +int pci_set_vga_state(struct pci_dev *dev, bool decode, + unsigned int command_bits, bool change_bridge) +{ + struct pci_bus *bus; + struct pci_dev *bridge; + u16 cmd; + + WARN_ON(command_bits & ~(PCI_COMMAND_IO|PCI_COMMAND_MEMORY)); + + pci_read_config_word(dev, PCI_COMMAND, &cmd); + if (decode == true) + cmd |= command_bits; + else + cmd &= ~command_bits; + pci_write_config_word(dev, PCI_COMMAND, cmd); + + if (change_bridge == false) + return 0; + + bus = dev->bus; + while (bus) { + bridge = bus->self; + if (bridge) { + pci_read_config_word(bridge, PCI_BRIDGE_CONTROL, + &cmd); + if (decode == true) + cmd |= PCI_BRIDGE_CTL_VGA; + else + cmd &= ~PCI_BRIDGE_CTL_VGA; + pci_write_config_word(bridge, PCI_BRIDGE_CONTROL, + cmd); + } + bus = bus->parent; + } + return 0; +} + #define RESOURCE_ALIGNMENT_PARAM_SIZE COMMAND_LINE_SIZE static char resource_alignment_param[RESOURCE_ALIGNMENT_PARAM_SIZE] = {0}; spinlock_t resource_alignment_lock = SPIN_LOCK_UNLOCKED; @@ -2672,6 +2752,10 @@ static int __init pci_setup(char *str) strlen(str + 19)); } else if (!strncmp(str, "ecrc=", 5)) { pcie_ecrc_get_policy(str + 5); + } else if (!strncmp(str, "hpiosize=", 9)) { + pci_hotplug_io_size = memparse(str + 9, &str); + } else if (!strncmp(str, "hpmemsize=", 10)) { + pci_hotplug_mem_size = memparse(str + 10, &str); } else { printk(KERN_ERR "PCI: Unknown option `%s'\n", str); diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 5ff4d25bf0e..d92d1954a2f 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -16,6 +16,7 @@ extern void pci_cleanup_rom(struct pci_dev *dev); extern int pci_mmap_fits(struct pci_dev *pdev, int resno, struct vm_area_struct *vma); #endif +int pci_probe_reset_function(struct pci_dev *dev); /** * struct pci_platform_pm_ops - Firmware PM callbacks @@ -133,7 +134,6 @@ static inline int pci_no_d1d2(struct pci_dev *dev) return (dev->no_d1d2 || parent_dstates); } -extern int pcie_mch_quirk; extern struct device_attribute pci_dev_attrs[]; extern struct device_attribute dev_attr_cpuaffinity; extern struct device_attribute dev_attr_cpulistaffinity; diff --git a/drivers/pci/pcie/aer/aer_inject.c b/drivers/pci/pcie/aer/aer_inject.c index d92ae21a59d..62d15f652bb 100644 --- a/drivers/pci/pcie/aer/aer_inject.c +++ b/drivers/pci/pcie/aer/aer_inject.c @@ -22,11 +22,10 @@ #include <linux/miscdevice.h> #include <linux/pci.h> #include <linux/fs.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include "aerdrv.h" -struct aer_error_inj -{ +struct aer_error_inj { u8 bus; u8 dev; u8 fn; @@ -38,8 +37,7 @@ struct aer_error_inj u32 header_log3; }; -struct aer_error -{ +struct aer_error { struct list_head list; unsigned int bus; unsigned int devfn; @@ -55,8 +53,7 @@ struct aer_error u32 source_id; }; -struct pci_bus_ops -{ +struct pci_bus_ops { struct list_head list; struct pci_bus *bus; struct pci_ops *ops; @@ -150,7 +147,7 @@ static u32 *find_pci_config_dword(struct aer_error *err, int where, target = &err->header_log1; break; case PCI_ERR_HEADER_LOG+8: - target = &err->header_log2; + target = &err->header_log2; break; case PCI_ERR_HEADER_LOG+12: target = &err->header_log3; @@ -258,8 +255,7 @@ static int pci_bus_set_aer_ops(struct pci_bus *bus) bus_ops = NULL; out: spin_unlock_irqrestore(&inject_lock, flags); - if (bus_ops) - kfree(bus_ops); + kfree(bus_ops); return 0; } @@ -401,10 +397,8 @@ static int aer_inject(struct aer_error_inj *einj) else ret = -EINVAL; out_put: - if (err_alloc) - kfree(err_alloc); - if (rperr_alloc) - kfree(rperr_alloc); + kfree(err_alloc); + kfree(rperr_alloc); pci_dev_put(dev); return ret; } @@ -458,8 +452,7 @@ static void __exit aer_inject_exit(void) } spin_lock_irqsave(&inject_lock, flags); - list_for_each_entry_safe(err, err_next, - &pci_bus_ops_list, list) { + list_for_each_entry_safe(err, err_next, &pci_bus_ops_list, list) { list_del(&err->list); kfree(err); } diff --git a/drivers/pci/pcie/aer/aerdrv.c b/drivers/pci/pcie/aer/aerdrv.c index 4770f13b3ca..10c0e62bd5a 100644 --- a/drivers/pci/pcie/aer/aerdrv.c +++ b/drivers/pci/pcie/aer/aerdrv.c @@ -38,7 +38,7 @@ MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL"); -static int __devinit aer_probe (struct pcie_device *dev); +static int __devinit aer_probe(struct pcie_device *dev); static void aer_remove(struct pcie_device *dev); static pci_ers_result_t aer_error_detected(struct pci_dev *dev, enum pci_channel_state error); @@ -47,7 +47,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev); static struct pci_error_handlers aer_error_handlers = { .error_detected = aer_error_detected, - .resume = aer_error_resume, + .resume = aer_error_resume, }; static struct pcie_port_service_driver aerdriver = { @@ -134,12 +134,12 @@ EXPORT_SYMBOL_GPL(aer_irq); * * Invoked when Root Port's AER service is loaded. **/ -static struct aer_rpc* aer_alloc_rpc(struct pcie_device *dev) +static struct aer_rpc *aer_alloc_rpc(struct pcie_device *dev) { struct aer_rpc *rpc; - if (!(rpc = kzalloc(sizeof(struct aer_rpc), - GFP_KERNEL))) + rpc = kzalloc(sizeof(struct aer_rpc), GFP_KERNEL); + if (!rpc) return NULL; /* @@ -189,26 +189,28 @@ static void aer_remove(struct pcie_device *dev) * * Invoked when PCI Express bus loads AER service driver. **/ -static int __devinit aer_probe (struct pcie_device *dev) +static int __devinit aer_probe(struct pcie_device *dev) { int status; struct aer_rpc *rpc; struct device *device = &dev->device; /* Init */ - if ((status = aer_init(dev))) + status = aer_init(dev); + if (status) return status; /* Alloc rpc data structure */ - if (!(rpc = aer_alloc_rpc(dev))) { + rpc = aer_alloc_rpc(dev); + if (!rpc) { dev_printk(KERN_DEBUG, device, "alloc rpc failed\n"); aer_remove(dev); return -ENOMEM; } /* Request IRQ ISR */ - if ((status = request_irq(dev->irq, aer_irq, IRQF_SHARED, "aerdrv", - dev))) { + status = request_irq(dev->irq, aer_irq, IRQF_SHARED, "aerdrv", dev); + if (status) { dev_printk(KERN_DEBUG, device, "request IRQ failed\n"); aer_remove(dev); return status; diff --git a/drivers/pci/pcie/aer/aerdrv.h b/drivers/pci/pcie/aer/aerdrv.h index bbd7428ca2d..bd833ea3ba4 100644 --- a/drivers/pci/pcie/aer/aerdrv.h +++ b/drivers/pci/pcie/aer/aerdrv.h @@ -16,12 +16,9 @@ #define AER_NONFATAL 0 #define AER_FATAL 1 #define AER_CORRECTABLE 2 -#define AER_UNCORRECTABLE 4 -#define AER_ERROR_MASK 0x001fffff -#define AER_ERROR(d) (d & AER_ERROR_MASK) /* Root Error Status Register Bits */ -#define ROOT_ERR_STATUS_MASKS 0x0f +#define ROOT_ERR_STATUS_MASKS 0x0f #define SYSTEM_ERROR_INTR_ON_MESG_MASK (PCI_EXP_RTCTL_SECEE| \ PCI_EXP_RTCTL_SENFEE| \ @@ -32,8 +29,6 @@ #define ERR_COR_ID(d) (d & 0xffff) #define ERR_UNCOR_ID(d) (d >> 16) -#define AER_SUCCESS 0 -#define AER_UNSUCCESS 1 #define AER_ERROR_SOURCES_MAX 100 #define AER_LOG_TLP_MASKS (PCI_ERR_UNC_POISON_TLP| \ @@ -43,13 +38,6 @@ PCI_ERR_UNC_UNX_COMP| \ PCI_ERR_UNC_MALF_TLP) -/* AER Error Info Flags */ -#define AER_TLP_HEADER_VALID_FLAG 0x00000001 -#define AER_MULTI_ERROR_VALID_FLAG 0x00000002 - -#define ERR_CORRECTABLE_ERROR_MASK 0x000031c1 -#define ERR_UNCORRECTABLE_ERROR_MASK 0x001ff010 - struct header_log_regs { unsigned int dw0; unsigned int dw1; @@ -61,11 +49,20 @@ struct header_log_regs { struct aer_err_info { struct pci_dev *dev[AER_MAX_MULTI_ERR_DEVICES]; int error_dev_num; - u16 id; - int severity; /* 0:NONFATAL | 1:FATAL | 2:COR */ - int flags; + + unsigned int id:16; + + unsigned int severity:2; /* 0:NONFATAL | 1:FATAL | 2:COR */ + unsigned int __pad1:5; + unsigned int multi_error_valid:1; + + unsigned int first_error:5; + unsigned int __pad2:2; + unsigned int tlp_header_valid:1; + unsigned int status; /* COR/UNCOR Error Status */ - struct header_log_regs tlp; /* TLP Header */ + unsigned int mask; /* COR/UNCOR Error Mask */ + struct header_log_regs tlp; /* TLP Header */ }; struct aer_err_source { @@ -125,6 +122,7 @@ extern void aer_delete_rootport(struct aer_rpc *rpc); extern int aer_init(struct pcie_device *dev); extern void aer_isr(struct work_struct *work); extern void aer_print_error(struct pci_dev *dev, struct aer_err_info *info); +extern void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info); extern irqreturn_t aer_irq(int irq, void *context); #ifdef CONFIG_ACPI @@ -136,4 +134,4 @@ static inline int aer_osc_setup(struct pcie_device *pciedev) } #endif -#endif //_AERDRV_H_ +#endif /* _AERDRV_H_ */ diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c index 3d8872704a5..9f5ccbeb4fa 100644 --- a/drivers/pci/pcie/aer/aerdrv_core.c +++ b/drivers/pci/pcie/aer/aerdrv_core.c @@ -49,10 +49,11 @@ int pci_enable_pcie_error_reporting(struct pci_dev *dev) PCI_EXP_DEVCTL_NFERE | PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE; - pci_write_config_word(dev, pos+PCI_EXP_DEVCTL, - reg16); + pci_write_config_word(dev, pos+PCI_EXP_DEVCTL, reg16); + return 0; } +EXPORT_SYMBOL_GPL(pci_enable_pcie_error_reporting); int pci_disable_pcie_error_reporting(struct pci_dev *dev) { @@ -68,10 +69,11 @@ int pci_disable_pcie_error_reporting(struct pci_dev *dev) PCI_EXP_DEVCTL_NFERE | PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE); - pci_write_config_word(dev, pos+PCI_EXP_DEVCTL, - reg16); + pci_write_config_word(dev, pos+PCI_EXP_DEVCTL, reg16); + return 0; } +EXPORT_SYMBOL_GPL(pci_disable_pcie_error_reporting); int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev) { @@ -92,6 +94,7 @@ int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev) return 0; } +EXPORT_SYMBOL_GPL(pci_cleanup_aer_uncorrect_error_status); #if 0 int pci_cleanup_aer_correct_error_status(struct pci_dev *dev) @@ -110,7 +113,6 @@ int pci_cleanup_aer_correct_error_status(struct pci_dev *dev) } #endif /* 0 */ - static int set_device_error_reporting(struct pci_dev *dev, void *data) { bool enable = *((bool *)data); @@ -164,8 +166,9 @@ static int add_error_device(struct aer_err_info *e_info, struct pci_dev *dev) e_info->dev[e_info->error_dev_num] = dev; e_info->error_dev_num++; return 1; - } else - return 0; + } + + return 0; } @@ -193,7 +196,7 @@ static int find_device_iter(struct pci_dev *dev, void *data) * If there is no multiple error, we stop * or continue based on the id comparing. */ - if (!(e_info->flags & AER_MULTI_ERROR_VALID_FLAG)) + if (!e_info->multi_error_valid) return result; /* @@ -233,24 +236,16 @@ static int find_device_iter(struct pci_dev *dev, void *data) status = 0; mask = 0; if (e_info->severity == AER_CORRECTABLE) { - pci_read_config_dword(dev, - pos + PCI_ERR_COR_STATUS, - &status); - pci_read_config_dword(dev, - pos + PCI_ERR_COR_MASK, - &mask); - if (status & ERR_CORRECTABLE_ERROR_MASK & ~mask) { + pci_read_config_dword(dev, pos + PCI_ERR_COR_STATUS, &status); + pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK, &mask); + if (status & ~mask) { add_error_device(e_info, dev); goto added; } } else { - pci_read_config_dword(dev, - pos + PCI_ERR_UNCOR_STATUS, - &status); - pci_read_config_dword(dev, - pos + PCI_ERR_UNCOR_MASK, - &mask); - if (status & ERR_UNCORRECTABLE_ERROR_MASK & ~mask) { + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status); + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, &mask); + if (status & ~mask) { add_error_device(e_info, dev); goto added; } @@ -259,7 +254,7 @@ static int find_device_iter(struct pci_dev *dev, void *data) return 0; added: - if (e_info->flags & AER_MULTI_ERROR_VALID_FLAG) + if (e_info->multi_error_valid) return 0; else return 1; @@ -411,8 +406,7 @@ static pci_ers_result_t broadcast_error_message(struct pci_dev *dev, pci_cleanup_aer_uncorrect_error_status(dev); dev->error_state = pci_channel_io_normal; } - } - else { + } else { /* * If the error is reported by an end point, we think this * error is related to the upstream link of the end point. @@ -473,7 +467,7 @@ static pci_ers_result_t reset_link(struct pcie_device *aerdev, if (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE) udev = dev; else - udev= dev->bus->self; + udev = dev->bus->self; data.is_downstream = 0; data.aer_driver = NULL; @@ -576,7 +570,7 @@ static pci_ers_result_t do_recovery(struct pcie_device *aerdev, * * Invoked when an error being detected by Root Port. */ -static void handle_error_source(struct pcie_device * aerdev, +static void handle_error_source(struct pcie_device *aerdev, struct pci_dev *dev, struct aer_err_info *info) { @@ -682,7 +676,7 @@ static void disable_root_aer(struct aer_rpc *rpc) * * Invoked by DPC handler to consume an error. */ -static struct aer_err_source* get_e_source(struct aer_rpc *rpc) +static struct aer_err_source *get_e_source(struct aer_rpc *rpc) { struct aer_err_source *e_source; unsigned long flags; @@ -702,32 +696,50 @@ static struct aer_err_source* get_e_source(struct aer_rpc *rpc) return e_source; } +/** + * get_device_error_info - read error status from dev and store it to info + * @dev: pointer to the device expected to have a error record + * @info: pointer to structure to store the error record + * + * Return 1 on success, 0 on error. + */ static int get_device_error_info(struct pci_dev *dev, struct aer_err_info *info) { - int pos; + int pos, temp; + + info->status = 0; + info->tlp_header_valid = 0; pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); /* The device might not support AER */ if (!pos) - return AER_SUCCESS; + return 1; if (info->severity == AER_CORRECTABLE) { pci_read_config_dword(dev, pos + PCI_ERR_COR_STATUS, &info->status); - if (!(info->status & ERR_CORRECTABLE_ERROR_MASK)) - return AER_UNSUCCESS; + pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK, + &info->mask); + if (!(info->status & ~info->mask)) + return 0; } else if (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE || info->severity == AER_NONFATAL) { /* Link is still healthy for IO reads */ pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &info->status); - if (!(info->status & ERR_UNCORRECTABLE_ERROR_MASK)) - return AER_UNSUCCESS; + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, + &info->mask); + if (!(info->status & ~info->mask)) + return 0; + + /* Get First Error Pointer */ + pci_read_config_dword(dev, pos + PCI_ERR_CAP, &temp); + info->first_error = PCI_ERR_CAP_FEP(temp); if (info->status & AER_LOG_TLP_MASKS) { - info->flags |= AER_TLP_HEADER_VALID_FLAG; + info->tlp_header_valid = 1; pci_read_config_dword(dev, pos + PCI_ERR_HEADER_LOG, &info->tlp.dw0); pci_read_config_dword(dev, @@ -739,7 +751,7 @@ static int get_device_error_info(struct pci_dev *dev, struct aer_err_info *info) } } - return AER_SUCCESS; + return 1; } static inline void aer_process_err_devices(struct pcie_device *p_device, @@ -753,14 +765,14 @@ static inline void aer_process_err_devices(struct pcie_device *p_device, e_info->id); } + /* Report all before handle them, not to lost records by reset etc. */ for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) { - if (get_device_error_info(e_info->dev[i], e_info) == - AER_SUCCESS) { + if (get_device_error_info(e_info->dev[i], e_info)) aer_print_error(e_info->dev[i], e_info); - handle_error_source(p_device, - e_info->dev[i], - e_info); - } + } + for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) { + if (get_device_error_info(e_info->dev[i], e_info)) + handle_error_source(p_device, e_info->dev[i], e_info); } } @@ -806,7 +818,9 @@ static void aer_isr_one_error(struct pcie_device *p_device, if (e_src->status & (PCI_ERR_ROOT_MULTI_COR_RCV | PCI_ERR_ROOT_MULTI_UNCOR_RCV)) - e_info->flags |= AER_MULTI_ERROR_VALID_FLAG; + e_info->multi_error_valid = 1; + + aer_print_port_info(p_device->port, e_info); find_source_device(p_device->port, e_info); aer_process_err_devices(p_device, e_info); @@ -863,10 +877,5 @@ int aer_init(struct pcie_device *dev) if (aer_osc_setup(dev) && !forceload) return -ENXIO; - return AER_SUCCESS; + return 0; } - -EXPORT_SYMBOL_GPL(pci_enable_pcie_error_reporting); -EXPORT_SYMBOL_GPL(pci_disable_pcie_error_reporting); -EXPORT_SYMBOL_GPL(pci_cleanup_aer_uncorrect_error_status); - diff --git a/drivers/pci/pcie/aer/aerdrv_errprint.c b/drivers/pci/pcie/aer/aerdrv_errprint.c index 0fc29ae80df..44acde72294 100644 --- a/drivers/pci/pcie/aer/aerdrv_errprint.c +++ b/drivers/pci/pcie/aer/aerdrv_errprint.c @@ -27,69 +27,70 @@ #define AER_AGENT_COMPLETER 2 #define AER_AGENT_TRANSMITTER 3 -#define AER_AGENT_REQUESTER_MASK (PCI_ERR_UNC_COMP_TIME| \ - PCI_ERR_UNC_UNSUP) - -#define AER_AGENT_COMPLETER_MASK PCI_ERR_UNC_COMP_ABORT - -#define AER_AGENT_TRANSMITTER_MASK(t, e) (e & (PCI_ERR_COR_REP_ROLL| \ - ((t == AER_CORRECTABLE) ? PCI_ERR_COR_REP_TIMER: 0))) +#define AER_AGENT_REQUESTER_MASK(t) ((t == AER_CORRECTABLE) ? \ + 0 : (PCI_ERR_UNC_COMP_TIME|PCI_ERR_UNC_UNSUP)) +#define AER_AGENT_COMPLETER_MASK(t) ((t == AER_CORRECTABLE) ? \ + 0 : PCI_ERR_UNC_COMP_ABORT) +#define AER_AGENT_TRANSMITTER_MASK(t) ((t == AER_CORRECTABLE) ? \ + (PCI_ERR_COR_REP_ROLL|PCI_ERR_COR_REP_TIMER) : 0) #define AER_GET_AGENT(t, e) \ - ((e & AER_AGENT_COMPLETER_MASK) ? AER_AGENT_COMPLETER : \ - (e & AER_AGENT_REQUESTER_MASK) ? AER_AGENT_REQUESTER : \ - (AER_AGENT_TRANSMITTER_MASK(t, e)) ? AER_AGENT_TRANSMITTER : \ + ((e & AER_AGENT_COMPLETER_MASK(t)) ? AER_AGENT_COMPLETER : \ + (e & AER_AGENT_REQUESTER_MASK(t)) ? AER_AGENT_REQUESTER : \ + (e & AER_AGENT_TRANSMITTER_MASK(t)) ? AER_AGENT_TRANSMITTER : \ AER_AGENT_RECEIVER) -#define AER_PHYSICAL_LAYER_ERROR_MASK PCI_ERR_COR_RCVR -#define AER_DATA_LINK_LAYER_ERROR_MASK(t, e) \ - (PCI_ERR_UNC_DLP| \ - PCI_ERR_COR_BAD_TLP| \ - PCI_ERR_COR_BAD_DLLP| \ - PCI_ERR_COR_REP_ROLL| \ - ((t == AER_CORRECTABLE) ? \ - PCI_ERR_COR_REP_TIMER: 0)) - #define AER_PHYSICAL_LAYER_ERROR 0 #define AER_DATA_LINK_LAYER_ERROR 1 #define AER_TRANSACTION_LAYER_ERROR 2 -#define AER_GET_LAYER_ERROR(t, e) \ - ((e & AER_PHYSICAL_LAYER_ERROR_MASK) ? \ - AER_PHYSICAL_LAYER_ERROR : \ - (e & AER_DATA_LINK_LAYER_ERROR_MASK(t, e)) ? \ - AER_DATA_LINK_LAYER_ERROR : \ - AER_TRANSACTION_LAYER_ERROR) +#define AER_PHYSICAL_LAYER_ERROR_MASK(t) ((t == AER_CORRECTABLE) ? \ + PCI_ERR_COR_RCVR : 0) +#define AER_DATA_LINK_LAYER_ERROR_MASK(t) ((t == AER_CORRECTABLE) ? \ + (PCI_ERR_COR_BAD_TLP| \ + PCI_ERR_COR_BAD_DLLP| \ + PCI_ERR_COR_REP_ROLL| \ + PCI_ERR_COR_REP_TIMER) : PCI_ERR_UNC_DLP) + +#define AER_GET_LAYER_ERROR(t, e) \ + ((e & AER_PHYSICAL_LAYER_ERROR_MASK(t)) ? AER_PHYSICAL_LAYER_ERROR : \ + (e & AER_DATA_LINK_LAYER_ERROR_MASK(t)) ? AER_DATA_LINK_LAYER_ERROR : \ + AER_TRANSACTION_LAYER_ERROR) + +#define AER_PR(info, pdev, fmt, args...) \ + printk("%s%s %s: " fmt, (info->severity == AER_CORRECTABLE) ? \ + KERN_WARNING : KERN_ERR, dev_driver_string(&pdev->dev), \ + dev_name(&pdev->dev), ## args) /* * AER error strings */ -static char* aer_error_severity_string[] = { +static char *aer_error_severity_string[] = { "Uncorrected (Non-Fatal)", "Uncorrected (Fatal)", "Corrected" }; -static char* aer_error_layer[] = { +static char *aer_error_layer[] = { "Physical Layer", "Data Link Layer", "Transaction Layer" }; -static char* aer_correctable_error_string[] = { - "Receiver Error ", /* Bit Position 0 */ +static char *aer_correctable_error_string[] = { + "Receiver Error ", /* Bit Position 0 */ NULL, NULL, NULL, NULL, NULL, - "Bad TLP ", /* Bit Position 6 */ - "Bad DLLP ", /* Bit Position 7 */ - "RELAY_NUM Rollover ", /* Bit Position 8 */ + "Bad TLP ", /* Bit Position 6 */ + "Bad DLLP ", /* Bit Position 7 */ + "RELAY_NUM Rollover ", /* Bit Position 8 */ NULL, NULL, NULL, - "Replay Timer Timeout ", /* Bit Position 12 */ - "Advisory Non-Fatal ", /* Bit Position 13 */ + "Replay Timer Timeout ", /* Bit Position 12 */ + "Advisory Non-Fatal ", /* Bit Position 13 */ NULL, NULL, NULL, @@ -110,7 +111,7 @@ static char* aer_correctable_error_string[] = { NULL, }; -static char* aer_uncorrectable_error_string[] = { +static char *aer_uncorrectable_error_string[] = { NULL, NULL, NULL, @@ -123,10 +124,10 @@ static char* aer_uncorrectable_error_string[] = { NULL, NULL, NULL, - "Poisoned TLP ", /* Bit Position 12 */ + "Poisoned TLP ", /* Bit Position 12 */ "Flow Control Protocol ", /* Bit Position 13 */ - "Completion Timeout ", /* Bit Position 14 */ - "Completer Abort ", /* Bit Position 15 */ + "Completion Timeout ", /* Bit Position 14 */ + "Completer Abort ", /* Bit Position 15 */ "Unexpected Completion ", /* Bit Position 16 */ "Receiver Overflow ", /* Bit Position 17 */ "Malformed TLP ", /* Bit Position 18 */ @@ -145,98 +146,69 @@ static char* aer_uncorrectable_error_string[] = { NULL, }; -static char* aer_agent_string[] = { +static char *aer_agent_string[] = { "Receiver ID", "Requester ID", "Completer ID", "Transmitter ID" }; -static char * aer_get_error_source_name(int severity, - unsigned int status, - char errmsg_buff[]) +static void __aer_print_error(struct aer_err_info *info, struct pci_dev *dev) { - int i; - char * errmsg = NULL; + int i, status; + char *errmsg = NULL; + + status = (info->status & ~info->mask); for (i = 0; i < 32; i++) { if (!(status & (1 << i))) continue; - if (severity == AER_CORRECTABLE) + if (info->severity == AER_CORRECTABLE) errmsg = aer_correctable_error_string[i]; else errmsg = aer_uncorrectable_error_string[i]; - if (!errmsg) { - sprintf(errmsg_buff, "Unknown Error Bit %2d ", i); - errmsg = errmsg_buff; - } - - break; + if (errmsg) + AER_PR(info, dev, " [%2d] %s%s\n", i, errmsg, + info->first_error == i ? " (First)" : ""); + else + AER_PR(info, dev, " [%2d] Unknown Error Bit%s\n", i, + info->first_error == i ? " (First)" : ""); } - - return errmsg; } -static DEFINE_SPINLOCK(logbuf_lock); -static char errmsg_buff[100]; void aer_print_error(struct pci_dev *dev, struct aer_err_info *info) { - char * errmsg; - int err_layer, agent; - char * loglevel; - - if (info->severity == AER_CORRECTABLE) - loglevel = KERN_WARNING; - else - loglevel = KERN_ERR; - - printk("%s+------ PCI-Express Device Error ------+\n", loglevel); - printk("%sError Severity\t\t: %s\n", loglevel, - aer_error_severity_string[info->severity]); - - if ( info->status == 0) { - printk("%sPCIE Bus Error type\t: (Unaccessible)\n", loglevel); - printk("%sUnaccessible Received\t: %s\n", loglevel, - info->flags & AER_MULTI_ERROR_VALID_FLAG ? - "Multiple" : "First"); - printk("%sUnregistered Agent ID\t: %04x\n", loglevel, - (dev->bus->number << 8) | dev->devfn); + int id = ((dev->bus->number << 8) | dev->devfn); + + if (info->status == 0) { + AER_PR(info, dev, + "PCIE Bus Error: severity=%s, type=Unaccessible, " + "id=%04x(Unregistered Agent ID)\n", + aer_error_severity_string[info->severity], id); } else { - err_layer = AER_GET_LAYER_ERROR(info->severity, info->status); - printk("%sPCIE Bus Error type\t: %s\n", loglevel, - aer_error_layer[err_layer]); - - spin_lock(&logbuf_lock); - errmsg = aer_get_error_source_name(info->severity, - info->status, - errmsg_buff); - printk("%s%s\t: %s\n", loglevel, errmsg, - info->flags & AER_MULTI_ERROR_VALID_FLAG ? - "Multiple" : "First"); - spin_unlock(&logbuf_lock); + int layer, agent; + layer = AER_GET_LAYER_ERROR(info->severity, info->status); agent = AER_GET_AGENT(info->severity, info->status); - printk("%s%s\t\t: %04x\n", loglevel, - aer_agent_string[agent], - (dev->bus->number << 8) | dev->devfn); - - printk("%sVendorID=%04xh, DeviceID=%04xh," - " Bus=%02xh, Device=%02xh, Function=%02xh\n", - loglevel, - dev->vendor, - dev->device, - dev->bus->number, - PCI_SLOT(dev->devfn), - PCI_FUNC(dev->devfn)); - - if (info->flags & AER_TLP_HEADER_VALID_FLAG) { + + AER_PR(info, dev, + "PCIE Bus Error: severity=%s, type=%s, id=%04x(%s)\n", + aer_error_severity_string[info->severity], + aer_error_layer[layer], id, aer_agent_string[agent]); + + AER_PR(info, dev, + " device [%04x:%04x] error status/mask=%08x/%08x\n", + dev->vendor, dev->device, info->status, info->mask); + + __aer_print_error(info, dev); + + if (info->tlp_header_valid) { unsigned char *tlp = (unsigned char *) &info->tlp; - printk("%sTLP Header:\n", loglevel); - printk("%s%02x%02x%02x%02x %02x%02x%02x%02x" + AER_PR(info, dev, " TLP Header:" + " %02x%02x%02x%02x %02x%02x%02x%02x" " %02x%02x%02x%02x %02x%02x%02x%02x\n", - loglevel, *(tlp + 3), *(tlp + 2), *(tlp + 1), *tlp, *(tlp + 7), *(tlp + 6), *(tlp + 5), *(tlp + 4), *(tlp + 11), *(tlp + 10), *(tlp + 9), @@ -244,5 +216,15 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info) *(tlp + 13), *(tlp + 12)); } } + + if (info->id && info->error_dev_num > 1 && info->id == id) + AER_PR(info, dev, + " Error of this Agent(%04x) is reported first\n", id); } +void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info) +{ + dev_info(&dev->dev, "AER: %s%s error received: id=%04x\n", + info->multi_error_valid ? "Multiple " : "", + aer_error_severity_string[info->severity], info->id); +} diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 3d27c97e048..f289ca9bf18 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -26,6 +26,13 @@ #endif #define MODULE_PARAM_PREFIX "pcie_aspm." +/* Note: those are not register definitions */ +#define ASPM_STATE_L0S_UP (1) /* Upstream direction L0s state */ +#define ASPM_STATE_L0S_DW (2) /* Downstream direction L0s state */ +#define ASPM_STATE_L1 (4) /* L1 state */ +#define ASPM_STATE_L0S (ASPM_STATE_L0S_UP | ASPM_STATE_L0S_DW) +#define ASPM_STATE_ALL (ASPM_STATE_L0S | ASPM_STATE_L1) + struct aspm_latency { u32 l0s; /* L0s latency (nsec) */ u32 l1; /* L1 latency (nsec) */ @@ -40,17 +47,20 @@ struct pcie_link_state { struct list_head link; /* node in parent's children list */ /* ASPM state */ - u32 aspm_support:2; /* Supported ASPM state */ - u32 aspm_enabled:2; /* Enabled ASPM state */ - u32 aspm_default:2; /* Default ASPM state by BIOS */ + u32 aspm_support:3; /* Supported ASPM state */ + u32 aspm_enabled:3; /* Enabled ASPM state */ + u32 aspm_capable:3; /* Capable ASPM state with latency */ + u32 aspm_default:3; /* Default ASPM state by BIOS */ + u32 aspm_disable:3; /* Disabled ASPM state */ /* Clock PM state */ u32 clkpm_capable:1; /* Clock PM capable? */ u32 clkpm_enabled:1; /* Current Clock PM state */ u32 clkpm_default:1; /* Default Clock PM state by BIOS */ - /* Latencies */ - struct aspm_latency latency; /* Exit latency */ + /* Exit latencies */ + struct aspm_latency latency_up; /* Upstream direction exit latency */ + struct aspm_latency latency_dw; /* Downstream direction exit latency */ /* * Endpoint acceptable latencies. A pcie downstream port only * has one slot under it, so at most there are 8 functions. @@ -82,7 +92,7 @@ static int policy_to_aspm_state(struct pcie_link_state *link) return 0; case POLICY_POWERSAVE: /* Enable ASPM L0s/L1 */ - return PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1; + return ASPM_STATE_ALL; case POLICY_DEFAULT: return link->aspm_default; } @@ -164,18 +174,6 @@ static void pcie_clkpm_cap_init(struct pcie_link_state *link, int blacklist) link->clkpm_capable = (blacklist) ? 0 : capable; } -static bool pcie_aspm_downstream_has_switch(struct pcie_link_state *link) -{ - struct pci_dev *child; - struct pci_bus *linkbus = link->pdev->subordinate; - - list_for_each_entry(child, &linkbus->devices, bus_list) { - if (child->pcie_type == PCI_EXP_TYPE_UPSTREAM) - return true; - } - return false; -} - /* * pcie_aspm_configure_common_clock: check if the 2 ends of a link * could use common clock. If they are, configure them to use the @@ -288,71 +286,133 @@ static u32 calc_l1_acceptable(u32 encoding) return (1000 << encoding); } -static void pcie_aspm_get_cap_device(struct pci_dev *pdev, u32 *state, - u32 *l0s, u32 *l1, u32 *enabled) +struct aspm_register_info { + u32 support:2; + u32 enabled:2; + u32 latency_encoding_l0s; + u32 latency_encoding_l1; +}; + +static void pcie_get_aspm_reg(struct pci_dev *pdev, + struct aspm_register_info *info) { int pos; u16 reg16; - u32 reg32, encoding; + u32 reg32; - *l0s = *l1 = *enabled = 0; pos = pci_find_capability(pdev, PCI_CAP_ID_EXP); pci_read_config_dword(pdev, pos + PCI_EXP_LNKCAP, ®32); - *state = (reg32 & PCI_EXP_LNKCAP_ASPMS) >> 10; - if (*state != PCIE_LINK_STATE_L0S && - *state != (PCIE_LINK_STATE_L1 | PCIE_LINK_STATE_L0S)) - *state = 0; - if (*state == 0) + info->support = (reg32 & PCI_EXP_LNKCAP_ASPMS) >> 10; + /* 00b and 10b are defined as "Reserved". */ + if (info->support == PCIE_LINK_STATE_L1) + info->support = 0; + info->latency_encoding_l0s = (reg32 & PCI_EXP_LNKCAP_L0SEL) >> 12; + info->latency_encoding_l1 = (reg32 & PCI_EXP_LNKCAP_L1EL) >> 15; + pci_read_config_word(pdev, pos + PCI_EXP_LNKCTL, ®16); + info->enabled = reg16 & PCI_EXP_LNKCTL_ASPMC; +} + +static void pcie_aspm_check_latency(struct pci_dev *endpoint) +{ + u32 latency, l1_switch_latency = 0; + struct aspm_latency *acceptable; + struct pcie_link_state *link; + + /* Device not in D0 doesn't need latency check */ + if ((endpoint->current_state != PCI_D0) && + (endpoint->current_state != PCI_UNKNOWN)) return; - encoding = (reg32 & PCI_EXP_LNKCAP_L0SEL) >> 12; - *l0s = calc_l0s_latency(encoding); - if (*state & PCIE_LINK_STATE_L1) { - encoding = (reg32 & PCI_EXP_LNKCAP_L1EL) >> 15; - *l1 = calc_l1_latency(encoding); + link = endpoint->bus->self->link_state; + acceptable = &link->acceptable[PCI_FUNC(endpoint->devfn)]; + + while (link) { + /* Check upstream direction L0s latency */ + if ((link->aspm_capable & ASPM_STATE_L0S_UP) && + (link->latency_up.l0s > acceptable->l0s)) + link->aspm_capable &= ~ASPM_STATE_L0S_UP; + + /* Check downstream direction L0s latency */ + if ((link->aspm_capable & ASPM_STATE_L0S_DW) && + (link->latency_dw.l0s > acceptable->l0s)) + link->aspm_capable &= ~ASPM_STATE_L0S_DW; + /* + * Check L1 latency. + * Every switch on the path to root complex need 1 + * more microsecond for L1. Spec doesn't mention L0s. + */ + latency = max_t(u32, link->latency_up.l1, link->latency_dw.l1); + if ((link->aspm_capable & ASPM_STATE_L1) && + (latency + l1_switch_latency > acceptable->l1)) + link->aspm_capable &= ~ASPM_STATE_L1; + l1_switch_latency += 1000; + + link = link->parent; } - pci_read_config_word(pdev, pos + PCI_EXP_LNKCTL, ®16); - *enabled = reg16 & (PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1); } static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) { - u32 support, l0s, l1, enabled; struct pci_dev *child, *parent = link->pdev; struct pci_bus *linkbus = parent->subordinate; + struct aspm_register_info upreg, dwreg; if (blacklist) { - /* Set support state to 0, so we will disable ASPM later */ - link->aspm_support = 0; - link->aspm_default = 0; - link->aspm_enabled = PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1; + /* Set enabled/disable so that we will disable ASPM later */ + link->aspm_enabled = ASPM_STATE_ALL; + link->aspm_disable = ASPM_STATE_ALL; return; } /* Configure common clock before checking latencies */ pcie_aspm_configure_common_clock(link); - /* upstream component states */ - pcie_aspm_get_cap_device(parent, &support, &l0s, &l1, &enabled); - link->aspm_support = support; - link->latency.l0s = l0s; - link->latency.l1 = l1; - link->aspm_enabled = enabled; - - /* downstream component states, all functions have the same setting */ + /* Get upstream/downstream components' register state */ + pcie_get_aspm_reg(parent, &upreg); child = list_entry(linkbus->devices.next, struct pci_dev, bus_list); - pcie_aspm_get_cap_device(child, &support, &l0s, &l1, &enabled); - link->aspm_support &= support; - link->latency.l0s = max_t(u32, link->latency.l0s, l0s); - link->latency.l1 = max_t(u32, link->latency.l1, l1); + pcie_get_aspm_reg(child, &dwreg); - if (!link->aspm_support) - return; - - link->aspm_enabled &= link->aspm_support; + /* + * Setup L0s state + * + * Note that we must not enable L0s in either direction on a + * given link unless components on both sides of the link each + * support L0s. + */ + if (dwreg.support & upreg.support & PCIE_LINK_STATE_L0S) + link->aspm_support |= ASPM_STATE_L0S; + if (dwreg.enabled & PCIE_LINK_STATE_L0S) + link->aspm_enabled |= ASPM_STATE_L0S_UP; + if (upreg.enabled & PCIE_LINK_STATE_L0S) + link->aspm_enabled |= ASPM_STATE_L0S_DW; + link->latency_up.l0s = calc_l0s_latency(upreg.latency_encoding_l0s); + link->latency_dw.l0s = calc_l0s_latency(dwreg.latency_encoding_l0s); + + /* Setup L1 state */ + if (upreg.support & dwreg.support & PCIE_LINK_STATE_L1) + link->aspm_support |= ASPM_STATE_L1; + if (upreg.enabled & dwreg.enabled & PCIE_LINK_STATE_L1) + link->aspm_enabled |= ASPM_STATE_L1; + link->latency_up.l1 = calc_l1_latency(upreg.latency_encoding_l1); + link->latency_dw.l1 = calc_l1_latency(dwreg.latency_encoding_l1); + + /* Save default state */ link->aspm_default = link->aspm_enabled; - /* ENDPOINT states*/ + /* Setup initial capable state. Will be updated later */ + link->aspm_capable = link->aspm_support; + /* + * If the downstream component has pci bridge function, don't + * do ASPM for now. + */ + list_for_each_entry(child, &linkbus->devices, bus_list) { + if (child->pcie_type == PCI_EXP_TYPE_PCI_BRIDGE) { + link->aspm_disable = ASPM_STATE_ALL; + break; + } + } + + /* Get and check endpoint acceptable latencies */ list_for_each_entry(child, &linkbus->devices, bus_list) { int pos; u32 reg32, encoding; @@ -365,109 +425,46 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) pos = pci_find_capability(child, PCI_CAP_ID_EXP); pci_read_config_dword(child, pos + PCI_EXP_DEVCAP, ®32); + /* Calculate endpoint L0s acceptable latency */ encoding = (reg32 & PCI_EXP_DEVCAP_L0S) >> 6; acceptable->l0s = calc_l0s_acceptable(encoding); - if (link->aspm_support & PCIE_LINK_STATE_L1) { - encoding = (reg32 & PCI_EXP_DEVCAP_L1) >> 9; - acceptable->l1 = calc_l1_acceptable(encoding); - } - } -} - -/** - * __pcie_aspm_check_state_one - check latency for endpoint device. - * @endpoint: pointer to the struct pci_dev of endpoint device - * - * TBD: The latency from the endpoint to root complex vary per switch's - * upstream link state above the device. Here we just do a simple check - * which assumes all links above the device can be in L1 state, that - * is we just consider the worst case. If switch's upstream link can't - * be put into L0S/L1, then our check is too strictly. - */ -static u32 __pcie_aspm_check_state_one(struct pci_dev *endpoint, u32 state) -{ - u32 l1_switch_latency = 0; - struct aspm_latency *acceptable; - struct pcie_link_state *link; - - link = endpoint->bus->self->link_state; - state &= link->aspm_support; - acceptable = &link->acceptable[PCI_FUNC(endpoint->devfn)]; + /* Calculate endpoint L1 acceptable latency */ + encoding = (reg32 & PCI_EXP_DEVCAP_L1) >> 9; + acceptable->l1 = calc_l1_acceptable(encoding); - while (link && state) { - if ((state & PCIE_LINK_STATE_L0S) && - (link->latency.l0s > acceptable->l0s)) - state &= ~PCIE_LINK_STATE_L0S; - if ((state & PCIE_LINK_STATE_L1) && - (link->latency.l1 + l1_switch_latency > acceptable->l1)) - state &= ~PCIE_LINK_STATE_L1; - link = link->parent; - /* - * Every switch on the path to root complex need 1 - * more microsecond for L1. Spec doesn't mention L0s. - */ - l1_switch_latency += 1000; - } - return state; -} - -static u32 pcie_aspm_check_state(struct pcie_link_state *link, u32 state) -{ - pci_power_t power_state; - struct pci_dev *child; - struct pci_bus *linkbus = link->pdev->subordinate; - - /* If no child, ignore the link */ - if (list_empty(&linkbus->devices)) - return state; - - list_for_each_entry(child, &linkbus->devices, bus_list) { - /* - * If downstream component of a link is pci bridge, we - * disable ASPM for now for the link - */ - if (child->pcie_type == PCI_EXP_TYPE_PCI_BRIDGE) - return 0; - - if ((child->pcie_type != PCI_EXP_TYPE_ENDPOINT && - child->pcie_type != PCI_EXP_TYPE_LEG_END)) - continue; - /* Device not in D0 doesn't need check latency */ - power_state = child->current_state; - if (power_state == PCI_D1 || power_state == PCI_D2 || - power_state == PCI_D3hot || power_state == PCI_D3cold) - continue; - state = __pcie_aspm_check_state_one(child, state); + pcie_aspm_check_latency(child); } - return state; } -static void __pcie_aspm_config_one_dev(struct pci_dev *pdev, unsigned int state) +static void pcie_config_aspm_dev(struct pci_dev *pdev, u32 val) { u16 reg16; int pos = pci_find_capability(pdev, PCI_CAP_ID_EXP); pci_read_config_word(pdev, pos + PCI_EXP_LNKCTL, ®16); reg16 &= ~0x3; - reg16 |= state; + reg16 |= val; pci_write_config_word(pdev, pos + PCI_EXP_LNKCTL, reg16); } -static void __pcie_aspm_config_link(struct pcie_link_state *link, u32 state) +static void pcie_config_aspm_link(struct pcie_link_state *link, u32 state) { + u32 upstream = 0, dwstream = 0; struct pci_dev *child, *parent = link->pdev; struct pci_bus *linkbus = parent->subordinate; - /* If no child, disable the link */ - if (list_empty(&linkbus->devices)) - state = 0; - /* - * If the downstream component has pci bridge function, don't - * do ASPM now. - */ - list_for_each_entry(child, &linkbus->devices, bus_list) { - if (child->pcie_type == PCI_EXP_TYPE_PCI_BRIDGE) - return; + /* Nothing to do if the link is already in the requested state */ + state &= (link->aspm_capable & ~link->aspm_disable); + if (link->aspm_enabled == state) + return; + /* Convert ASPM state to upstream/downstream ASPM register state */ + if (state & ASPM_STATE_L0S_UP) + dwstream |= PCIE_LINK_STATE_L0S; + if (state & ASPM_STATE_L0S_DW) + upstream |= PCIE_LINK_STATE_L0S; + if (state & ASPM_STATE_L1) { + upstream |= PCIE_LINK_STATE_L1; + dwstream |= PCIE_LINK_STATE_L1; } /* * Spec 2.0 suggests all functions should be configured the @@ -475,67 +472,24 @@ static void __pcie_aspm_config_link(struct pcie_link_state *link, u32 state) * upstream component first and then downstream, and vice * versa for disabling ASPM L1. Spec doesn't mention L0S. */ - if (state & PCIE_LINK_STATE_L1) - __pcie_aspm_config_one_dev(parent, state); - + if (state & ASPM_STATE_L1) + pcie_config_aspm_dev(parent, upstream); list_for_each_entry(child, &linkbus->devices, bus_list) - __pcie_aspm_config_one_dev(child, state); - - if (!(state & PCIE_LINK_STATE_L1)) - __pcie_aspm_config_one_dev(parent, state); + pcie_config_aspm_dev(child, dwstream); + if (!(state & ASPM_STATE_L1)) + pcie_config_aspm_dev(parent, upstream); link->aspm_enabled = state; } -/* Check the whole hierarchy, and configure each link in the hierarchy */ -static void __pcie_aspm_configure_link_state(struct pcie_link_state *link, - u32 state) +static void pcie_config_aspm_path(struct pcie_link_state *link) { - struct pcie_link_state *leaf, *root = link->root; - - state &= (PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1); - - /* Check all links who have specific root port link */ - list_for_each_entry(leaf, &link_list, sibling) { - if (!list_empty(&leaf->children) || (leaf->root != root)) - continue; - state = pcie_aspm_check_state(leaf, state); - } - /* Check root port link too in case it hasn't children */ - state = pcie_aspm_check_state(root, state); - if (link->aspm_enabled == state) - return; - /* - * We must change the hierarchy. See comments in - * __pcie_aspm_config_link for the order - **/ - if (state & PCIE_LINK_STATE_L1) { - list_for_each_entry(leaf, &link_list, sibling) { - if (leaf->root == root) - __pcie_aspm_config_link(leaf, state); - } - } else { - list_for_each_entry_reverse(leaf, &link_list, sibling) { - if (leaf->root == root) - __pcie_aspm_config_link(leaf, state); - } + while (link) { + pcie_config_aspm_link(link, policy_to_aspm_state(link)); + link = link->parent; } } -/* - * pcie_aspm_configure_link_state: enable/disable PCI express link state - * @pdev: the root port or switch downstream port - */ -static void pcie_aspm_configure_link_state(struct pcie_link_state *link, - u32 state) -{ - down_read(&pci_bus_sem); - mutex_lock(&aspm_lock); - __pcie_aspm_configure_link_state(link, state); - mutex_unlock(&aspm_lock); - up_read(&pci_bus_sem); -} - static void free_link_state(struct pcie_link_state *link) { link->pdev->link_state = NULL; @@ -570,10 +524,9 @@ static int pcie_aspm_sanity_check(struct pci_dev *pdev) return 0; } -static struct pcie_link_state *pcie_aspm_setup_link_state(struct pci_dev *pdev) +static struct pcie_link_state *alloc_pcie_link_state(struct pci_dev *pdev) { struct pcie_link_state *link; - int blacklist = !!pcie_aspm_sanity_check(pdev); link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) @@ -599,15 +552,7 @@ static struct pcie_link_state *pcie_aspm_setup_link_state(struct pci_dev *pdev) link->root = link->parent->root; list_add(&link->sibling, &link_list); - pdev->link_state = link; - - /* Check ASPM capability */ - pcie_aspm_cap_init(link, blacklist); - - /* Check Clock PM capability */ - pcie_clkpm_cap_init(link, blacklist); - return link; } @@ -618,8 +563,8 @@ static struct pcie_link_state *pcie_aspm_setup_link_state(struct pci_dev *pdev) */ void pcie_aspm_init_link_state(struct pci_dev *pdev) { - u32 state; struct pcie_link_state *link; + int blacklist = !!pcie_aspm_sanity_check(pdev); if (aspm_disabled || !pdev->is_pcie || pdev->link_state) return; @@ -637,47 +582,64 @@ void pcie_aspm_init_link_state(struct pci_dev *pdev) goto out; mutex_lock(&aspm_lock); - link = pcie_aspm_setup_link_state(pdev); + link = alloc_pcie_link_state(pdev); if (!link) goto unlock; /* - * Setup initial ASPM state - * - * If link has switch, delay the link config. The leaf link - * initialization will config the whole hierarchy. But we must - * make sure BIOS doesn't set unsupported link state. + * Setup initial ASPM state. Note that we need to configure + * upstream links also because capable state of them can be + * update through pcie_aspm_cap_init(). */ - if (pcie_aspm_downstream_has_switch(link)) { - state = pcie_aspm_check_state(link, link->aspm_default); - __pcie_aspm_config_link(link, state); - } else { - state = policy_to_aspm_state(link); - __pcie_aspm_configure_link_state(link, state); - } + pcie_aspm_cap_init(link, blacklist); + pcie_config_aspm_path(link); /* Setup initial Clock PM state */ - state = (link->clkpm_capable) ? policy_to_clkpm_state(link) : 0; - pcie_set_clkpm(link, state); + pcie_clkpm_cap_init(link, blacklist); + pcie_set_clkpm(link, policy_to_clkpm_state(link)); unlock: mutex_unlock(&aspm_lock); out: up_read(&pci_bus_sem); } +/* Recheck latencies and update aspm_capable for links under the root */ +static void pcie_update_aspm_capable(struct pcie_link_state *root) +{ + struct pcie_link_state *link; + BUG_ON(root->parent); + list_for_each_entry(link, &link_list, sibling) { + if (link->root != root) + continue; + link->aspm_capable = link->aspm_support; + } + list_for_each_entry(link, &link_list, sibling) { + struct pci_dev *child; + struct pci_bus *linkbus = link->pdev->subordinate; + if (link->root != root) + continue; + list_for_each_entry(child, &linkbus->devices, bus_list) { + if ((child->pcie_type != PCI_EXP_TYPE_ENDPOINT) && + (child->pcie_type != PCI_EXP_TYPE_LEG_END)) + continue; + pcie_aspm_check_latency(child); + } + } +} + /* @pdev: the endpoint device */ void pcie_aspm_exit_link_state(struct pci_dev *pdev) { struct pci_dev *parent = pdev->bus->self; - struct pcie_link_state *link_state = parent->link_state; + struct pcie_link_state *link, *root, *parent_link; - if (aspm_disabled || !pdev->is_pcie || !parent || !link_state) + if (aspm_disabled || !pdev->is_pcie || !parent || !parent->link_state) return; - if (parent->pcie_type != PCI_EXP_TYPE_ROOT_PORT && - parent->pcie_type != PCI_EXP_TYPE_DOWNSTREAM) + if ((parent->pcie_type != PCI_EXP_TYPE_ROOT_PORT) && + (parent->pcie_type != PCI_EXP_TYPE_DOWNSTREAM)) return; + down_read(&pci_bus_sem); mutex_lock(&aspm_lock); - /* * All PCIe functions are in one slot, remove one function will remove * the whole slot, so just wait until we are the last function left. @@ -685,13 +647,20 @@ void pcie_aspm_exit_link_state(struct pci_dev *pdev) if (!list_is_last(&pdev->bus_list, &parent->subordinate->devices)) goto out; + link = parent->link_state; + root = link->root; + parent_link = link->parent; + /* All functions are removed, so just disable ASPM for the link */ - __pcie_aspm_config_one_dev(parent, 0); - list_del(&link_state->sibling); - list_del(&link_state->link); + pcie_config_aspm_link(link, 0); + list_del(&link->sibling); + list_del(&link->link); /* Clock PM is for endpoint device */ + free_link_state(link); - free_link_state(link_state); + /* Recheck latencies and configure upstream links */ + pcie_update_aspm_capable(root); + pcie_config_aspm_path(parent_link); out: mutex_unlock(&aspm_lock); up_read(&pci_bus_sem); @@ -700,18 +669,23 @@ out: /* @pdev: the root port or switch downstream port */ void pcie_aspm_pm_state_change(struct pci_dev *pdev) { - struct pcie_link_state *link_state = pdev->link_state; + struct pcie_link_state *link = pdev->link_state; - if (aspm_disabled || !pdev->is_pcie || !pdev->link_state) + if (aspm_disabled || !pdev->is_pcie || !link) return; - if (pdev->pcie_type != PCI_EXP_TYPE_ROOT_PORT && - pdev->pcie_type != PCI_EXP_TYPE_DOWNSTREAM) + if ((pdev->pcie_type != PCI_EXP_TYPE_ROOT_PORT) && + (pdev->pcie_type != PCI_EXP_TYPE_DOWNSTREAM)) return; /* - * devices changed PM state, we should recheck if latency meets all - * functions' requirement + * Devices changed PM state, we should recheck if latency + * meets all functions' requirement */ - pcie_aspm_configure_link_state(link_state, link_state->aspm_enabled); + down_read(&pci_bus_sem); + mutex_lock(&aspm_lock); + pcie_update_aspm_capable(link->root); + pcie_config_aspm_path(link); + mutex_unlock(&aspm_lock); + up_read(&pci_bus_sem); } /* @@ -721,7 +695,7 @@ void pcie_aspm_pm_state_change(struct pci_dev *pdev) void pci_disable_link_state(struct pci_dev *pdev, int state) { struct pci_dev *parent = pdev->bus->self; - struct pcie_link_state *link_state; + struct pcie_link_state *link; if (aspm_disabled || !pdev->is_pcie) return; @@ -733,12 +707,16 @@ void pci_disable_link_state(struct pci_dev *pdev, int state) down_read(&pci_bus_sem); mutex_lock(&aspm_lock); - link_state = parent->link_state; - link_state->aspm_support &= ~state; - __pcie_aspm_configure_link_state(link_state, link_state->aspm_enabled); + link = parent->link_state; + if (state & PCIE_LINK_STATE_L0S) + link->aspm_disable |= ASPM_STATE_L0S; + if (state & PCIE_LINK_STATE_L1) + link->aspm_disable |= ASPM_STATE_L1; + pcie_config_aspm_link(link, policy_to_aspm_state(link)); + if (state & PCIE_LINK_STATE_CLKPM) { - link_state->clkpm_capable = 0; - pcie_set_clkpm(link_state, 0); + link->clkpm_capable = 0; + pcie_set_clkpm(link, 0); } mutex_unlock(&aspm_lock); up_read(&pci_bus_sem); @@ -748,7 +726,7 @@ EXPORT_SYMBOL(pci_disable_link_state); static int pcie_aspm_set_policy(const char *val, struct kernel_param *kp) { int i; - struct pcie_link_state *link_state; + struct pcie_link_state *link; for (i = 0; i < ARRAY_SIZE(policy_str); i++) if (!strncmp(val, policy_str[i], strlen(policy_str[i]))) @@ -761,10 +739,9 @@ static int pcie_aspm_set_policy(const char *val, struct kernel_param *kp) down_read(&pci_bus_sem); mutex_lock(&aspm_lock); aspm_policy = i; - list_for_each_entry(link_state, &link_list, sibling) { - __pcie_aspm_configure_link_state(link_state, - policy_to_aspm_state(link_state)); - pcie_set_clkpm(link_state, policy_to_clkpm_state(link_state)); + list_for_each_entry(link, &link_list, sibling) { + pcie_config_aspm_link(link, policy_to_aspm_state(link)); + pcie_set_clkpm(link, policy_to_clkpm_state(link)); } mutex_unlock(&aspm_lock); up_read(&pci_bus_sem); @@ -802,18 +779,28 @@ static ssize_t link_state_store(struct device *dev, size_t n) { struct pci_dev *pdev = to_pci_dev(dev); - int state; + struct pcie_link_state *link, *root = pdev->link_state->root; + u32 val = buf[0] - '0', state = 0; - if (n < 1) + if (n < 1 || val > 3) return -EINVAL; - state = buf[0]-'0'; - if (state >= 0 && state <= 3) { - /* setup link aspm state */ - pcie_aspm_configure_link_state(pdev->link_state, state); - return n; - } - return -EINVAL; + /* Convert requested state to ASPM state */ + if (val & PCIE_LINK_STATE_L0S) + state |= ASPM_STATE_L0S; + if (val & PCIE_LINK_STATE_L1) + state |= ASPM_STATE_L1; + + down_read(&pci_bus_sem); + mutex_lock(&aspm_lock); + list_for_each_entry(link, &link_list, sibling) { + if (link->root != root) + continue; + pcie_config_aspm_link(link, state); + } + mutex_unlock(&aspm_lock); + up_read(&pci_bus_sem); + return n; } static ssize_t clk_ctl_show(struct device *dev, diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c index 13ffdc35ea0..52f84fca9f7 100644 --- a/drivers/pci/pcie/portdrv_core.c +++ b/drivers/pci/pcie/portdrv_core.c @@ -187,14 +187,9 @@ static int pcie_port_enable_msix(struct pci_dev *dev, int *vectors, int mask) */ static int assign_interrupt_mode(struct pci_dev *dev, int *vectors, int mask) { - struct pcie_port_data *port_data = pci_get_drvdata(dev); int irq, interrupt_mode = PCIE_PORT_NO_IRQ; int i; - /* Check MSI quirk */ - if (port_data->port_type == PCIE_RC_PORT && pcie_mch_quirk) - goto Fallback; - /* Try to use MSI-X if supported */ if (!pcie_port_enable_msix(dev, vectors, mask)) return PCIE_PORT_MSIX_MODE; @@ -203,7 +198,6 @@ static int assign_interrupt_mode(struct pci_dev *dev, int *vectors, int mask) if (!pci_enable_msi(dev)) interrupt_mode = PCIE_PORT_MSI_MODE; - Fallback: if (interrupt_mode == PCIE_PORT_NO_IRQ && dev->pin) interrupt_mode = PCIE_PORT_INTx_MODE; diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c index 091ce70051e..6df5c984a79 100644 --- a/drivers/pci/pcie/portdrv_pci.c +++ b/drivers/pci/pcie/portdrv_pci.c @@ -205,6 +205,7 @@ static pci_ers_result_t pcie_portdrv_slot_reset(struct pci_dev *dev) /* If fatal, restore cfg space for possible link reset at upstream */ if (dev->error_state == pci_channel_io_frozen) { + dev->state_saved = true; pci_restore_state(dev); pcie_portdrv_restore_config(dev); pci_enable_pcie_error_reporting(dev); diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 40e75f6a505..8105e32117f 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -235,7 +235,10 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, res->start = l64; res->end = l64 + sz64; dev_printk(KERN_DEBUG, &dev->dev, - "reg %x 64bit mmio: %pR\n", pos, res); + "reg %x %s: %pR\n", pos, + (res->flags & IORESOURCE_PREFETCH) ? + "64bit mmio pref" : "64bit mmio", + res); } res->flags |= IORESOURCE_MEM_64; @@ -249,7 +252,9 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, res->end = l + sz; dev_printk(KERN_DEBUG, &dev->dev, "reg %x %s: %pR\n", pos, - (res->flags & IORESOURCE_IO) ? "io port" : "32bit mmio", + (res->flags & IORESOURCE_IO) ? "io port" : + ((res->flags & IORESOURCE_PREFETCH) ? + "32bit mmio pref" : "32bit mmio"), res); } @@ -692,6 +697,23 @@ static void set_pcie_port_type(struct pci_dev *pdev) pdev->pcie_type = (reg16 & PCI_EXP_FLAGS_TYPE) >> 4; } +static void set_pcie_hotplug_bridge(struct pci_dev *pdev) +{ + int pos; + u16 reg16; + u32 reg32; + + pos = pci_find_capability(pdev, PCI_CAP_ID_EXP); + if (!pos) + return; + pci_read_config_word(pdev, pos + PCI_EXP_FLAGS, ®16); + if (!(reg16 & PCI_EXP_FLAGS_SLOT)) + return; + pci_read_config_dword(pdev, pos + PCI_EXP_SLTCAP, ®32); + if (reg32 & PCI_EXP_SLTCAP_HPC) + pdev->is_hotplug_bridge = 1; +} + #define LEGACY_IO_RESOURCE (IORESOURCE_IO | IORESOURCE_PCI_FIXED) /** @@ -799,6 +821,7 @@ int pci_setup_device(struct pci_dev *dev) pci_read_irq(dev); dev->transparent = ((dev->class & 0xff) == 1); pci_read_bases(dev, 2, PCI_ROM_ADDRESS1); + set_pcie_hotplug_bridge(dev); break; case PCI_HEADER_TYPE_CARDBUS: /* CardBus bridge header */ @@ -1009,6 +1032,9 @@ void pci_device_add(struct pci_dev *dev, struct pci_bus *bus) /* Fix up broken headers */ pci_fixup_device(pci_fixup_header, dev); + /* Clear the state_saved flag. */ + dev->state_saved = false; + /* Initialize various capabilities */ pci_init_capabilities(dev); @@ -1061,8 +1087,7 @@ int pci_scan_slot(struct pci_bus *bus, int devfn) if (dev && !dev->is_added) /* new device? */ nr++; - if ((dev && dev->multifunction) || - (!dev && pcibios_scan_all_fns(bus, devfn))) { + if (dev && dev->multifunction) { for (fn = 1; fn < 8; fn++) { dev = pci_scan_single_device(bus, devfn + fn); if (dev) { diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 85ce23997be..6099facecd7 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -31,8 +31,6 @@ int isa_dma_bridge_buggy; EXPORT_SYMBOL(isa_dma_bridge_buggy); int pci_pci_problems; EXPORT_SYMBOL(pci_pci_problems); -int pcie_mch_quirk; -EXPORT_SYMBOL(pcie_mch_quirk); #ifdef CONFIG_PCI_QUIRKS /* @@ -1203,6 +1201,7 @@ static void __init asus_hides_smbus_hostbridge(struct pci_dev *dev) switch(dev->subsystem_device) { case 0x00b8: /* Compaq Evo D510 CMT */ case 0x00b9: /* Compaq Evo D510 SFF */ + case 0x00ba: /* Compaq Evo D510 USDT */ /* Motherboard doesn't have Host bridge * subvendor/subdevice IDs and on-board VGA * controller is disabled if an AGP card is @@ -1501,7 +1500,8 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_EESSC, quirk_a static void __devinit quirk_pcie_mch(struct pci_dev *pdev) { - pcie_mch_quirk = 1; + pci_msi_off(pdev); + pdev->no_msi = 1; } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E7520_MCH, quirk_pcie_mch); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E7320_MCH, quirk_pcie_mch); @@ -1569,10 +1569,8 @@ static void quirk_reroute_to_boot_interrupts_intel(struct pci_dev *dev) return; dev->irq_reroute_variant = INTEL_IRQ_REROUTE_VARIANT; - - printk(KERN_INFO "PCI quirk: reroute interrupts for 0x%04x:0x%04x\n", - dev->vendor, dev->device); - return; + dev_info(&dev->dev, "rerouting interrupts for [%04x:%04x]\n", + dev->vendor, dev->device); } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_80333_0, quirk_reroute_to_boot_interrupts_intel); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_80333_1, quirk_reroute_to_boot_interrupts_intel); @@ -1614,8 +1612,8 @@ static void quirk_disable_intel_boot_interrupt(struct pci_dev *dev) pci_config_word |= INTEL_6300_DISABLE_BOOT_IRQ; pci_write_config_word(dev, INTEL_6300_IOAPIC_ABAR, pci_config_word); - printk(KERN_INFO "disabled boot interrupt on device 0x%04x:0x%04x\n", - dev->vendor, dev->device); + dev_info(&dev->dev, "disabled boot interrupts on device [%04x:%04x]\n", + dev->vendor, dev->device); } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB_10, quirk_disable_intel_boot_interrupt); DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB_10, quirk_disable_intel_boot_interrupt); @@ -1647,8 +1645,8 @@ static void quirk_disable_broadcom_boot_interrupt(struct pci_dev *dev) pci_write_config_dword(dev, BC_HT1000_FEATURE_REG, pci_config_dword); - printk(KERN_INFO "disabled boot interrupts on PCI device" - "0x%04x:0x%04x\n", dev->vendor, dev->device); + dev_info(&dev->dev, "disabled boot interrupts on device [%04x:%04x]\n", + dev->vendor, dev->device); } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_HT1000SB, quirk_disable_broadcom_boot_interrupt); DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_HT1000SB, quirk_disable_broadcom_boot_interrupt); @@ -1678,8 +1676,8 @@ static void quirk_disable_amd_813x_boot_interrupt(struct pci_dev *dev) pci_config_dword &= ~AMD_813X_NOIOAMODE; pci_write_config_dword(dev, AMD_813X_MISC, pci_config_dword); - printk(KERN_INFO "disabled boot interrupts on PCI device " - "0x%04x:0x%04x\n", dev->vendor, dev->device); + dev_info(&dev->dev, "disabled boot interrupts on device [%04x:%04x]\n", + dev->vendor, dev->device); } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8131_BRIDGE, quirk_disable_amd_813x_boot_interrupt); DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8132_BRIDGE, quirk_disable_amd_813x_boot_interrupt); @@ -1695,14 +1693,13 @@ static void quirk_disable_amd_8111_boot_interrupt(struct pci_dev *dev) pci_read_config_word(dev, AMD_8111_PCI_IRQ_ROUTING, &pci_config_word); if (!pci_config_word) { - printk(KERN_INFO "boot interrupts on PCI device 0x%04x:0x%04x " - "already disabled\n", - dev->vendor, dev->device); + dev_info(&dev->dev, "boot interrupts on device [%04x:%04x] " + "already disabled\n", dev->vendor, dev->device); return; } pci_write_config_word(dev, AMD_8111_PCI_IRQ_ROUTING, 0); - printk(KERN_INFO "disabled boot interrupts on PCI device " - "0x%04x:0x%04x\n", dev->vendor, dev->device); + dev_info(&dev->dev, "disabled boot interrupts on device [%04x:%04x]\n", + dev->vendor, dev->device); } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8111_SMBUS, quirk_disable_amd_8111_boot_interrupt); DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8111_SMBUS, quirk_disable_amd_8111_boot_interrupt); @@ -2384,8 +2381,10 @@ static void __devinit nv_msi_ht_cap_quirk_leaf(struct pci_dev *dev) } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, nv_msi_ht_cap_quirk_leaf); +DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, nv_msi_ht_cap_quirk_leaf); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL, PCI_ANY_ID, nv_msi_ht_cap_quirk_all); +DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_AL, PCI_ANY_ID, nv_msi_ht_cap_quirk_all); static void __devinit quirk_msi_intx_disable_bug(struct pci_dev *dev) { @@ -2494,6 +2493,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10e6, quirk_i82576_sriov); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10e7, quirk_i82576_sriov); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10e8, quirk_i82576_sriov); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x150a, quirk_i82576_sriov); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x150d, quirk_i82576_sriov); #endif /* CONFIG_PCI_IOV */ diff --git a/drivers/pci/search.c b/drivers/pci/search.c index e8cb5051c31..ec415352d9b 100644 --- a/drivers/pci/search.c +++ b/drivers/pci/search.c @@ -113,37 +113,6 @@ pci_find_next_bus(const struct pci_bus *from) return b; } -#ifdef CONFIG_PCI_LEGACY -/** - * pci_find_device - begin or continue searching for a PCI device by vendor/device id - * @vendor: PCI vendor id to match, or %PCI_ANY_ID to match all vendor ids - * @device: PCI device id to match, or %PCI_ANY_ID to match all device ids - * @from: Previous PCI device found in search, or %NULL for new search. - * - * Iterates through the list of known PCI devices. If a PCI device is found - * with a matching @vendor and @device, a pointer to its device structure is - * returned. Otherwise, %NULL is returned. - * A new search is initiated by passing %NULL as the @from argument. - * Otherwise if @from is not %NULL, searches continue from next device - * on the global list. - * - * NOTE: Do not use this function any more; use pci_get_device() instead, as - * the PCI device returned by this function can disappear at any moment in - * time. - */ -struct pci_dev *pci_find_device(unsigned int vendor, unsigned int device, - struct pci_dev *from) -{ - struct pci_dev *pdev; - - pci_dev_get(from); - pdev = pci_get_subsys(vendor, device, PCI_ANY_ID, PCI_ANY_ID, from); - pci_dev_put(pdev); - return pdev; -} -EXPORT_SYMBOL(pci_find_device); -#endif /* CONFIG_PCI_LEGACY */ - /** * pci_get_slot - locate PCI device for a given PCI slot * @bus: PCI bus on which desired PCI device resides diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 7c443b4583a..cb1a027eb55 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -309,7 +309,7 @@ static struct resource *find_free_bus_resource(struct pci_bus *bus, unsigned lon since these windows have 4K granularity and the IO ranges of non-bridge PCI devices are limited to 256 bytes. We must be careful with the ISA aliasing though. */ -static void pbus_size_io(struct pci_bus *bus) +static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size) { struct pci_dev *dev; struct resource *b_res = find_free_bus_resource(bus, IORESOURCE_IO); @@ -336,6 +336,8 @@ static void pbus_size_io(struct pci_bus *bus) size1 += r_size; } } + if (size < min_size) + size = min_size; /* To be fixed in 2.5: we should have sort of HAVE_ISA flag in the struct pci_bus. */ #if defined(CONFIG_ISA) || defined(CONFIG_EISA) @@ -354,7 +356,8 @@ static void pbus_size_io(struct pci_bus *bus) /* Calculate the size of the bus and minimal alignment which guarantees that all child resources fit in this size. */ -static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, unsigned long type) +static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, + unsigned long type, resource_size_t min_size) { struct pci_dev *dev; resource_size_t min_align, align, size; @@ -404,6 +407,8 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, unsigned long mem64_mask &= r->flags & IORESOURCE_MEM_64; } } + if (size < min_size) + size = min_size; align = 0; min_align = 0; @@ -483,6 +488,7 @@ void __ref pci_bus_size_bridges(struct pci_bus *bus) { struct pci_dev *dev; unsigned long mask, prefmask; + resource_size_t min_mem_size = 0, min_io_size = 0; list_for_each_entry(dev, &bus->devices, bus_list) { struct pci_bus *b = dev->subordinate; @@ -512,8 +518,12 @@ void __ref pci_bus_size_bridges(struct pci_bus *bus) case PCI_CLASS_BRIDGE_PCI: pci_bridge_check_ranges(bus); + if (bus->self->is_hotplug_bridge) { + min_io_size = pci_hotplug_io_size; + min_mem_size = pci_hotplug_mem_size; + } default: - pbus_size_io(bus); + pbus_size_io(bus, min_io_size); /* If the bridge supports prefetchable range, size it separately. If it doesn't, or its prefetchable window has already been allocated by arch code, try @@ -521,9 +531,11 @@ void __ref pci_bus_size_bridges(struct pci_bus *bus) resources. */ mask = IORESOURCE_MEM; prefmask = IORESOURCE_MEM | IORESOURCE_PREFETCH; - if (pbus_size_mem(bus, prefmask, prefmask)) + if (pbus_size_mem(bus, prefmask, prefmask, min_mem_size)) mask = prefmask; /* Success, size non-prefetch only. */ - pbus_size_mem(bus, mask, IORESOURCE_MEM); + else + min_mem_size += min_mem_size; + pbus_size_mem(bus, mask, IORESOURCE_MEM, min_mem_size); break; } } diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c index 88cdd1a937d..706f82d8111 100644 --- a/drivers/pci/setup-res.c +++ b/drivers/pci/setup-res.c @@ -119,6 +119,7 @@ int pci_claim_resource(struct pci_dev *dev, int resource) return err; } +EXPORT_SYMBOL(pci_claim_resource); #ifdef CONFIG_PCI_QUIRKS void pci_disable_bridge_window(struct pci_dev *dev) diff --git a/drivers/pcmcia/au1000_pb1x00.c b/drivers/pcmcia/au1000_pb1x00.c index d6b4bd1db7d..b1984ed72d1 100644 --- a/drivers/pcmcia/au1000_pb1x00.c +++ b/drivers/pcmcia/au1000_pb1x00.c @@ -26,7 +26,6 @@ #include <linux/delay.h> #include <linux/ioport.h> #include <linux/kernel.h> -#include <linux/tqueue.h> #include <linux/timer.h> #include <linux/mm.h> #include <linux/proc_fs.h> diff --git a/drivers/pcmcia/au1000_xxs1500.c b/drivers/pcmcia/au1000_xxs1500.c index 9627390835c..b43d47b5081 100644 --- a/drivers/pcmcia/au1000_xxs1500.c +++ b/drivers/pcmcia/au1000_xxs1500.c @@ -30,7 +30,6 @@ #include <linux/delay.h> #include <linux/ioport.h> #include <linux/kernel.h> -#include <linux/tqueue.h> #include <linux/timer.h> #include <linux/mm.h> #include <linux/proc_fs.h> diff --git a/drivers/pcmcia/ds.c b/drivers/pcmcia/ds.c index 304ff6d5cf3..9f300d3cb12 100644 --- a/drivers/pcmcia/ds.c +++ b/drivers/pcmcia/ds.c @@ -236,7 +236,6 @@ pcmcia_store_new_id(struct device_driver *driver, const char *buf, size_t count) if (!dynid) return -ENOMEM; - INIT_LIST_HEAD(&dynid->node); dynid->id.match_flags = match_flags; dynid->id.manf_id = manf_id; dynid->id.card_id = card_id; @@ -246,7 +245,7 @@ pcmcia_store_new_id(struct device_driver *driver, const char *buf, size_t count) memcpy(dynid->id.prod_id_hash, prod_id_hash, sizeof(__u32) * 4); spin_lock(&pdrv->dynids.lock); - list_add_tail(&pdrv->dynids.list, &dynid->node); + list_add_tail(&dynid->node, &pdrv->dynids.list); spin_unlock(&pdrv->dynids.lock); if (get_driver(&pdrv->drv)) { diff --git a/drivers/pcmcia/o2micro.h b/drivers/pcmcia/o2micro.h index 5554015a781..72188c462c9 100644 --- a/drivers/pcmcia/o2micro.h +++ b/drivers/pcmcia/o2micro.h @@ -48,6 +48,9 @@ #ifndef PCI_DEVICE_ID_O2_6812 #define PCI_DEVICE_ID_O2_6812 0x6872 #endif +#ifndef PCI_DEVICE_ID_O2_6933 +#define PCI_DEVICE_ID_O2_6933 0x6933 +#endif /* Additional PCI configuration registers */ @@ -154,6 +157,7 @@ static int o2micro_override(struct yenta_socket *socket) case PCI_DEVICE_ID_O2_6812: case PCI_DEVICE_ID_O2_6832: case PCI_DEVICE_ID_O2_6836: + case PCI_DEVICE_ID_O2_6933: dev_printk(KERN_INFO, &socket->dev->dev, "Yenta O2: old bridge, disabling read " "prefetch/write burst\n"); diff --git a/drivers/pcmcia/pcmcia_ioctl.c b/drivers/pcmcia/pcmcia_ioctl.c index 6095f8daecd..7b424e0b044 100644 --- a/drivers/pcmcia/pcmcia_ioctl.c +++ b/drivers/pcmcia/pcmcia_ioctl.c @@ -286,7 +286,7 @@ static int pccard_get_status(struct pcmcia_socket *s, return 0; } /* pccard_get_status */ -int pccard_get_configuration_info(struct pcmcia_socket *s, +static int pccard_get_configuration_info(struct pcmcia_socket *s, struct pcmcia_device *p_dev, config_info_t *config) { diff --git a/drivers/pcmcia/pcmcia_resource.c b/drivers/pcmcia/pcmcia_resource.c index f5d0ba8e22d..d919e96c0af 100644 --- a/drivers/pcmcia/pcmcia_resource.c +++ b/drivers/pcmcia/pcmcia_resource.c @@ -489,7 +489,7 @@ int pcmcia_request_configuration(struct pcmcia_device *p_dev, pccard_io_map iomap; if (!(s->state & SOCKET_PRESENT)) - return -ENODEV;; + return -ENODEV; if (req->IntType & INT_CARDBUS) { ds_dbg(p_dev->socket, 0, "IntType may not be INT_CARDBUS\n"); @@ -902,7 +902,7 @@ struct pcmcia_cfg_mem { * * pcmcia_loop_config() loops over all configuration options, and calls * the driver-specific conf_check() for each one, checking whether - * it is a valid one. + * it is a valid one. Returns 0 on success or errorcode otherwise. */ int pcmcia_loop_config(struct pcmcia_device *p_dev, int (*conf_check) (struct pcmcia_device *p_dev, @@ -915,7 +915,7 @@ int pcmcia_loop_config(struct pcmcia_device *p_dev, struct pcmcia_cfg_mem *cfg_mem; tuple_t *tuple; - int ret = -ENODEV; + int ret; unsigned int vcc; cfg_mem = kzalloc(sizeof(struct pcmcia_cfg_mem), GFP_KERNEL); diff --git a/drivers/pcmcia/yenta_socket.c b/drivers/pcmcia/yenta_socket.c index 3ecd7c99d8e..737fe5d87c4 100644 --- a/drivers/pcmcia/yenta_socket.c +++ b/drivers/pcmcia/yenta_socket.c @@ -622,11 +622,12 @@ static int yenta_search_res(struct yenta_socket *socket, struct resource *res, static int yenta_allocate_res(struct yenta_socket *socket, int nr, unsigned type, int addr_start, int addr_end) { - struct resource *root, *res; + struct pci_dev *dev = socket->dev; + struct resource *res; struct pci_bus_region region; unsigned mask; - res = socket->dev->resource + PCI_BRIDGE_RESOURCES + nr; + res = dev->resource + PCI_BRIDGE_RESOURCES + nr; /* Already allocated? */ if (res->parent) return 0; @@ -636,17 +637,16 @@ static int yenta_allocate_res(struct yenta_socket *socket, int nr, unsigned type if (type & IORESOURCE_IO) mask = ~3; - res->name = socket->dev->subordinate->name; + res->name = dev->subordinate->name; res->flags = type; region.start = config_readl(socket, addr_start) & mask; region.end = config_readl(socket, addr_end) | ~mask; if (region.start && region.end > region.start && !override_bios) { - pcibios_bus_to_resource(socket->dev, res, ®ion); - root = pci_find_parent_resource(socket->dev, res); - if (root && (request_resource(root, res) == 0)) + pcibios_bus_to_resource(dev, res, ®ion); + if (pci_claim_resource(dev, PCI_BRIDGE_RESOURCES + nr) == 0) return 0; - dev_printk(KERN_INFO, &socket->dev->dev, + dev_printk(KERN_INFO, &dev->dev, "Preassigned resource %d busy or not available, " "reconfiguring...\n", nr); @@ -672,7 +672,7 @@ static int yenta_allocate_res(struct yenta_socket *socket, int nr, unsigned type return 1; } - dev_printk(KERN_INFO, &socket->dev->dev, + dev_printk(KERN_INFO, &dev->dev, "no resource of type %x available, trying to continue...\n", type); res->start = res->end = res->flags = 0; diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig index 1999b183481..cef3e1d9b92 100644 --- a/drivers/video/Kconfig +++ b/drivers/video/Kconfig @@ -7,6 +7,8 @@ menu "Graphics support" source "drivers/char/agp/Kconfig" +source "drivers/gpu/vga/Kconfig" + source "drivers/gpu/drm/Kconfig" config VGASTATE diff --git a/fs/afs/write.c b/fs/afs/write.c index c2e7a7ff008..c63a3c8beb7 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -712,7 +712,6 @@ int afs_writeback_all(struct afs_vnode *vnode) .bdi = mapping->backing_dev_info, .sync_mode = WB_SYNC_ALL, .nr_to_write = LONG_MAX, - .for_writepages = 1, .range_cyclic = 1, }; int ret; diff --git a/fs/block_dev.c b/fs/block_dev.c index 3581a4e5394..71e7e03ac34 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -420,7 +420,6 @@ static void bdev_destroy_inode(struct inode *inode) { struct bdev_inode *bdi = BDEV_I(inode); - bdi->bdev.bd_inode_backing_dev_info = NULL; kmem_cache_free(bdev_cachep, bdi); } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 15831d5c736..8b819279001 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1600,6 +1600,7 @@ struct btrfs_root *open_ctree(struct super_block *sb, sb->s_blocksize = 4096; sb->s_blocksize_bits = blksize_bits(4096); + sb->s_bdi = &fs_info->bdi; /* * we set the i_size on the btree inode to the max possible int. diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index d6f0806c682..7b2f401e604 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -740,7 +740,6 @@ int btrfs_fdatawrite_range(struct address_space *mapping, loff_t start, .nr_to_write = mapping->nrpages * 2, .range_start = start, .range_end = end, - .for_writepages = 1, }; return btrfs_writepages(mapping, &wbc); } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 628235cf44b..8e1e5e19d21 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -35,21 +35,29 @@ int nr_pdflush_threads; /* + * Passed into wb_writeback(), essentially a subset of writeback_control + */ +struct wb_writeback_args { + long nr_pages; + struct super_block *sb; + enum writeback_sync_modes sync_mode; + int for_kupdate; + int range_cyclic; +}; + +/* * Work items for the bdi_writeback threads */ struct bdi_work { - struct list_head list; - struct list_head wait_list; - struct rcu_head rcu_head; + struct list_head list; /* pending work list */ + struct rcu_head rcu_head; /* for RCU free/clear of work */ - unsigned long seen; - atomic_t pending; + unsigned long seen; /* threads that have seen this work */ + atomic_t pending; /* number of threads still to do work */ - struct super_block *sb; - unsigned long nr_pages; - enum writeback_sync_modes sync_mode; + struct wb_writeback_args args; /* writeback arguments */ - unsigned long state; + unsigned long state; /* flag bits, see WS_* */ }; enum { @@ -66,22 +74,13 @@ static inline bool bdi_work_on_stack(struct bdi_work *work) } static inline void bdi_work_init(struct bdi_work *work, - struct writeback_control *wbc) + struct wb_writeback_args *args) { INIT_RCU_HEAD(&work->rcu_head); - work->sb = wbc->sb; - work->nr_pages = wbc->nr_to_write; - work->sync_mode = wbc->sync_mode; + work->args = *args; work->state = WS_USED; } -static inline void bdi_work_init_on_stack(struct bdi_work *work, - struct writeback_control *wbc) -{ - bdi_work_init(work, wbc); - work->state |= WS_ONSTACK; -} - /** * writeback_in_progress - determine whether there is writeback in progress * @bdi: the device's backing_dev_info structure. @@ -98,6 +97,11 @@ static void bdi_work_clear(struct bdi_work *work) { clear_bit(WS_USED_B, &work->state); smp_mb__after_clear_bit(); + /* + * work can have disappeared at this point. bit waitq functions + * should be able to tolerate this, provided bdi_sched_wait does + * not dereference it's pointer argument. + */ wake_up_bit(&work->state, WS_USED_B); } @@ -113,7 +117,8 @@ static void bdi_work_free(struct rcu_head *head) static void wb_work_complete(struct bdi_work *work) { - const enum writeback_sync_modes sync_mode = work->sync_mode; + const enum writeback_sync_modes sync_mode = work->args.sync_mode; + int onstack = bdi_work_on_stack(work); /* * For allocated work, we can clear the done/seen bit right here. @@ -121,9 +126,9 @@ static void wb_work_complete(struct bdi_work *work) * to after the RCU grace period, since the stack could be invalidated * as soon as bdi_work_clear() has done the wakeup. */ - if (!bdi_work_on_stack(work)) + if (!onstack) bdi_work_clear(work); - if (sync_mode == WB_SYNC_NONE || bdi_work_on_stack(work)) + if (sync_mode == WB_SYNC_NONE || onstack) call_rcu(&work->rcu_head, bdi_work_free); } @@ -146,21 +151,19 @@ static void wb_clear_pending(struct bdi_writeback *wb, struct bdi_work *work) static void bdi_queue_work(struct backing_dev_info *bdi, struct bdi_work *work) { - if (work) { - work->seen = bdi->wb_mask; - BUG_ON(!work->seen); - atomic_set(&work->pending, bdi->wb_cnt); - BUG_ON(!bdi->wb_cnt); - - /* - * Make sure stores are seen before it appears on the list - */ - smp_mb(); + work->seen = bdi->wb_mask; + BUG_ON(!work->seen); + atomic_set(&work->pending, bdi->wb_cnt); + BUG_ON(!bdi->wb_cnt); - spin_lock(&bdi->wb_lock); - list_add_tail_rcu(&work->list, &bdi->work_list); - spin_unlock(&bdi->wb_lock); - } + /* + * list_add_tail_rcu() contains the necessary barriers to + * make sure the above stores are seen before the item is + * noticed on the list + */ + spin_lock(&bdi->wb_lock); + list_add_tail_rcu(&work->list, &bdi->work_list); + spin_unlock(&bdi->wb_lock); /* * If the default thread isn't there, make sure we add it. When @@ -171,15 +174,7 @@ static void bdi_queue_work(struct backing_dev_info *bdi, struct bdi_work *work) else { struct bdi_writeback *wb = &bdi->wb; - /* - * If we failed allocating the bdi work item, wake up the wb - * thread always. As a safety precaution, it'll flush out - * everything - */ - if (!wb_has_dirty_io(wb)) { - if (work) - wb_clear_pending(wb, work); - } else if (wb->task) + if (wb->task) wake_up_process(wb->task); } } @@ -194,48 +189,75 @@ static void bdi_wait_on_work_clear(struct bdi_work *work) TASK_UNINTERRUPTIBLE); } -static struct bdi_work *bdi_alloc_work(struct writeback_control *wbc) +static void bdi_alloc_queue_work(struct backing_dev_info *bdi, + struct wb_writeback_args *args) { struct bdi_work *work; + /* + * This is WB_SYNC_NONE writeback, so if allocation fails just + * wakeup the thread for old dirty data writeback + */ work = kmalloc(sizeof(*work), GFP_ATOMIC); - if (work) - bdi_work_init(work, wbc); + if (work) { + bdi_work_init(work, args); + bdi_queue_work(bdi, work); + } else { + struct bdi_writeback *wb = &bdi->wb; - return work; + if (wb->task) + wake_up_process(wb->task); + } } -void bdi_start_writeback(struct writeback_control *wbc) +/** + * bdi_sync_writeback - start and wait for writeback + * @bdi: the backing device to write from + * @sb: write inodes from this super_block + * + * Description: + * This does WB_SYNC_ALL data integrity writeback and waits for the + * IO to complete. Callers must hold the sb s_umount semaphore for + * reading, to avoid having the super disappear before we are done. + */ +static void bdi_sync_writeback(struct backing_dev_info *bdi, + struct super_block *sb) { - const bool must_wait = wbc->sync_mode == WB_SYNC_ALL; - struct bdi_work work_stack, *work = NULL; + struct wb_writeback_args args = { + .sb = sb, + .sync_mode = WB_SYNC_ALL, + .nr_pages = LONG_MAX, + .range_cyclic = 0, + }; + struct bdi_work work; - if (!must_wait) - work = bdi_alloc_work(wbc); + bdi_work_init(&work, &args); + work.state |= WS_ONSTACK; - if (!work) { - work = &work_stack; - bdi_work_init_on_stack(work, wbc); - } + bdi_queue_work(bdi, &work); + bdi_wait_on_work_clear(&work); +} - bdi_queue_work(wbc->bdi, work); +/** + * bdi_start_writeback - start writeback + * @bdi: the backing device to write from + * @nr_pages: the number of pages to write + * + * Description: + * This does WB_SYNC_NONE opportunistic writeback. The IO is only + * started when this function returns, we make no guarentees on + * completion. Caller need not hold sb s_umount semaphore. + * + */ +void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages) +{ + struct wb_writeback_args args = { + .sync_mode = WB_SYNC_NONE, + .nr_pages = nr_pages, + .range_cyclic = 1, + }; - /* - * If the sync mode is WB_SYNC_ALL, block waiting for the work to - * complete. If not, we only need to wait for the work to be started, - * if we allocated it on-stack. We use the same mechanism, if the - * wait bit is set in the bdi_work struct, then threads will not - * clear pending until after they are done. - * - * Note that work == &work_stack if must_wait is true, so we don't - * need to do call_rcu() here ever, since the completion path will - * have done that for us. - */ - if (must_wait || work == &work_stack) { - bdi_wait_on_work_clear(work); - if (work != &work_stack) - call_rcu(&work->rcu_head, bdi_work_free); - } + bdi_alloc_queue_work(bdi, &args); } /* @@ -671,17 +693,16 @@ static inline bool over_bground_thresh(void) * older_than_this takes precedence over nr_to_write. So we'll only write back * all dirty pages if they are all attached to "old" mappings. */ -static long wb_writeback(struct bdi_writeback *wb, long nr_pages, - struct super_block *sb, - enum writeback_sync_modes sync_mode, int for_kupdate) +static long wb_writeback(struct bdi_writeback *wb, + struct wb_writeback_args *args) { struct writeback_control wbc = { .bdi = wb->bdi, - .sb = sb, - .sync_mode = sync_mode, + .sb = args->sb, + .sync_mode = args->sync_mode, .older_than_this = NULL, - .for_kupdate = for_kupdate, - .range_cyclic = 1, + .for_kupdate = args->for_kupdate, + .range_cyclic = args->range_cyclic, }; unsigned long oldest_jif; long wrote = 0; @@ -691,13 +712,18 @@ static long wb_writeback(struct bdi_writeback *wb, long nr_pages, oldest_jif = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); } + if (!wbc.range_cyclic) { + wbc.range_start = 0; + wbc.range_end = LLONG_MAX; + } for (;;) { /* * Don't flush anything for non-integrity writeback where * no nr_pages was given */ - if (!for_kupdate && nr_pages <= 0 && sync_mode == WB_SYNC_NONE) + if (!args->for_kupdate && args->nr_pages <= 0 && + args->sync_mode == WB_SYNC_NONE) break; /* @@ -705,7 +731,8 @@ static long wb_writeback(struct bdi_writeback *wb, long nr_pages, * periodic background writeout and we are below the * background dirty threshold, don't do anything */ - if (for_kupdate && nr_pages <= 0 && !over_bground_thresh()) + if (args->for_kupdate && args->nr_pages <= 0 && + !over_bground_thresh()) break; wbc.more_io = 0; @@ -713,7 +740,7 @@ static long wb_writeback(struct bdi_writeback *wb, long nr_pages, wbc.nr_to_write = MAX_WRITEBACK_PAGES; wbc.pages_skipped = 0; writeback_inodes_wb(wb, &wbc); - nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write; + args->nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write; wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write; /* @@ -731,7 +758,11 @@ static long wb_writeback(struct bdi_writeback *wb, long nr_pages, /* * Return the next bdi_work struct that hasn't been processed by this - * wb thread yet + * wb thread yet. ->seen is initially set for each thread that exists + * for this device, when a thread first notices a piece of work it + * clears its bit. Depending on writeback type, the thread will notify + * completion on either receiving the work (WB_SYNC_NONE) or after + * it is done (WB_SYNC_ALL). */ static struct bdi_work *get_next_work_item(struct backing_dev_info *bdi, struct bdi_writeback *wb) @@ -741,8 +772,9 @@ static struct bdi_work *get_next_work_item(struct backing_dev_info *bdi, rcu_read_lock(); list_for_each_entry_rcu(work, &bdi->work_list, list) { - if (!test_and_clear_bit(wb->nr, &work->seen)) + if (!test_bit(wb->nr, &work->seen)) continue; + clear_bit(wb->nr, &work->seen); ret = work; break; @@ -767,8 +799,16 @@ static long wb_check_old_data_flush(struct bdi_writeback *wb) global_page_state(NR_UNSTABLE_NFS) + (inodes_stat.nr_inodes - inodes_stat.nr_unused); - if (nr_pages) - return wb_writeback(wb, nr_pages, NULL, WB_SYNC_NONE, 1); + if (nr_pages) { + struct wb_writeback_args args = { + .nr_pages = nr_pages, + .sync_mode = WB_SYNC_NONE, + .for_kupdate = 1, + .range_cyclic = 1, + }; + + return wb_writeback(wb, &args); + } return 0; } @@ -780,35 +820,31 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait) { struct backing_dev_info *bdi = wb->bdi; struct bdi_work *work; - long nr_pages, wrote = 0; + long wrote = 0; while ((work = get_next_work_item(bdi, wb)) != NULL) { - enum writeback_sync_modes sync_mode; - - nr_pages = work->nr_pages; + struct wb_writeback_args args = work->args; /* * Override sync mode, in case we must wait for completion */ if (force_wait) - work->sync_mode = sync_mode = WB_SYNC_ALL; - else - sync_mode = work->sync_mode; + work->args.sync_mode = args.sync_mode = WB_SYNC_ALL; /* * If this isn't a data integrity operation, just notify * that we have seen this work and we are now starting it. */ - if (sync_mode == WB_SYNC_NONE) + if (args.sync_mode == WB_SYNC_NONE) wb_clear_pending(wb, work); - wrote += wb_writeback(wb, nr_pages, work->sb, sync_mode, 0); + wrote += wb_writeback(wb, &args); /* * This is a data integrity writeback, so only do the * notification when we have completed the work. */ - if (sync_mode == WB_SYNC_ALL) + if (args.sync_mode == WB_SYNC_ALL) wb_clear_pending(wb, work); } @@ -849,8 +885,7 @@ int bdi_writeback_task(struct bdi_writeback *wb) } wait_jiffies = msecs_to_jiffies(dirty_writeback_interval * 10); - set_current_state(TASK_INTERRUPTIBLE); - schedule_timeout(wait_jiffies); + schedule_timeout_interruptible(wait_jiffies); try_to_freeze(); } @@ -858,67 +893,28 @@ int bdi_writeback_task(struct bdi_writeback *wb) } /* - * Schedule writeback for all backing devices. Expensive! If this is a data - * integrity operation, writeback will be complete when this returns. If - * we are simply called for WB_SYNC_NONE, then writeback will merely be - * scheduled to run. + * Schedule writeback for all backing devices. This does WB_SYNC_NONE + * writeback, for integrity writeback see bdi_sync_writeback(). */ -static void bdi_writeback_all(struct writeback_control *wbc) +static void bdi_writeback_all(struct super_block *sb, long nr_pages) { - const bool must_wait = wbc->sync_mode == WB_SYNC_ALL; + struct wb_writeback_args args = { + .sb = sb, + .nr_pages = nr_pages, + .sync_mode = WB_SYNC_NONE, + }; struct backing_dev_info *bdi; - struct bdi_work *work; - LIST_HEAD(list); - -restart: - spin_lock(&bdi_lock); - list_for_each_entry(bdi, &bdi_list, bdi_list) { - struct bdi_work *work; + rcu_read_lock(); + list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { if (!bdi_has_dirty_io(bdi)) continue; - /* - * If work allocation fails, do the writes inline. We drop - * the lock and restart the list writeout. This should be OK, - * since this happens rarely and because the writeout should - * eventually make more free memory available. - */ - work = bdi_alloc_work(wbc); - if (!work) { - struct writeback_control __wbc; - - /* - * Not a data integrity writeout, just continue - */ - if (!must_wait) - continue; - - spin_unlock(&bdi_lock); - __wbc = *wbc; - __wbc.bdi = bdi; - writeback_inodes_wbc(&__wbc); - goto restart; - } - if (must_wait) - list_add_tail(&work->wait_list, &list); - - bdi_queue_work(bdi, work); + bdi_alloc_queue_work(bdi, &args); } - spin_unlock(&bdi_lock); - - /* - * If this is for WB_SYNC_ALL, wait for pending work to complete - * before returning. - */ - while (!list_empty(&list)) { - work = list_entry(list.next, struct bdi_work, wait_list); - list_del(&work->wait_list); - bdi_wait_on_work_clear(work); - call_rcu(&work->rcu_head, bdi_work_free); - } + rcu_read_unlock(); } /* @@ -927,17 +923,10 @@ restart: */ void wakeup_flusher_threads(long nr_pages) { - struct writeback_control wbc = { - .sync_mode = WB_SYNC_NONE, - .older_than_this = NULL, - .range_cyclic = 1, - }; - if (nr_pages == 0) nr_pages = global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS); - wbc.nr_to_write = nr_pages; - bdi_writeback_all(&wbc); + bdi_writeback_all(NULL, nr_pages); } static noinline void block_dump___mark_inode_dirty(struct inode *inode) @@ -1084,7 +1073,7 @@ EXPORT_SYMBOL(__mark_inode_dirty); * on the writer throttling path, and we get decent balancing between many * throttled threads: we don't want them all piling up on inode_sync_wait. */ -static void wait_sb_inodes(struct writeback_control *wbc) +static void wait_sb_inodes(struct super_block *sb) { struct inode *inode, *old_inode = NULL; @@ -1092,7 +1081,7 @@ static void wait_sb_inodes(struct writeback_control *wbc) * We need to be protected against the filesystem going from * r/o to r/w or vice versa. */ - WARN_ON(!rwsem_is_locked(&wbc->sb->s_umount)); + WARN_ON(!rwsem_is_locked(&sb->s_umount)); spin_lock(&inode_lock); @@ -1103,7 +1092,7 @@ static void wait_sb_inodes(struct writeback_control *wbc) * In which case, the inode may not be on the dirty list, but * we still have to wait for that writeout. */ - list_for_each_entry(inode, &wbc->sb->s_inodes, i_sb_list) { + list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { struct address_space *mapping; if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW)) @@ -1143,14 +1132,8 @@ static void wait_sb_inodes(struct writeback_control *wbc) * for IO completion of submitted IO. The number of pages submitted is * returned. */ -long writeback_inodes_sb(struct super_block *sb) +void writeback_inodes_sb(struct super_block *sb) { - struct writeback_control wbc = { - .sb = sb, - .sync_mode = WB_SYNC_NONE, - .range_start = 0, - .range_end = LLONG_MAX, - }; unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY); unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS); long nr_to_write; @@ -1158,9 +1141,7 @@ long writeback_inodes_sb(struct super_block *sb) nr_to_write = nr_dirty + nr_unstable + (inodes_stat.nr_inodes - inodes_stat.nr_unused); - wbc.nr_to_write = nr_to_write; - bdi_writeback_all(&wbc); - return nr_to_write - wbc.nr_to_write; + bdi_writeback_all(sb, nr_to_write); } EXPORT_SYMBOL(writeback_inodes_sb); @@ -1171,20 +1152,10 @@ EXPORT_SYMBOL(writeback_inodes_sb); * This function writes and waits on any dirty inode belonging to this * super_block. The number of pages synced is returned. */ -long sync_inodes_sb(struct super_block *sb) +void sync_inodes_sb(struct super_block *sb) { - struct writeback_control wbc = { - .sb = sb, - .sync_mode = WB_SYNC_ALL, - .range_start = 0, - .range_end = LLONG_MAX, - }; - long nr_to_write = LONG_MAX; /* doesn't actually matter */ - - wbc.nr_to_write = nr_to_write; - bdi_writeback_all(&wbc); - wait_sb_inodes(&wbc); - return nr_to_write - wbc.nr_to_write; + bdi_sync_writeback(sb->s_bdi, sb); + wait_sb_inodes(sb); } EXPORT_SYMBOL(sync_inodes_sb); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 4567db6f943..e5dbecd87b0 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -894,6 +894,8 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) if (err) goto err_put_conn; + sb->s_bdi = &fc->bdi; + /* Handle umasking inside the fuse code */ if (sb->s_flags & MS_POSIXACL) fc->dont_mask = 1; diff --git a/fs/inode.c b/fs/inode.c index ae7b67e4866..b2ba83d2c4e 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -182,9 +182,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) if (sb->s_bdev) { struct backing_dev_info *bdi; - bdi = sb->s_bdev->bd_inode_backing_dev_info; - if (!bdi) - bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info; + bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info; mapping->backing_dev_info = bdi; } inode->i_private = NULL; diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 7b4088b2364..0df600e9162 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -220,7 +220,6 @@ static int journal_submit_inode_data_buffers(struct address_space *mapping) .nr_to_write = mapping->nrpages * 2, .range_start = 0, .range_end = i_size_read(mapping->host), - .for_writepages = 1, }; ret = generic_writepages(mapping, &wbc); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 867f7050453..de935692d40 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1918,6 +1918,8 @@ static inline void nfs_initialise_sb(struct super_block *sb) if (server->flags & NFS_MOUNT_NOAC) sb->s_flags |= MS_SYNCHRONOUS; + sb->s_bdi = &server->backing_dev_info; + nfs_super_set_maxbytes(sb, server->maxfilesize); } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 120acadc6a8..53eb26c16b5 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1490,7 +1490,6 @@ static int nfs_write_mapping(struct address_space *mapping, int how) .nr_to_write = LONG_MAX, .range_start = 0, .range_end = LLONG_MAX, - .for_writepages = 1, }; return __nfs_write_mapping(mapping, &wbc, how); diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index d4168e269c5..ad391a8c3e7 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -591,9 +591,7 @@ int init_nilfs(struct the_nilfs *nilfs, struct nilfs_sb_info *sbi, char *data) nilfs->ns_mount_state = le16_to_cpu(sbp->s_state); - bdi = nilfs->ns_bdev->bd_inode_backing_dev_info; - if (!bdi) - bdi = nilfs->ns_bdev->bd_inode->i_mapping->backing_dev_info; + bdi = nilfs->ns_bdev->bd_inode->i_mapping->backing_dev_info; nilfs->ns_bdi = bdi ? : &default_backing_dev_info; /* Finding last segment */ diff --git a/fs/super.c b/fs/super.c index 9cda337ddae..b03fea8fbfb 100644 --- a/fs/super.c +++ b/fs/super.c @@ -707,6 +707,12 @@ static int set_bdev_super(struct super_block *s, void *data) { s->s_bdev = data; s->s_dev = s->s_bdev->bd_dev; + + /* + * We set the bdi here to the queue backing, file systems can + * overwrite this in ->fill_super() + */ + s->s_bdi = &bdev_get_queue(s->s_bdev)->backing_dev_info; return 0; } diff --git a/fs/sync.c b/fs/sync.c index 192340930bb..c08467a5d7c 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -27,6 +27,13 @@ */ static int __sync_filesystem(struct super_block *sb, int wait) { + /* + * This should be safe, as we require bdi backing to actually + * write out data in the first place + */ + if (!sb->s_bdi) + return 0; + /* Avoid doing twice syncing and cache pruning for quota sync */ if (!wait) { writeout_quota_sb(sb, -1); @@ -101,7 +108,7 @@ restart: spin_unlock(&sb_lock); down_read(&sb->s_umount); - if (!(sb->s_flags & MS_RDONLY) && sb->s_root) + if (!(sb->s_flags & MS_RDONLY) && sb->s_root && sb->s_bdi) __sync_filesystem(sb, wait); up_read(&sb->s_umount); diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c index 1c8991b0db1..ee1ce68fd98 100644 --- a/fs/ubifs/budget.c +++ b/fs/ubifs/budget.c @@ -54,29 +54,15 @@ * @nr_to_write: how many dirty pages to write-back * * This function shrinks UBIFS liability by means of writing back some amount - * of dirty inodes and their pages. Returns the amount of pages which were - * written back. The returned value does not include dirty inodes which were - * synchronized. + * of dirty inodes and their pages. * * Note, this function synchronizes even VFS inodes which are locked * (@i_mutex) by the caller of the budgeting function, because write-back does * not touch @i_mutex. */ -static int shrink_liability(struct ubifs_info *c, int nr_to_write) +static void shrink_liability(struct ubifs_info *c, int nr_to_write) { - int nr_written; - - nr_written = writeback_inodes_sb(c->vfs_sb); - if (!nr_written) { - /* - * Re-try again but wait on pages/inodes which are being - * written-back concurrently (e.g., by pdflush). - */ - nr_written = sync_inodes_sb(c->vfs_sb); - } - - dbg_budg("%d pages were written back", nr_written); - return nr_written; + writeback_inodes_sb(c->vfs_sb); } /** diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 51763aa8f4d..c4af069df1a 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1980,6 +1980,7 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent) if (err) goto out_bdi; + sb->s_bdi = &c->bdi; sb->s_fs_info = c; sb->s_magic = UBIFS_SUPER_MAGIC; sb->s_blocksize = UBIFS_BLOCK_SIZE; diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index c65e4ce6c3a..1fa3ffb7c93 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -248,7 +248,6 @@ struct acpi_device_perf { /* Wakeup Management */ struct acpi_device_wakeup_flags { u8 valid:1; /* Can successfully enable wakeup? */ - u8 prepared:1; /* Has the wake-up capability been enabled? */ u8 run_wake:1; /* Run-Wake GPE devices */ }; @@ -263,6 +262,7 @@ struct acpi_device_wakeup { struct acpi_handle_list resources; struct acpi_device_wakeup_state state; struct acpi_device_wakeup_flags flags; + int prepare_count; }; /* Device */ @@ -369,10 +369,26 @@ int register_acpi_bus_type(struct acpi_bus_type *); int unregister_acpi_bus_type(struct acpi_bus_type *); struct device *acpi_get_physical_device(acpi_handle); +struct acpi_pci_root { + struct list_head node; + struct acpi_device * device; + struct acpi_pci_id id; + struct pci_bus *bus; + u16 segment; + u8 bus_nr; + + u32 osc_support_set; /* _OSC state of support bits */ + u32 osc_control_set; /* _OSC state of control bits */ + u32 osc_control_qry; /* the latest _OSC query result */ + + u32 osc_queried:1; /* has _OSC control been queried? */ +}; + /* helper */ acpi_handle acpi_get_child(acpi_handle, acpi_integer); int acpi_is_root_bridge(acpi_handle); acpi_handle acpi_get_pci_rootbridge_handle(unsigned int, unsigned int); +struct acpi_pci_root *acpi_pci_find_root(acpi_handle handle); #define DEVICE_ACPI_HANDLE(dev) ((acpi_handle)((dev)->archdata.acpi_handle)) #ifdef CONFIG_PM_SLEEP diff --git a/include/asm-generic/pci.h b/include/asm-generic/pci.h index b4326b5466e..26373cff454 100644 --- a/include/asm-generic/pci.h +++ b/include/asm-generic/pci.h @@ -30,7 +30,18 @@ pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res, res->end = region->end; } -#define pcibios_scan_all_fns(a, b) 0 +static inline struct resource * +pcibios_select_root(struct pci_dev *pdev, struct resource *res) +{ + struct resource *root = NULL; + + if (res->flags & IORESOURCE_IO) + root = &ioport_resource; + if (res->flags & IORESOURCE_MEM) + root = &iomem_resource; + + return root; +} #ifndef HAVE_ARCH_PCI_GET_LEGACY_IDE_IRQ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel) diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index f169bcb90b5..0ee33c2e612 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -59,6 +59,7 @@ struct bdi_writeback { struct backing_dev_info { struct list_head bdi_list; + struct rcu_head rcu_head; unsigned long ra_pages; /* max readahead in PAGE_CACHE_SIZE units */ unsigned long state; /* Always use atomic bitops on this */ unsigned int capabilities; /* Device capabilities */ @@ -100,7 +101,7 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...); int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev); void bdi_unregister(struct backing_dev_info *bdi); -void bdi_start_writeback(struct writeback_control *wbc); +void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages); int bdi_writeback_task(struct bdi_writeback *wb); int bdi_has_dirty_io(struct backing_dev_info *bdi); diff --git a/include/linux/fs.h b/include/linux/fs.h index b21cf6b9c80..90162fb3bf0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -655,7 +655,6 @@ struct block_device { int bd_invalidated; struct gendisk * bd_disk; struct list_head bd_list; - struct backing_dev_info *bd_inode_backing_dev_info; /* * Private data. You must have bd_claim'ed the block_device * to use this. NOTE: bd_claim allows an owner to claim @@ -1343,6 +1342,7 @@ struct super_block { int s_nr_dentry_unused; /* # of dentry on lru */ struct block_device *s_bdev; + struct backing_dev_info *s_bdi; struct mtd_info *s_mtd; struct list_head s_instances; struct quota_info s_dquot; /* Diskquota specific options */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 115fb7ba508..f5c7cd343e5 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -241,6 +241,7 @@ struct pci_dev { unsigned int d1_support:1; /* Low power state D1 is supported */ unsigned int d2_support:1; /* Low power state D2 is supported */ unsigned int no_d1d2:1; /* Only allow D0 and D3 */ + unsigned int wakeup_prepared:1; #ifdef CONFIG_PCIEASPM struct pcie_link_state *link_state; /* ASPM link state. */ @@ -273,9 +274,12 @@ struct pci_dev { unsigned int ari_enabled:1; /* ARI forwarding */ unsigned int is_managed:1; unsigned int is_pcie:1; + unsigned int needs_freset:1; /* Dev requires fundamental reset */ unsigned int state_saved:1; unsigned int is_physfn:1; unsigned int is_virtfn:1; + unsigned int reset_fn:1; + unsigned int is_hotplug_bridge:1; pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ @@ -794,6 +798,11 @@ int __must_check __pci_register_driver(struct pci_driver *, struct module *, void pci_unregister_driver(struct pci_driver *dev); void pci_remove_behind_bridge(struct pci_dev *dev); struct pci_driver *pci_dev_driver(const struct pci_dev *dev); +int pci_add_dynid(struct pci_driver *drv, + unsigned int vendor, unsigned int device, + unsigned int subvendor, unsigned int subdevice, + unsigned int class, unsigned int class_mask, + unsigned long driver_data); const struct pci_device_id *pci_match_id(const struct pci_device_id *ids, struct pci_dev *dev); int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, @@ -805,6 +814,8 @@ int pci_cfg_space_size_ext(struct pci_dev *dev); int pci_cfg_space_size(struct pci_dev *dev); unsigned char pci_bus_max_busnr(struct pci_bus *bus); +int pci_set_vga_state(struct pci_dev *pdev, bool decode, + unsigned int command_bits, bool change_bridge); /* kmem_cache style wrapper around pci_alloc_consistent() */ #include <linux/dmapool.h> @@ -1236,6 +1247,9 @@ extern int pci_pci_problems; extern unsigned long pci_cardbus_io_size; extern unsigned long pci_cardbus_mem_size; +extern unsigned long pci_hotplug_io_size; +extern unsigned long pci_hotplug_mem_size; + int pcibios_add_platform_entries(struct pci_dev *dev); void pcibios_disable_device(struct pci_dev *dev); int pcibios_set_pcie_reset_state(struct pci_dev *dev, diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 4391741b99d..652ba797696 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -62,7 +62,8 @@ enum pcie_link_width { }; enum pcie_link_speed { - PCIE_2PT5GB = 0x14, + PCIE_2_5GB = 0x14, + PCIE_5_0GB = 0x15, PCIE_LNK_SPEED_UNKNOWN = 0xFF, }; @@ -226,11 +227,18 @@ struct hotplug_params { #ifdef CONFIG_ACPI #include <acpi/acpi.h> #include <acpi/acpi_bus.h> -extern acpi_status acpi_get_hp_params_from_firmware(struct pci_bus *bus, - struct hotplug_params *hpp); +int pci_get_hp_params(struct pci_dev *dev, struct hotplug_params *hpp); int acpi_get_hp_hw_control_from_firmware(struct pci_dev *dev, u32 flags); int acpi_pci_check_ejectable(struct pci_bus *pbus, acpi_handle handle); -int acpi_pci_detect_ejectable(struct pci_bus *pbus); +int acpi_pci_detect_ejectable(acpi_handle handle); +#else +static inline int pci_get_hp_params(struct pci_dev *dev, + struct hotplug_params *hpp) +{ + return -ENODEV; +} #endif + +void pci_configure_slot(struct pci_dev *dev); #endif diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 0d96be93b92..8975add8668 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2,6 +2,9 @@ * PCI Class, Vendor and Device IDs * * Please keep sorted. + * + * Do not add new entries to this file unless the definitions + * are shared between multiple drivers. */ /* Device classes and subclasses */ diff --git a/include/linux/vgaarb.h b/include/linux/vgaarb.h new file mode 100644 index 00000000000..e81c64af80c --- /dev/null +++ b/include/linux/vgaarb.h @@ -0,0 +1,200 @@ +/* + * vgaarb.c + * + * (C) Copyright 2005 Benjamin Herrenschmidt <benh@kernel.crashing.org> + * (C) Copyright 2007 Paulo R. Zanoni <przanoni@gmail.com> + * (C) Copyright 2007, 2009 Tiago Vignatti <vignatti@freedesktop.org> + */ + +#ifndef LINUX_VGA_H + +#include <asm/vga.h> + +/* Legacy VGA regions */ +#define VGA_RSRC_NONE 0x00 +#define VGA_RSRC_LEGACY_IO 0x01 +#define VGA_RSRC_LEGACY_MEM 0x02 +#define VGA_RSRC_LEGACY_MASK (VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM) +/* Non-legacy access */ +#define VGA_RSRC_NORMAL_IO 0x04 +#define VGA_RSRC_NORMAL_MEM 0x08 + +/* Passing that instead of a pci_dev to use the system "default" + * device, that is the one used by vgacon. Archs will probably + * have to provide their own vga_default_device(); + */ +#define VGA_DEFAULT_DEVICE (NULL) + +/* For use by clients */ + +/** + * vga_set_legacy_decoding + * + * @pdev: pci device of the VGA card + * @decodes: bit mask of what legacy regions the card decodes + * + * Indicates to the arbiter if the card decodes legacy VGA IOs, + * legacy VGA Memory, both, or none. All cards default to both, + * the card driver (fbdev for example) should tell the arbiter + * if it has disabled legacy decoding, so the card can be left + * out of the arbitration process (and can be safe to take + * interrupts at any time. + */ +extern void vga_set_legacy_decoding(struct pci_dev *pdev, + unsigned int decodes); + +/** + * vga_get - acquire & locks VGA resources + * + * @pdev: pci device of the VGA card or NULL for the system default + * @rsrc: bit mask of resources to acquire and lock + * @interruptible: blocking should be interruptible by signals ? + * + * This function acquires VGA resources for the given + * card and mark those resources locked. If the resource requested + * are "normal" (and not legacy) resources, the arbiter will first check + * wether the card is doing legacy decoding for that type of resource. If + * yes, the lock is "converted" into a legacy resource lock. + * The arbiter will first look for all VGA cards that might conflict + * and disable their IOs and/or Memory access, inlcuding VGA forwarding + * on P2P bridges if necessary, so that the requested resources can + * be used. Then, the card is marked as locking these resources and + * the IO and/or Memory accesse are enabled on the card (including + * VGA forwarding on parent P2P bridges if any). + * This function will block if some conflicting card is already locking + * one of the required resources (or any resource on a different bus + * segment, since P2P bridges don't differenciate VGA memory and IO + * afaik). You can indicate wether this blocking should be interruptible + * by a signal (for userland interface) or not. + * Must not be called at interrupt time or in atomic context. + * If the card already owns the resources, the function succeeds. + * Nested calls are supported (a per-resource counter is maintained) + */ + +extern int vga_get(struct pci_dev *pdev, unsigned int rsrc, + int interruptible); + +/** + * vga_get_interruptible + * + * Shortcut to vga_get + */ + +static inline int vga_get_interruptible(struct pci_dev *pdev, + unsigned int rsrc) +{ + return vga_get(pdev, rsrc, 1); +} + +/** + * vga_get_uninterruptible + * + * Shortcut to vga_get + */ + +static inline int vga_get_uninterruptible(struct pci_dev *pdev, + unsigned int rsrc) +{ + return vga_get(pdev, rsrc, 0); +} + +/** + * vga_tryget - try to acquire & lock legacy VGA resources + * + * @pdev: pci devivce of VGA card or NULL for system default + * @rsrc: bit mask of resources to acquire and lock + * + * This function performs the same operation as vga_get(), but + * will return an error (-EBUSY) instead of blocking if the resources + * are already locked by another card. It can be called in any context + */ + +extern int vga_tryget(struct pci_dev *pdev, unsigned int rsrc); + +/** + * vga_put - release lock on legacy VGA resources + * + * @pdev: pci device of VGA card or NULL for system default + * @rsrc: but mask of resource to release + * + * This function releases resources previously locked by vga_get() + * or vga_tryget(). The resources aren't disabled right away, so + * that a subsequence vga_get() on the same card will succeed + * immediately. Resources have a counter, so locks are only + * released if the counter reaches 0. + */ + +extern void vga_put(struct pci_dev *pdev, unsigned int rsrc); + + +/** + * vga_default_device + * + * This can be defined by the platform. The default implementation + * is rather dumb and will probably only work properly on single + * vga card setups and/or x86 platforms. + * + * If your VGA default device is not PCI, you'll have to return + * NULL here. In this case, I assume it will not conflict with + * any PCI card. If this is not true, I'll have to define two archs + * hooks for enabling/disabling the VGA default device if that is + * possible. This may be a problem with real _ISA_ VGA cards, in + * addition to a PCI one. I don't know at this point how to deal + * with that card. Can theirs IOs be disabled at all ? If not, then + * I suppose it's a matter of having the proper arch hook telling + * us about it, so we basically never allow anybody to succeed a + * vga_get()... + */ + +#ifndef __ARCH_HAS_VGA_DEFAULT_DEVICE +extern struct pci_dev *vga_default_device(void); +#endif + +/** + * vga_conflicts + * + * Architectures should define this if they have several + * independant PCI domains that can afford concurrent VGA + * decoding + */ + +#ifndef __ARCH_HAS_VGA_CONFLICT +static inline int vga_conflicts(struct pci_dev *p1, struct pci_dev *p2) +{ + return 1; +} +#endif + +/** + * vga_client_register + * + * @pdev: pci device of the VGA client + * @cookie: client cookie to be used in callbacks + * @irq_set_state: irq state change callback + * @set_vga_decode: vga decode change callback + * + * return value: 0 on success, -1 on failure + * Register a client with the VGA arbitration logic + * + * Clients have two callback mechanisms they can use. + * irq enable/disable callback - + * If a client can't disable its GPUs VGA resources, then we + * need to be able to ask it to turn off its irqs when we + * turn off its mem and io decoding. + * set_vga_decode + * If a client can disable its GPU VGA resource, it will + * get a callback from this to set the encode/decode state + * + * Rationale: we cannot disable VGA decode resources unconditionally + * some single GPU laptops seem to require ACPI or BIOS access to the + * VGA registers to control things like backlights etc. + * Hopefully newer multi-GPU laptops do something saner, and desktops + * won't have any special ACPI for this. + * They driver will get a callback when VGA arbitration is first used + * by userspace since we some older X servers have issues. + */ +int vga_client_register(struct pci_dev *pdev, void *cookie, + void (*irq_set_state)(void *cookie, bool state), + unsigned int (*set_vga_decode)(void *cookie, bool state)); + +#endif /* LINUX_VGA_H */ diff --git a/include/linux/writeback.h b/include/linux/writeback.h index d347632f186..75cf58666ff 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -50,7 +50,6 @@ struct writeback_control { unsigned encountered_congestion:1; /* An output: a queue is full */ unsigned for_kupdate:1; /* A kupdate writeback */ unsigned for_reclaim:1; /* Invoked from the page allocator */ - unsigned for_writepages:1; /* This is a writepages() call */ unsigned range_cyclic:1; /* range_start is cyclic */ unsigned more_io:1; /* more io to be dispatched */ /* @@ -69,8 +68,8 @@ struct writeback_control { */ struct bdi_writeback; int inode_wait(void *); -long writeback_inodes_sb(struct super_block *); -long sync_inodes_sb(struct super_block *); +void writeback_inodes_sb(struct super_block *); +void sync_inodes_sb(struct super_block *); void writeback_inodes_wbc(struct writeback_control *wbc); long wb_do_writeback(struct bdi_writeback *wb, int force_wait); void wakeup_flusher_threads(long nr_pages); diff --git a/include/pcmcia/ss.h b/include/pcmcia/ss.h index 9b4ac9385f5..9a3b4986517 100644 --- a/include/pcmcia/ss.h +++ b/include/pcmcia/ss.h @@ -90,14 +90,14 @@ typedef struct pccard_io_map { u_char map; u_char flags; u_short speed; - u_int start, stop; + phys_addr_t start, stop; } pccard_io_map; typedef struct pccard_mem_map { u_char map; u_char flags; u_short speed; - u_long static_start; + phys_addr_t static_start; u_int card_start; struct resource *res; } pccard_mem_map; diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 7d8b5bc7418..8d433c4e370 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -227,7 +227,6 @@ TRACE_EVENT(ext4_da_writepages, __field( char, nonblocking ) __field( char, for_kupdate ) __field( char, for_reclaim ) - __field( char, for_writepages ) __field( char, range_cyclic ) ), @@ -241,16 +240,15 @@ TRACE_EVENT(ext4_da_writepages, __entry->nonblocking = wbc->nonblocking; __entry->for_kupdate = wbc->for_kupdate; __entry->for_reclaim = wbc->for_reclaim; - __entry->for_writepages = wbc->for_writepages; __entry->range_cyclic = wbc->range_cyclic; ), - TP_printk("dev %s ino %lu nr_t_write %ld pages_skipped %ld range_start %llu range_end %llu nonblocking %d for_kupdate %d for_reclaim %d for_writepages %d range_cyclic %d", + TP_printk("dev %s ino %lu nr_t_write %ld pages_skipped %ld range_start %llu range_end %llu nonblocking %d for_kupdate %d for_reclaim %d range_cyclic %d", jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->nr_to_write, __entry->pages_skipped, __entry->range_start, __entry->range_end, __entry->nonblocking, __entry->for_kupdate, __entry->for_reclaim, - __entry->for_writepages, __entry->range_cyclic) + __entry->range_cyclic) ); TRACE_EVENT(ext4_da_writepages_result, diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 6bb59f70740..1a631ba684a 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -91,7 +91,9 @@ extern int sysctl_nr_trim_pages; #ifdef CONFIG_RCU_TORTURE_TEST extern int rcutorture_runnable; #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */ +#ifdef CONFIG_BLOCK extern int blk_iopoll_enabled; +#endif /* Constants used for minimum and maximum */ #ifdef CONFIG_DETECT_SOFTLOCKUP @@ -998,6 +1000,7 @@ static struct ctl_table kern_table[] = { .proc_handler = &proc_dointvec, }, #endif +#ifdef CONFIG_BLOCK { .ctl_name = CTL_UNNUMBERED, .procname = "blk_iopoll", @@ -1006,6 +1009,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = &proc_dointvec, }, +#endif /* * NOTE: do not add new entries to this table unless you have read * Documentation/sysctl/ctl_unnumbered.txt diff --git a/mm/backing-dev.c b/mm/backing-dev.c index d3ca0dac111..3d3accb1f80 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -26,6 +26,12 @@ struct backing_dev_info default_backing_dev_info = { EXPORT_SYMBOL_GPL(default_backing_dev_info); static struct class *bdi_class; + +/* + * bdi_lock protects updates to bdi_list and bdi_pending_list, as well as + * reader side protection for bdi_pending_list. bdi_list has RCU reader side + * locking. + */ DEFINE_SPINLOCK(bdi_lock); LIST_HEAD(bdi_list); LIST_HEAD(bdi_pending_list); @@ -284,9 +290,9 @@ static int bdi_start_fn(void *ptr) /* * Add us to the active bdi_list */ - spin_lock(&bdi_lock); - list_add(&bdi->bdi_list, &bdi_list); - spin_unlock(&bdi_lock); + spin_lock_bh(&bdi_lock); + list_add_rcu(&bdi->bdi_list, &bdi_list); + spin_unlock_bh(&bdi_lock); bdi_task_init(bdi, wb); @@ -389,7 +395,7 @@ static int bdi_forker_task(void *ptr) if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list)) wb_do_writeback(me, 0); - spin_lock(&bdi_lock); + spin_lock_bh(&bdi_lock); /* * Check if any existing bdi's have dirty data without @@ -410,7 +416,7 @@ static int bdi_forker_task(void *ptr) if (list_empty(&bdi_pending_list)) { unsigned long wait; - spin_unlock(&bdi_lock); + spin_unlock_bh(&bdi_lock); wait = msecs_to_jiffies(dirty_writeback_interval * 10); schedule_timeout(wait); try_to_freeze(); @@ -426,7 +432,7 @@ static int bdi_forker_task(void *ptr) bdi = list_entry(bdi_pending_list.next, struct backing_dev_info, bdi_list); list_del_init(&bdi->bdi_list); - spin_unlock(&bdi_lock); + spin_unlock_bh(&bdi_lock); wb = &bdi->wb; wb->task = kthread_run(bdi_start_fn, wb, "flush-%s", @@ -445,9 +451,9 @@ static int bdi_forker_task(void *ptr) * a chance to flush other bdi's to free * memory. */ - spin_lock(&bdi_lock); + spin_lock_bh(&bdi_lock); list_add_tail(&bdi->bdi_list, &bdi_pending_list); - spin_unlock(&bdi_lock); + spin_unlock_bh(&bdi_lock); bdi_flush_io(bdi); } @@ -456,6 +462,24 @@ static int bdi_forker_task(void *ptr) return 0; } +static void bdi_add_to_pending(struct rcu_head *head) +{ + struct backing_dev_info *bdi; + + bdi = container_of(head, struct backing_dev_info, rcu_head); + INIT_LIST_HEAD(&bdi->bdi_list); + + spin_lock(&bdi_lock); + list_add_tail(&bdi->bdi_list, &bdi_pending_list); + spin_unlock(&bdi_lock); + + /* + * We are now on the pending list, wake up bdi_forker_task() + * to finish the job and add us back to the active bdi_list + */ + wake_up_process(default_backing_dev_info.wb.task); +} + /* * Add the default flusher task that gets created for any bdi * that has dirty data pending writeout @@ -478,16 +502,29 @@ void static bdi_add_default_flusher_task(struct backing_dev_info *bdi) * waiting for previous additions to finish. */ if (!test_and_set_bit(BDI_pending, &bdi->state)) { - list_move_tail(&bdi->bdi_list, &bdi_pending_list); + list_del_rcu(&bdi->bdi_list); /* - * We are now on the pending list, wake up bdi_forker_task() - * to finish the job and add us back to the active bdi_list + * We must wait for the current RCU period to end before + * moving to the pending list. So schedule that operation + * from an RCU callback. */ - wake_up_process(default_backing_dev_info.wb.task); + call_rcu(&bdi->rcu_head, bdi_add_to_pending); } } +/* + * Remove bdi from bdi_list, and ensure that it is no longer visible + */ +static void bdi_remove_from_list(struct backing_dev_info *bdi) +{ + spin_lock_bh(&bdi_lock); + list_del_rcu(&bdi->bdi_list); + spin_unlock_bh(&bdi_lock); + + synchronize_rcu(); +} + int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...) { @@ -506,9 +543,9 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, goto exit; } - spin_lock(&bdi_lock); - list_add_tail(&bdi->bdi_list, &bdi_list); - spin_unlock(&bdi_lock); + spin_lock_bh(&bdi_lock); + list_add_tail_rcu(&bdi->bdi_list, &bdi_list); + spin_unlock_bh(&bdi_lock); bdi->dev = dev; @@ -526,9 +563,7 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, wb->task = NULL; ret = -ENOMEM; - spin_lock(&bdi_lock); - list_del(&bdi->bdi_list); - spin_unlock(&bdi_lock); + bdi_remove_from_list(bdi); goto exit; } } @@ -565,9 +600,7 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi) /* * Make sure nobody finds us on the bdi_list anymore */ - spin_lock(&bdi_lock); - list_del(&bdi->bdi_list); - spin_unlock(&bdi_lock); + bdi_remove_from_list(bdi); /* * Finally, kill the kernel threads. We don't need to be RCU @@ -599,6 +632,7 @@ int bdi_init(struct backing_dev_info *bdi) bdi->max_ratio = 100; bdi->max_prop_frac = PROP_FRAC_BASE; spin_lock_init(&bdi->wb_lock); + INIT_RCU_HEAD(&bdi->rcu_head); INIT_LIST_HEAD(&bdi->bdi_list); INIT_LIST_HEAD(&bdi->wb_list); INIT_LIST_HEAD(&bdi->work_list); @@ -634,7 +668,19 @@ void bdi_destroy(struct backing_dev_info *bdi) { int i; - WARN_ON(bdi_has_dirty_io(bdi)); + /* + * Splice our entries to the default_backing_dev_info, if this + * bdi disappears + */ + if (bdi_has_dirty_io(bdi)) { + struct bdi_writeback *dst = &default_backing_dev_info.wb; + + spin_lock(&inode_lock); + list_splice(&bdi->wb.b_dirty, &dst->b_dirty); + list_splice(&bdi->wb.b_io, &dst->b_io); + list_splice(&bdi->wb.b_more_io, &dst->b_more_io); + spin_unlock(&inode_lock); + } bdi_unregister(bdi); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index dd73d29c15a..1eea4fa0d41 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -315,7 +315,7 @@ int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) { int ret = 0; - spin_lock(&bdi_lock); + spin_lock_bh(&bdi_lock); if (min_ratio > bdi->max_ratio) { ret = -EINVAL; } else { @@ -327,7 +327,7 @@ int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) ret = -EINVAL; } } - spin_unlock(&bdi_lock); + spin_unlock_bh(&bdi_lock); return ret; } @@ -339,14 +339,14 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio) if (max_ratio > 100) return -EINVAL; - spin_lock(&bdi_lock); + spin_lock_bh(&bdi_lock); if (bdi->min_ratio > max_ratio) { ret = -EINVAL; } else { bdi->max_ratio = max_ratio; bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100; } - spin_unlock(&bdi_lock); + spin_unlock_bh(&bdi_lock); return ret; } @@ -582,16 +582,8 @@ static void balance_dirty_pages(struct address_space *mapping) if ((laptop_mode && pages_written) || (!laptop_mode && ((nr_writeback = global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS)) - > background_thresh))) { - struct writeback_control wbc = { - .bdi = bdi, - .sync_mode = WB_SYNC_NONE, - .nr_to_write = nr_writeback, - }; - - - bdi_start_writeback(&wbc); - } + > background_thresh))) + bdi_start_writeback(bdi, nr_writeback); } void set_page_dirty_balance(struct page *page, int page_mkwrite) @@ -1020,12 +1012,10 @@ int do_writepages(struct address_space *mapping, struct writeback_control *wbc) if (wbc->nr_to_write <= 0) return 0; - wbc->for_writepages = 1; if (mapping->a_ops->writepages) ret = mapping->a_ops->writepages(mapping, wbc); else ret = generic_writepages(mapping, wbc); - wbc->for_writepages = 0; return ret; } diff --git a/mm/slub.c b/mm/slub.c index a5789b91d17..0a216aae227 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1071,6 +1071,8 @@ static inline unsigned long kmem_cache_flags(unsigned long objsize, } #define slub_debug 0 +#define disable_higher_order_debug 0 + static inline unsigned long slabs_node(struct kmem_cache *s, int node) { return 0; } static inline unsigned long node_nr_slabs(struct kmem_cache_node *n) |