diff options
Diffstat (limited to 'Documentation')
| -rw-r--r-- | Documentation/ABI/testing/sysfs-bus-pci | 10 | ||||
| -rw-r--r-- | Documentation/PCI/pci-error-recovery.txt | 119 | ||||
| -rw-r--r-- | Documentation/vgaarbiter.txt | 194 |
3 files changed, 281 insertions, 42 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 |