linux-sg2042/drivers/rapidio/rio-scan.c

1201 lines
32 KiB
C
Raw Normal View History

/*
* RapidIO enumeration and discovery support
*
* Copyright 2005 MontaVista Software, Inc.
* Matt Porter <mporter@kernel.crashing.org>
*
* Copyright 2009 Integrated Device Technology, Inc.
* Alex Bounine <alexandre.bounine@idt.com>
* - Added Port-Write/Error Management initialization and handling
*
* Copyright 2009 Sysgo AG
* Thomas Moll <thomas.moll@sysgo.com>
* - Added Input- Output- enable functionality, to allow full communication
*
* 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.
*/
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/delay.h>
#include <linux/dma-mapping.h>
#include <linux/init.h>
#include <linux/rio.h>
#include <linux/rio_drv.h>
#include <linux/rio_ids.h>
#include <linux/rio_regs.h>
#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/timer.h>
rapidio: fix blocking wait for discovery ready The following set of patches provides modifications targeting support of multiple RapidIO master port (mport) devices on a CPU-side of RapidIO-capable board. While the RapidIO subsystem code has definitions suitable for multi-controller/multi-net support, the existing implementation cannot be considered ready for multiple mport configurations. =========== NOTES: ============= a) The patches below do not address RapidIO side view of multiport processing elements defined in Part 6 of RapidIO spec Rev.2.1 (section 6.4.1). These devices have Base Device ID CSR (0x60) and Component Tag CSR (0x6C) shared by all SRIO ports. For example, Freescale's P4080, P3041 and P5020 have a dual-port SRIO controller implemented according the specification. Enumeration/discovery of such devices from RapidIO side may require device-specific fixups. b) Devices referenced above may also require implementation specific code to setup a host device ID for mport device. These operations are not addressed by patches in this package. ================================= Details about provided patches: 1. Fix blocking wait for discovery ready While it does not happen on PowerPC based platforms, there is possibility of stalled CPU warning dump on x86 based platforms that run RapidIO discovery process if they wait too long for being enumerated. Currently users can avoid it by disabling the soft-lockup detector using "nosoftlockup" kernel parameter OR by ensuring that enumeration is completed before soft-lockup is detected. This patch eliminates blocking wait and keeps a scheduler running. It also is required for patch 3 below which introduces asynchronous discovery process. 2. Use device lists handling on per-net basis This patch allows to correctly support multiple RapidIO nets and resolves possible issues caused by using single global list of devices during RapidIO system enumeration/discovery. The most common sign of existing issue is incorrect contents of switch routing tables in systems with multiple mport controllers while single-port configuration performs as expected. The patch does not eliminate the global RapidIO device list but changes some routines in enumeration/discovery to use per-net device lists instead. This way compatibility with upper layer RIO routines is preserved. 3. Run discovery as an asynchronous process This patch modifies RapidIO initialization routine to asynchronously run the discovery process for each corresponding mport. This allows having an arbitrary order of enumerating and discovering mports without creating a deadlock situation if an enumerator port was registered after a discovering one. On boards with multiple discovering mports it also eliminates order dependency between mports and may reduce total time of RapidIO subsystem initialization. Making netID matching to mportID ensures consistent netID assignment in multiport RapidIO systems with asynchronous discovery process (global counter implementation is affected by race between threads). 4. Rework RIONET to support multiple RIO master ports In the current version of the driver rionet_probe() has comment "XXX Make multi-net safe". Now it is a good time to address this comment. This patch makes RIONET driver multi-net safe/capable by introducing per-net lists of RapidIO network peers. It also enables to register network adapters for all available mport devices. 5. Add destination ID allocation mechanism The patch replaces a single global destination ID counter with per-net allocation mechanism to allow independent destID management for each available RapidIO network. Using bitmap based mechanism instead of counters allows destination ID release and reuse in systems that support hot-swap. This patch: Fix blocking wait loop in the RapidIO discovery routine to avoid warning dumps about stalled CPU on x86 platforms. Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com> Cc: Matt Porter <mporter@kernel.crashing.org> Cc: Li Yang <leoli@freescale.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-05 08:16:04 +08:00
#include <linux/sched.h>
#include <linux/jiffies.h>
#include <linux/slab.h>
#include "rio.h"
static void rio_init_em(struct rio_dev *rdev);
static int next_destid = 0;
static int next_comptag = 1;
static int rio_mport_phys_table[] = {
RIO_EFB_PAR_EP_ID,
RIO_EFB_PAR_EP_REC_ID,
RIO_EFB_SER_EP_ID,
RIO_EFB_SER_EP_REC_ID,
-1,
};
/**
* rio_destid_alloc - Allocate next available destID for given network
* @net: RIO network
*
* Returns next available device destination ID for the specified RIO network.
* Marks allocated ID as one in use.
* Returns RIO_INVALID_DESTID if new destID is not available.
*/
static u16 rio_destid_alloc(struct rio_net *net)
{
int destid;
struct rio_id_table *idtab = &net->destid_table;
spin_lock(&idtab->lock);
destid = find_first_zero_bit(idtab->table, idtab->max);
if (destid < idtab->max) {
set_bit(destid, idtab->table);
destid += idtab->start;
} else
destid = RIO_INVALID_DESTID;
spin_unlock(&idtab->lock);
return (u16)destid;
}
/**
* rio_destid_reserve - Reserve the specivied destID
* @net: RIO network
* @destid: destID to reserve
*
* Tries to reserve the specified destID.
* Returns 0 if successfull.
*/
static int rio_destid_reserve(struct rio_net *net, u16 destid)
{
int oldbit;
struct rio_id_table *idtab = &net->destid_table;
destid -= idtab->start;
spin_lock(&idtab->lock);
oldbit = test_and_set_bit(destid, idtab->table);
spin_unlock(&idtab->lock);
return oldbit;
}
/**
* rio_destid_free - free a previously allocated destID
* @net: RIO network
* @destid: destID to free
*
* Makes the specified destID available for use.
*/
static void rio_destid_free(struct rio_net *net, u16 destid)
{
struct rio_id_table *idtab = &net->destid_table;
destid -= idtab->start;
spin_lock(&idtab->lock);
clear_bit(destid, idtab->table);
spin_unlock(&idtab->lock);
}
/**
* rio_destid_first - return first destID in use
* @net: RIO network
*/
static u16 rio_destid_first(struct rio_net *net)
{
int destid;
struct rio_id_table *idtab = &net->destid_table;
spin_lock(&idtab->lock);
destid = find_first_bit(idtab->table, idtab->max);
if (destid >= idtab->max)
destid = RIO_INVALID_DESTID;
else
destid += idtab->start;
spin_unlock(&idtab->lock);
return (u16)destid;
}
/**
* rio_destid_next - return next destID in use
* @net: RIO network
* @from: destination ID from which search shall continue
*/
static u16 rio_destid_next(struct rio_net *net, u16 from)
{
int destid;
struct rio_id_table *idtab = &net->destid_table;
spin_lock(&idtab->lock);
destid = find_next_bit(idtab->table, idtab->max, from);
if (destid >= idtab->max)
destid = RIO_INVALID_DESTID;
else
destid += idtab->start;
spin_unlock(&idtab->lock);
return (u16)destid;
}
/**
* rio_get_device_id - Get the base/extended device id for a device
* @port: RIO master port
* @destid: Destination ID of device
* @hopcount: Hopcount to device
*
* Reads the base/extended device id from a device. Returns the
* 8/16-bit device ID.
*/
static u16 rio_get_device_id(struct rio_mport *port, u16 destid, u8 hopcount)
{
u32 result;
rio_mport_read_config_32(port, destid, hopcount, RIO_DID_CSR, &result);
return RIO_GET_DID(port->sys_size, result);
}
/**
* rio_set_device_id - Set the base/extended device id for a device
* @port: RIO master port
* @destid: Destination ID of device
* @hopcount: Hopcount to device
* @did: Device ID value to be written
*
* Writes the base/extended device id from a device.
*/
static void rio_set_device_id(struct rio_mport *port, u16 destid, u8 hopcount, u16 did)
{
rio_mport_write_config_32(port, destid, hopcount, RIO_DID_CSR,
RIO_SET_DID(port->sys_size, did));
}
/**
* rio_local_set_device_id - Set the base/extended device id for a port
* @port: RIO master port
* @did: Device ID value to be written
*
* Writes the base/extended device id from a device.
*/
static void rio_local_set_device_id(struct rio_mport *port, u16 did)
{
rio_local_write_config_32(port, RIO_DID_CSR, RIO_SET_DID(port->sys_size,
did));
}
/**
* rio_clear_locks- Release all host locks and signal enumeration complete
* @net: RIO network to run on
*
* Marks the component tag CSR on each device with the enumeration
* complete flag. When complete, it then release the host locks on
* each device. Returns 0 on success or %-EINVAL on failure.
*/
static int rio_clear_locks(struct rio_net *net)
{
struct rio_mport *port = net->hport;
struct rio_dev *rdev;
u32 result;
int ret = 0;
/* Release host device id locks */
rio_local_write_config_32(port, RIO_HOST_DID_LOCK_CSR,
port->host_deviceid);
rio_local_read_config_32(port, RIO_HOST_DID_LOCK_CSR, &result);
if ((result & 0xffff) != 0xffff) {
printk(KERN_INFO
"RIO: badness when releasing host lock on master port, result %8.8x\n",
result);
ret = -EINVAL;
}
list_for_each_entry(rdev, &net->devices, net_list) {
rio_write_config_32(rdev, RIO_HOST_DID_LOCK_CSR,
port->host_deviceid);
rio_read_config_32(rdev, RIO_HOST_DID_LOCK_CSR, &result);
if ((result & 0xffff) != 0xffff) {
printk(KERN_INFO
"RIO: badness when releasing host lock on vid %4.4x did %4.4x\n",
rdev->vid, rdev->did);
ret = -EINVAL;
}
/* Mark device as discovered and enable master */
rio_read_config_32(rdev,
rdev->phys_efptr + RIO_PORT_GEN_CTL_CSR,
&result);
result |= RIO_PORT_GEN_DISCOVERED | RIO_PORT_GEN_MASTER;
rio_write_config_32(rdev,
rdev->phys_efptr + RIO_PORT_GEN_CTL_CSR,
result);
}
return ret;
}
/**
* rio_enum_host- Set host lock and initialize host destination ID
* @port: Master port to issue transaction
*
* Sets the local host master port lock and destination ID register
* with the host device ID value. The host device ID value is provided
* by the platform. Returns %0 on success or %-1 on failure.
*/
static int rio_enum_host(struct rio_mport *port)
{
u32 result;
/* Set master port host device id lock */
rio_local_write_config_32(port, RIO_HOST_DID_LOCK_CSR,
port->host_deviceid);
rio_local_read_config_32(port, RIO_HOST_DID_LOCK_CSR, &result);
if ((result & 0xffff) != port->host_deviceid)
return -1;
/* Set master port destid and init destid ctr */
rio_local_set_device_id(port, port->host_deviceid);
return 0;
}
/**
* rio_device_has_destid- Test if a device contains a destination ID register
* @port: Master port to issue transaction
* @src_ops: RIO device source operations
* @dst_ops: RIO device destination operations
*
* Checks the provided @src_ops and @dst_ops for the necessary transaction
* capabilities that indicate whether or not a device will implement a
* destination ID register. Returns 1 if true or 0 if false.
*/
static int rio_device_has_destid(struct rio_mport *port, int src_ops,
int dst_ops)
{
u32 mask = RIO_OPS_READ | RIO_OPS_WRITE | RIO_OPS_ATOMIC_TST_SWP | RIO_OPS_ATOMIC_INC | RIO_OPS_ATOMIC_DEC | RIO_OPS_ATOMIC_SET | RIO_OPS_ATOMIC_CLR;
return !!((src_ops | dst_ops) & mask);
}
/**
* rio_release_dev- Frees a RIO device struct
* @dev: LDM device associated with a RIO device struct
*
* Gets the RIO device struct associated a RIO device struct.
* The RIO device struct is freed.
*/
static void rio_release_dev(struct device *dev)
{
struct rio_dev *rdev;
rdev = to_rio_dev(dev);
kfree(rdev);
}
/**
* rio_is_switch- Tests if a RIO device has switch capabilities
* @rdev: RIO device
*
* Gets the RIO device Processing Element Features register
* contents and tests for switch capabilities. Returns 1 if
* the device is a switch or 0 if it is not a switch.
* The RIO device struct is freed.
*/
static int rio_is_switch(struct rio_dev *rdev)
{
if (rdev->pef & RIO_PEF_SWITCH)
return 1;
return 0;
}
/**
* rio_setup_device- Allocates and sets up a RIO device
* @net: RIO network
* @port: Master port to send transactions
* @destid: Current destination ID
* @hopcount: Current hopcount
* @do_enum: Enumeration/Discovery mode flag
*
* Allocates a RIO device and configures fields based on configuration
* space contents. If device has a destination ID register, a destination
* ID is either assigned in enumeration mode or read from configuration
* space in discovery mode. If the device has switch capabilities, then
* a switch is allocated and configured appropriately. Returns a pointer
* to a RIO device on success or NULL on failure.
*
*/
static struct rio_dev *rio_setup_device(struct rio_net *net,
struct rio_mport *port, u16 destid,
u8 hopcount, int do_enum)
{
int ret = 0;
struct rio_dev *rdev;
struct rio_switch *rswitch = NULL;
int result, rdid;
size_t size;
u32 swpinfo = 0;
size = sizeof(struct rio_dev);
if (rio_mport_read_config_32(port, destid, hopcount,
RIO_PEF_CAR, &result))
return NULL;
if (result & (RIO_PEF_SWITCH | RIO_PEF_MULTIPORT)) {
rio_mport_read_config_32(port, destid, hopcount,
RIO_SWP_INFO_CAR, &swpinfo);
if (result & RIO_PEF_SWITCH) {
size += (RIO_GET_TOTAL_PORTS(swpinfo) *
sizeof(rswitch->nextdev[0])) + sizeof(*rswitch);
}
}
rdev = kzalloc(size, GFP_KERNEL);
if (!rdev)
return NULL;
rdev->net = net;
rdev->pef = result;
rdev->swpinfo = swpinfo;
rio_mport_read_config_32(port, destid, hopcount, RIO_DEV_ID_CAR,
&result);
rdev->did = result >> 16;
rdev->vid = result & 0xffff;
rio_mport_read_config_32(port, destid, hopcount, RIO_DEV_INFO_CAR,
&rdev->device_rev);
rio_mport_read_config_32(port, destid, hopcount, RIO_ASM_ID_CAR,
&result);
rdev->asm_did = result >> 16;
rdev->asm_vid = result & 0xffff;
rio_mport_read_config_32(port, destid, hopcount, RIO_ASM_INFO_CAR,
&result);
rdev->asm_rev = result >> 16;
if (rdev->pef & RIO_PEF_EXT_FEATURES) {
rdev->efptr = result & 0xffff;
rdev->phys_efptr = rio_mport_get_physefb(port, 0, destid,
hopcount);
rdev->em_efptr = rio_mport_get_feature(port, 0, destid,
hopcount, RIO_EFB_ERR_MGMNT);
}
rio_mport_read_config_32(port, destid, hopcount, RIO_SRC_OPS_CAR,
&rdev->src_ops);
rio_mport_read_config_32(port, destid, hopcount, RIO_DST_OPS_CAR,
&rdev->dst_ops);
if (do_enum) {
/* Assign component tag to device */
if (next_comptag >= 0x10000) {
pr_err("RIO: Component Tag Counter Overflow\n");
goto cleanup;
}
rio_mport_write_config_32(port, destid, hopcount,
RIO_COMPONENT_TAG_CSR, next_comptag);
rdev->comp_tag = next_comptag++;
rapidio: convert switch drivers to modules Rework RapidIO switch drivers to add an option to build them as loadable kernel modules. This patch removes RapidIO-specific vmlinux section and converts switch drivers to be compatible with LDM driver registration method. To simplify registration of device-specific callback routines this patch introduces rio_switch_ops data structure. The sw_sysfs() callback is removed from the list of device-specific operations because under the new structure its functions can be handled by switch driver's probe() and remove() routines. If a specific switch device driver is not loaded the RapidIO subsystem core will use default standard-based operations to configure a switch. Because the current implementation of RapidIO enumeration/discovery method relies on availability of device-specific operations for error management, switch device drivers must be loaded before the RapidIO enumeration/discovery starts. This patch also moves several common routines from enumeration/discovery module into the RapidIO core code to make switch-specific operations accessible to all components of RapidIO subsystem. Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com> Cc: Matt Porter <mporter@kernel.crashing.org> Cc: Li Yang <leoli@freescale.com> Cc: Kumar Gala <galak@kernel.crashing.org> Cc: Andre van Herk <andre.van.herk@Prodrive.nl> Cc: Micha Nelissen <micha.nelissen@Prodrive.nl> Cc: Stef van Os <stef.van.os@Prodrive.nl> Cc: Jean Delvare <jdelvare@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-04 06:08:50 +08:00
rdev->do_enum = true;
} else {
rio_mport_read_config_32(port, destid, hopcount,
RIO_COMPONENT_TAG_CSR,
&rdev->comp_tag);
}
if (rio_device_has_destid(port, rdev->src_ops, rdev->dst_ops)) {
if (do_enum) {
rio_set_device_id(port, destid, hopcount, next_destid);
rdev->destid = next_destid;
next_destid = rio_destid_alloc(net);
} else
rdev->destid = rio_get_device_id(port, destid, hopcount);
rdev->hopcount = 0xff;
} else {
/* Switch device has an associated destID which
* will be adjusted later
*/
rdev->destid = destid;
rdev->hopcount = hopcount;
}
/* If a PE has both switch and other functions, show it as a switch */
if (rio_is_switch(rdev)) {
rswitch = rdev->rswitch;
rswitch->switchid = rdev->comp_tag & RIO_CTAG_UDEVID;
rswitch->port_ok = 0;
rapidio: convert switch drivers to modules Rework RapidIO switch drivers to add an option to build them as loadable kernel modules. This patch removes RapidIO-specific vmlinux section and converts switch drivers to be compatible with LDM driver registration method. To simplify registration of device-specific callback routines this patch introduces rio_switch_ops data structure. The sw_sysfs() callback is removed from the list of device-specific operations because under the new structure its functions can be handled by switch driver's probe() and remove() routines. If a specific switch device driver is not loaded the RapidIO subsystem core will use default standard-based operations to configure a switch. Because the current implementation of RapidIO enumeration/discovery method relies on availability of device-specific operations for error management, switch device drivers must be loaded before the RapidIO enumeration/discovery starts. This patch also moves several common routines from enumeration/discovery module into the RapidIO core code to make switch-specific operations accessible to all components of RapidIO subsystem. Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com> Cc: Matt Porter <mporter@kernel.crashing.org> Cc: Li Yang <leoli@freescale.com> Cc: Kumar Gala <galak@kernel.crashing.org> Cc: Andre van Herk <andre.van.herk@Prodrive.nl> Cc: Micha Nelissen <micha.nelissen@Prodrive.nl> Cc: Stef van Os <stef.van.os@Prodrive.nl> Cc: Jean Delvare <jdelvare@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-04 06:08:50 +08:00
spin_lock_init(&rswitch->lock);
rswitch->route_table = kzalloc(sizeof(u8)*
RIO_MAX_ROUTE_ENTRIES(port->sys_size),
GFP_KERNEL);
if (!rswitch->route_table)
goto cleanup;
/* Initialize switch route table */
for (rdid = 0; rdid < RIO_MAX_ROUTE_ENTRIES(port->sys_size);
rdid++)
rswitch->route_table[rdid] = RIO_INVALID_ROUTE;
dev_set_name(&rdev->dev, "%02x:s:%04x", rdev->net->id,
rswitch->switchid);
rapidio: convert switch drivers to modules Rework RapidIO switch drivers to add an option to build them as loadable kernel modules. This patch removes RapidIO-specific vmlinux section and converts switch drivers to be compatible with LDM driver registration method. To simplify registration of device-specific callback routines this patch introduces rio_switch_ops data structure. The sw_sysfs() callback is removed from the list of device-specific operations because under the new structure its functions can be handled by switch driver's probe() and remove() routines. If a specific switch device driver is not loaded the RapidIO subsystem core will use default standard-based operations to configure a switch. Because the current implementation of RapidIO enumeration/discovery method relies on availability of device-specific operations for error management, switch device drivers must be loaded before the RapidIO enumeration/discovery starts. This patch also moves several common routines from enumeration/discovery module into the RapidIO core code to make switch-specific operations accessible to all components of RapidIO subsystem. Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com> Cc: Matt Porter <mporter@kernel.crashing.org> Cc: Li Yang <leoli@freescale.com> Cc: Kumar Gala <galak@kernel.crashing.org> Cc: Andre van Herk <andre.van.herk@Prodrive.nl> Cc: Micha Nelissen <micha.nelissen@Prodrive.nl> Cc: Stef van Os <stef.van.os@Prodrive.nl> Cc: Jean Delvare <jdelvare@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-04 06:08:50 +08:00
if (do_enum)
rio_route_clr_table(rdev, RIO_GLOBAL_TABLE, 0);
list_add_tail(&rswitch->node, &net->switches);
} else {
if (do_enum)
/*Enable Input Output Port (transmitter reviever)*/
rio_enable_rx_tx_port(port, 0, destid, hopcount, 0);
dev_set_name(&rdev->dev, "%02x:e:%04x", rdev->net->id,
rdev->destid);
}
rapidio: make enumeration/discovery configurable Systems that use RapidIO fabric may need to implement their own enumeration and discovery methods which are better suitable for needs of a target application. The following set of patches is intended to simplify process of introduction of new RapidIO fabric enumeration/discovery methods. The first patch offers ability to add new RapidIO enumeration/discovery methods using kernel configuration options. This new configuration option mechanism allows to select statically linked or modular enumeration/discovery method(s) from the list of existing methods or use external module(s). This patch also updates the currently existing enumeration/discovery code to be used as a statically linked or modular method. The corresponding configuration option is named "Basic enumeration/discovery" method. This is the only one configuration option available today but new methods are expected to be introduced after adoption of provided patches. The second patch address a long time complaint of RapidIO subsystem users regarding fabric enumeration/discovery start sequence. Existing implementation offers only a boot-time enumeration/discovery start which requires synchronized boot of all endpoints in RapidIO network. While it works for small closed configurations with limited number of endpoints, using this approach in systems with large number of endpoints is quite challenging. To eliminate requirement for synchronized start the second patch introduces RapidIO enumeration/discovery start from user space. For compatibility with the existing RapidIO subsystem implementation, automatic boot time enumeration/discovery start can be configured in by specifying "rio-scan.scan=1" command line parameter if statically linked basic enumeration method is selected. This patch: Rework to implement RapidIO enumeration/discovery method selection combined with ability to use enumeration/discovery as a kernel module. This patch adds ability to introduce new RapidIO enumeration/discovery methods using kernel configuration options. Configuration option mechanism allows to select statically linked or modular enumeration/discovery method from the list of existing methods or use external modules. If a modular enumeration/discovery is selected each RapidIO mport device can have its own method attached to it. The existing enumeration/discovery code was updated to be used as statically linked or modular method. This configuration option is named "Basic enumeration/discovery" method. Several common routines have been moved from rio-scan.c to make them available to other enumeration methods and reduce number of exported symbols. Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com> Cc: Matt Porter <mporter@kernel.crashing.org> Cc: Li Yang <leoli@freescale.com> Cc: Kumar Gala <galak@kernel.crashing.org> Cc: Andre van Herk <andre.van.herk@Prodrive.nl> Cc: Micha Nelissen <micha.nelissen@Prodrive.nl> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-05-25 06:55:05 +08:00
rio_attach_device(rdev);
device_initialize(&rdev->dev);
rdev->dev.release = rio_release_dev;
rio_dev_get(rdev);
rdev->dma_mask = DMA_BIT_MASK(32);
rdev->dev.dma_mask = &rdev->dma_mask;
rdev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
if (rdev->dst_ops & RIO_DST_OPS_DOORBELL)
rio_init_dbell_res(&rdev->riores[RIO_DOORBELL_RESOURCE],
0, 0xffff);
ret = rio_add_device(rdev);
if (ret)
goto cleanup;
return rdev;
cleanup:
if (rswitch)
kfree(rswitch->route_table);
kfree(rdev);
return NULL;
}
/**
* rio_sport_is_active- Tests if a switch port has an active connection.
* @port: Master port to send transaction
* @destid: Associated destination ID for switch
* @hopcount: Hopcount to reach switch
* @sport: Switch port number
*
* Reads the port error status CSR for a particular switch port to
* determine if the port has an active link. Returns
* %RIO_PORT_N_ERR_STS_PORT_OK if the port is active or %0 if it is
* inactive.
*/
static int
rio_sport_is_active(struct rio_mport *port, u16 destid, u8 hopcount, int sport)
{
u32 result = 0;
u32 ext_ftr_ptr;
ext_ftr_ptr = rio_mport_get_efb(port, 0, destid, hopcount, 0);
while (ext_ftr_ptr) {
rio_mport_read_config_32(port, destid, hopcount,
ext_ftr_ptr, &result);
result = RIO_GET_BLOCK_ID(result);
if ((result == RIO_EFB_SER_EP_FREE_ID) ||
(result == RIO_EFB_SER_EP_FREE_ID_V13P) ||
(result == RIO_EFB_SER_EP_FREC_ID))
break;
ext_ftr_ptr = rio_mport_get_efb(port, 0, destid, hopcount,
ext_ftr_ptr);
}
if (ext_ftr_ptr)
rio_mport_read_config_32(port, destid, hopcount,
ext_ftr_ptr +
RIO_PORT_N_ERR_STS_CSR(sport),
&result);
return result & RIO_PORT_N_ERR_STS_PORT_OK;
}
/**
* rio_get_host_deviceid_lock- Reads the Host Device ID Lock CSR on a device
* @port: Master port to send transaction
* @hopcount: Number of hops to the device
*
* Used during enumeration to read the Host Device ID Lock CSR on a
* RIO device. Returns the value of the lock register.
*/
static u16 rio_get_host_deviceid_lock(struct rio_mport *port, u8 hopcount)
{
u32 result;
rio_mport_read_config_32(port, RIO_ANY_DESTID(port->sys_size), hopcount,
RIO_HOST_DID_LOCK_CSR, &result);
return (u16) (result & 0xffff);
}
/**
* rio_enum_peer- Recursively enumerate a RIO network through a master port
* @net: RIO network being enumerated
* @port: Master port to send transactions
* @hopcount: Number of hops into the network
* @prev: Previous RIO device connected to the enumerated one
* @prev_port: Port on previous RIO device
*
* Recursively enumerates a RIO network. Transactions are sent via the
* master port passed in @port.
*/
static int rio_enum_peer(struct rio_net *net, struct rio_mport *port,
u8 hopcount, struct rio_dev *prev, int prev_port)
{
struct rio_dev *rdev;
u32 regval;
int tmp;
if (rio_mport_chk_dev_access(port,
RIO_ANY_DESTID(port->sys_size), hopcount)) {
pr_debug("RIO: device access check failed\n");
return -1;
}
if (rio_get_host_deviceid_lock(port, hopcount) == port->host_deviceid) {
pr_debug("RIO: PE already discovered by this host\n");
/*
* Already discovered by this host. Add it as another
* link to the existing device.
*/
rio_mport_read_config_32(port, RIO_ANY_DESTID(port->sys_size),
hopcount, RIO_COMPONENT_TAG_CSR, &regval);
if (regval) {
rdev = rio_get_comptag((regval & 0xffff), NULL);
if (rdev && prev && rio_is_switch(prev)) {
pr_debug("RIO: redundant path to %s\n",
rio_name(rdev));
prev->rswitch->nextdev[prev_port] = rdev;
}
}
return 0;
}
/* Attempt to acquire device lock */
rio_mport_write_config_32(port, RIO_ANY_DESTID(port->sys_size),
hopcount,
RIO_HOST_DID_LOCK_CSR, port->host_deviceid);
while ((tmp = rio_get_host_deviceid_lock(port, hopcount))
< port->host_deviceid) {
/* Delay a bit */
mdelay(1);
/* Attempt to acquire device lock again */
rio_mport_write_config_32(port, RIO_ANY_DESTID(port->sys_size),
hopcount,
RIO_HOST_DID_LOCK_CSR,
port->host_deviceid);
}
if (rio_get_host_deviceid_lock(port, hopcount) > port->host_deviceid) {
pr_debug(
"RIO: PE locked by a higher priority host...retreating\n");
return -1;
}
/* Setup new RIO device */
rdev = rio_setup_device(net, port, RIO_ANY_DESTID(port->sys_size),
hopcount, 1);
if (rdev) {
/* Add device to the global and bus/net specific list. */
list_add_tail(&rdev->net_list, &net->devices);
rdev->prev = prev;
if (prev && rio_is_switch(prev))
prev->rswitch->nextdev[prev_port] = rdev;
} else
return -1;
if (rio_is_switch(rdev)) {
int sw_destid;
int cur_destid;
int sw_inport;
u16 destid;
int port_num;
sw_inport = RIO_GET_PORT_NUM(rdev->swpinfo);
rio_route_add_entry(rdev, RIO_GLOBAL_TABLE,
port->host_deviceid, sw_inport, 0);
rdev->rswitch->route_table[port->host_deviceid] = sw_inport;
destid = rio_destid_first(net);
while (destid != RIO_INVALID_DESTID && destid < next_destid) {
if (destid != port->host_deviceid) {
rio_route_add_entry(rdev, RIO_GLOBAL_TABLE,
destid, sw_inport, 0);
rdev->rswitch->route_table[destid] = sw_inport;
}
destid = rio_destid_next(net, destid + 1);
}
pr_debug(
"RIO: found %s (vid %4.4x did %4.4x) with %d ports\n",
rio_name(rdev), rdev->vid, rdev->did,
RIO_GET_TOTAL_PORTS(rdev->swpinfo));
sw_destid = next_destid;
for (port_num = 0;
port_num < RIO_GET_TOTAL_PORTS(rdev->swpinfo);
port_num++) {
if (sw_inport == port_num) {
rio_enable_rx_tx_port(port, 0,
RIO_ANY_DESTID(port->sys_size),
hopcount, port_num);
rdev->rswitch->port_ok |= (1 << port_num);
continue;
}
cur_destid = next_destid;
if (rio_sport_is_active
(port, RIO_ANY_DESTID(port->sys_size), hopcount,
port_num)) {
pr_debug(
"RIO: scanning device on port %d\n",
port_num);
rio_enable_rx_tx_port(port, 0,
RIO_ANY_DESTID(port->sys_size),
hopcount, port_num);
rdev->rswitch->port_ok |= (1 << port_num);
rio_route_add_entry(rdev, RIO_GLOBAL_TABLE,
RIO_ANY_DESTID(port->sys_size),
port_num, 0);
if (rio_enum_peer(net, port, hopcount + 1,
rdev, port_num) < 0)
return -1;
/* Update routing tables */
destid = rio_destid_next(net, cur_destid + 1);
if (destid != RIO_INVALID_DESTID) {
for (destid = cur_destid;
destid < next_destid;) {
if (destid != port->host_deviceid) {
rio_route_add_entry(rdev,
RIO_GLOBAL_TABLE,
destid,
port_num,
0);
rdev->rswitch->
route_table[destid] =
port_num;
}
destid = rio_destid_next(net,
destid + 1);
}
}
} else {
/* If switch supports Error Management,
* set PORT_LOCKOUT bit for unused port
*/
if (rdev->em_efptr)
rio_set_port_lockout(rdev, port_num, 1);
rdev->rswitch->port_ok &= ~(1 << port_num);
}
}
/* Direct Port-write messages to the enumeratiing host */
if ((rdev->src_ops & RIO_SRC_OPS_PORT_WRITE) &&
(rdev->em_efptr)) {
rio_write_config_32(rdev,
rdev->em_efptr + RIO_EM_PW_TGT_DEVID,
(port->host_deviceid << 16) |
(port->sys_size << 15));
}
rio_init_em(rdev);
/* Check for empty switch */
if (next_destid == sw_destid)
next_destid = rio_destid_alloc(net);
rdev->destid = sw_destid;
} else
pr_debug("RIO: found %s (vid %4.4x did %4.4x)\n",
rio_name(rdev), rdev->vid, rdev->did);
return 0;
}
/**
* rio_enum_complete- Tests if enumeration of a network is complete
* @port: Master port to send transaction
*
* Tests the PGCCSR discovered bit for non-zero value (enumeration
* complete flag). Return %1 if enumeration is complete or %0 if
* enumeration is incomplete.
*/
static int rio_enum_complete(struct rio_mport *port)
{
u32 regval;
rio_local_read_config_32(port, port->phys_efptr + RIO_PORT_GEN_CTL_CSR,
&regval);
return (regval & RIO_PORT_GEN_DISCOVERED) ? 1 : 0;
}
/**
* rio_disc_peer- Recursively discovers a RIO network through a master port
* @net: RIO network being discovered
* @port: Master port to send transactions
* @destid: Current destination ID in network
* @hopcount: Number of hops into the network
* @prev: previous rio_dev
* @prev_port: previous port number
*
* Recursively discovers a RIO network. Transactions are sent via the
* master port passed in @port.
*/
static int
rio_disc_peer(struct rio_net *net, struct rio_mport *port, u16 destid,
u8 hopcount, struct rio_dev *prev, int prev_port)
{
u8 port_num, route_port;
struct rio_dev *rdev;
u16 ndestid;
/* Setup new RIO device */
if ((rdev = rio_setup_device(net, port, destid, hopcount, 0))) {
/* Add device to the global and bus/net specific list. */
list_add_tail(&rdev->net_list, &net->devices);
rdev->prev = prev;
if (prev && rio_is_switch(prev))
prev->rswitch->nextdev[prev_port] = rdev;
} else
return -1;
if (rio_is_switch(rdev)) {
/* Associated destid is how we accessed this switch */
rdev->destid = destid;
pr_debug(
"RIO: found %s (vid %4.4x did %4.4x) with %d ports\n",
rio_name(rdev), rdev->vid, rdev->did,
RIO_GET_TOTAL_PORTS(rdev->swpinfo));
for (port_num = 0;
port_num < RIO_GET_TOTAL_PORTS(rdev->swpinfo);
port_num++) {
if (RIO_GET_PORT_NUM(rdev->swpinfo) == port_num)
continue;
if (rio_sport_is_active
(port, destid, hopcount, port_num)) {
pr_debug(
"RIO: scanning device on port %d\n",
port_num);
rio_lock_device(port, destid, hopcount, 1000);
for (ndestid = 0;
ndestid < RIO_ANY_DESTID(port->sys_size);
ndestid++) {
rio_route_get_entry(rdev,
RIO_GLOBAL_TABLE,
ndestid,
&route_port, 0);
if (route_port == port_num)
break;
}
if (ndestid == RIO_ANY_DESTID(port->sys_size))
continue;
rio_unlock_device(port, destid, hopcount);
if (rio_disc_peer(net, port, ndestid,
hopcount + 1, rdev, port_num) < 0)
return -1;
}
}
} else
pr_debug("RIO: found %s (vid %4.4x did %4.4x)\n",
rio_name(rdev), rdev->vid, rdev->did);
return 0;
}
/**
* rio_mport_is_active- Tests if master port link is active
* @port: Master port to test
*
* Reads the port error status CSR for the master port to
* determine if the port has an active link. Returns
* %RIO_PORT_N_ERR_STS_PORT_OK if the master port is active
* or %0 if it is inactive.
*/
static int rio_mport_is_active(struct rio_mport *port)
{
u32 result = 0;
u32 ext_ftr_ptr;
int *entry = rio_mport_phys_table;
do {
if ((ext_ftr_ptr =
rio_mport_get_feature(port, 1, 0, 0, *entry)))
break;
} while (*++entry >= 0);
if (ext_ftr_ptr)
rio_local_read_config_32(port,
ext_ftr_ptr +
RIO_PORT_N_ERR_STS_CSR(port->index),
&result);
return result & RIO_PORT_N_ERR_STS_PORT_OK;
}
/**
* rio_alloc_net- Allocate and configure a new RIO network
* @port: Master port associated with the RIO network
* @do_enum: Enumeration/Discovery mode flag
* @start: logical minimal start id for new net
*
* Allocates a RIO network structure, initializes per-network
* list heads, and adds the associated master port to the
* network list of associated master ports. Returns a
* RIO network pointer on success or %NULL on failure.
*/
static struct rio_net *rio_alloc_net(struct rio_mport *port,
int do_enum, u16 start)
{
struct rio_net *net;
2007-07-19 16:49:03 +08:00
net = kzalloc(sizeof(struct rio_net), GFP_KERNEL);
if (net && do_enum) {
net->destid_table.table = kcalloc(
BITS_TO_LONGS(RIO_MAX_ROUTE_ENTRIES(port->sys_size)),
sizeof(long),
GFP_KERNEL);
if (net->destid_table.table == NULL) {
pr_err("RIO: failed to allocate destID table\n");
kfree(net);
net = NULL;
} else {
net->destid_table.start = start;
net->destid_table.max =
RIO_MAX_ROUTE_ENTRIES(port->sys_size);
spin_lock_init(&net->destid_table.lock);
}
}
if (net) {
INIT_LIST_HEAD(&net->node);
INIT_LIST_HEAD(&net->devices);
INIT_LIST_HEAD(&net->switches);
INIT_LIST_HEAD(&net->mports);
list_add_tail(&port->nnode, &net->mports);
net->hport = port;
net->id = port->id;
}
return net;
}
/**
* rio_update_route_tables- Updates route tables in switches
* @net: RIO network to run update on
*
* For each enumerated device, ensure that each switch in a system
* has correct routing entries. Add routes for devices that where
* unknown dirung the first enumeration pass through the switch.
*/
static void rio_update_route_tables(struct rio_net *net)
{
struct rio_dev *rdev, *swrdev;
struct rio_switch *rswitch;
u8 sport;
u16 destid;
list_for_each_entry(rdev, &net->devices, net_list) {
destid = rdev->destid;
list_for_each_entry(rswitch, &net->switches, node) {
if (rio_is_switch(rdev) && (rdev->rswitch == rswitch))
continue;
if (RIO_INVALID_ROUTE == rswitch->route_table[destid]) {
swrdev = sw_to_rio_dev(rswitch);
/* Skip if destid ends in empty switch*/
if (swrdev->destid == destid)
continue;
sport = RIO_GET_PORT_NUM(swrdev->swpinfo);
rapidio: convert switch drivers to modules Rework RapidIO switch drivers to add an option to build them as loadable kernel modules. This patch removes RapidIO-specific vmlinux section and converts switch drivers to be compatible with LDM driver registration method. To simplify registration of device-specific callback routines this patch introduces rio_switch_ops data structure. The sw_sysfs() callback is removed from the list of device-specific operations because under the new structure its functions can be handled by switch driver's probe() and remove() routines. If a specific switch device driver is not loaded the RapidIO subsystem core will use default standard-based operations to configure a switch. Because the current implementation of RapidIO enumeration/discovery method relies on availability of device-specific operations for error management, switch device drivers must be loaded before the RapidIO enumeration/discovery starts. This patch also moves several common routines from enumeration/discovery module into the RapidIO core code to make switch-specific operations accessible to all components of RapidIO subsystem. Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com> Cc: Matt Porter <mporter@kernel.crashing.org> Cc: Li Yang <leoli@freescale.com> Cc: Kumar Gala <galak@kernel.crashing.org> Cc: Andre van Herk <andre.van.herk@Prodrive.nl> Cc: Micha Nelissen <micha.nelissen@Prodrive.nl> Cc: Stef van Os <stef.van.os@Prodrive.nl> Cc: Jean Delvare <jdelvare@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-04 06:08:50 +08:00
rio_route_add_entry(swrdev, RIO_GLOBAL_TABLE,
destid, sport, 0);
rswitch->route_table[destid] = sport;
}
}
}
}
/**
* rio_init_em - Initializes RIO Error Management (for switches)
rapidio: fix new kernel-doc warnings Fix a bunch of new rapidio kernel-doc warnings: Warning(include/linux/rio.h:123): No description found for parameter 'comp_tag' Warning(include/linux/rio.h:123): No description found for parameter 'phys_efptr' Warning(include/linux/rio.h:123): No description found for parameter 'em_efptr' Warning(include/linux/rio.h:123): No description found for parameter 'pwcback' Warning(include/linux/rio.h:247): No description found for parameter 'set_domain' Warning(include/linux/rio.h:247): No description found for parameter 'get_domain' Warning(drivers/rapidio/rio-scan.c:1133): No description found for parameter 'rdev' Warning(drivers/rapidio/rio-scan.c:1133): Excess function parameter 'port' description in 'rio_init_em' Warning(drivers/rapidio/rio.c:349): No description found for parameter 'rdev' Warning(drivers/rapidio/rio.c:349): Excess function parameter 'mport' description in 'rio_request_inb_pwrite' Warning(drivers/rapidio/rio.c:393): No description found for parameter 'port' Warning(drivers/rapidio/rio.c:393): No description found for parameter 'local' Warning(drivers/rapidio/rio.c:393): No description found for parameter 'destid' Warning(drivers/rapidio/rio.c:393): No description found for parameter 'hopcount' Warning(drivers/rapidio/rio.c:393): Excess function parameter 'rdev' description in 'rio_mport_get_physefb' Warning(drivers/rapidio/rio.c:845): Excess function parameter 'local' description in 'rio_std_route_clr_table' Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Alexandre Bounine <alexandre.bounine@idt.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-29 06:08:08 +08:00
* @rdev: RIO device
*
* For each enumerated switch, call device-specific error management
* initialization routine (if supplied by the switch driver).
*/
static void rio_init_em(struct rio_dev *rdev)
{
if (rio_is_switch(rdev) && (rdev->em_efptr) &&
rapidio: convert switch drivers to modules Rework RapidIO switch drivers to add an option to build them as loadable kernel modules. This patch removes RapidIO-specific vmlinux section and converts switch drivers to be compatible with LDM driver registration method. To simplify registration of device-specific callback routines this patch introduces rio_switch_ops data structure. The sw_sysfs() callback is removed from the list of device-specific operations because under the new structure its functions can be handled by switch driver's probe() and remove() routines. If a specific switch device driver is not loaded the RapidIO subsystem core will use default standard-based operations to configure a switch. Because the current implementation of RapidIO enumeration/discovery method relies on availability of device-specific operations for error management, switch device drivers must be loaded before the RapidIO enumeration/discovery starts. This patch also moves several common routines from enumeration/discovery module into the RapidIO core code to make switch-specific operations accessible to all components of RapidIO subsystem. Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com> Cc: Matt Porter <mporter@kernel.crashing.org> Cc: Li Yang <leoli@freescale.com> Cc: Kumar Gala <galak@kernel.crashing.org> Cc: Andre van Herk <andre.van.herk@Prodrive.nl> Cc: Micha Nelissen <micha.nelissen@Prodrive.nl> Cc: Stef van Os <stef.van.os@Prodrive.nl> Cc: Jean Delvare <jdelvare@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-04 06:08:50 +08:00
rdev->rswitch->ops && rdev->rswitch->ops->em_init) {
rdev->rswitch->ops->em_init(rdev);
}
}
/**
* rio_pw_enable - Enables/disables port-write handling by a master port
* @port: Master port associated with port-write handling
* @enable: 1=enable, 0=disable
*/
static void rio_pw_enable(struct rio_mport *port, int enable)
{
if (port->ops->pwenable)
port->ops->pwenable(port, enable);
}
/**
* rio_enum_mport- Start enumeration through a master port
* @mport: Master port to send transactions
* @flags: Enumeration control flags
*
* Starts the enumeration process. If somebody has enumerated our
* master port device, then give up. If not and we have an active
* link, then start recursive peer enumeration. Returns %0 if
* enumeration succeeds or %-EBUSY if enumeration fails.
*/
static int rio_enum_mport(struct rio_mport *mport, u32 flags)
{
struct rio_net *net = NULL;
int rc = 0;
printk(KERN_INFO "RIO: enumerate master port %d, %s\n", mport->id,
mport->name);
/*
* To avoid multiple start requests (repeat enumeration is not supported
* by this method) check if enumeration/discovery was performed for this
* mport: if mport was added into the list of mports for a net exit
* with error.
*/
if (mport->nnode.next || mport->nnode.prev)
return -EBUSY;
/* If somebody else enumerated our master port device, bail. */
if (rio_enum_host(mport) < 0) {
printk(KERN_INFO
"RIO: master port %d device has been enumerated by a remote host\n",
mport->id);
rc = -EBUSY;
goto out;
}
/* If master port has an active link, allocate net and enum peers */
if (rio_mport_is_active(mport)) {
net = rio_alloc_net(mport, 1, 0);
if (!net) {
printk(KERN_ERR "RIO: failed to allocate new net\n");
rc = -ENOMEM;
goto out;
}
/* reserve mport destID in new net */
rio_destid_reserve(net, mport->host_deviceid);
/* Enable Input Output Port (transmitter reviever) */
rio_enable_rx_tx_port(mport, 1, 0, 0, 0);
/* Set component tag for host */
rio_local_write_config_32(mport, RIO_COMPONENT_TAG_CSR,
next_comptag++);
next_destid = rio_destid_alloc(net);
if (rio_enum_peer(net, mport, 0, NULL, 0) < 0) {
/* A higher priority host won enumeration, bail. */
printk(KERN_INFO
"RIO: master port %d device has lost enumeration to a remote host\n",
mport->id);
rio_clear_locks(net);
rc = -EBUSY;
goto out;
}
/* free the last allocated destID (unused) */
rio_destid_free(net, next_destid);
rio_update_route_tables(net);
rio_clear_locks(net);
rio_pw_enable(mport, 1);
} else {
printk(KERN_INFO "RIO: master port %d link inactive\n",
mport->id);
rc = -EINVAL;
}
out:
return rc;
}
/**
* rio_build_route_tables- Generate route tables from switch route entries
* @net: RIO network to run route tables scan on
*
* For each switch device, generate a route table by copying existing
* route entries from the switch.
*/
static void rio_build_route_tables(struct rio_net *net)
{
struct rio_switch *rswitch;
struct rio_dev *rdev;
int i;
u8 sport;
list_for_each_entry(rswitch, &net->switches, node) {
rdev = sw_to_rio_dev(rswitch);
rio_lock_device(net->hport, rdev->destid,
rdev->hopcount, 1000);
for (i = 0;
i < RIO_MAX_ROUTE_ENTRIES(net->hport->sys_size);
i++) {
if (rio_route_get_entry(rdev, RIO_GLOBAL_TABLE,
i, &sport, 0) < 0)
continue;
rswitch->route_table[i] = sport;
}
rio_unlock_device(net->hport, rdev->destid, rdev->hopcount);
}
}
/**
* rio_disc_mport- Start discovery through a master port
* @mport: Master port to send transactions
* @flags: discovery control flags
*
* Starts the discovery process. If we have an active link,
* then wait for the signal that enumeration is complete (if wait
* is allowed).
* When enumeration completion is signaled, start recursive
* peer discovery. Returns %0 if discovery succeeds or %-EBUSY
* on failure.
*/
static int rio_disc_mport(struct rio_mport *mport, u32 flags)
{
struct rio_net *net = NULL;
rapidio: fix blocking wait for discovery ready The following set of patches provides modifications targeting support of multiple RapidIO master port (mport) devices on a CPU-side of RapidIO-capable board. While the RapidIO subsystem code has definitions suitable for multi-controller/multi-net support, the existing implementation cannot be considered ready for multiple mport configurations. =========== NOTES: ============= a) The patches below do not address RapidIO side view of multiport processing elements defined in Part 6 of RapidIO spec Rev.2.1 (section 6.4.1). These devices have Base Device ID CSR (0x60) and Component Tag CSR (0x6C) shared by all SRIO ports. For example, Freescale's P4080, P3041 and P5020 have a dual-port SRIO controller implemented according the specification. Enumeration/discovery of such devices from RapidIO side may require device-specific fixups. b) Devices referenced above may also require implementation specific code to setup a host device ID for mport device. These operations are not addressed by patches in this package. ================================= Details about provided patches: 1. Fix blocking wait for discovery ready While it does not happen on PowerPC based platforms, there is possibility of stalled CPU warning dump on x86 based platforms that run RapidIO discovery process if they wait too long for being enumerated. Currently users can avoid it by disabling the soft-lockup detector using "nosoftlockup" kernel parameter OR by ensuring that enumeration is completed before soft-lockup is detected. This patch eliminates blocking wait and keeps a scheduler running. It also is required for patch 3 below which introduces asynchronous discovery process. 2. Use device lists handling on per-net basis This patch allows to correctly support multiple RapidIO nets and resolves possible issues caused by using single global list of devices during RapidIO system enumeration/discovery. The most common sign of existing issue is incorrect contents of switch routing tables in systems with multiple mport controllers while single-port configuration performs as expected. The patch does not eliminate the global RapidIO device list but changes some routines in enumeration/discovery to use per-net device lists instead. This way compatibility with upper layer RIO routines is preserved. 3. Run discovery as an asynchronous process This patch modifies RapidIO initialization routine to asynchronously run the discovery process for each corresponding mport. This allows having an arbitrary order of enumerating and discovering mports without creating a deadlock situation if an enumerator port was registered after a discovering one. On boards with multiple discovering mports it also eliminates order dependency between mports and may reduce total time of RapidIO subsystem initialization. Making netID matching to mportID ensures consistent netID assignment in multiport RapidIO systems with asynchronous discovery process (global counter implementation is affected by race between threads). 4. Rework RIONET to support multiple RIO master ports In the current version of the driver rionet_probe() has comment "XXX Make multi-net safe". Now it is a good time to address this comment. This patch makes RIONET driver multi-net safe/capable by introducing per-net lists of RapidIO network peers. It also enables to register network adapters for all available mport devices. 5. Add destination ID allocation mechanism The patch replaces a single global destination ID counter with per-net allocation mechanism to allow independent destID management for each available RapidIO network. Using bitmap based mechanism instead of counters allows destination ID release and reuse in systems that support hot-swap. This patch: Fix blocking wait loop in the RapidIO discovery routine to avoid warning dumps about stalled CPU on x86 platforms. Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com> Cc: Matt Porter <mporter@kernel.crashing.org> Cc: Li Yang <leoli@freescale.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-05 08:16:04 +08:00
unsigned long to_end;
printk(KERN_INFO "RIO: discover master port %d, %s\n", mport->id,
mport->name);
/* If master port has an active link, allocate net and discover peers */
if (rio_mport_is_active(mport)) {
if (rio_enum_complete(mport))
goto enum_done;
else if (flags & RIO_SCAN_ENUM_NO_WAIT)
return -EAGAIN;
rapidio: fix blocking wait for discovery ready The following set of patches provides modifications targeting support of multiple RapidIO master port (mport) devices on a CPU-side of RapidIO-capable board. While the RapidIO subsystem code has definitions suitable for multi-controller/multi-net support, the existing implementation cannot be considered ready for multiple mport configurations. =========== NOTES: ============= a) The patches below do not address RapidIO side view of multiport processing elements defined in Part 6 of RapidIO spec Rev.2.1 (section 6.4.1). These devices have Base Device ID CSR (0x60) and Component Tag CSR (0x6C) shared by all SRIO ports. For example, Freescale's P4080, P3041 and P5020 have a dual-port SRIO controller implemented according the specification. Enumeration/discovery of such devices from RapidIO side may require device-specific fixups. b) Devices referenced above may also require implementation specific code to setup a host device ID for mport device. These operations are not addressed by patches in this package. ================================= Details about provided patches: 1. Fix blocking wait for discovery ready While it does not happen on PowerPC based platforms, there is possibility of stalled CPU warning dump on x86 based platforms that run RapidIO discovery process if they wait too long for being enumerated. Currently users can avoid it by disabling the soft-lockup detector using "nosoftlockup" kernel parameter OR by ensuring that enumeration is completed before soft-lockup is detected. This patch eliminates blocking wait and keeps a scheduler running. It also is required for patch 3 below which introduces asynchronous discovery process. 2. Use device lists handling on per-net basis This patch allows to correctly support multiple RapidIO nets and resolves possible issues caused by using single global list of devices during RapidIO system enumeration/discovery. The most common sign of existing issue is incorrect contents of switch routing tables in systems with multiple mport controllers while single-port configuration performs as expected. The patch does not eliminate the global RapidIO device list but changes some routines in enumeration/discovery to use per-net device lists instead. This way compatibility with upper layer RIO routines is preserved. 3. Run discovery as an asynchronous process This patch modifies RapidIO initialization routine to asynchronously run the discovery process for each corresponding mport. This allows having an arbitrary order of enumerating and discovering mports without creating a deadlock situation if an enumerator port was registered after a discovering one. On boards with multiple discovering mports it also eliminates order dependency between mports and may reduce total time of RapidIO subsystem initialization. Making netID matching to mportID ensures consistent netID assignment in multiport RapidIO systems with asynchronous discovery process (global counter implementation is affected by race between threads). 4. Rework RIONET to support multiple RIO master ports In the current version of the driver rionet_probe() has comment "XXX Make multi-net safe". Now it is a good time to address this comment. This patch makes RIONET driver multi-net safe/capable by introducing per-net lists of RapidIO network peers. It also enables to register network adapters for all available mport devices. 5. Add destination ID allocation mechanism The patch replaces a single global destination ID counter with per-net allocation mechanism to allow independent destID management for each available RapidIO network. Using bitmap based mechanism instead of counters allows destination ID release and reuse in systems that support hot-swap. This patch: Fix blocking wait loop in the RapidIO discovery routine to avoid warning dumps about stalled CPU on x86 platforms. Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com> Cc: Matt Porter <mporter@kernel.crashing.org> Cc: Li Yang <leoli@freescale.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-05 08:16:04 +08:00
pr_debug("RIO: wait for enumeration to complete...\n");
rapidio: fix blocking wait for discovery ready The following set of patches provides modifications targeting support of multiple RapidIO master port (mport) devices on a CPU-side of RapidIO-capable board. While the RapidIO subsystem code has definitions suitable for multi-controller/multi-net support, the existing implementation cannot be considered ready for multiple mport configurations. =========== NOTES: ============= a) The patches below do not address RapidIO side view of multiport processing elements defined in Part 6 of RapidIO spec Rev.2.1 (section 6.4.1). These devices have Base Device ID CSR (0x60) and Component Tag CSR (0x6C) shared by all SRIO ports. For example, Freescale's P4080, P3041 and P5020 have a dual-port SRIO controller implemented according the specification. Enumeration/discovery of such devices from RapidIO side may require device-specific fixups. b) Devices referenced above may also require implementation specific code to setup a host device ID for mport device. These operations are not addressed by patches in this package. ================================= Details about provided patches: 1. Fix blocking wait for discovery ready While it does not happen on PowerPC based platforms, there is possibility of stalled CPU warning dump on x86 based platforms that run RapidIO discovery process if they wait too long for being enumerated. Currently users can avoid it by disabling the soft-lockup detector using "nosoftlockup" kernel parameter OR by ensuring that enumeration is completed before soft-lockup is detected. This patch eliminates blocking wait and keeps a scheduler running. It also is required for patch 3 below which introduces asynchronous discovery process. 2. Use device lists handling on per-net basis This patch allows to correctly support multiple RapidIO nets and resolves possible issues caused by using single global list of devices during RapidIO system enumeration/discovery. The most common sign of existing issue is incorrect contents of switch routing tables in systems with multiple mport controllers while single-port configuration performs as expected. The patch does not eliminate the global RapidIO device list but changes some routines in enumeration/discovery to use per-net device lists instead. This way compatibility with upper layer RIO routines is preserved. 3. Run discovery as an asynchronous process This patch modifies RapidIO initialization routine to asynchronously run the discovery process for each corresponding mport. This allows having an arbitrary order of enumerating and discovering mports without creating a deadlock situation if an enumerator port was registered after a discovering one. On boards with multiple discovering mports it also eliminates order dependency between mports and may reduce total time of RapidIO subsystem initialization. Making netID matching to mportID ensures consistent netID assignment in multiport RapidIO systems with asynchronous discovery process (global counter implementation is affected by race between threads). 4. Rework RIONET to support multiple RIO master ports In the current version of the driver rionet_probe() has comment "XXX Make multi-net safe". Now it is a good time to address this comment. This patch makes RIONET driver multi-net safe/capable by introducing per-net lists of RapidIO network peers. It also enables to register network adapters for all available mport devices. 5. Add destination ID allocation mechanism The patch replaces a single global destination ID counter with per-net allocation mechanism to allow independent destID management for each available RapidIO network. Using bitmap based mechanism instead of counters allows destination ID release and reuse in systems that support hot-swap. This patch: Fix blocking wait loop in the RapidIO discovery routine to avoid warning dumps about stalled CPU on x86 platforms. Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com> Cc: Matt Porter <mporter@kernel.crashing.org> Cc: Li Yang <leoli@freescale.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-05 08:16:04 +08:00
to_end = jiffies + CONFIG_RAPIDIO_DISC_TIMEOUT * HZ;
while (time_before(jiffies, to_end)) {
if (rio_enum_complete(mport))
goto enum_done;
msleep(10);
}
rapidio: fix blocking wait for discovery ready The following set of patches provides modifications targeting support of multiple RapidIO master port (mport) devices on a CPU-side of RapidIO-capable board. While the RapidIO subsystem code has definitions suitable for multi-controller/multi-net support, the existing implementation cannot be considered ready for multiple mport configurations. =========== NOTES: ============= a) The patches below do not address RapidIO side view of multiport processing elements defined in Part 6 of RapidIO spec Rev.2.1 (section 6.4.1). These devices have Base Device ID CSR (0x60) and Component Tag CSR (0x6C) shared by all SRIO ports. For example, Freescale's P4080, P3041 and P5020 have a dual-port SRIO controller implemented according the specification. Enumeration/discovery of such devices from RapidIO side may require device-specific fixups. b) Devices referenced above may also require implementation specific code to setup a host device ID for mport device. These operations are not addressed by patches in this package. ================================= Details about provided patches: 1. Fix blocking wait for discovery ready While it does not happen on PowerPC based platforms, there is possibility of stalled CPU warning dump on x86 based platforms that run RapidIO discovery process if they wait too long for being enumerated. Currently users can avoid it by disabling the soft-lockup detector using "nosoftlockup" kernel parameter OR by ensuring that enumeration is completed before soft-lockup is detected. This patch eliminates blocking wait and keeps a scheduler running. It also is required for patch 3 below which introduces asynchronous discovery process. 2. Use device lists handling on per-net basis This patch allows to correctly support multiple RapidIO nets and resolves possible issues caused by using single global list of devices during RapidIO system enumeration/discovery. The most common sign of existing issue is incorrect contents of switch routing tables in systems with multiple mport controllers while single-port configuration performs as expected. The patch does not eliminate the global RapidIO device list but changes some routines in enumeration/discovery to use per-net device lists instead. This way compatibility with upper layer RIO routines is preserved. 3. Run discovery as an asynchronous process This patch modifies RapidIO initialization routine to asynchronously run the discovery process for each corresponding mport. This allows having an arbitrary order of enumerating and discovering mports without creating a deadlock situation if an enumerator port was registered after a discovering one. On boards with multiple discovering mports it also eliminates order dependency between mports and may reduce total time of RapidIO subsystem initialization. Making netID matching to mportID ensures consistent netID assignment in multiport RapidIO systems with asynchronous discovery process (global counter implementation is affected by race between threads). 4. Rework RIONET to support multiple RIO master ports In the current version of the driver rionet_probe() has comment "XXX Make multi-net safe". Now it is a good time to address this comment. This patch makes RIONET driver multi-net safe/capable by introducing per-net lists of RapidIO network peers. It also enables to register network adapters for all available mport devices. 5. Add destination ID allocation mechanism The patch replaces a single global destination ID counter with per-net allocation mechanism to allow independent destID management for each available RapidIO network. Using bitmap based mechanism instead of counters allows destination ID release and reuse in systems that support hot-swap. This patch: Fix blocking wait loop in the RapidIO discovery routine to avoid warning dumps about stalled CPU on x86 platforms. Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com> Cc: Matt Porter <mporter@kernel.crashing.org> Cc: Li Yang <leoli@freescale.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-05 08:16:04 +08:00
pr_debug("RIO: discovery timeout on mport %d %s\n",
mport->id, mport->name);
goto bail;
enum_done:
pr_debug("RIO: ... enumeration done\n");
net = rio_alloc_net(mport, 0, 0);
rapidio: fix blocking wait for discovery ready The following set of patches provides modifications targeting support of multiple RapidIO master port (mport) devices on a CPU-side of RapidIO-capable board. While the RapidIO subsystem code has definitions suitable for multi-controller/multi-net support, the existing implementation cannot be considered ready for multiple mport configurations. =========== NOTES: ============= a) The patches below do not address RapidIO side view of multiport processing elements defined in Part 6 of RapidIO spec Rev.2.1 (section 6.4.1). These devices have Base Device ID CSR (0x60) and Component Tag CSR (0x6C) shared by all SRIO ports. For example, Freescale's P4080, P3041 and P5020 have a dual-port SRIO controller implemented according the specification. Enumeration/discovery of such devices from RapidIO side may require device-specific fixups. b) Devices referenced above may also require implementation specific code to setup a host device ID for mport device. These operations are not addressed by patches in this package. ================================= Details about provided patches: 1. Fix blocking wait for discovery ready While it does not happen on PowerPC based platforms, there is possibility of stalled CPU warning dump on x86 based platforms that run RapidIO discovery process if they wait too long for being enumerated. Currently users can avoid it by disabling the soft-lockup detector using "nosoftlockup" kernel parameter OR by ensuring that enumeration is completed before soft-lockup is detected. This patch eliminates blocking wait and keeps a scheduler running. It also is required for patch 3 below which introduces asynchronous discovery process. 2. Use device lists handling on per-net basis This patch allows to correctly support multiple RapidIO nets and resolves possible issues caused by using single global list of devices during RapidIO system enumeration/discovery. The most common sign of existing issue is incorrect contents of switch routing tables in systems with multiple mport controllers while single-port configuration performs as expected. The patch does not eliminate the global RapidIO device list but changes some routines in enumeration/discovery to use per-net device lists instead. This way compatibility with upper layer RIO routines is preserved. 3. Run discovery as an asynchronous process This patch modifies RapidIO initialization routine to asynchronously run the discovery process for each corresponding mport. This allows having an arbitrary order of enumerating and discovering mports without creating a deadlock situation if an enumerator port was registered after a discovering one. On boards with multiple discovering mports it also eliminates order dependency between mports and may reduce total time of RapidIO subsystem initialization. Making netID matching to mportID ensures consistent netID assignment in multiport RapidIO systems with asynchronous discovery process (global counter implementation is affected by race between threads). 4. Rework RIONET to support multiple RIO master ports In the current version of the driver rionet_probe() has comment "XXX Make multi-net safe". Now it is a good time to address this comment. This patch makes RIONET driver multi-net safe/capable by introducing per-net lists of RapidIO network peers. It also enables to register network adapters for all available mport devices. 5. Add destination ID allocation mechanism The patch replaces a single global destination ID counter with per-net allocation mechanism to allow independent destID management for each available RapidIO network. Using bitmap based mechanism instead of counters allows destination ID release and reuse in systems that support hot-swap. This patch: Fix blocking wait loop in the RapidIO discovery routine to avoid warning dumps about stalled CPU on x86 platforms. Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com> Cc: Matt Porter <mporter@kernel.crashing.org> Cc: Li Yang <leoli@freescale.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-05 08:16:04 +08:00
if (!net) {
printk(KERN_ERR "RIO: Failed to allocate new net\n");
goto bail;
}
/* Read DestID assigned by enumerator */
rio_local_read_config_32(mport, RIO_DID_CSR,
&mport->host_deviceid);
mport->host_deviceid = RIO_GET_DID(mport->sys_size,
mport->host_deviceid);
if (rio_disc_peer(net, mport, RIO_ANY_DESTID(mport->sys_size),
0, NULL, 0) < 0) {
printk(KERN_INFO
"RIO: master port %d device has failed discovery\n",
mport->id);
goto bail;
}
rio_build_route_tables(net);
}
return 0;
rapidio: fix blocking wait for discovery ready The following set of patches provides modifications targeting support of multiple RapidIO master port (mport) devices on a CPU-side of RapidIO-capable board. While the RapidIO subsystem code has definitions suitable for multi-controller/multi-net support, the existing implementation cannot be considered ready for multiple mport configurations. =========== NOTES: ============= a) The patches below do not address RapidIO side view of multiport processing elements defined in Part 6 of RapidIO spec Rev.2.1 (section 6.4.1). These devices have Base Device ID CSR (0x60) and Component Tag CSR (0x6C) shared by all SRIO ports. For example, Freescale's P4080, P3041 and P5020 have a dual-port SRIO controller implemented according the specification. Enumeration/discovery of such devices from RapidIO side may require device-specific fixups. b) Devices referenced above may also require implementation specific code to setup a host device ID for mport device. These operations are not addressed by patches in this package. ================================= Details about provided patches: 1. Fix blocking wait for discovery ready While it does not happen on PowerPC based platforms, there is possibility of stalled CPU warning dump on x86 based platforms that run RapidIO discovery process if they wait too long for being enumerated. Currently users can avoid it by disabling the soft-lockup detector using "nosoftlockup" kernel parameter OR by ensuring that enumeration is completed before soft-lockup is detected. This patch eliminates blocking wait and keeps a scheduler running. It also is required for patch 3 below which introduces asynchronous discovery process. 2. Use device lists handling on per-net basis This patch allows to correctly support multiple RapidIO nets and resolves possible issues caused by using single global list of devices during RapidIO system enumeration/discovery. The most common sign of existing issue is incorrect contents of switch routing tables in systems with multiple mport controllers while single-port configuration performs as expected. The patch does not eliminate the global RapidIO device list but changes some routines in enumeration/discovery to use per-net device lists instead. This way compatibility with upper layer RIO routines is preserved. 3. Run discovery as an asynchronous process This patch modifies RapidIO initialization routine to asynchronously run the discovery process for each corresponding mport. This allows having an arbitrary order of enumerating and discovering mports without creating a deadlock situation if an enumerator port was registered after a discovering one. On boards with multiple discovering mports it also eliminates order dependency between mports and may reduce total time of RapidIO subsystem initialization. Making netID matching to mportID ensures consistent netID assignment in multiport RapidIO systems with asynchronous discovery process (global counter implementation is affected by race between threads). 4. Rework RIONET to support multiple RIO master ports In the current version of the driver rionet_probe() has comment "XXX Make multi-net safe". Now it is a good time to address this comment. This patch makes RIONET driver multi-net safe/capable by introducing per-net lists of RapidIO network peers. It also enables to register network adapters for all available mport devices. 5. Add destination ID allocation mechanism The patch replaces a single global destination ID counter with per-net allocation mechanism to allow independent destID management for each available RapidIO network. Using bitmap based mechanism instead of counters allows destination ID release and reuse in systems that support hot-swap. This patch: Fix blocking wait loop in the RapidIO discovery routine to avoid warning dumps about stalled CPU on x86 platforms. Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com> Cc: Matt Porter <mporter@kernel.crashing.org> Cc: Li Yang <leoli@freescale.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-05 08:16:04 +08:00
bail:
return -EBUSY;
}
rapidio: make enumeration/discovery configurable Systems that use RapidIO fabric may need to implement their own enumeration and discovery methods which are better suitable for needs of a target application. The following set of patches is intended to simplify process of introduction of new RapidIO fabric enumeration/discovery methods. The first patch offers ability to add new RapidIO enumeration/discovery methods using kernel configuration options. This new configuration option mechanism allows to select statically linked or modular enumeration/discovery method(s) from the list of existing methods or use external module(s). This patch also updates the currently existing enumeration/discovery code to be used as a statically linked or modular method. The corresponding configuration option is named "Basic enumeration/discovery" method. This is the only one configuration option available today but new methods are expected to be introduced after adoption of provided patches. The second patch address a long time complaint of RapidIO subsystem users regarding fabric enumeration/discovery start sequence. Existing implementation offers only a boot-time enumeration/discovery start which requires synchronized boot of all endpoints in RapidIO network. While it works for small closed configurations with limited number of endpoints, using this approach in systems with large number of endpoints is quite challenging. To eliminate requirement for synchronized start the second patch introduces RapidIO enumeration/discovery start from user space. For compatibility with the existing RapidIO subsystem implementation, automatic boot time enumeration/discovery start can be configured in by specifying "rio-scan.scan=1" command line parameter if statically linked basic enumeration method is selected. This patch: Rework to implement RapidIO enumeration/discovery method selection combined with ability to use enumeration/discovery as a kernel module. This patch adds ability to introduce new RapidIO enumeration/discovery methods using kernel configuration options. Configuration option mechanism allows to select statically linked or modular enumeration/discovery method from the list of existing methods or use external modules. If a modular enumeration/discovery is selected each RapidIO mport device can have its own method attached to it. The existing enumeration/discovery code was updated to be used as statically linked or modular method. This configuration option is named "Basic enumeration/discovery" method. Several common routines have been moved from rio-scan.c to make them available to other enumeration methods and reduce number of exported symbols. Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com> Cc: Matt Porter <mporter@kernel.crashing.org> Cc: Li Yang <leoli@freescale.com> Cc: Kumar Gala <galak@kernel.crashing.org> Cc: Andre van Herk <andre.van.herk@Prodrive.nl> Cc: Micha Nelissen <micha.nelissen@Prodrive.nl> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-05-25 06:55:05 +08:00
static struct rio_scan rio_scan_ops = {
.enumerate = rio_enum_mport,
.discover = rio_disc_mport,
};
static bool scan;
module_param(scan, bool, 0);
MODULE_PARM_DESC(scan, "Start RapidIO network enumeration/discovery "
"(default = 0)");
/**
* rio_basic_attach:
*
* When this enumeration/discovery method is loaded as a module this function
* registers its specific enumeration and discover routines for all available
* RapidIO mport devices. The "scan" command line parameter controls ability of
* the module to start RapidIO enumeration/discovery automatically.
*
* Returns 0 for success or -EIO if unable to register itself.
*
* This enumeration/discovery method cannot be unloaded and therefore does not
* provide a matching cleanup_module routine.
*/
static int __init rio_basic_attach(void)
{
if (rio_register_scan(RIO_MPORT_ANY, &rio_scan_ops))
return -EIO;
if (scan)
rio_init_mports();
return 0;
}
late_initcall(rio_basic_attach);
MODULE_DESCRIPTION("Basic RapidIO enumeration/discovery");
MODULE_LICENSE("GPL");