linux/drivers/s390/crypto/ap_bus.h

316 lines
9.9 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0+ */
/*
* Copyright IBM Corp. 2006, 2012
* Author(s): Cornelia Huck <cornelia.huck@de.ibm.com>
* Martin Schwidefsky <schwidefsky@de.ibm.com>
* Ralph Wuerthner <rwuerthn@de.ibm.com>
* Felix Beck <felix.beck@de.ibm.com>
* Holger Dengler <hd@linux.vnet.ibm.com>
*
* Adjunct processor bus header file.
*/
#ifndef _AP_BUS_H_
#define _AP_BUS_H_
#include <linux/device.h>
#include <linux/types.h>
#include <asm/isc.h>
#include <asm/ap.h>
#define AP_DEVICES 256 /* Number of AP devices. */
#define AP_DOMAINS 256 /* Number of AP domains. */
s390/zcrypt: multiple zcrypt device nodes support This patch is an extension to the zcrypt device driver to provide, support and maintain multiple zcrypt device nodes. The individual zcrypt device nodes can be restricted in terms of crypto cards, domains and available ioctls. Such a device node can be used as a base for container solutions like docker to control and restrict the access to crypto resources. The handling is done with a new sysfs subdir /sys/class/zcrypt. Echoing a name (or an empty sting) into the attribute "create" creates a new zcrypt device node. In /sys/class/zcrypt a new link will appear which points to the sysfs device tree of this new device. The attribute files "ioctlmask", "apmask" and "aqmask" in this directory are used to customize this new zcrypt device node instance. Finally the zcrypt device node can be destroyed by echoing the name into /sys/class/zcrypt/destroy. The internal structs holding the device info are reference counted - so a destroy will not hard remove a device but only marks it as removable when the reference counter drops to zero. The mask values are bitmaps in big endian order starting with bit 0. So adapter number 0 is the leftmost bit, mask is 0x8000... The sysfs attributes accept 2 different formats: * Absolute hex string starting with 0x like "0x12345678" does set the mask starting from left to right. If the given string is shorter than the mask it is padded with 0s on the right. If the string is longer than the mask an error comes back (EINVAL). * Relative format - a concatenation (done with ',') of the terms +<bitnr>[-<bitnr>] or -<bitnr>[-<bitnr>]. <bitnr> may be any valid number (hex, decimal or octal) in the range 0...255. Here are some examples: "+0-15,+32,-128,-0xFF" "-0-255,+1-16,+0x128" "+1,+2,+3,+4,-5,-7-10" A simple usage examples: # create new zcrypt device 'my_zcrypt': echo "my_zcrypt" >/sys/class/zcrypt/create # go into the device dir of this new device echo "my_zcrypt" >create cd my_zcrypt/ ls -l total 0 -rw-r--r-- 1 root root 4096 Jul 20 15:23 apmask -rw-r--r-- 1 root root 4096 Jul 20 15:23 aqmask -r--r--r-- 1 root root 4096 Jul 20 15:23 dev -rw-r--r-- 1 root root 4096 Jul 20 15:23 ioctlmask lrwxrwxrwx 1 root root 0 Jul 20 15:23 subsystem -> ../../../../class/zcrypt ... # customize this zcrypt node clone # enable only adapter 0 and 2 echo "0xa0" >apmask # enable only domain 6 echo "+6" >aqmask # enable all 256 ioctls echo "+0-255" >ioctls # now the /dev/my_zcrypt may be used # finally destroy it echo "my_zcrypt" >/sys/class/zcrypt/destroy Please note that a very similar 'filtering behavior' also applies to the parent z90crypt device. The two mask attributes apmask and aqmask in /sys/bus/ap act the very same for the z90crypt device node. However the implementation here is totally different as the ap bus acts on bind/unbind of queue devices and associated drivers but the effect is still the same. So there are two filters active for each additional zcrypt device node: The adapter/domain needs to be enabled on the ap bus level and it needs to be active on the zcrypt device node level. Signed-off-by: Harald Freudenberger <freude@linux.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2018-09-17 22:18:41 +08:00
#define AP_IOCTLS 256 /* Number of ioctls. */
#define AP_RESET_TIMEOUT (HZ*0.7) /* Time in ticks for reset timeouts. */
#define AP_CONFIG_TIME 30 /* Time in seconds between AP bus rescans. */
#define AP_POLL_TIME 1 /* Time in ticks between receive polls. */
extern int ap_domain_index;
extern spinlock_t ap_list_lock;
extern struct list_head ap_card_list;
static inline int ap_test_bit(unsigned int *ptr, unsigned int nr)
{
return (*ptr & (0x80000000u >> nr)) != 0;
}
#define AP_RESPONSE_NORMAL 0x00
#define AP_RESPONSE_Q_NOT_AVAIL 0x01
#define AP_RESPONSE_RESET_IN_PROGRESS 0x02
#define AP_RESPONSE_DECONFIGURED 0x03
#define AP_RESPONSE_CHECKSTOPPED 0x04
#define AP_RESPONSE_BUSY 0x05
#define AP_RESPONSE_INVALID_ADDRESS 0x06
#define AP_RESPONSE_OTHERWISE_CHANGED 0x07
#define AP_RESPONSE_Q_FULL 0x10
#define AP_RESPONSE_NO_PENDING_REPLY 0x10
#define AP_RESPONSE_INDEX_TOO_BIG 0x11
#define AP_RESPONSE_NO_FIRST_PART 0x13
#define AP_RESPONSE_MESSAGE_TOO_BIG 0x15
#define AP_RESPONSE_REQ_FAC_NOT_INST 0x16
/*
* Known device types
*/
#define AP_DEVICE_TYPE_PCICC 3
#define AP_DEVICE_TYPE_PCICA 4
#define AP_DEVICE_TYPE_PCIXCC 5
#define AP_DEVICE_TYPE_CEX2A 6
#define AP_DEVICE_TYPE_CEX2C 7
#define AP_DEVICE_TYPE_CEX3A 8
#define AP_DEVICE_TYPE_CEX3C 9
#define AP_DEVICE_TYPE_CEX4 10
#define AP_DEVICE_TYPE_CEX5 11
#define AP_DEVICE_TYPE_CEX6 12
/*
* Known function facilities
*/
#define AP_FUNC_MEX4K 1
#define AP_FUNC_CRT4K 2
#define AP_FUNC_COPRO 3
#define AP_FUNC_ACCEL 4
#define AP_FUNC_EP11 5
#define AP_FUNC_APXA 6
/*
* AP interrupt states
*/
#define AP_INTR_DISABLED 0 /* AP interrupt disabled */
#define AP_INTR_ENABLED 1 /* AP interrupt enabled */
/*
* AP device states
*/
enum ap_state {
AP_STATE_RESET_START,
AP_STATE_RESET_WAIT,
AP_STATE_SETIRQ_WAIT,
AP_STATE_IDLE,
AP_STATE_WORKING,
AP_STATE_QUEUE_FULL,
AP_STATE_SUSPEND_WAIT,
s390/zcrypt: revisit ap device remove procedure Working with the vfio-ap driver let to some revisit of the way how an ap (queue) device is removed from the driver. With the current implementation all the cleanup was done before the driver even got notified about the removal. Now the ap queue removal is done in 3 steps: 1) A preparation step, all ap messages within the queue are flushed and so the driver does 'receive' them. Also a new state AP_STATE_REMOVE assigned to the queue makes sure there are no new messages queued in. 2) Now the driver's remove function is invoked and the driver should do the job of cleaning up it's internal administration lists or whatever. After 2) is done it is guaranteed, that the driver is not invoked any more. On the other hand the driver has to make sure that the APQN is not accessed any more after step 2 is complete. 3) Now the ap bus code does the job of total cleanup of the APQN. A reset with zero is triggered and the state of the queue goes to AP_STATE_UNBOUND. After step 3) is complete, the ap queue has no pending messages and the APQN is cleared and so there are no requests and replies lingering around in the firmware queue for this APQN. Also the interrupts are disabled. After these remove steps the ap queue device may be assigned to another driver. Stress testing this remove/probe procedure showed a problem with the correct module reference counting. The actual receive of an reply in the driver is done asynchronous with completions. So with a driver change on an ap queue the message flush triggers completions but the threads waiting for the completions may run at a time where the queue already has the new driver assigned. So the module_put() at receive time needs to be done on the driver module which queued the ap message. This change is also part of this patch. Signed-off-by: Harald Freudenberger <freude@linux.ibm.com> Reviewed-by: Ingo Franzki <ifranzki@linux.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2019-02-23 00:24:11 +08:00
AP_STATE_REMOVE, /* about to be removed from driver */
AP_STATE_UNBOUND, /* momentary not bound to a driver */
AP_STATE_BORKED, /* broken */
NR_AP_STATES
};
/*
* AP device events
*/
enum ap_event {
AP_EVENT_POLL,
AP_EVENT_TIMEOUT,
NR_AP_EVENTS
};
/*
* AP wait behaviour
*/
enum ap_wait {
AP_WAIT_AGAIN, /* retry immediately */
AP_WAIT_TIMEOUT, /* wait for timeout */
AP_WAIT_INTERRUPT, /* wait for thin interrupt (if available) */
AP_WAIT_NONE, /* no wait */
NR_AP_WAIT
};
struct ap_device;
struct ap_message;
s390/zcrypt: AP bus support for alternate driver(s) The current AP bus, AP devices and AP device drivers implementation uses a clearly defined mapping for binding AP devices to AP device drivers. So for example a CEX6C queue will always be bound to the cex4queue device driver. The Linux Device Driver model has no sensitivity for more than one device driver eligible for one device type. If there exist more than one drivers matching to the device type, simple all drivers are tried consecutively. There is no way to determine and influence the probing order of the drivers. With KVM there is a need to provide additional device drivers matching to the very same type of AP devices. With a simple implementation the KVM drivers run in competition to the regular drivers. Whichever 'wins' a device depends on build order and implementation details within the common Linux Device Driver Model and is not deterministic. However, a userspace process could figure out which device should be bound to which driver and sort out the correct binding by manipulating attributes in the sysfs. If for security reasons a AP device must not get bound to the 'wrong' device driver the sorting out has to be done within the Linux kernel by the AP bus code. This patch modifies the behavior of the AP bus for probing drivers for devices in a way that two sets of drivers are usable. Two new bitmasks 'apmask' and 'aqmask' are used to mark a subset of the APQN range for 'usable by the ap bus and the default drivers' or 'not usable by the default drivers and thus available for alternate drivers like vfio-xxx'. So an APQN which is addressed by this masking only the default drivers will be probed. In contrary an APQN which is not addressed by the masks will never be probed and bound to default drivers but onny to alternate drivers. Eventually the two masks give a way to divide the range of APQNs into two pools: one pool of APQNs used by the AP bus and the default drivers and thus via zcrypt drivers available to the userspace of the system. And another pool where no zcrypt drivers are bound to and which can be used by alternate drivers (like vfio-xxx) for their needs. This division is hot-plug save and makes sure a APQN assigned to an alternate driver is at no time somehow exploitable by the wrong party. The two masks are located in sysfs at /sys/bus/ap/apmask and /sys/bus/ap/aqmask. The mask syntax is exactly the same as the already existing mask attributes in the /sys/bus/ap directory (for example ap_usage_domain_mask and ap_control_domain_mask). By default all APQNs belong to the ap bus and the default drivers: cat /sys/bus/ap/apmask 0xffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff cat /sys/bus/ap/aqmask 0xffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff The masks can be changed at boot time with the kernel command line like this: ... ap.apmask=0xffff ap.aqmask=0x40 This would give these two pools: default drivers pool: adapter 0 - 15, domain 1 alternate drivers pool: adapter 0 - 15, all but domain 1 adapter 16-255, all domains The sysfs attributes for this two masks are writeable and an administrator is able to reconfigure the assignements on the fly by writing new mask values into. With changing the mask(s) a revision of the existing queue to driver bindings is done. So all APQNs which are bound to the 'wrong' driver are reprobed via kernel function device_reprobe() and thus the new correct driver will be assigned with respect of the changed apmask and aqmask bits. The mask values are bitmaps in big endian order starting with bit 0. So adapter number 0 is the leftmost bit, mask is 0x8000... The sysfs attributes accept 2 different formats: - Absolute hex string starting with 0x like "0x12345678" does set the mask starting from left to right. If the given string is shorter than the mask it is padded with 0s on the right. If the string is longer than the mask an error comes back (EINVAL). - '+' or '-' followed by a numerical value. Valid examples are "+1", "-13", "+0x41", "-0xff" and even "+0" and "-0". Only the addressed bit in the mask is switched on ('+') or off ('-'). This patch will also be the base for an upcoming extension to the zcrypt drivers to be able to provide additional zcrypt device nodes with filtering based on ap and aq masks. Signed-off-by: Harald Freudenberger <freude@linux.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2018-07-20 14:36:53 +08:00
/*
* The ap driver struct includes a flags field which holds some info for
* the ap bus about the driver. Currently only one flag is supported and
* used: The DEFAULT flag marks an ap driver as a default driver which is
* used together with the apmask and aqmask whitelisting of the ap bus.
*/
#define AP_DRIVER_FLAG_DEFAULT 0x0001
struct ap_driver {
struct device_driver driver;
struct ap_device_id *ids;
s390/zcrypt: AP bus support for alternate driver(s) The current AP bus, AP devices and AP device drivers implementation uses a clearly defined mapping for binding AP devices to AP device drivers. So for example a CEX6C queue will always be bound to the cex4queue device driver. The Linux Device Driver model has no sensitivity for more than one device driver eligible for one device type. If there exist more than one drivers matching to the device type, simple all drivers are tried consecutively. There is no way to determine and influence the probing order of the drivers. With KVM there is a need to provide additional device drivers matching to the very same type of AP devices. With a simple implementation the KVM drivers run in competition to the regular drivers. Whichever 'wins' a device depends on build order and implementation details within the common Linux Device Driver Model and is not deterministic. However, a userspace process could figure out which device should be bound to which driver and sort out the correct binding by manipulating attributes in the sysfs. If for security reasons a AP device must not get bound to the 'wrong' device driver the sorting out has to be done within the Linux kernel by the AP bus code. This patch modifies the behavior of the AP bus for probing drivers for devices in a way that two sets of drivers are usable. Two new bitmasks 'apmask' and 'aqmask' are used to mark a subset of the APQN range for 'usable by the ap bus and the default drivers' or 'not usable by the default drivers and thus available for alternate drivers like vfio-xxx'. So an APQN which is addressed by this masking only the default drivers will be probed. In contrary an APQN which is not addressed by the masks will never be probed and bound to default drivers but onny to alternate drivers. Eventually the two masks give a way to divide the range of APQNs into two pools: one pool of APQNs used by the AP bus and the default drivers and thus via zcrypt drivers available to the userspace of the system. And another pool where no zcrypt drivers are bound to and which can be used by alternate drivers (like vfio-xxx) for their needs. This division is hot-plug save and makes sure a APQN assigned to an alternate driver is at no time somehow exploitable by the wrong party. The two masks are located in sysfs at /sys/bus/ap/apmask and /sys/bus/ap/aqmask. The mask syntax is exactly the same as the already existing mask attributes in the /sys/bus/ap directory (for example ap_usage_domain_mask and ap_control_domain_mask). By default all APQNs belong to the ap bus and the default drivers: cat /sys/bus/ap/apmask 0xffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff cat /sys/bus/ap/aqmask 0xffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff The masks can be changed at boot time with the kernel command line like this: ... ap.apmask=0xffff ap.aqmask=0x40 This would give these two pools: default drivers pool: adapter 0 - 15, domain 1 alternate drivers pool: adapter 0 - 15, all but domain 1 adapter 16-255, all domains The sysfs attributes for this two masks are writeable and an administrator is able to reconfigure the assignements on the fly by writing new mask values into. With changing the mask(s) a revision of the existing queue to driver bindings is done. So all APQNs which are bound to the 'wrong' driver are reprobed via kernel function device_reprobe() and thus the new correct driver will be assigned with respect of the changed apmask and aqmask bits. The mask values are bitmaps in big endian order starting with bit 0. So adapter number 0 is the leftmost bit, mask is 0x8000... The sysfs attributes accept 2 different formats: - Absolute hex string starting with 0x like "0x12345678" does set the mask starting from left to right. If the given string is shorter than the mask it is padded with 0s on the right. If the string is longer than the mask an error comes back (EINVAL). - '+' or '-' followed by a numerical value. Valid examples are "+1", "-13", "+0x41", "-0xff" and even "+0" and "-0". Only the addressed bit in the mask is switched on ('+') or off ('-'). This patch will also be the base for an upcoming extension to the zcrypt drivers to be able to provide additional zcrypt device nodes with filtering based on ap and aq masks. Signed-off-by: Harald Freudenberger <freude@linux.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2018-07-20 14:36:53 +08:00
unsigned int flags;
int (*probe)(struct ap_device *);
void (*remove)(struct ap_device *);
void (*suspend)(struct ap_device *);
void (*resume)(struct ap_device *);
};
#define to_ap_drv(x) container_of((x), struct ap_driver, driver)
int ap_driver_register(struct ap_driver *, struct module *, char *);
void ap_driver_unregister(struct ap_driver *);
struct ap_device {
struct device device;
struct ap_driver *drv; /* Pointer to AP device driver. */
int device_type; /* AP device type. */
};
#define to_ap_dev(x) container_of((x), struct ap_device, device)
struct ap_card {
struct ap_device ap_dev;
struct list_head list; /* Private list of AP cards. */
struct list_head queues; /* List of assoc. AP queues */
void *private; /* ap driver private pointer. */
int raw_hwtype; /* AP raw hardware type. */
unsigned int functions; /* AP device function bitfield. */
int queue_depth; /* AP queue depth.*/
int id; /* AP card number. */
atomic_t total_request_count; /* # requests ever for this AP device.*/
};
#define to_ap_card(x) container_of((x), struct ap_card, ap_dev.device)
struct ap_queue {
struct ap_device ap_dev;
struct list_head list; /* Private list of AP queues. */
struct ap_card *card; /* Ptr to assoc. AP card. */
spinlock_t lock; /* Per device lock. */
void *private; /* ap driver private pointer. */
ap_qid_t qid; /* AP queue id. */
int interrupt; /* indicate if interrupts are enabled */
int queue_count; /* # messages currently on AP queue. */
enum ap_state state; /* State of the AP device. */
int pendingq_count; /* # requests on pendingq list. */
int requestq_count; /* # requests on requestq list. */
int total_request_count; /* # requests ever for this AP device.*/
int request_timeout; /* Request timeout in jiffies. */
struct timer_list timeout; /* Timer for request timeouts. */
struct list_head pendingq; /* List of message sent to AP queue. */
struct list_head requestq; /* List of message yet to be sent. */
struct ap_message *reply; /* Per device reply message. */
};
#define to_ap_queue(x) container_of((x), struct ap_queue, ap_dev.device)
typedef enum ap_wait (ap_func_t)(struct ap_queue *queue);
struct ap_message {
struct list_head list; /* Request queueing. */
unsigned long long psmid; /* Message id. */
void *message; /* Pointer to message buffer. */
size_t length; /* Message length. */
int rc; /* Return code for this message */
void *private; /* ap driver private pointer. */
unsigned int special:1; /* Used for special commands. */
/* receive is called from tasklet context */
void (*receive)(struct ap_queue *, struct ap_message *,
struct ap_message *);
};
/**
* ap_init_message() - Initialize ap_message.
* Initialize a message before using. Otherwise this might result in
* unexpected behaviour.
*/
static inline void ap_init_message(struct ap_message *ap_msg)
{
memset(ap_msg, 0, sizeof(*ap_msg));
}
/**
* ap_release_message() - Release ap_message.
* Releases all memory used internal within the ap_message struct
* Currently this is the message and private field.
*/
static inline void ap_release_message(struct ap_message *ap_msg)
{
kzfree(ap_msg->message);
kzfree(ap_msg->private);
}
#define for_each_ap_card(_ac) \
list_for_each_entry(_ac, &ap_card_list, list)
#define for_each_ap_queue(_aq, _ac) \
list_for_each_entry(_aq, &(_ac)->queues, list)
/*
* Note: don't use ap_send/ap_recv after using ap_queue_message
* for the first time. Otherwise the ap message queue will get
* confused.
*/
int ap_send(ap_qid_t, unsigned long long, void *, size_t);
int ap_recv(ap_qid_t, unsigned long long *, void *, size_t);
enum ap_wait ap_sm_event(struct ap_queue *aq, enum ap_event event);
enum ap_wait ap_sm_event_loop(struct ap_queue *aq, enum ap_event event);
void ap_queue_message(struct ap_queue *aq, struct ap_message *ap_msg);
void ap_cancel_message(struct ap_queue *aq, struct ap_message *ap_msg);
void ap_flush_queue(struct ap_queue *aq);
void *ap_airq_ptr(void);
void ap_wait(enum ap_wait wait);
void ap_request_timeout(struct timer_list *t);
void ap_bus_force_rescan(void);
int ap_test_config_usage_domain(unsigned int domain);
int ap_test_config_ctrl_domain(unsigned int domain);
void ap_queue_init_reply(struct ap_queue *aq, struct ap_message *ap_msg);
struct ap_queue *ap_queue_create(ap_qid_t qid, int device_type);
s390/zcrypt: revisit ap device remove procedure Working with the vfio-ap driver let to some revisit of the way how an ap (queue) device is removed from the driver. With the current implementation all the cleanup was done before the driver even got notified about the removal. Now the ap queue removal is done in 3 steps: 1) A preparation step, all ap messages within the queue are flushed and so the driver does 'receive' them. Also a new state AP_STATE_REMOVE assigned to the queue makes sure there are no new messages queued in. 2) Now the driver's remove function is invoked and the driver should do the job of cleaning up it's internal administration lists or whatever. After 2) is done it is guaranteed, that the driver is not invoked any more. On the other hand the driver has to make sure that the APQN is not accessed any more after step 2 is complete. 3) Now the ap bus code does the job of total cleanup of the APQN. A reset with zero is triggered and the state of the queue goes to AP_STATE_UNBOUND. After step 3) is complete, the ap queue has no pending messages and the APQN is cleared and so there are no requests and replies lingering around in the firmware queue for this APQN. Also the interrupts are disabled. After these remove steps the ap queue device may be assigned to another driver. Stress testing this remove/probe procedure showed a problem with the correct module reference counting. The actual receive of an reply in the driver is done asynchronous with completions. So with a driver change on an ap queue the message flush triggers completions but the threads waiting for the completions may run at a time where the queue already has the new driver assigned. So the module_put() at receive time needs to be done on the driver module which queued the ap message. This change is also part of this patch. Signed-off-by: Harald Freudenberger <freude@linux.ibm.com> Reviewed-by: Ingo Franzki <ifranzki@linux.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2019-02-23 00:24:11 +08:00
void ap_queue_prepare_remove(struct ap_queue *aq);
void ap_queue_remove(struct ap_queue *aq);
void ap_queue_suspend(struct ap_device *ap_dev);
void ap_queue_resume(struct ap_device *ap_dev);
s390/zcrypt: reinit ap queue state machine during device probe Until the vfio-ap driver came into live there was a well known agreement about the way how ap devices are initialized and their states when the driver's probe function is called. However, the vfio device driver when receiving an ap queue device does additional resets thereby removing the registration for interrupts for the ap device done by the ap bus core code. So when later the vfio driver releases the device and one of the default zcrypt drivers takes care of the device the interrupt registration needs to get renewed. The current code does no renew and result is that requests send into such a queue will never see a reply processed - the application hangs. This patch adds a function which resets the aq queue state machine for the ap queue device and triggers the walk through the initial states (which are reset and registration for interrupts). This function is now called before the driver's probe function is invoked. When the association between driver and device is released, the driver's remove function is called. The current implementation calls a ap queue function ap_queue_remove(). This invokation has been moved to the ap bus function to make the probe / remove pair for ap bus and drivers more symmetric. Fixes: 7e0bdbe5c21c ("s390/zcrypt: AP bus support for alternate driver(s)") Cc: stable@vger.kernel.org # 4.19+ Signed-off-by: Harald Freudenberger <freude@linux.ibm.com> Reviewd-by: Tony Krowiak <akrowiak@linux.ibm.com> Reviewd-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2018-11-09 21:59:24 +08:00
void ap_queue_reinit_state(struct ap_queue *aq);
struct ap_card *ap_card_create(int id, int queue_depth, int raw_device_type,
int comp_device_type, unsigned int functions);
s390/zcrypt: multiple zcrypt device nodes support This patch is an extension to the zcrypt device driver to provide, support and maintain multiple zcrypt device nodes. The individual zcrypt device nodes can be restricted in terms of crypto cards, domains and available ioctls. Such a device node can be used as a base for container solutions like docker to control and restrict the access to crypto resources. The handling is done with a new sysfs subdir /sys/class/zcrypt. Echoing a name (or an empty sting) into the attribute "create" creates a new zcrypt device node. In /sys/class/zcrypt a new link will appear which points to the sysfs device tree of this new device. The attribute files "ioctlmask", "apmask" and "aqmask" in this directory are used to customize this new zcrypt device node instance. Finally the zcrypt device node can be destroyed by echoing the name into /sys/class/zcrypt/destroy. The internal structs holding the device info are reference counted - so a destroy will not hard remove a device but only marks it as removable when the reference counter drops to zero. The mask values are bitmaps in big endian order starting with bit 0. So adapter number 0 is the leftmost bit, mask is 0x8000... The sysfs attributes accept 2 different formats: * Absolute hex string starting with 0x like "0x12345678" does set the mask starting from left to right. If the given string is shorter than the mask it is padded with 0s on the right. If the string is longer than the mask an error comes back (EINVAL). * Relative format - a concatenation (done with ',') of the terms +<bitnr>[-<bitnr>] or -<bitnr>[-<bitnr>]. <bitnr> may be any valid number (hex, decimal or octal) in the range 0...255. Here are some examples: "+0-15,+32,-128,-0xFF" "-0-255,+1-16,+0x128" "+1,+2,+3,+4,-5,-7-10" A simple usage examples: # create new zcrypt device 'my_zcrypt': echo "my_zcrypt" >/sys/class/zcrypt/create # go into the device dir of this new device echo "my_zcrypt" >create cd my_zcrypt/ ls -l total 0 -rw-r--r-- 1 root root 4096 Jul 20 15:23 apmask -rw-r--r-- 1 root root 4096 Jul 20 15:23 aqmask -r--r--r-- 1 root root 4096 Jul 20 15:23 dev -rw-r--r-- 1 root root 4096 Jul 20 15:23 ioctlmask lrwxrwxrwx 1 root root 0 Jul 20 15:23 subsystem -> ../../../../class/zcrypt ... # customize this zcrypt node clone # enable only adapter 0 and 2 echo "0xa0" >apmask # enable only domain 6 echo "+6" >aqmask # enable all 256 ioctls echo "+0-255" >ioctls # now the /dev/my_zcrypt may be used # finally destroy it echo "my_zcrypt" >/sys/class/zcrypt/destroy Please note that a very similar 'filtering behavior' also applies to the parent z90crypt device. The two mask attributes apmask and aqmask in /sys/bus/ap act the very same for the z90crypt device node. However the implementation here is totally different as the ap bus acts on bind/unbind of queue devices and associated drivers but the effect is still the same. So there are two filters active for each additional zcrypt device node: The adapter/domain needs to be enabled on the ap bus level and it needs to be active on the zcrypt device node level. Signed-off-by: Harald Freudenberger <freude@linux.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2018-09-17 22:18:41 +08:00
struct ap_perms {
unsigned long ioctlm[BITS_TO_LONGS(AP_IOCTLS)];
unsigned long apm[BITS_TO_LONGS(AP_DEVICES)];
unsigned long aqm[BITS_TO_LONGS(AP_DOMAINS)];
};
extern struct ap_perms ap_perms;
extern struct mutex ap_perms_mutex;
s390/zcrypt: AP bus support for alternate driver(s) The current AP bus, AP devices and AP device drivers implementation uses a clearly defined mapping for binding AP devices to AP device drivers. So for example a CEX6C queue will always be bound to the cex4queue device driver. The Linux Device Driver model has no sensitivity for more than one device driver eligible for one device type. If there exist more than one drivers matching to the device type, simple all drivers are tried consecutively. There is no way to determine and influence the probing order of the drivers. With KVM there is a need to provide additional device drivers matching to the very same type of AP devices. With a simple implementation the KVM drivers run in competition to the regular drivers. Whichever 'wins' a device depends on build order and implementation details within the common Linux Device Driver Model and is not deterministic. However, a userspace process could figure out which device should be bound to which driver and sort out the correct binding by manipulating attributes in the sysfs. If for security reasons a AP device must not get bound to the 'wrong' device driver the sorting out has to be done within the Linux kernel by the AP bus code. This patch modifies the behavior of the AP bus for probing drivers for devices in a way that two sets of drivers are usable. Two new bitmasks 'apmask' and 'aqmask' are used to mark a subset of the APQN range for 'usable by the ap bus and the default drivers' or 'not usable by the default drivers and thus available for alternate drivers like vfio-xxx'. So an APQN which is addressed by this masking only the default drivers will be probed. In contrary an APQN which is not addressed by the masks will never be probed and bound to default drivers but onny to alternate drivers. Eventually the two masks give a way to divide the range of APQNs into two pools: one pool of APQNs used by the AP bus and the default drivers and thus via zcrypt drivers available to the userspace of the system. And another pool where no zcrypt drivers are bound to and which can be used by alternate drivers (like vfio-xxx) for their needs. This division is hot-plug save and makes sure a APQN assigned to an alternate driver is at no time somehow exploitable by the wrong party. The two masks are located in sysfs at /sys/bus/ap/apmask and /sys/bus/ap/aqmask. The mask syntax is exactly the same as the already existing mask attributes in the /sys/bus/ap directory (for example ap_usage_domain_mask and ap_control_domain_mask). By default all APQNs belong to the ap bus and the default drivers: cat /sys/bus/ap/apmask 0xffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff cat /sys/bus/ap/aqmask 0xffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff The masks can be changed at boot time with the kernel command line like this: ... ap.apmask=0xffff ap.aqmask=0x40 This would give these two pools: default drivers pool: adapter 0 - 15, domain 1 alternate drivers pool: adapter 0 - 15, all but domain 1 adapter 16-255, all domains The sysfs attributes for this two masks are writeable and an administrator is able to reconfigure the assignements on the fly by writing new mask values into. With changing the mask(s) a revision of the existing queue to driver bindings is done. So all APQNs which are bound to the 'wrong' driver are reprobed via kernel function device_reprobe() and thus the new correct driver will be assigned with respect of the changed apmask and aqmask bits. The mask values are bitmaps in big endian order starting with bit 0. So adapter number 0 is the leftmost bit, mask is 0x8000... The sysfs attributes accept 2 different formats: - Absolute hex string starting with 0x like "0x12345678" does set the mask starting from left to right. If the given string is shorter than the mask it is padded with 0s on the right. If the string is longer than the mask an error comes back (EINVAL). - '+' or '-' followed by a numerical value. Valid examples are "+1", "-13", "+0x41", "-0xff" and even "+0" and "-0". Only the addressed bit in the mask is switched on ('+') or off ('-'). This patch will also be the base for an upcoming extension to the zcrypt drivers to be able to provide additional zcrypt device nodes with filtering based on ap and aq masks. Signed-off-by: Harald Freudenberger <freude@linux.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2018-07-20 14:36:53 +08:00
/*
* check APQN for owned/reserved by ap bus and default driver(s).
* Checks if this APQN is or will be in use by the ap bus
* and the default set of drivers.
* If yes, returns 1, if not returns 0. On error a negative
* errno value is returned.
*/
int ap_owned_by_def_drv(int card, int queue);
/*
* check 'matrix' of APQNs for owned/reserved by ap bus and
* default driver(s).
* Checks if there is at least one APQN in the given 'matrix'
* marked as owned/reserved by the ap bus and default driver(s).
* If such an APQN is found the return value is 1, otherwise
* 0 is returned. On error a negative errno value is returned.
* The parameter apm is a bitmask which should be declared
* as DECLARE_BITMAP(apm, AP_DEVICES), the aqm parameter is
* similar, should be declared as DECLARE_BITMAP(aqm, AP_DOMAINS).
*/
int ap_apqn_in_matrix_owned_by_def_drv(unsigned long *apm,
unsigned long *aqm);
s390/zcrypt: multiple zcrypt device nodes support This patch is an extension to the zcrypt device driver to provide, support and maintain multiple zcrypt device nodes. The individual zcrypt device nodes can be restricted in terms of crypto cards, domains and available ioctls. Such a device node can be used as a base for container solutions like docker to control and restrict the access to crypto resources. The handling is done with a new sysfs subdir /sys/class/zcrypt. Echoing a name (or an empty sting) into the attribute "create" creates a new zcrypt device node. In /sys/class/zcrypt a new link will appear which points to the sysfs device tree of this new device. The attribute files "ioctlmask", "apmask" and "aqmask" in this directory are used to customize this new zcrypt device node instance. Finally the zcrypt device node can be destroyed by echoing the name into /sys/class/zcrypt/destroy. The internal structs holding the device info are reference counted - so a destroy will not hard remove a device but only marks it as removable when the reference counter drops to zero. The mask values are bitmaps in big endian order starting with bit 0. So adapter number 0 is the leftmost bit, mask is 0x8000... The sysfs attributes accept 2 different formats: * Absolute hex string starting with 0x like "0x12345678" does set the mask starting from left to right. If the given string is shorter than the mask it is padded with 0s on the right. If the string is longer than the mask an error comes back (EINVAL). * Relative format - a concatenation (done with ',') of the terms +<bitnr>[-<bitnr>] or -<bitnr>[-<bitnr>]. <bitnr> may be any valid number (hex, decimal or octal) in the range 0...255. Here are some examples: "+0-15,+32,-128,-0xFF" "-0-255,+1-16,+0x128" "+1,+2,+3,+4,-5,-7-10" A simple usage examples: # create new zcrypt device 'my_zcrypt': echo "my_zcrypt" >/sys/class/zcrypt/create # go into the device dir of this new device echo "my_zcrypt" >create cd my_zcrypt/ ls -l total 0 -rw-r--r-- 1 root root 4096 Jul 20 15:23 apmask -rw-r--r-- 1 root root 4096 Jul 20 15:23 aqmask -r--r--r-- 1 root root 4096 Jul 20 15:23 dev -rw-r--r-- 1 root root 4096 Jul 20 15:23 ioctlmask lrwxrwxrwx 1 root root 0 Jul 20 15:23 subsystem -> ../../../../class/zcrypt ... # customize this zcrypt node clone # enable only adapter 0 and 2 echo "0xa0" >apmask # enable only domain 6 echo "+6" >aqmask # enable all 256 ioctls echo "+0-255" >ioctls # now the /dev/my_zcrypt may be used # finally destroy it echo "my_zcrypt" >/sys/class/zcrypt/destroy Please note that a very similar 'filtering behavior' also applies to the parent z90crypt device. The two mask attributes apmask and aqmask in /sys/bus/ap act the very same for the z90crypt device node. However the implementation here is totally different as the ap bus acts on bind/unbind of queue devices and associated drivers but the effect is still the same. So there are two filters active for each additional zcrypt device node: The adapter/domain needs to be enabled on the ap bus level and it needs to be active on the zcrypt device node level. Signed-off-by: Harald Freudenberger <freude@linux.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2018-09-17 22:18:41 +08:00
/*
* ap_parse_mask_str() - helper function to parse a bitmap string
* and clear/set the bits in the bitmap accordingly. The string may be
* given as absolute value, a hex string like 0x1F2E3D4C5B6A" simple
* overwriting the current content of the bitmap. Or as relative string
* like "+1-16,-32,-0x40,+128" where only single bits or ranges of
* bits are cleared or set. Distinction is done based on the very
* first character which may be '+' or '-' for the relative string
* and othewise assume to be an absolute value string. If parsing fails
* a negative errno value is returned. All arguments and bitmaps are
* big endian order.
*/
int ap_parse_mask_str(const char *str,
unsigned long *bitmap, int bits,
struct mutex *lock);
#endif /* _AP_BUS_H_ */