On 10/27/20 12:55 PM, Harald Freudenberger wrote:
On 22.10.20 19:11, Tony Krowiak wrote:Introduces a new driver callback to prevent a root user from unbinding an AP queue from its device driver if the queue is in use. The callback will be invoked whenever a change to the AP bus's sysfs apmask or aqmask attributes would result in one or more AP queues being removed from its driver. If the callback responds in the affirmative for any driver queried, the change to the apmask or aqmask will be rejected with a device in use error. For this patch, only non-default drivers will be queried. Currently, there is only one non-default driver, the vfio_ap device driver. The vfio_ap device driver facilitates pass-through of an AP queue to a guest. The idea here is that a guest may be administered by a different sysadmin than the host and we don't want AP resources to unexpectedly disappear from a guest's AP configuration (i.e., adapters and domains assigned to the matrix mdev). This will enforce the proper procedure for removing AP resources intended for guest usage which is to first unassign them from the matrix mdev, then unbind them from the vfio_ap device driver. Signed-off-by: Tony Krowiak <akrowiak@xxxxxxxxxxxxx> --- drivers/s390/crypto/ap_bus.c | 148 ++++++++++++++++++++++++++++++++--- drivers/s390/crypto/ap_bus.h | 4 + 2 files changed, 142 insertions(+), 10 deletions(-) diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 485cbfcbf06e..998e61cd86d9 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -35,6 +35,7 @@ #include <linux/mod_devicetable.h> #include <linux/debugfs.h> #include <linux/ctype.h> +#include <linux/module.h>#include "ap_bus.h"#include "ap_debug.h" @@ -893,6 +894,23 @@ static int modify_bitmap(const char *str, unsigned long *bitmap, int bits) return 0; }+static int ap_parse_bitmap_str(const char *str, unsigned long *bitmap, int bits,+ unsigned long *newmap) +{ + unsigned long size; + int rc; + + size = BITS_TO_LONGS(bits)*sizeof(unsigned long); + if (*str == '+' || *str == '-') { + memcpy(newmap, bitmap, size); + rc = modify_bitmap(str, newmap, bits); + } else { + memset(newmap, 0, size); + rc = hex2bitmap(str, newmap, bits); + } + return rc; +} + int ap_parse_mask_str(const char *str, unsigned long *bitmap, int bits, struct mutex *lock) @@ -912,14 +930,7 @@ int ap_parse_mask_str(const char *str, kfree(newmap); return -ERESTARTSYS; } - - if (*str == '+' || *str == '-') { - memcpy(newmap, bitmap, size); - rc = modify_bitmap(str, newmap, bits); - } else { - memset(newmap, 0, size); - rc = hex2bitmap(str, newmap, bits); - } + rc = ap_parse_bitmap_str(str, bitmap, bits, newmap); if (rc == 0) memcpy(bitmap, newmap, size); mutex_unlock(lock); @@ -1111,12 +1122,70 @@ static ssize_t apmask_show(struct bus_type *bus, char *buf) return rc; }+static int __verify_card_reservations(struct device_driver *drv, void *data)+{ + int rc = 0; + struct ap_driver *ap_drv = to_ap_drv(drv); + unsigned long *newapm = (unsigned long *)data; + + /* + * No need to verify whether the driver is using the queues if it is the + * default driver. + */ + if (ap_drv->flags & AP_DRIVER_FLAG_DEFAULT) + return 0; + + /* The non-default driver's module must be loaded */Can you please update this comment? It should be something like /* increase the driver's module refcounter to be sure it is not going away when we invoke the callback function. */
Will do.
+ if (!try_module_get(drv->owner)) + return 0; + + if (ap_drv->in_use) + if (ap_drv->in_use(newapm, ap_perms.aqm)) + rc = -EBUSY; +And here: /* release driver's module */ or simmilar
Okay
+ module_put(drv->owner); + + return rc; +} + +static int apmask_commit(unsigned long *newapm) +{ + int rc; + unsigned long reserved[BITS_TO_LONGS(AP_DEVICES)]; + + /* + * Check if any bits in the apmask have been set which will + * result in queues being removed from non-default drivers + */ + if (bitmap_andnot(reserved, newapm, ap_perms.apm, AP_DEVICES)) { + rc = bus_for_each_drv(&ap_bus_type, NULL, reserved, + __verify_card_reservations); + if (rc) + return rc; + } + + memcpy(ap_perms.apm, newapm, APMASKSIZE); + + return 0; +} + static ssize_t apmask_store(struct bus_type *bus, const char *buf, size_t count) { int rc; + DECLARE_BITMAP(newapm, AP_DEVICES); + + if (mutex_lock_interruptible(&ap_perms_mutex)) + return -ERESTARTSYS; + + rc = ap_parse_bitmap_str(buf, ap_perms.apm, AP_DEVICES, newapm); + if (rc) + goto done;- rc = ap_parse_mask_str(buf, ap_perms.apm, AP_DEVICES, &ap_perms_mutex);+ rc = apmask_commit(newapm); + +done: + mutex_unlock(&ap_perms_mutex); if (rc) return rc;@@ -1142,12 +1211,71 @@ static ssize_t aqmask_show(struct bus_type *bus, char *buf)return rc; }+static int __verify_queue_reservations(struct device_driver *drv, void *data)+{ + int rc = 0; + struct ap_driver *ap_drv = to_ap_drv(drv); + unsigned long *newaqm = (unsigned long *)data; + + /* + * If the reserved bits do not identify queues reserved for use by the + * non-default driver, there is no need to verify the driver is using + * the queues. + */ + if (ap_drv->flags & AP_DRIVER_FLAG_DEFAULT) + return 0; + + /* The non-default driver's module must be loaded */Same here.
Okay
+ if (!try_module_get(drv->owner)) + return 0; + + if (ap_drv->in_use) + if (ap_drv->in_use(ap_perms.apm, newaqm)) + rc = -EBUSY; +and here
Okay
+ module_put(drv->owner); + + return rc; +} + +static int aqmask_commit(unsigned long *newaqm) +{ + int rc; + unsigned long reserved[BITS_TO_LONGS(AP_DOMAINS)]; + + /* + * Check if any bits in the aqmask have been set which will + * result in queues being removed from non-default drivers + */ + if (bitmap_andnot(reserved, newaqm, ap_perms.aqm, AP_DOMAINS)) { + rc = bus_for_each_drv(&ap_bus_type, NULL, reserved, + __verify_queue_reservations); + if (rc) + return rc; + } + + memcpy(ap_perms.aqm, newaqm, AQMASKSIZE); + + return 0; +} + static ssize_t aqmask_store(struct bus_type *bus, const char *buf, size_t count) { int rc; + DECLARE_BITMAP(newaqm, AP_DOMAINS);- rc = ap_parse_mask_str(buf, ap_perms.aqm, AP_DOMAINS, &ap_perms_mutex);+ if (mutex_lock_interruptible(&ap_perms_mutex)) + return -ERESTARTSYS; + + rc = ap_parse_bitmap_str(buf, ap_perms.aqm, AP_DOMAINS, newaqm); + if (rc) + goto done; + + rc = aqmask_commit(newaqm); + +done: + mutex_unlock(&ap_perms_mutex); if (rc) return rc;diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.hindex 5029b80132aa..6ce154d924d3 100644 --- a/drivers/s390/crypto/ap_bus.h +++ b/drivers/s390/crypto/ap_bus.h @@ -145,6 +145,7 @@ struct ap_driver {int (*probe)(struct ap_device *);void (*remove)(struct ap_device *); + bool (*in_use)(unsigned long *apm, unsigned long *aqm); };#define to_ap_drv(x) container_of((x), struct ap_driver, driver)@@ -293,6 +294,9 @@ void ap_queue_init_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);+#define APMASKSIZE (BITS_TO_LONGS(AP_DEVICES) * sizeof(unsigned long))+#define AQMASKSIZE (BITS_TO_LONGS(AP_DOMAINS) * sizeof(unsigned long)) + struct ap_perms { unsigned long ioctlm[BITS_TO_LONGS(AP_IOCTLS)]; unsigned long apm[BITS_TO_LONGS(AP_DEVICES)];I still don't like this code. That's because of what it is doing - not because of the code quality. And Halil, you are right. It is adding more pressure to the mutex used for locking the apmask and aqmask stuff (and the zcrypt multiple device drivers support code also). I am very concerned about the in_use callback which is called with the ap_perms_mutex held AND during bus_for_each_drv (so holding the overall AP BUS mutex) and then diving into the vfio_ap ... with yet another mutex to protect the vfio structs. Reviewed-by: Harald Freudenberger <freude@xxxxxxxxxxxxx>
Thank you for your review. Maybe you ought to bring these concerns up withour crypto architect. Halil came up with a solution for the potential deadlock situation. We will be using the mutex_trylock() function in our sysfs assignment interfaces which make the call to the AP bus to check permissions (which also
locks ap_perms). If the mutex_trylock() fails, we return from the assignment function with -EBUSY. This should resolve that potential deadlock issue.
