static ssize_t version_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
u64 slu_id, app_id;
struct genwqe_dev *cd = dev_get_drvdata(dev);
slu_id = __genwqe_readq(cd, IO_SLU_UNITCFG);
app_id = __genwqe_readq(cd, IO_APP_UNITCFG);
return sprintf(buf, "%016llx.%016llx\n", slu_id, app_id);
}
static int genwqe_read_ids(struct genwqe_dev *cd)
{
int err = 0;
int slu_id;
struct pci_dev *pci_dev = cd->pci_dev;
cd->slu_unitcfg = __genwqe_readq(cd, IO_SLU_UNITCFG);
if (cd->slu_unitcfg == IO_ILLEGAL_VALUE) {
dev_err(&pci_dev->dev,
"err: SLUID=%016llx\n", cd->slu_unitcfg);
err = -EIO;
goto out_err;
}
slu_id = genwqe_get_slu_id(cd);
if (slu_id < GENWQE_SLU_ARCH_REQ || slu_id == 0xff) {
dev_err(&pci_dev->dev,
"err: incompatible SLU Architecture %u\n", slu_id);
err = -ENOENT;
goto out_err;
}
cd->app_unitcfg = __genwqe_readq(cd, IO_APP_UNITCFG);
if (cd->app_unitcfg == IO_ILLEGAL_VALUE) {
dev_err(&pci_dev->dev,
"err: APPID=%016llx\n", cd->app_unitcfg);
err = -EIO;
goto out_err;
}
genwqe_read_app_id(cd, cd->app_name, sizeof(cd->app_name));
/*
* Is access to all registers possible? If we are a VF the
* answer is obvious. If we run fully virtualized, we need to
* check if we can access all registers. If we do not have
* full access we will cause an UR and some informational FIRs
* in the PF, but that should not harm.
*/
if (pci_dev->is_virtfn)
cd->is_privileged = 0;
else
cd->is_privileged = (__genwqe_readq(cd, IO_SLU_BITSTREAM)
!= IO_ILLEGAL_VALUE);
out_err:
return err;
}
/**
* curr_bitstream_show() - Show the current bitstream id
*
* There is a bug in some old versions of the CPLD which selects the
* bitstream, which causes the IO_SLU_BITSTREAM register to report
* unreliable data in very rare cases. This makes this sysfs
* unreliable up to the point were a new CPLD version is being used.
*
* Unfortunately there is no automatic way yet to query the CPLD
* version, such that you need to manually ensure via programming
* tools that you have a recent version of the CPLD software.
*
* The proposed circumvention is to use a special recovery bitstream
* on the backup partition (0) to identify problems while loading the
* image.
*/
static ssize_t curr_bitstream_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
int curr_bitstream;
struct genwqe_dev *cd = dev_get_drvdata(dev);
curr_bitstream = __genwqe_readq(cd, IO_SLU_BITSTREAM) & 0x1;
return sprintf(buf, "%d\n", curr_bitstream);
}
static ssize_t tempsens_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
u64 tempsens;
struct genwqe_dev *cd = dev_get_drvdata(dev);
tempsens = __genwqe_readq(cd, IO_SLU_TEMPERATURE_SENSOR);
return sprintf(buf, "%016llx\n", tempsens);
}
static ssize_t queue_working_time_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
u64 t;
struct genwqe_dev *cd = dev_get_drvdata(dev);
t = __genwqe_readq(cd, IO_SLC_QUEUE_WTIME);
return sprintf(buf, "%016llx\n", t);
}
static ssize_t freerunning_timer_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
u64 t;
struct genwqe_dev *cd = dev_get_drvdata(dev);
t = __genwqe_readq(cd, IO_SLC_FREE_RUNNING_TIMER);
return sprintf(buf, "%016llx\n", t);
}
/**
* genwqe_health_thread() - Health checking thread
*
* This thread is only started for the PF of the card.
*
* This thread monitors the health of the card. A critical situation
* is when we read registers which contain -1 (IO_ILLEGAL_VALUE). In
* this case we need to be recovered from outside. Writing to
* registers will very likely not work either.
*
* This thread must only exit if kthread_should_stop() becomes true.
*
* Condition for the health-thread to trigger:
* a) when a kthread_stop() request comes in or
* b) a critical GFIR occured
*
* Informational GFIRs are checked and potentially printed in
* health_check_interval seconds.
*/
static int genwqe_health_thread(void *data)
{
int rc, should_stop = 0;
struct genwqe_dev *cd = data;
struct pci_dev *pci_dev = cd->pci_dev;
u64 gfir, gfir_masked, slu_unitcfg, app_unitcfg;
health_thread_begin:
while (!kthread_should_stop()) {
rc = wait_event_interruptible_timeout(cd->health_waitq,
(genwqe_health_check_cond(cd, &gfir) ||
(should_stop = kthread_should_stop())),
genwqe_health_check_interval * HZ);
if (should_stop)
break;
if (gfir == IO_ILLEGAL_VALUE) {
dev_err(&pci_dev->dev,
"[%s] GFIR=%016llx\n", __func__, gfir);
goto fatal_error;
}
slu_unitcfg = __genwqe_readq(cd, IO_SLU_UNITCFG);
if (slu_unitcfg == IO_ILLEGAL_VALUE) {
dev_err(&pci_dev->dev,
"[%s] SLU_UNITCFG=%016llx\n",
__func__, slu_unitcfg);
goto fatal_error;
}
app_unitcfg = __genwqe_readq(cd, IO_APP_UNITCFG);
if (app_unitcfg == IO_ILLEGAL_VALUE) {
dev_err(&pci_dev->dev,
"[%s] APP_UNITCFG=%016llx\n",
__func__, app_unitcfg);
goto fatal_error;
}
gfir = __genwqe_readq(cd, IO_SLC_CFGREG_GFIR);
if (gfir == IO_ILLEGAL_VALUE) {
dev_err(&pci_dev->dev,
"[%s] %s: GFIR=%016llx\n", __func__,
(gfir & GFIR_ERR_TRIGGER) ? "err" : "info",
gfir);
goto fatal_error;
}
gfir_masked = genwqe_fir_checking(cd);
if (gfir_masked == IO_ILLEGAL_VALUE)
goto fatal_error;
/*
* GFIR ErrorTrigger bits set => reset the card!
* Never do this for old/manufacturing images!
*/
if ((gfir_masked) && !cd->skip_recovery &&
genwqe_recovery_on_fatal_gfir_required(cd)) {
cd->card_state = GENWQE_CARD_FATAL_ERROR;
rc = genwqe_recover_card(cd, 0);
if (rc < 0) {
/* FIXME Card is unusable and needs unbind! */
goto fatal_error;
}
}
if (cd->card_state == GENWQE_CARD_RELOAD_BITSTREAM) {
/* Userspace requested card bitstream reload */
rc = genwqe_reload_bistream(cd);
if (rc)
goto fatal_error;
}
cd->last_gfir = gfir;
cond_resched();
}
return 0;
fatal_error:
if (cd->use_platform_recovery) {
/*
* Since we use raw accessors, EEH errors won't be detected
* by the platform until we do a non-raw MMIO or config space
* read
*/
readq(cd->mmio + IO_SLC_CFGREG_GFIR);
/* We do nothing if the card is going over PCI recovery */
if (pci_channel_offline(pci_dev))
return -EIO;
/*
* If it's supported by the platform, we try a fundamental reset
* to recover from a fatal error. Otherwise, we continue to wait
* for an external recovery procedure to take care of it.
*/
rc = genwqe_platform_recovery(cd);
if (!rc)
goto health_thread_begin;
}
dev_err(&pci_dev->dev,
"[%s] card unusable. Please trigger unbind!\n", __func__);
/* Bring down logical devices to inform user space via udev remove. */
cd->card_state = GENWQE_CARD_FATAL_ERROR;
genwqe_stop(cd);
/* genwqe_bus_reset failed(). Now wait for genwqe_remove(). */
while (!kthread_should_stop())
cond_resched();
return -EIO;
}
/**
* genwqe_fir_checking() - Check the fault isolation registers of the card
*
* If this code works ok, can be tried out with help of the genwqe_poke tool:
* sudo ./tools/genwqe_poke 0x8 0xfefefefefef
*
* Now the relevant FIRs/sFIRs should be printed out and the driver should
* invoke recovery (devices are removed and readded).
*/
static u64 genwqe_fir_checking(struct genwqe_dev *cd)
{
int j, iterations = 0;
u64 mask, fir, fec, uid, gfir, gfir_masked, sfir, sfec;
u32 fir_addr, fir_clr_addr, fec_addr, sfir_addr, sfec_addr;
struct pci_dev *pci_dev = cd->pci_dev;
healthMonitor:
iterations++;
if (iterations > 16) {
dev_err(&pci_dev->dev, "* exit looping after %d times\n",
iterations);
goto fatal_error;
}
gfir = __genwqe_readq(cd, IO_SLC_CFGREG_GFIR);
if (gfir != 0x0)
dev_err(&pci_dev->dev, "* 0x%08x 0x%016llx\n",
IO_SLC_CFGREG_GFIR, gfir);
if (gfir == IO_ILLEGAL_VALUE)
goto fatal_error;
/*
* Avoid printing when to GFIR bit is on prevents contignous
* printout e.g. for the following bug:
* FIR set without a 2ndary FIR/FIR cannot be cleared
* Comment out the following if to get the prints:
*/
if (gfir == 0)
return 0;
gfir_masked = gfir & GFIR_ERR_TRIGGER; /* fatal errors */
for (uid = 0; uid < GENWQE_MAX_UNITS; uid++) { /* 0..2 in zEDC */
/* read the primary FIR (pfir) */
fir_addr = (uid << 24) + 0x08;
fir = __genwqe_readq(cd, fir_addr);
if (fir == 0x0)
continue; /* no error in this unit */
dev_err(&pci_dev->dev, "* 0x%08x 0x%016llx\n", fir_addr, fir);
if (fir == IO_ILLEGAL_VALUE)
goto fatal_error;
/* read primary FEC */
fec_addr = (uid << 24) + 0x18;
fec = __genwqe_readq(cd, fec_addr);
dev_err(&pci_dev->dev, "* 0x%08x 0x%016llx\n", fec_addr, fec);
if (fec == IO_ILLEGAL_VALUE)
goto fatal_error;
for (j = 0, mask = 1ULL; j < 64; j++, mask <<= 1) {
/* secondary fir empty, skip it */
if ((fir & mask) == 0x0)
continue;
sfir_addr = (uid << 24) + 0x100 + 0x08 * j;
sfir = __genwqe_readq(cd, sfir_addr);
if (sfir == IO_ILLEGAL_VALUE)
goto fatal_error;
dev_err(&pci_dev->dev,
"* 0x%08x 0x%016llx\n", sfir_addr, sfir);
sfec_addr = (uid << 24) + 0x300 + 0x08 * j;
sfec = __genwqe_readq(cd, sfec_addr);
if (sfec == IO_ILLEGAL_VALUE)
goto fatal_error;
dev_err(&pci_dev->dev,
"* 0x%08x 0x%016llx\n", sfec_addr, sfec);
gfir = __genwqe_readq(cd, IO_SLC_CFGREG_GFIR);
if (gfir == IO_ILLEGAL_VALUE)
goto fatal_error;
/* gfir turned on during routine! get out and
start over. */
if ((gfir_masked == 0x0) &&
(gfir & GFIR_ERR_TRIGGER)) {
goto healthMonitor;
}
/* do not clear if we entered with a fatal gfir */
if (gfir_masked == 0x0) {
/* NEW clear by mask the logged bits */
sfir_addr = (uid << 24) + 0x100 + 0x08 * j;
__genwqe_writeq(cd, sfir_addr, sfir);
dev_dbg(&pci_dev->dev,
"[HM] Clearing 2ndary FIR 0x%08x with 0x%016llx\n",
sfir_addr, sfir);
/*
* note, these cannot be error-Firs
* since gfir_masked is 0 after sfir
* was read. Also, it is safe to do
* this write if sfir=0. Still need to
* clear the primary. This just means
* there is no secondary FIR.
*/
/* clear by mask the logged bit. */
fir_clr_addr = (uid << 24) + 0x10;
__genwqe_writeq(cd, fir_clr_addr, mask);
dev_dbg(&pci_dev->dev,
"[HM] Clearing primary FIR 0x%08x with 0x%016llx\n",
fir_clr_addr, mask);
}
}
}
gfir = __genwqe_readq(cd, IO_SLC_CFGREG_GFIR);
if (gfir == IO_ILLEGAL_VALUE)
goto fatal_error;
if ((gfir_masked == 0x0) && (gfir & GFIR_ERR_TRIGGER)) {
/*
* Check once more that it didn't go on after all the
* FIRS were cleared.
*/
dev_dbg(&pci_dev->dev, "ACK! Another FIR! Recursing %d!\n",
iterations);
goto healthMonitor;
}
return gfir_masked;
fatal_error:
return IO_ILLEGAL_VALUE;
}
static int genwqe_health_check_cond(struct genwqe_dev *cd, u64 *gfir)
{
*gfir = __genwqe_readq(cd, IO_SLC_CFGREG_GFIR);
return (*gfir & GFIR_ERR_TRIGGER) &&
genwqe_recovery_on_fatal_gfir_required(cd);
}
