1
0
Fork 0

cxl: Adapter failure handling

Check the AFU state whenever an API is called. The hypervisor may
issue a reset of the adapter when it detects a fault. When it happens,
it launches an error recovery which will either move the AFU to a
permanent failure state, or in the disabled state.
If the AFU is found to be disabled, detach all existing contexts from
it before issuing a AFU reset to re-enable it.

Before detaching contexts, notify any kernel driver through the EEH
callbacks of the AFU pci device.

Co-authored-by: Frederic Barrat <fbarrat@linux.vnet.ibm.com>
Signed-off-by: Frederic Barrat <fbarrat@linux.vnet.ibm.com>
Signed-off-by: Christophe Lombard <clombard@linux.vnet.ibm.com>
Reviewed-by: Manoj Kumar <manoj@linux.vnet.ibm.com>
Acked-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
hifive-unleashed-5.1
Christophe Lombard 2016-03-04 12:26:41 +01:00 committed by Michael Ellerman
parent d601ea918b
commit 0d400f77c1
7 changed files with 198 additions and 35 deletions

View File

@ -220,7 +220,7 @@ int __detach_context(struct cxl_context *ctx)
* If detach fails when hw is down, we don't care.
*/
WARN_ON(cxl_ops->detach_process(ctx) &&
cxl_ops->link_ok(ctx->afu->adapter));
cxl_ops->link_ok(ctx->afu->adapter, ctx->afu));
flush_work(&ctx->fault_work); /* Only needed for dedicated process */
/* release the reference to the group leader and mm handling pid */

View File

@ -379,6 +379,8 @@ struct cxl_afu_guest {
phys_addr_t p2n_phys;
u64 p2n_size;
int max_ints;
struct mutex recovery_lock;
int previous_state;
};
struct cxl_afu {
@ -617,7 +619,7 @@ struct cxl_process_element {
__be32 software_state;
} __packed;
static inline bool cxl_adapter_link_ok(struct cxl *cxl)
static inline bool cxl_adapter_link_ok(struct cxl *cxl, struct cxl_afu *afu)
{
struct pci_dev *pdev;
@ -636,13 +638,13 @@ static inline void __iomem *_cxl_p1_addr(struct cxl *cxl, cxl_p1_reg_t reg)
static inline void cxl_p1_write(struct cxl *cxl, cxl_p1_reg_t reg, u64 val)
{
if (likely(cxl_adapter_link_ok(cxl)))
if (likely(cxl_adapter_link_ok(cxl, NULL)))
out_be64(_cxl_p1_addr(cxl, reg), val);
}
static inline u64 cxl_p1_read(struct cxl *cxl, cxl_p1_reg_t reg)
{
if (likely(cxl_adapter_link_ok(cxl)))
if (likely(cxl_adapter_link_ok(cxl, NULL)))
return in_be64(_cxl_p1_addr(cxl, reg));
else
return ~0ULL;
@ -656,13 +658,13 @@ static inline void __iomem *_cxl_p1n_addr(struct cxl_afu *afu, cxl_p1n_reg_t reg
static inline void cxl_p1n_write(struct cxl_afu *afu, cxl_p1n_reg_t reg, u64 val)
{
if (likely(cxl_adapter_link_ok(afu->adapter)))
if (likely(cxl_adapter_link_ok(afu->adapter, afu)))
out_be64(_cxl_p1n_addr(afu, reg), val);
}
static inline u64 cxl_p1n_read(struct cxl_afu *afu, cxl_p1n_reg_t reg)
{
if (likely(cxl_adapter_link_ok(afu->adapter)))
if (likely(cxl_adapter_link_ok(afu->adapter, afu)))
return in_be64(_cxl_p1n_addr(afu, reg));
else
return ~0ULL;
@ -675,13 +677,13 @@ static inline void __iomem *_cxl_p2n_addr(struct cxl_afu *afu, cxl_p2n_reg_t reg
static inline void cxl_p2n_write(struct cxl_afu *afu, cxl_p2n_reg_t reg, u64 val)
{
if (likely(cxl_adapter_link_ok(afu->adapter)))
if (likely(cxl_adapter_link_ok(afu->adapter, afu)))
out_be64(_cxl_p2n_addr(afu, reg), val);
}
static inline u64 cxl_p2n_read(struct cxl_afu *afu, cxl_p2n_reg_t reg)
{
if (likely(cxl_adapter_link_ok(afu->adapter)))
if (likely(cxl_adapter_link_ok(afu->adapter, afu)))
return in_be64(_cxl_p2n_addr(afu, reg));
else
return ~0ULL;
@ -857,7 +859,7 @@ struct cxl_backend_ops {
u64 wed, u64 amr);
int (*detach_process)(struct cxl_context *ctx);
bool (*support_attributes)(const char *attr_name, enum cxl_attrs type);
bool (*link_ok)(struct cxl *cxl);
bool (*link_ok)(struct cxl *cxl, struct cxl_afu *afu);
void (*release_afu)(struct device *dev);
ssize_t (*afu_read_err_buffer)(struct cxl_afu *afu, char *buf,
loff_t off, size_t count);

View File

@ -76,7 +76,7 @@ static int __afu_open(struct inode *inode, struct file *file, bool master)
if (!afu->current_mode)
goto err_put_afu;
if (!cxl_ops->link_ok(adapter)) {
if (!cxl_ops->link_ok(adapter, afu)) {
rc = -EIO;
goto err_put_afu;
}
@ -257,7 +257,7 @@ long afu_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
if (ctx->status == CLOSED)
return -EIO;
if (!cxl_ops->link_ok(ctx->afu->adapter))
if (!cxl_ops->link_ok(ctx->afu->adapter, ctx->afu))
return -EIO;
pr_devel("afu_ioctl\n");
@ -287,7 +287,7 @@ int afu_mmap(struct file *file, struct vm_area_struct *vm)
if (ctx->status != STARTED)
return -EIO;
if (!cxl_ops->link_ok(ctx->afu->adapter))
if (!cxl_ops->link_ok(ctx->afu->adapter, ctx->afu))
return -EIO;
return cxl_context_iomap(ctx, vm);
@ -334,7 +334,7 @@ ssize_t afu_read(struct file *file, char __user *buf, size_t count,
int rc;
DEFINE_WAIT(wait);
if (!cxl_ops->link_ok(ctx->afu->adapter))
if (!cxl_ops->link_ok(ctx->afu->adapter, ctx->afu))
return -EIO;
if (count < CXL_READ_MIN_SIZE)
@ -347,7 +347,7 @@ ssize_t afu_read(struct file *file, char __user *buf, size_t count,
if (ctx_event_pending(ctx))
break;
if (!cxl_ops->link_ok(ctx->afu->adapter)) {
if (!cxl_ops->link_ok(ctx->afu->adapter, ctx->afu)) {
rc = -EIO;
goto out;
}

View File

@ -15,6 +15,46 @@
#include "hcalls.h"
#include "trace.h"
#define CXL_ERROR_DETECTED_EVENT 1
#define CXL_SLOT_RESET_EVENT 2
#define CXL_RESUME_EVENT 3
static void pci_error_handlers(struct cxl_afu *afu,
int bus_error_event,
pci_channel_state_t state)
{
struct pci_dev *afu_dev;
if (afu->phb == NULL)
return;
list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) {
if (!afu_dev->driver)
continue;
switch (bus_error_event) {
case CXL_ERROR_DETECTED_EVENT:
afu_dev->error_state = state;
if (afu_dev->driver->err_handler &&
afu_dev->driver->err_handler->error_detected)
afu_dev->driver->err_handler->error_detected(afu_dev, state);
break;
case CXL_SLOT_RESET_EVENT:
afu_dev->error_state = state;
if (afu_dev->driver->err_handler &&
afu_dev->driver->err_handler->slot_reset)
afu_dev->driver->err_handler->slot_reset(afu_dev);
break;
case CXL_RESUME_EVENT:
if (afu_dev->driver->err_handler &&
afu_dev->driver->err_handler->resume)
afu_dev->driver->err_handler->resume(afu_dev);
break;
}
}
}
static irqreturn_t guest_handle_psl_slice_error(struct cxl_context *ctx, u64 dsisr,
u64 errstat)
@ -133,6 +173,22 @@ static irqreturn_t guest_psl_irq(int irq, void *data)
return rc;
}
static int afu_read_error_state(struct cxl_afu *afu, int *state_out)
{
u64 state;
int rc = 0;
rc = cxl_h_read_error_state(afu->guest->handle, &state);
if (!rc) {
WARN_ON(state != H_STATE_NORMAL &&
state != H_STATE_DISABLE &&
state != H_STATE_TEMP_UNAVAILABLE &&
state != H_STATE_PERM_UNAVAILABLE);
*state_out = state & 0xffffffff;
}
return rc;
}
static irqreturn_t guest_slice_irq_err(int irq, void *data)
{
struct cxl_afu *afu = data;
@ -201,10 +257,26 @@ static int irq_free_range(struct cxl *adapter, int irq, int len)
static int guest_reset(struct cxl *adapter)
{
int rc;
struct cxl_afu *afu = NULL;
int i, rc;
pr_devel("Adapter reset request\n");
for (i = 0; i < adapter->slices; i++) {
if ((afu = adapter->afu[i])) {
pci_error_handlers(afu, CXL_ERROR_DETECTED_EVENT,
pci_channel_io_frozen);
cxl_context_detach_all(afu);
}
}
rc = cxl_h_reset_adapter(adapter->guest->handle);
for (i = 0; i < adapter->slices; i++) {
if (!rc && (afu = adapter->afu[i])) {
pci_error_handlers(afu, CXL_SLOT_RESET_EVENT,
pci_channel_io_normal);
pci_error_handlers(afu, CXL_RESUME_EVENT, 0);
}
}
return rc;
}
@ -556,7 +628,7 @@ static int guest_detach_process(struct cxl_context *ctx)
pr_devel("in %s\n", __func__);
trace_cxl_detach(ctx);
if (!cxl_ops->link_ok(ctx->afu->adapter))
if (!cxl_ops->link_ok(ctx->afu->adapter, ctx->afu))
return -EIO;
if (ctx->afu->current_mode == CXL_MODE_DIRECTED)
@ -730,8 +802,95 @@ static void guest_unmap_slice_regs(struct cxl_afu *afu)
iounmap(afu->p2n_mmio);
}
static bool guest_link_ok(struct cxl *cxl)
static int afu_update_state(struct cxl_afu *afu)
{
int rc, cur_state;
rc = afu_read_error_state(afu, &cur_state);
if (rc)
return rc;
if (afu->guest->previous_state == cur_state)
return 0;
pr_devel("AFU(%d) update state to %#x\n", afu->slice, cur_state);
switch (cur_state) {
case H_STATE_NORMAL:
afu->guest->previous_state = cur_state;
rc = 1;
break;
case H_STATE_DISABLE:
pci_error_handlers(afu, CXL_ERROR_DETECTED_EVENT,
pci_channel_io_frozen);
cxl_context_detach_all(afu);
if ((rc = cxl_ops->afu_reset(afu)))
pr_devel("reset hcall failed %d\n", rc);
rc = afu_read_error_state(afu, &cur_state);
if (!rc && cur_state == H_STATE_NORMAL) {
pci_error_handlers(afu, CXL_SLOT_RESET_EVENT,
pci_channel_io_normal);
pci_error_handlers(afu, CXL_RESUME_EVENT, 0);
rc = 1;
}
afu->guest->previous_state = 0;
break;
case H_STATE_TEMP_UNAVAILABLE:
afu->guest->previous_state = cur_state;
break;
case H_STATE_PERM_UNAVAILABLE:
dev_err(&afu->dev, "AFU is in permanent error state\n");
pci_error_handlers(afu, CXL_ERROR_DETECTED_EVENT,
pci_channel_io_perm_failure);
afu->guest->previous_state = cur_state;
break;
default:
pr_err("Unexpected AFU(%d) error state: %#x\n",
afu->slice, cur_state);
return -EINVAL;
}
return rc;
}
static int afu_do_recovery(struct cxl_afu *afu)
{
int rc;
/* many threads can arrive here, in case of detach_all for example.
* Only one needs to drive the recovery
*/
if (mutex_trylock(&afu->guest->recovery_lock)) {
rc = afu_update_state(afu);
mutex_unlock(&afu->guest->recovery_lock);
return rc;
}
return 0;
}
static bool guest_link_ok(struct cxl *cxl, struct cxl_afu *afu)
{
int state;
if (afu) {
if (afu_read_error_state(afu, &state) ||
state != H_STATE_NORMAL) {
if (afu_do_recovery(afu) > 0) {
/* check again in case we've just fixed it */
if (!afu_read_error_state(afu, &state) &&
state == H_STATE_NORMAL)
return true;
}
return false;
}
}
return true;
}
@ -770,6 +929,8 @@ int cxl_guest_init_afu(struct cxl *adapter, int slice, struct device_node *afu_n
return -ENOMEM;
}
mutex_init(&afu->guest->recovery_lock);
if ((rc = dev_set_name(&afu->dev, "afu%i.%i",
adapter->adapter_num,
slice)))

View File

@ -48,7 +48,7 @@ int cxl_afu_slbia(struct cxl_afu *afu)
/* If the adapter has gone down, we can assume that we
* will PERST it and that will invalidate everything.
*/
if (!cxl_ops->link_ok(afu->adapter))
if (!cxl_ops->link_ok(afu->adapter, afu))
return -EIO;
cpu_relax();
}

View File

@ -42,7 +42,7 @@ static int afu_control(struct cxl_afu *afu, u64 command,
goto out;
}
if (!cxl_ops->link_ok(afu->adapter)) {
if (!cxl_ops->link_ok(afu->adapter, afu)) {
afu->enabled = enabled;
rc = -EIO;
goto out;
@ -92,7 +92,7 @@ static int native_afu_reset(struct cxl_afu *afu)
static int native_afu_check_and_enable(struct cxl_afu *afu)
{
if (!cxl_ops->link_ok(afu->adapter)) {
if (!cxl_ops->link_ok(afu->adapter, afu)) {
WARN(1, "Refusing to enable afu while link down!\n");
return -EIO;
}
@ -114,7 +114,7 @@ int cxl_psl_purge(struct cxl_afu *afu)
pr_devel("PSL purge request\n");
if (!cxl_ops->link_ok(afu->adapter)) {
if (!cxl_ops->link_ok(afu->adapter, afu)) {
dev_warn(&afu->dev, "PSL Purge called with link down, ignoring\n");
rc = -EIO;
goto out;
@ -136,7 +136,7 @@ int cxl_psl_purge(struct cxl_afu *afu)
rc = -EBUSY;
goto out;
}
if (!cxl_ops->link_ok(afu->adapter)) {
if (!cxl_ops->link_ok(afu->adapter, afu)) {
rc = -EIO;
goto out;
}
@ -250,7 +250,7 @@ int cxl_tlb_slb_invalidate(struct cxl *adapter)
dev_warn(&adapter->dev, "WARNING: CXL adapter wide TLBIA timed out!\n");
return -EBUSY;
}
if (!cxl_ops->link_ok(adapter))
if (!cxl_ops->link_ok(adapter, NULL))
return -EIO;
cpu_relax();
}
@ -261,7 +261,7 @@ int cxl_tlb_slb_invalidate(struct cxl *adapter)
dev_warn(&adapter->dev, "WARNING: CXL adapter wide SLBIA timed out!\n");
return -EBUSY;
}
if (!cxl_ops->link_ok(adapter))
if (!cxl_ops->link_ok(adapter, NULL))
return -EIO;
cpu_relax();
}
@ -302,7 +302,7 @@ static void slb_invalid(struct cxl_context *ctx)
cxl_p1_write(adapter, CXL_PSL_SLBIA, CXL_TLB_SLB_IQ_LPIDPID);
while (1) {
if (!cxl_ops->link_ok(adapter))
if (!cxl_ops->link_ok(adapter, NULL))
break;
slbia = cxl_p1_read(adapter, CXL_PSL_SLBIA);
if (!(slbia & CXL_TLB_SLB_P))
@ -333,7 +333,7 @@ static int do_process_element_cmd(struct cxl_context *ctx,
rc = -EBUSY;
goto out;
}
if (!cxl_ops->link_ok(ctx->afu->adapter)) {
if (!cxl_ops->link_ok(ctx->afu->adapter, ctx->afu)) {
dev_warn(&ctx->afu->dev, "WARNING: Device link down, aborting Process Element Command!\n");
rc = -EIO;
goto out;
@ -389,7 +389,7 @@ static int terminate_process_element(struct cxl_context *ctx)
* should always succeed: it's not running if the hw has gone
* away and is being reset.
*/
if (cxl_ops->link_ok(ctx->afu->adapter))
if (cxl_ops->link_ok(ctx->afu->adapter, ctx->afu))
rc = do_process_element_cmd(ctx, CXL_SPA_SW_CMD_TERMINATE,
CXL_PE_SOFTWARE_STATE_V | CXL_PE_SOFTWARE_STATE_T);
ctx->elem->software_state = 0; /* Remove Valid bit */
@ -408,7 +408,7 @@ static int remove_process_element(struct cxl_context *ctx)
/* We could be asked to remove when the hw is down. Again, if
* the hw is down, the PE is gone, so we succeed.
*/
if (cxl_ops->link_ok(ctx->afu->adapter))
if (cxl_ops->link_ok(ctx->afu->adapter, ctx->afu))
rc = do_process_element_cmd(ctx, CXL_SPA_SW_CMD_REMOVE, 0);
if (!rc)
@ -650,7 +650,7 @@ static int native_afu_activate_mode(struct cxl_afu *afu, int mode)
if (!(mode & afu->modes_supported))
return -EINVAL;
if (!cxl_ops->link_ok(afu->adapter)) {
if (!cxl_ops->link_ok(afu->adapter, afu)) {
WARN(1, "Device link is down, refusing to activate!\n");
return -EIO;
}
@ -666,7 +666,7 @@ static int native_afu_activate_mode(struct cxl_afu *afu, int mode)
static int native_attach_process(struct cxl_context *ctx, bool kernel,
u64 wed, u64 amr)
{
if (!cxl_ops->link_ok(ctx->afu->adapter)) {
if (!cxl_ops->link_ok(ctx->afu->adapter, ctx->afu)) {
WARN(1, "Device link is down, refusing to attach process!\n");
return -EIO;
}
@ -718,7 +718,7 @@ static int native_get_irq_info(struct cxl_afu *afu, struct cxl_irq_info *info)
/* If the adapter has gone away, we can't get any meaningful
* information.
*/
if (!cxl_ops->link_ok(afu->adapter))
if (!cxl_ops->link_ok(afu->adapter, afu))
return -EIO;
info->dsisr = cxl_p2n_read(afu, CXL_PSL_DSISR_An);
@ -975,7 +975,7 @@ static bool native_support_attributes(const char *attr_name,
static int native_afu_cr_read64(struct cxl_afu *afu, int cr, u64 off, u64 *out)
{
if (unlikely(!cxl_ops->link_ok(afu->adapter)))
if (unlikely(!cxl_ops->link_ok(afu->adapter, afu)))
return -EIO;
if (unlikely(off >= afu->crs_len))
return -ERANGE;
@ -986,7 +986,7 @@ static int native_afu_cr_read64(struct cxl_afu *afu, int cr, u64 off, u64 *out)
static int native_afu_cr_read32(struct cxl_afu *afu, int cr, u64 off, u32 *out)
{
if (unlikely(!cxl_ops->link_ok(afu->adapter)))
if (unlikely(!cxl_ops->link_ok(afu->adapter, afu)))
return -EIO;
if (unlikely(off >= afu->crs_len))
return -ERANGE;
@ -1021,7 +1021,7 @@ static int native_afu_cr_read8(struct cxl_afu *afu, int cr, u64 off, u8 *out)
static int native_afu_cr_write32(struct cxl_afu *afu, int cr, u64 off, u32 in)
{
if (unlikely(!cxl_ops->link_ok(afu->adapter)))
if (unlikely(!cxl_ops->link_ok(afu->adapter, afu)))
return -EIO;
if (unlikely(off >= afu->crs_len))
return -ERANGE;

View File

@ -49,7 +49,7 @@ static bool cxl_pci_enable_device_hook(struct pci_dev *dev)
phb = pci_bus_to_host(dev->bus);
afu = (struct cxl_afu *)phb->private_data;
if (!cxl_ops->link_ok(afu->adapter)) {
if (!cxl_ops->link_ok(afu->adapter, afu)) {
dev_warn(&dev->dev, "%s: Device link is down, refusing to enable AFU\n", __func__);
return false;
}