summaryrefslogtreecommitdiff
path: root/drivers/misc/cxl
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/misc/cxl')
-rw-r--r--drivers/misc/cxl/api.c28
-rw-r--r--drivers/misc/cxl/context.c3
-rw-r--r--drivers/misc/cxl/cxl.h15
-rw-r--r--drivers/misc/cxl/fault.c10
-rw-r--r--drivers/misc/cxl/guest.c78
-rw-r--r--drivers/misc/cxl/native.c29
-rw-r--r--drivers/misc/cxl/pci.c64
-rw-r--r--drivers/misc/cxl/sysfs.c10
8 files changed, 170 insertions, 67 deletions
diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index 2107c948406d..6d228ccd884d 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -68,15 +68,6 @@ struct cxl_context *cxl_get_context(struct pci_dev *dev)
}
EXPORT_SYMBOL_GPL(cxl_get_context);
-struct device *cxl_get_phys_dev(struct pci_dev *dev)
-{
- struct cxl_afu *afu;
-
- afu = cxl_pci_to_afu(dev);
-
- return afu->adapter->dev.parent;
-}
-
int cxl_release_context(struct cxl_context *ctx)
{
if (ctx->status >= STARTED)
@@ -192,6 +183,7 @@ int cxl_start_context(struct cxl_context *ctx, u64 wed,
ctx->pid = get_task_pid(task, PIDTYPE_PID);
ctx->glpid = get_task_pid(task->group_leader, PIDTYPE_PID);
kernel = false;
+ ctx->real_mode = false;
}
cxl_ctx_get();
@@ -228,6 +220,24 @@ void cxl_set_master(struct cxl_context *ctx)
}
EXPORT_SYMBOL_GPL(cxl_set_master);
+int cxl_set_translation_mode(struct cxl_context *ctx, bool real_mode)
+{
+ if (ctx->status == STARTED) {
+ /*
+ * We could potentially update the PE and issue an update LLCMD
+ * to support this, but it doesn't seem to have a good use case
+ * since it's trivial to just create a second kernel context
+ * with different translation modes, so until someone convinces
+ * me otherwise:
+ */
+ return -EBUSY;
+ }
+
+ ctx->real_mode = real_mode;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(cxl_set_translation_mode);
+
/* wrappers around afu_* file ops which are EXPORTED */
int cxl_fd_open(struct inode *inode, struct file *file)
{
diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c
index 7edea9c19199..26d206b1d08c 100644
--- a/drivers/misc/cxl/context.c
+++ b/drivers/misc/cxl/context.c
@@ -297,8 +297,7 @@ static void reclaim_ctx(struct rcu_head *rcu)
if (ctx->kernelapi)
kfree(ctx->mapping);
- if (ctx->irq_bitmap)
- kfree(ctx->irq_bitmap);
+ kfree(ctx->irq_bitmap);
/* Drop ref to the afu device taken during cxl_context_init */
cxl_afu_put(ctx->afu);
diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index 73dc2a33da74..4fe50788ff45 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -178,15 +178,6 @@ static const cxl_p2n_reg_t CXL_PSL_WED_An = {0x0A0};
#define CXL_PSL_SR_An_MP (1ull << (63-62)) /* Master Process */
#define CXL_PSL_SR_An_LE (1ull << (63-63)) /* Little Endian */
-/****** CXL_PSL_LLCMD_An ****************************************************/
-#define CXL_LLCMD_TERMINATE 0x0001000000000000ULL
-#define CXL_LLCMD_REMOVE 0x0002000000000000ULL
-#define CXL_LLCMD_SUSPEND 0x0003000000000000ULL
-#define CXL_LLCMD_RESUME 0x0004000000000000ULL
-#define CXL_LLCMD_ADD 0x0005000000000000ULL
-#define CXL_LLCMD_UPDATE 0x0006000000000000ULL
-#define CXL_LLCMD_HANDLE_MASK 0x000000000000ffffULL
-
/****** CXL_PSL_ID_An ****************************************************/
#define CXL_PSL_ID_An_F (1ull << (63-31))
#define CXL_PSL_ID_An_L (1ull << (63-30))
@@ -376,11 +367,13 @@ struct cxl_afu_native {
};
struct cxl_afu_guest {
+ struct cxl_afu *parent;
u64 handle;
phys_addr_t p2n_phys;
u64 p2n_size;
int max_ints;
- struct mutex recovery_lock;
+ bool handle_err;
+ struct delayed_work work_err;
int previous_state;
};
@@ -524,6 +517,7 @@ struct cxl_context {
bool pe_inserted;
bool master;
bool kernel;
+ bool real_mode;
bool pending_irq;
bool pending_fault;
bool pending_afu_err;
@@ -580,6 +574,7 @@ struct cxl {
bool perst_loads_image;
bool perst_select_user;
bool perst_same_image;
+ bool psl_timebase_synced;
};
int cxl_pci_alloc_one_irq(struct cxl *adapter);
diff --git a/drivers/misc/cxl/fault.c b/drivers/misc/cxl/fault.c
index 9a8650bcb042..377e650a2a1d 100644
--- a/drivers/misc/cxl/fault.c
+++ b/drivers/misc/cxl/fault.c
@@ -149,11 +149,13 @@ static void cxl_handle_page_fault(struct cxl_context *ctx,
* update_mmu_cache() will not have loaded the hash since current->trap
* is not a 0x400 or 0x300, so just call hash_page_mm() here.
*/
- access = _PAGE_PRESENT;
+ access = _PAGE_PRESENT | _PAGE_READ;
if (dsisr & CXL_PSL_DSISR_An_S)
- access |= _PAGE_RW;
- if ((!ctx->kernel) || ~(dar & (1ULL << 63)))
- access |= _PAGE_USER;
+ access |= _PAGE_WRITE;
+
+ access |= _PAGE_PRIVILEGED;
+ if ((!ctx->kernel) || (REGION_ID(dar) == USER_REGION_ID))
+ access &= ~_PAGE_PRIVILEGED;
if (dsisr & DSISR_NOHPTE)
inv_flags |= HPTE_NOHPTE_UPDATE;
diff --git a/drivers/misc/cxl/guest.c b/drivers/misc/cxl/guest.c
index 8213372de2b7..bc8d0b9870eb 100644
--- a/drivers/misc/cxl/guest.c
+++ b/drivers/misc/cxl/guest.c
@@ -178,6 +178,9 @@ static int afu_read_error_state(struct cxl_afu *afu, int *state_out)
u64 state;
int rc = 0;
+ if (!afu)
+ return -EIO;
+
rc = cxl_h_read_error_state(afu->guest->handle, &state);
if (!rc) {
WARN_ON(state != H_STATE_NORMAL &&
@@ -552,6 +555,17 @@ static int attach_afu_directed(struct cxl_context *ctx, u64 wed, u64 amr)
elem->common.sstp0 = cpu_to_be64(ctx->sstp0);
elem->common.sstp1 = cpu_to_be64(ctx->sstp1);
+
+ /*
+ * Ensure we have at least one interrupt allocated to take faults for
+ * kernel contexts that may not have allocated any AFU IRQs at all:
+ */
+ if (ctx->irqs.range[0] == 0) {
+ rc = afu_register_irqs(ctx, 0);
+ if (rc)
+ goto out_free;
+ }
+
for (r = 0; r < CXL_IRQ_RANGES; r++) {
for (i = 0; i < ctx->irqs.range[r]; i++) {
if (r == 0 && i == 0) {
@@ -597,6 +611,7 @@ static int attach_afu_directed(struct cxl_context *ctx, u64 wed, u64 amr)
enable_afu_irqs(ctx);
}
+out_free:
free_page((u64)elem);
return rc;
}
@@ -605,6 +620,9 @@ static int guest_attach_process(struct cxl_context *ctx, bool kernel, u64 wed, u
{
pr_devel("in %s\n", __func__);
+ if (ctx->real_mode)
+ return -EPERM;
+
ctx->kernel = kernel;
if (ctx->afu->current_mode == CXL_MODE_DIRECTED)
return attach_afu_directed(ctx, wed, amr);
@@ -818,7 +836,6 @@ static int afu_update_state(struct cxl_afu *afu)
switch (cur_state) {
case H_STATE_NORMAL:
afu->guest->previous_state = cur_state;
- rc = 1;
break;
case H_STATE_DISABLE:
@@ -834,7 +851,6 @@ static int afu_update_state(struct cxl_afu *afu)
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;
@@ -859,39 +875,30 @@ static int afu_update_state(struct cxl_afu *afu)
return rc;
}
-static int afu_do_recovery(struct cxl_afu *afu)
+static void afu_handle_errstate(struct work_struct *work)
{
- int rc;
+ struct cxl_afu_guest *afu_guest =
+ container_of(to_delayed_work(work), struct cxl_afu_guest, work_err);
- /* 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;
+ if (!afu_update_state(afu_guest->parent) &&
+ afu_guest->previous_state == H_STATE_PERM_UNAVAILABLE)
+ return;
+
+ if (afu_guest->handle_err == true)
+ schedule_delayed_work(&afu_guest->work_err,
+ msecs_to_jiffies(3000));
}
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;
- }
+ if (afu && (!afu_read_error_state(afu, &state))) {
+ if (state == H_STATE_NORMAL)
+ return true;
}
- return true;
+ return false;
}
static int afu_properties_look_ok(struct cxl_afu *afu)
@@ -929,8 +936,6 @@ 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)))
@@ -986,6 +991,15 @@ int cxl_guest_init_afu(struct cxl *adapter, int slice, struct device_node *afu_n
afu->enabled = true;
+ /*
+ * wake up the cpu periodically to check the state
+ * of the AFU using "afu" stored in the guest structure.
+ */
+ afu->guest->parent = afu;
+ afu->guest->handle_err = true;
+ INIT_DELAYED_WORK(&afu->guest->work_err, afu_handle_errstate);
+ schedule_delayed_work(&afu->guest->work_err, msecs_to_jiffies(1000));
+
if ((rc = cxl_pci_vphb_add(afu)))
dev_info(&afu->dev, "Can't register vPHB\n");
@@ -1014,6 +1028,10 @@ void cxl_guest_remove_afu(struct cxl_afu *afu)
if (!afu)
return;
+ /* flush and stop pending job */
+ afu->guest->handle_err = false;
+ flush_delayed_work(&afu->guest->work_err);
+
cxl_pci_vphb_remove(afu);
cxl_sysfs_afu_remove(afu);
@@ -1101,6 +1119,12 @@ struct cxl *cxl_guest_init_adapter(struct device_node *np, struct platform_devic
adapter->dev.release = release_adapter;
dev_set_drvdata(&pdev->dev, adapter);
+ /*
+ * Hypervisor controls PSL timebase initialization (p1 register).
+ * On FW840, PSL is initialized.
+ */
+ adapter->psl_timebase_synced = true;
+
if ((rc = cxl_of_read_adapter_handle(adapter, np)))
goto err1;
diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c
index ecf7557cd657..55d8a1459f28 100644
--- a/drivers/misc/cxl/native.c
+++ b/drivers/misc/cxl/native.c
@@ -186,16 +186,25 @@ static int spa_max_procs(int spa_size)
int cxl_alloc_spa(struct cxl_afu *afu)
{
+ unsigned spa_size;
+
/* Work out how many pages to allocate */
afu->native->spa_order = 0;
do {
afu->native->spa_order++;
- afu->native->spa_size = (1 << afu->native->spa_order) * PAGE_SIZE;
+ spa_size = (1 << afu->native->spa_order) * PAGE_SIZE;
+
+ if (spa_size > 0x100000) {
+ dev_warn(&afu->dev, "num_of_processes too large for the SPA, limiting to %i (0x%x)\n",
+ afu->native->spa_max_procs, afu->native->spa_size);
+ afu->num_procs = afu->native->spa_max_procs;
+ break;
+ }
+
+ afu->native->spa_size = spa_size;
afu->native->spa_max_procs = spa_max_procs(afu->native->spa_size);
} while (afu->native->spa_max_procs < afu->num_procs);
- WARN_ON(afu->native->spa_size > 0x100000); /* Max size supported by the hardware */
-
if (!(afu->native->spa = (struct cxl_process_element *)
__get_free_pages(GFP_KERNEL | __GFP_ZERO, afu->native->spa_order))) {
pr_err("cxl_alloc_spa: Unable to allocate scheduled process area\n");
@@ -486,8 +495,9 @@ static u64 calculate_sr(struct cxl_context *ctx)
if (mfspr(SPRN_LPCR) & LPCR_TC)
sr |= CXL_PSL_SR_An_TC;
if (ctx->kernel) {
- sr |= CXL_PSL_SR_An_R | (mfmsr() & MSR_SF);
- sr |= CXL_PSL_SR_An_HV;
+ if (!ctx->real_mode)
+ sr |= CXL_PSL_SR_An_R;
+ sr |= (mfmsr() & MSR_SF) | CXL_PSL_SR_An_HV;
} else {
sr |= CXL_PSL_SR_An_PR | CXL_PSL_SR_An_R;
sr &= ~(CXL_PSL_SR_An_HV);
@@ -526,6 +536,15 @@ static int attach_afu_directed(struct cxl_context *ctx, u64 wed, u64 amr)
ctx->elem->common.sstp0 = cpu_to_be64(ctx->sstp0);
ctx->elem->common.sstp1 = cpu_to_be64(ctx->sstp1);
+ /*
+ * Ensure we have the multiplexed PSL interrupt set up to take faults
+ * for kernel contexts that may not have allocated any AFU IRQs at all:
+ */
+ if (ctx->irqs.range[0] == 0) {
+ ctx->irqs.offset[0] = ctx->afu->native->psl_hwirq;
+ ctx->irqs.range[0] = 1;
+ }
+
for (r = 0; r < CXL_IRQ_RANGES; r++) {
ctx->elem->ivte_offsets[r] = cpu_to_be16(ctx->irqs.offset[r]);
ctx->elem->ivte_ranges[r] = cpu_to_be16(ctx->irqs.range[r]);
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 2844e975bf79..a08fcc888a71 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -21,6 +21,7 @@
#include <asm/msi_bitmap.h>
#include <asm/pnv-pci.h>
#include <asm/io.h>
+#include <asm/reg.h>
#include "cxl.h"
#include <misc/cxl.h>
@@ -321,12 +322,43 @@ static void dump_afu_descriptor(struct cxl_afu *afu)
#undef show_reg
}
+#define CAPP_UNIT0_ID 0xBA
+#define CAPP_UNIT1_ID 0XBE
+
+static u64 get_capp_unit_id(struct device_node *np)
+{
+ u32 phb_index;
+
+ /*
+ * For chips other than POWER8NVL, we only have CAPP 0,
+ * irrespective of which PHB is used.
+ */
+ if (!pvr_version_is(PVR_POWER8NVL))
+ return CAPP_UNIT0_ID;
+
+ /*
+ * For POWER8NVL, assume CAPP 0 is attached to PHB0 and
+ * CAPP 1 is attached to PHB1.
+ */
+ if (of_property_read_u32(np, "ibm,phb-index", &phb_index))
+ return 0;
+
+ if (phb_index == 0)
+ return CAPP_UNIT0_ID;
+
+ if (phb_index == 1)
+ return CAPP_UNIT1_ID;
+
+ return 0;
+}
+
static int init_implementation_adapter_regs(struct cxl *adapter, struct pci_dev *dev)
{
struct device_node *np;
const __be32 *prop;
u64 psl_dsnctl;
u64 chipid;
+ u64 capp_unit_id;
if (!(np = pnv_pci_get_phb_node(dev)))
return -ENODEV;
@@ -336,10 +368,19 @@ static int init_implementation_adapter_regs(struct cxl *adapter, struct pci_dev
if (!np)
return -ENODEV;
chipid = be32_to_cpup(prop);
+ capp_unit_id = get_capp_unit_id(np);
of_node_put(np);
+ if (!capp_unit_id) {
+ pr_err("cxl: invalid capp unit id\n");
+ return -ENODEV;
+ }
+ psl_dsnctl = 0x0000900000000000ULL; /* pteupd ttype, scdone */
+ psl_dsnctl |= (0x2ULL << (63-38)); /* MMIO hang pulse: 256 us */
/* Tell PSL where to route data to */
- psl_dsnctl = 0x02E8900002000000ULL | (chipid << (63-5));
+ psl_dsnctl |= (chipid << (63-5));
+ psl_dsnctl |= (capp_unit_id << (63-13));
+
cxl_p1_write(adapter, CXL_PSL_DSNDCTL, psl_dsnctl);
cxl_p1_write(adapter, CXL_PSL_RESLCKTO, 0x20000000200ULL);
/* snoop write mask */
@@ -355,22 +396,24 @@ static int init_implementation_adapter_regs(struct cxl *adapter, struct pci_dev
#define TBSYNC_CNT(n) (((u64)n & 0x7) << (63-6))
#define _2048_250MHZ_CYCLES 1
-static int cxl_setup_psl_timebase(struct cxl *adapter, struct pci_dev *dev)
+static void cxl_setup_psl_timebase(struct cxl *adapter, struct pci_dev *dev)
{
u64 psl_tb;
int delta;
unsigned int retry = 0;
struct device_node *np;
+ adapter->psl_timebase_synced = false;
+
if (!(np = pnv_pci_get_phb_node(dev)))
- return -ENODEV;
+ return;
/* Do not fail when CAPP timebase sync is not supported by OPAL */
of_node_get(np);
if (! of_get_property(np, "ibm,capp-timebase-sync", NULL)) {
of_node_put(np);
- pr_err("PSL: Timebase sync: OPAL support missing\n");
- return 0;
+ dev_info(&dev->dev, "PSL timebase inactive: OPAL support missing\n");
+ return;
}
of_node_put(np);
@@ -389,8 +432,8 @@ static int cxl_setup_psl_timebase(struct cxl *adapter, struct pci_dev *dev)
do {
msleep(1);
if (retry++ > 5) {
- pr_err("PSL: Timebase sync: giving up!\n");
- return -EIO;
+ dev_info(&dev->dev, "PSL timebase can't synchronize\n");
+ return;
}
psl_tb = cxl_p1_read(adapter, CXL_PSL_Timebase);
delta = mftb() - psl_tb;
@@ -398,7 +441,8 @@ static int cxl_setup_psl_timebase(struct cxl *adapter, struct pci_dev *dev)
delta = -delta;
} while (tb_to_ns(delta) > 16000);
- return 0;
+ adapter->psl_timebase_synced = true;
+ return;
}
static int init_implementation_afu_regs(struct cxl_afu *afu)
@@ -1144,8 +1188,8 @@ static int cxl_configure_adapter(struct cxl *adapter, struct pci_dev *dev)
if ((rc = pnv_phb_to_cxl_mode(dev, OPAL_PHB_CAPI_MODE_SNOOP_ON)))
goto err;
- if ((rc = cxl_setup_psl_timebase(adapter, dev)))
- goto err;
+ /* Ignore error, adapter init is not dependant on timebase sync */
+ cxl_setup_psl_timebase(adapter, dev);
if ((rc = cxl_native_register_psl_err_irq(adapter)))
goto err;
diff --git a/drivers/misc/cxl/sysfs.c b/drivers/misc/cxl/sysfs.c
index 25913c08794c..b043c20f158f 100644
--- a/drivers/misc/cxl/sysfs.c
+++ b/drivers/misc/cxl/sysfs.c
@@ -57,6 +57,15 @@ static ssize_t image_loaded_show(struct device *device,
return scnprintf(buf, PAGE_SIZE, "factory\n");
}
+static ssize_t psl_timebase_synced_show(struct device *device,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct cxl *adapter = to_cxl_adapter(device);
+
+ return scnprintf(buf, PAGE_SIZE, "%i\n", adapter->psl_timebase_synced);
+}
+
static ssize_t reset_adapter_store(struct device *device,
struct device_attribute *attr,
const char *buf, size_t count)
@@ -142,6 +151,7 @@ static struct device_attribute adapter_attrs[] = {
__ATTR_RO(psl_revision),
__ATTR_RO(base_image),
__ATTR_RO(image_loaded),
+ __ATTR_RO(psl_timebase_synced),
__ATTR_RW(load_image_on_perst),
__ATTR_RW(perst_reloads_same_image),
__ATTR(reset, S_IWUSR, NULL, reset_adapter_store),
generated by cgit v1.2.3 (git 2.39.0) at 2024-11-19 09:39:17 +0300