*
*/
-#include <linux/kernel.h>
-#include <linux/sysctl.h>
-#include <linux/cache.h>
-#include <linux/mmzone.h>
-#include <linux/nodemask.h>
-#include <asm/sn/intr.h>
-#include <asm/sn/sn_sal.h>
-#include <asm/sn/nodepda.h>
-#include <asm/sn/addrs.h>
+#include <linux/device.h>
+#include <linux/hardirq.h>
#include "xpc.h"
/* XPC is exiting flag */
int xpc_exiting;
-/* SH_IPI_ACCESS shub register value on startup */
-static u64 xpc_sh1_IPI_access;
-static u64 xpc_sh2_IPI_access0;
-static u64 xpc_sh2_IPI_access1;
-static u64 xpc_sh2_IPI_access2;
-static u64 xpc_sh2_IPI_access3;
-
-/* original protection values for each node */
-u64 xpc_prot_vec[MAX_NUMNODES];
-
/* this partition's reserved page pointers */
struct xpc_rsvd_page *xpc_rsvd_page;
-static u64 *xpc_part_nasids;
-u64 *xpc_mach_nasids;
+static unsigned long *xpc_part_nasids;
+unsigned long *xpc_mach_nasids;
-/* >>> next two variables should be 'xpc_' if they remain here */
-static int xp_sizeof_nasid_mask; /* actual size in bytes of nasid mask */
-int xp_nasid_mask_words; /* actual size in words of nasid mask */
+static int xpc_nasid_mask_nbytes; /* #of bytes in nasid mask */
+int xpc_nasid_mask_nlongs; /* #of longs in nasid mask */
struct xpc_partition *xpc_partitions;
/*
- * Generic buffer used to store a local copy of portions of a remote
- * partition's reserved page (either its header and part_nasids mask,
- * or its vars).
- */
-char *xpc_remote_copy_buffer;
-void *xpc_remote_copy_buffer_base;
-
-/*
* Guarantee that the kmalloc'd memory is cacheline aligned.
*/
void *
* Given a nasid, get the physical address of the partition's reserved page
* for that nasid. This function returns 0 on any error.
*/
-static u64
+static unsigned long
xpc_get_rsvd_page_pa(int nasid)
{
enum xp_retval ret;
- s64 status;
u64 cookie = 0;
- u64 rp_pa = nasid; /* seed with nasid */
- u64 len = 0;
- u64 buf = buf;
- u64 buf_len = 0;
+ unsigned long rp_pa = nasid; /* seed with nasid */
+ size_t len = 0;
+ size_t buf_len = 0;
+ void *buf = buf;
void *buf_base = NULL;
+ enum xp_retval (*get_partition_rsvd_page_pa)
+ (void *, u64 *, unsigned long *, size_t *) =
+ xpc_arch_ops.get_partition_rsvd_page_pa;
while (1) {
- status = sn_partition_reserved_page_pa(buf, &cookie, &rp_pa,
- &len);
+ /* !!! rp_pa will need to be _gpa on UV.
+ * ??? So do we save it into the architecture specific parts
+ * ??? of the xpc_partition structure? Do we rename this
+ * ??? function or have two versions? Rename rp_pa for UV to
+ * ??? rp_gpa?
+ */
+ ret = get_partition_rsvd_page_pa(buf, &cookie, &rp_pa, &len);
- dev_dbg(xpc_part, "SAL returned with status=%li, cookie="
- "0x%016lx, address=0x%016lx, len=0x%016lx\n",
- status, cookie, rp_pa, len);
+ dev_dbg(xpc_part, "SAL returned with ret=%d, cookie=0x%016lx, "
+ "address=0x%016lx, len=0x%016lx\n", ret,
+ (unsigned long)cookie, rp_pa, len);
- if (status != SALRET_MORE_PASSES)
+ if (ret != xpNeedMoreInfo)
break;
- /* >>> L1_CACHE_ALIGN() is only a sn2-bte_copy requirement */
+ /* !!! L1_CACHE_ALIGN() is only a sn2-bte_copy requirement */
if (L1_CACHE_ALIGN(len) > buf_len) {
kfree(buf_base);
buf_len = L1_CACHE_ALIGN(len);
- buf = (u64)xpc_kmalloc_cacheline_aligned(buf_len,
- GFP_KERNEL,
- &buf_base);
+ buf = xpc_kmalloc_cacheline_aligned(buf_len, GFP_KERNEL,
+ &buf_base);
if (buf_base == NULL) {
dev_err(xpc_part, "unable to kmalloc "
"len=0x%016lx\n", buf_len);
- status = SALRET_ERROR;
+ ret = xpNoMemory;
break;
}
}
- ret = xp_remote_memcpy((void *)buf, (void *)rp_pa, buf_len);
+ ret = xp_remote_memcpy(xp_pa(buf), rp_pa, buf_len);
if (ret != xpSuccess) {
dev_dbg(xpc_part, "xp_remote_memcpy failed %d\n", ret);
- status = SALRET_ERROR;
break;
}
}
kfree(buf_base);
- if (status != SALRET_OK)
+ if (ret != xpSuccess)
rp_pa = 0;
dev_dbg(xpc_part, "reserved page at phys address 0x%016lx\n", rp_pa);
* other partitions to discover we are alive and establish initial
* communications.
*/
-struct xpc_rsvd_page *
+int
xpc_setup_rsvd_page(void)
{
+ int ret;
struct xpc_rsvd_page *rp;
- u64 rp_pa;
+ unsigned long rp_pa;
+ unsigned long new_ts_jiffies;
/* get the local reserved page's address */
preempt_disable();
- rp_pa = xpc_get_rsvd_page_pa(cpuid_to_nasid(smp_processor_id()));
+ rp_pa = xpc_get_rsvd_page_pa(xp_cpu_to_nasid(smp_processor_id()));
preempt_enable();
if (rp_pa == 0) {
dev_err(xpc_part, "SAL failed to locate the reserved page\n");
- return NULL;
+ return -ESRCH;
}
rp = (struct xpc_rsvd_page *)__va(rp_pa);
/* SAL_versions < 3 had a SAL_partid defined as a u8 */
rp->SAL_partid &= 0xff;
}
- BUG_ON(rp->SAL_partid != sn_partition_id);
+ BUG_ON(rp->SAL_partid != xp_partition_id);
if (rp->SAL_partid < 0 || rp->SAL_partid >= xp_max_npartitions) {
dev_err(xpc_part, "the reserved page's partid of %d is outside "
"supported range (< 0 || >= %d)\n", rp->SAL_partid,
xp_max_npartitions);
- return NULL;
+ return -EINVAL;
}
rp->version = XPC_RP_VERSION;
/* SAL_version 1 didn't set the nasids_size field */
rp->SAL_nasids_size = 128;
}
- xp_sizeof_nasid_mask = rp->SAL_nasids_size;
- xp_nasid_mask_words = DIV_ROUND_UP(xp_sizeof_nasid_mask,
- BYTES_PER_WORD);
+ xpc_nasid_mask_nbytes = rp->SAL_nasids_size;
+ xpc_nasid_mask_nlongs = BITS_TO_LONGS(rp->SAL_nasids_size *
+ BITS_PER_BYTE);
/* setup the pointers to the various items in the reserved page */
xpc_part_nasids = XPC_RP_PART_NASIDS(rp);
xpc_mach_nasids = XPC_RP_MACH_NASIDS(rp);
- if (xpc_rsvd_page_init(rp) != xpSuccess)
- return NULL;
+ ret = xpc_arch_ops.setup_rsvd_page(rp);
+ if (ret != 0)
+ return ret;
/*
* Set timestamp of when reserved page was setup by XPC.
* This signifies to the remote partition that our reserved
* page is initialized.
*/
- rp->stamp = CURRENT_TIME;
+ new_ts_jiffies = jiffies;
+ if (new_ts_jiffies == 0 || new_ts_jiffies == rp->ts_jiffies)
+ new_ts_jiffies++;
+ rp->ts_jiffies = new_ts_jiffies;
- return rp;
+ xpc_rsvd_page = rp;
+ return 0;
}
-/*
- * Change protections to allow IPI operations (and AMO operations on
- * Shub 1.1 systems).
- */
void
-xpc_allow_IPI_ops(void)
+xpc_teardown_rsvd_page(void)
{
- int node;
- int nasid;
-
- /* >>> Change SH_IPI_ACCESS code to use SAL call once it is available */
-
- if (is_shub2()) {
- xpc_sh2_IPI_access0 =
- (u64)HUB_L((u64 *)LOCAL_MMR_ADDR(SH2_IPI_ACCESS0));
- xpc_sh2_IPI_access1 =
- (u64)HUB_L((u64 *)LOCAL_MMR_ADDR(SH2_IPI_ACCESS1));
- xpc_sh2_IPI_access2 =
- (u64)HUB_L((u64 *)LOCAL_MMR_ADDR(SH2_IPI_ACCESS2));
- xpc_sh2_IPI_access3 =
- (u64)HUB_L((u64 *)LOCAL_MMR_ADDR(SH2_IPI_ACCESS3));
-
- for_each_online_node(node) {
- nasid = cnodeid_to_nasid(node);
- HUB_S((u64 *)GLOBAL_MMR_ADDR(nasid, SH2_IPI_ACCESS0),
- -1UL);
- HUB_S((u64 *)GLOBAL_MMR_ADDR(nasid, SH2_IPI_ACCESS1),
- -1UL);
- HUB_S((u64 *)GLOBAL_MMR_ADDR(nasid, SH2_IPI_ACCESS2),
- -1UL);
- HUB_S((u64 *)GLOBAL_MMR_ADDR(nasid, SH2_IPI_ACCESS3),
- -1UL);
- }
-
- } else {
- xpc_sh1_IPI_access =
- (u64)HUB_L((u64 *)LOCAL_MMR_ADDR(SH1_IPI_ACCESS));
-
- for_each_online_node(node) {
- nasid = cnodeid_to_nasid(node);
- HUB_S((u64 *)GLOBAL_MMR_ADDR(nasid, SH1_IPI_ACCESS),
- -1UL);
-
- /*
- * Since the BIST collides with memory operations on
- * SHUB 1.1 sn_change_memprotect() cannot be used.
- */
- if (enable_shub_wars_1_1()) {
- /* open up everything */
- xpc_prot_vec[node] = (u64)HUB_L((u64 *)
- GLOBAL_MMR_ADDR
- (nasid,
- SH1_MD_DQLP_MMR_DIR_PRIVEC0));
- HUB_S((u64 *)
- GLOBAL_MMR_ADDR(nasid,
- SH1_MD_DQLP_MMR_DIR_PRIVEC0),
- -1UL);
- HUB_S((u64 *)
- GLOBAL_MMR_ADDR(nasid,
- SH1_MD_DQRP_MMR_DIR_PRIVEC0),
- -1UL);
- }
- }
- }
-}
-
-/*
- * Restrict protections to disallow IPI operations (and AMO operations on
- * Shub 1.1 systems).
- */
-void
-xpc_restrict_IPI_ops(void)
-{
- int node;
- int nasid;
-
- /* >>> Change SH_IPI_ACCESS code to use SAL call once it is available */
-
- if (is_shub2()) {
-
- for_each_online_node(node) {
- nasid = cnodeid_to_nasid(node);
- HUB_S((u64 *)GLOBAL_MMR_ADDR(nasid, SH2_IPI_ACCESS0),
- xpc_sh2_IPI_access0);
- HUB_S((u64 *)GLOBAL_MMR_ADDR(nasid, SH2_IPI_ACCESS1),
- xpc_sh2_IPI_access1);
- HUB_S((u64 *)GLOBAL_MMR_ADDR(nasid, SH2_IPI_ACCESS2),
- xpc_sh2_IPI_access2);
- HUB_S((u64 *)GLOBAL_MMR_ADDR(nasid, SH2_IPI_ACCESS3),
- xpc_sh2_IPI_access3);
- }
-
- } else {
-
- for_each_online_node(node) {
- nasid = cnodeid_to_nasid(node);
- HUB_S((u64 *)GLOBAL_MMR_ADDR(nasid, SH1_IPI_ACCESS),
- xpc_sh1_IPI_access);
-
- if (enable_shub_wars_1_1()) {
- HUB_S((u64 *)GLOBAL_MMR_ADDR(nasid,
- SH1_MD_DQLP_MMR_DIR_PRIVEC0),
- xpc_prot_vec[node]);
- HUB_S((u64 *)GLOBAL_MMR_ADDR(nasid,
- SH1_MD_DQRP_MMR_DIR_PRIVEC0),
- xpc_prot_vec[node]);
- }
- }
- }
+ /* a zero timestamp indicates our rsvd page is not initialized */
+ xpc_rsvd_page->ts_jiffies = 0;
}
/*
* part_nasids mask.
*/
enum xp_retval
-xpc_get_remote_rp(int nasid, u64 *discovered_nasids,
- struct xpc_rsvd_page *remote_rp, u64 *remote_rp_pa)
+xpc_get_remote_rp(int nasid, unsigned long *discovered_nasids,
+ struct xpc_rsvd_page *remote_rp, unsigned long *remote_rp_pa)
{
- int i;
+ int l;
enum xp_retval ret;
/* get the reserved page's physical address */
return xpNoRsvdPageAddr;
/* pull over the reserved page header and part_nasids mask */
- ret = xp_remote_memcpy(remote_rp, (void *)*remote_rp_pa,
- XPC_RP_HEADER_SIZE + xp_sizeof_nasid_mask);
+ ret = xp_remote_memcpy(xp_pa(remote_rp), *remote_rp_pa,
+ XPC_RP_HEADER_SIZE + xpc_nasid_mask_nbytes);
if (ret != xpSuccess)
return ret;
if (discovered_nasids != NULL) {
- u64 *remote_part_nasids = XPC_RP_PART_NASIDS(remote_rp);
+ unsigned long *remote_part_nasids =
+ XPC_RP_PART_NASIDS(remote_rp);
- for (i = 0; i < xp_nasid_mask_words; i++)
- discovered_nasids[i] |= remote_part_nasids[i];
+ for (l = 0; l < xpc_nasid_mask_nlongs; l++)
+ discovered_nasids[l] |= remote_part_nasids[l];
}
- /* check that the partid is valid and is for another partition */
-
- if (remote_rp->SAL_partid < 0 ||
- remote_rp->SAL_partid >= xp_max_npartitions) {
- return xpInvalidPartid;
- }
-
- if (remote_rp->SAL_partid == sn_partition_id)
- return xpLocalPartid;
-
- /* see if the rest of the reserved page has been set up by XPC */
- if (timespec_equal(&remote_rp->stamp, &ZERO_STAMP))
+ /* zero timestamp indicates the reserved page has not been setup */
+ if (remote_rp->ts_jiffies == 0)
return xpRsvdPageNotSet;
if (XPC_VERSION_MAJOR(remote_rp->version) !=
return xpBadVersion;
}
- if (remote_rp->max_npartitions <= sn_partition_id)
+ /* check that both remote and local partids are valid for each side */
+ if (remote_rp->SAL_partid < 0 ||
+ remote_rp->SAL_partid >= xp_max_npartitions ||
+ remote_rp->max_npartitions <= xp_partition_id) {
return xpInvalidPartid;
+ }
+
+ if (remote_rp->SAL_partid == xp_partition_id)
+ return xpLocalPartid;
return xpSuccess;
}
/*
- * See if the other side has responded to a partition disengage request
- * from us.
+ * See if the other side has responded to a partition deactivate request
+ * from us. Though we requested the remote partition to deactivate with regard
+ * to us, we really only need to wait for the other side to disengage from us.
*/
int
xpc_partition_disengaged(struct xpc_partition *part)
short partid = XPC_PARTID(part);
int disengaged;
- disengaged = (xpc_partition_engaged(1UL << partid) == 0);
- if (part->disengage_request_timeout) {
+ disengaged = !xpc_arch_ops.partition_engaged(partid);
+ if (part->disengage_timeout) {
if (!disengaged) {
- if (time_before(jiffies,
- part->disengage_request_timeout)) {
+ if (time_is_after_jiffies(part->disengage_timeout)) {
/* timelimit hasn't been reached yet */
return 0;
}
/*
- * Other side hasn't responded to our disengage
+ * Other side hasn't responded to our deactivate
* request in a timely fashion, so assume it's dead.
*/
- dev_info(xpc_part, "disengage from remote partition %d "
- "timed out\n", partid);
- xpc_disengage_request_timedout = 1;
- xpc_clear_partition_engaged(1UL << partid);
+ dev_info(xpc_part, "deactivate request to remote "
+ "partition %d timed out\n", partid);
+ xpc_disengage_timedout = 1;
+ xpc_arch_ops.assume_partition_disengaged(partid);
disengaged = 1;
}
- part->disengage_request_timeout = 0;
+ part->disengage_timeout = 0;
/* cancel the timer function, provided it's not us */
- if (!in_interrupt()) {
- del_singleshot_timer_sync(&part->
- disengage_request_timer);
- }
+ if (!in_interrupt())
+ del_singleshot_timer_sync(&part->disengage_timer);
- DBUG_ON(part->act_state != XPC_P_DEACTIVATING &&
- part->act_state != XPC_P_INACTIVE);
- if (part->act_state != XPC_P_INACTIVE)
+ DBUG_ON(part->act_state != XPC_P_AS_DEACTIVATING &&
+ part->act_state != XPC_P_AS_INACTIVE);
+ if (part->act_state != XPC_P_AS_INACTIVE)
xpc_wakeup_channel_mgr(part);
- if (XPC_SUPPORTS_DISENGAGE_REQUEST(part->remote_vars_version))
- xpc_cancel_partition_disengage_request(part);
+ xpc_arch_ops.cancel_partition_deactivation_request(part);
}
return disengaged;
}
dev_dbg(xpc_part, "setting partition %d to ACTIVE\n", XPC_PARTID(part));
spin_lock_irqsave(&part->act_lock, irq_flags);
- if (part->act_state == XPC_P_ACTIVATING) {
- part->act_state = XPC_P_ACTIVE;
+ if (part->act_state == XPC_P_AS_ACTIVATING) {
+ part->act_state = XPC_P_AS_ACTIVE;
ret = xpSuccess;
} else {
DBUG_ON(part->reason == xpSuccess);
}
/*
- * Notify XPC that the partition is down.
+ * Start the process of deactivating the specified partition.
*/
void
xpc_deactivate_partition(const int line, struct xpc_partition *part,
spin_lock_irqsave(&part->act_lock, irq_flags);
- if (part->act_state == XPC_P_INACTIVE) {
+ if (part->act_state == XPC_P_AS_INACTIVE) {
XPC_SET_REASON(part, reason, line);
spin_unlock_irqrestore(&part->act_lock, irq_flags);
if (reason == xpReactivating) {
/* we interrupt ourselves to reactivate partition */
- xpc_IPI_send_local_reactivate(part->reactivate_nasid);
+ xpc_arch_ops.request_partition_reactivation(part);
}
return;
}
- if (part->act_state == XPC_P_DEACTIVATING) {
+ if (part->act_state == XPC_P_AS_DEACTIVATING) {
if ((part->reason == xpUnloading && reason != xpUnloading) ||
reason == xpReactivating) {
XPC_SET_REASON(part, reason, line);
return;
}
- part->act_state = XPC_P_DEACTIVATING;
+ part->act_state = XPC_P_AS_DEACTIVATING;
XPC_SET_REASON(part, reason, line);
spin_unlock_irqrestore(&part->act_lock, irq_flags);
- if (XPC_SUPPORTS_DISENGAGE_REQUEST(part->remote_vars_version)) {
- xpc_request_partition_disengage(part);
- xpc_IPI_send_disengage(part);
+ /* ask remote partition to deactivate with regard to us */
+ xpc_arch_ops.request_partition_deactivation(part);
- /* set a timelimit on the disengage request */
- part->disengage_request_timeout = jiffies +
- (xpc_disengage_request_timelimit * HZ);
- part->disengage_request_timer.expires =
- part->disengage_request_timeout;
- add_timer(&part->disengage_request_timer);
- }
+ /* set a timelimit on the disengage phase of the deactivation request */
+ part->disengage_timeout = jiffies + (xpc_disengage_timelimit * HZ);
+ part->disengage_timer.expires = part->disengage_timeout;
+ add_timer(&part->disengage_timer);
dev_dbg(xpc_part, "bringing partition %d down, reason = %d\n",
XPC_PARTID(part), reason);
XPC_PARTID(part));
spin_lock_irqsave(&part->act_lock, irq_flags);
- part->act_state = XPC_P_INACTIVE;
+ part->act_state = XPC_P_AS_INACTIVE;
spin_unlock_irqrestore(&part->act_lock, irq_flags);
part->remote_rp_pa = 0;
}
{
void *remote_rp_base;
struct xpc_rsvd_page *remote_rp;
- u64 remote_rp_pa;
+ unsigned long remote_rp_pa;
int region;
int region_size;
int max_regions;
int nasid;
struct xpc_rsvd_page *rp;
- u64 *discovered_nasids;
+ unsigned long *discovered_nasids;
enum xp_retval ret;
remote_rp = xpc_kmalloc_cacheline_aligned(XPC_RP_HEADER_SIZE +
- xp_sizeof_nasid_mask,
+ xpc_nasid_mask_nbytes,
GFP_KERNEL, &remote_rp_base);
if (remote_rp == NULL)
return;
- discovered_nasids = kzalloc(sizeof(u64) * xp_nasid_mask_words,
+ discovered_nasids = kzalloc(sizeof(long) * xpc_nasid_mask_nlongs,
GFP_KERNEL);
if (discovered_nasids == NULL) {
kfree(remote_rp_base);
* protection is in regards to memory, IOI and IPI.
*/
max_regions = 64;
- region_size = sn_region_size;
+ region_size = xp_region_size;
switch (region_size) {
case 128:
dev_dbg(xpc_part, "checking nasid %d\n", nasid);
- if (XPC_NASID_IN_ARRAY(nasid, xpc_part_nasids)) {
+ if (test_bit(nasid / 2, xpc_part_nasids)) {
dev_dbg(xpc_part, "PROM indicates Nasid %d is "
"part of the local partition; skipping "
"region\n", nasid);
break;
}
- if (!(XPC_NASID_IN_ARRAY(nasid, xpc_mach_nasids))) {
+ if (!(test_bit(nasid / 2, xpc_mach_nasids))) {
dev_dbg(xpc_part, "PROM indicates Nasid %d was "
"not on Numa-Link network at reset\n",
nasid);
continue;
}
- if (XPC_NASID_IN_ARRAY(nasid, discovered_nasids)) {
+ if (test_bit(nasid / 2, discovered_nasids)) {
dev_dbg(xpc_part, "Nasid %d is part of a "
"partition which was previously "
"discovered\n", nasid);
continue;
}
- xpc_initiate_partition_activation(remote_rp,
- remote_rp_pa, nasid);
+ xpc_arch_ops.request_partition_activation(remote_rp,
+ remote_rp_pa, nasid);
}
}
xpc_initiate_partid_to_nasids(short partid, void *nasid_mask)
{
struct xpc_partition *part;
- u64 part_nasid_pa;
+ unsigned long part_nasid_pa;
part = &xpc_partitions[partid];
if (part->remote_rp_pa == 0)
return xpPartitionDown;
- memset(nasid_mask, 0, XP_NASID_MASK_BYTES);
+ memset(nasid_mask, 0, xpc_nasid_mask_nbytes);
- part_nasid_pa = (u64)XPC_RP_PART_NASIDS(part->remote_rp_pa);
+ part_nasid_pa = (unsigned long)XPC_RP_PART_NASIDS(part->remote_rp_pa);
- return xp_remote_memcpy(nasid_mask, (void *)part_nasid_pa,
- xp_sizeof_nasid_mask);
+ return xp_remote_memcpy(xp_pa(nasid_mask), part_nasid_pa,
+ xpc_nasid_mask_nbytes);
}