aboutsummaryrefslogtreecommitdiff
path: root/drivers/misc/sgi-xp/xpc_partition.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/misc/sgi-xp/xpc_partition.c')
-rw-r--r--drivers/misc/sgi-xp/xpc_partition.c928
1 files changed, 141 insertions, 787 deletions
diff --git a/drivers/misc/sgi-xp/xpc_partition.c b/drivers/misc/sgi-xp/xpc_partition.c
index 7dd4b5812c4..6722f6fe4dc 100644
--- a/drivers/misc/sgi-xp/xpc_partition.c
+++ b/drivers/misc/sgi-xp/xpc_partition.c
@@ -15,57 +15,22 @@
*
*/
-#include <linux/kernel.h>
-#include <linux/sysctl.h>
-#include <linux/cache.h>
-#include <linux/mmzone.h>
-#include <linux/nodemask.h>
-#include <asm/uncached.h>
-#include <asm/sn/bte.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;
-static u64 *xpc_mach_nasids;
-struct xpc_vars *xpc_vars;
-struct xpc_vars_part *xpc_vars_part;
+static unsigned long *xpc_part_nasids;
+unsigned long *xpc_mach_nasids;
-static int xp_nasid_mask_bytes; /* actual size in bytes of nasid mask */
-static int xp_nasid_mask_words; /* actual size in words of nasid mask */
-
-/*
- * For performance reasons, each entry of xpc_partitions[] is cacheline
- * aligned. And xpc_partitions[] is padded with an additional entry at the
- * end so that the last legitimate entry doesn't share its cacheline with
- * another variable.
- */
-struct xpc_partition xpc_partitions[XP_MAX_PARTITIONS + 1];
+static int xpc_nasid_mask_nbytes; /* #of bytes in nasid mask */
+int xpc_nasid_mask_nlongs; /* #of longs in nasid mask */
-/*
- * 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;
+struct xpc_partition *xpc_partitions;
/*
* Guarantee that the kmalloc'd memory is cacheline aligned.
@@ -95,56 +60,59 @@ xpc_kmalloc_cacheline_aligned(size_t size, gfp_t flags, void **base)
* 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)
{
- bte_result_t bte_res;
- s64 status;
+ enum xp_retval ret;
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;
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 = xpc_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 */
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;
}
}
- bte_res = xp_bte_copy(rp_pa, buf, buf_len,
- (BTE_NOTIFY | BTE_WACQUIRE), NULL);
- if (bte_res != BTE_SUCCESS) {
- dev_dbg(xpc_part, "xp_bte_copy failed %i\n", bte_res);
- status = SALRET_ERROR;
+ 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);
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);
@@ -156,300 +124,77 @@ xpc_get_rsvd_page_pa(int nasid)
* other partitions to discover we are alive and establish initial
* communications.
*/
-struct xpc_rsvd_page *
-xpc_rsvd_page_init(void)
+int
+xpc_setup_rsvd_page(void)
{
+ int ret;
struct xpc_rsvd_page *rp;
- AMO_t *amos_page;
- u64 rp_pa, nasid_array = 0;
- int i, ret;
+ 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);
- if (rp->partid != sn_partition_id) {
- dev_err(xpc_part, "the reserved page's partid of %d should be "
- "%d\n", rp->partid, sn_partition_id);
- return NULL;
+ if (rp->SAL_version < 3) {
+ /* SAL_versions < 3 had a SAL_partid defined as a u8 */
+ rp->SAL_partid &= 0xff;
+ }
+ 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 -EINVAL;
}
rp->version = XPC_RP_VERSION;
+ rp->max_npartitions = xp_max_npartitions;
/* establish the actual sizes of the nasid masks */
if (rp->SAL_version == 1) {
/* SAL_version 1 didn't set the nasids_size field */
- rp->nasids_size = 128;
+ rp->SAL_nasids_size = 128;
}
- xp_nasid_mask_bytes = rp->nasids_size;
- xp_nasid_mask_words = xp_nasid_mask_bytes / 8;
+ 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);
- xpc_vars = XPC_RP_VARS(rp);
- xpc_vars_part = XPC_RP_VARS_PART(rp);
-
- /*
- * Before clearing xpc_vars, see if a page of AMOs had been previously
- * allocated. If not we'll need to allocate one and set permissions
- * so that cross-partition AMOs are allowed.
- *
- * The allocated AMO page needs MCA reporting to remain disabled after
- * XPC has unloaded. To make this work, we keep a copy of the pointer
- * to this page (i.e., amos_page) in the struct xpc_vars structure,
- * which is pointed to by the reserved page, and re-use that saved copy
- * on subsequent loads of XPC. This AMO page is never freed, and its
- * memory protections are never restricted.
- */
- amos_page = xpc_vars->amos_page;
- if (amos_page == NULL) {
- amos_page = (AMO_t *)TO_AMO(uncached_alloc_page(0, 1));
- if (amos_page == NULL) {
- dev_err(xpc_part, "can't allocate page of AMOs\n");
- return NULL;
- }
-
- /*
- * Open up AMO-R/W to cpu. This is done for Shub 1.1 systems
- * when xpc_allow_IPI_ops() is called via xpc_hb_init().
- */
- if (!enable_shub_wars_1_1()) {
- ret = sn_change_memprotect(ia64_tpa((u64)amos_page),
- PAGE_SIZE,
- SN_MEMPROT_ACCESS_CLASS_1,
- &nasid_array);
- if (ret != 0) {
- dev_err(xpc_part, "can't change memory "
- "protections\n");
- uncached_free_page(__IA64_UNCACHED_OFFSET |
- TO_PHYS((u64)amos_page), 1);
- return NULL;
- }
- }
- } else if (!IS_AMO_ADDRESS((u64)amos_page)) {
- /*
- * EFI's XPBOOT can also set amos_page in the reserved page,
- * but it happens to leave it as an uncached physical address
- * and we need it to be an uncached virtual, so we'll have to
- * convert it.
- */
- if (!IS_AMO_PHYS_ADDRESS((u64)amos_page)) {
- dev_err(xpc_part, "previously used amos_page address "
- "is bad = 0x%p\n", (void *)amos_page);
- return NULL;
- }
- amos_page = (AMO_t *)TO_AMO((u64)amos_page);
- }
-
- /* clear xpc_vars */
- memset(xpc_vars, 0, sizeof(struct xpc_vars));
-
- xpc_vars->version = XPC_V_VERSION;
- xpc_vars->act_nasid = cpuid_to_nasid(0);
- xpc_vars->act_phys_cpuid = cpu_physical_id(0);
- xpc_vars->vars_part_pa = __pa(xpc_vars_part);
- xpc_vars->amos_page_pa = ia64_tpa((u64)amos_page);
- xpc_vars->amos_page = amos_page; /* save for next load of XPC */
-
- /* clear xpc_vars_part */
- memset((u64 *)xpc_vars_part, 0, sizeof(struct xpc_vars_part) *
- XP_MAX_PARTITIONS);
-
- /* initialize the activate IRQ related AMO variables */
- for (i = 0; i < xp_nasid_mask_words; i++)
- (void)xpc_IPI_init(XPC_ACTIVATE_IRQ_AMOS + i);
-
- /* initialize the engaged remote partitions related AMO variables */
- (void)xpc_IPI_init(XPC_ENGAGED_PARTITIONS_AMO);
- (void)xpc_IPI_init(XPC_DISENGAGE_REQUEST_AMO);
- /* timestamp of when reserved page was setup by XPC */
- rp->stamp = CURRENT_TIME;
+ ret = xpc_setup_rsvd_page_sn(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->vars_pa = __pa(xpc_vars);
+ 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]);
- }
- }
- }
-}
-
-/*
- * At periodic intervals, scan through all active partitions and ensure
- * their heartbeat is still active. If not, the partition is deactivated.
- */
-void
-xpc_check_remote_hb(void)
-{
- struct xpc_vars *remote_vars;
- struct xpc_partition *part;
- short partid;
- bte_result_t bres;
-
- remote_vars = (struct xpc_vars *)xpc_remote_copy_buffer;
-
- for (partid = 1; partid < XP_MAX_PARTITIONS; partid++) {
-
- if (xpc_exiting)
- break;
-
- if (partid == sn_partition_id)
- continue;
-
- part = &xpc_partitions[partid];
-
- if (part->act_state == XPC_P_INACTIVE ||
- part->act_state == XPC_P_DEACTIVATING) {
- continue;
- }
-
- /* pull the remote_hb cache line */
- bres = xp_bte_copy(part->remote_vars_pa,
- (u64)remote_vars,
- XPC_RP_VARS_SIZE,
- (BTE_NOTIFY | BTE_WACQUIRE), NULL);
- if (bres != BTE_SUCCESS) {
- XPC_DEACTIVATE_PARTITION(part,
- xpc_map_bte_errors(bres));
- continue;
- }
-
- dev_dbg(xpc_part, "partid = %d, heartbeat = %ld, last_heartbeat"
- " = %ld, heartbeat_offline = %ld, HB_mask = 0x%lx\n",
- partid, remote_vars->heartbeat, part->last_heartbeat,
- remote_vars->heartbeat_offline,
- remote_vars->heartbeating_to_mask);
-
- if (((remote_vars->heartbeat == part->last_heartbeat) &&
- (remote_vars->heartbeat_offline == 0)) ||
- !xpc_hb_allowed(sn_partition_id, remote_vars)) {
-
- XPC_DEACTIVATE_PARTITION(part, xpNoHeartbeat);
- continue;
- }
-
- part->last_heartbeat = remote_vars->heartbeat;
- }
+ /* a zero timestamp indicates our rsvd page is not initialized */
+ xpc_rsvd_page->ts_jiffies = 0;
}
/*
@@ -459,11 +204,12 @@ xpc_check_remote_hb(void)
* is large enough to contain a copy of their reserved page header and
* part_nasids mask.
*/
-static enum xp_retval
-xpc_get_remote_rp(int nasid, u64 *discovered_nasids,
- struct xpc_rsvd_page *remote_rp, u64 *remote_rp_pa)
+enum xp_retval
+xpc_get_remote_rp(int nasid, unsigned long *discovered_nasids,
+ struct xpc_rsvd_page *remote_rp, unsigned long *remote_rp_pa)
{
- int bres, i;
+ int l;
+ enum xp_retval ret;
/* get the reserved page's physical address */
@@ -472,355 +218,45 @@ xpc_get_remote_rp(int nasid, u64 *discovered_nasids,
return xpNoRsvdPageAddr;
/* pull over the reserved page header and part_nasids mask */
- bres = xp_bte_copy(*remote_rp_pa, (u64)remote_rp,
- XPC_RP_HEADER_SIZE + xp_nasid_mask_bytes,
- (BTE_NOTIFY | BTE_WACQUIRE), NULL);
- if (bres != BTE_SUCCESS)
- return xpc_map_bte_errors(bres);
+ 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);
-
- for (i = 0; i < xp_nasid_mask_words; i++)
- discovered_nasids[i] |= remote_part_nasids[i];
- }
-
- /* check that the partid is for another partition */
+ unsigned long *remote_part_nasids =
+ XPC_RP_PART_NASIDS(remote_rp);
- if (remote_rp->partid < 1 ||
- remote_rp->partid > (XP_MAX_PARTITIONS - 1)) {
- return xpInvalidPartid;
+ for (l = 0; l < xpc_nasid_mask_nlongs; l++)
+ discovered_nasids[l] |= remote_part_nasids[l];
}
- if (remote_rp->partid == sn_partition_id)
- return xpLocalPartid;
+ /* 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) !=
XPC_VERSION_MAJOR(XPC_RP_VERSION)) {
return xpBadVersion;
}
- return xpSuccess;
-}
-
-/*
- * Get a copy of the remote partition's XPC variables from the reserved page.
- *
- * remote_vars points to a buffer that is cacheline aligned for BTE copies and
- * assumed to be of size XPC_RP_VARS_SIZE.
- */
-static enum xp_retval
-xpc_get_remote_vars(u64 remote_vars_pa, struct xpc_vars *remote_vars)
-{
- int bres;
-
- if (remote_vars_pa == 0)
- return xpVarsNotSet;
-
- /* pull over the cross partition variables */
- bres = xp_bte_copy(remote_vars_pa, (u64)remote_vars, XPC_RP_VARS_SIZE,
- (BTE_NOTIFY | BTE_WACQUIRE), NULL);
- if (bres != BTE_SUCCESS)
- return xpc_map_bte_errors(bres);
-
- if (XPC_VERSION_MAJOR(remote_vars->version) !=
- XPC_VERSION_MAJOR(XPC_V_VERSION)) {
- return xpBadVersion;
- }
-
- return xpSuccess;
-}
-
-/*
- * Update the remote partition's info.
- */
-static void
-xpc_update_partition_info(struct xpc_partition *part, u8 remote_rp_version,
- struct timespec *remote_rp_stamp, u64 remote_rp_pa,
- u64 remote_vars_pa, struct xpc_vars *remote_vars)
-{
- part->remote_rp_version = remote_rp_version;
- dev_dbg(xpc_part, " remote_rp_version = 0x%016x\n",
- part->remote_rp_version);
-
- part->remote_rp_stamp = *remote_rp_stamp;
- dev_dbg(xpc_part, " remote_rp_stamp (tv_sec = 0x%lx tv_nsec = 0x%lx\n",
- part->remote_rp_stamp.tv_sec, part->remote_rp_stamp.tv_nsec);
-
- part->remote_rp_pa = remote_rp_pa;
- dev_dbg(xpc_part, " remote_rp_pa = 0x%016lx\n", part->remote_rp_pa);
-
- part->remote_vars_pa = remote_vars_pa;
- dev_dbg(xpc_part, " remote_vars_pa = 0x%016lx\n",
- part->remote_vars_pa);
-
- part->last_heartbeat = remote_vars->heartbeat;
- dev_dbg(xpc_part, " last_heartbeat = 0x%016lx\n",
- part->last_heartbeat);
-
- part->remote_vars_part_pa = remote_vars->vars_part_pa;
- dev_dbg(xpc_part, " remote_vars_part_pa = 0x%016lx\n",
- part->remote_vars_part_pa);
-
- part->remote_act_nasid = remote_vars->act_nasid;
- dev_dbg(xpc_part, " remote_act_nasid = 0x%x\n",
- part->remote_act_nasid);
-
- part->remote_act_phys_cpuid = remote_vars->act_phys_cpuid;
- dev_dbg(xpc_part, " remote_act_phys_cpuid = 0x%x\n",
- part->remote_act_phys_cpuid);
-
- part->remote_amos_page_pa = remote_vars->amos_page_pa;
- dev_dbg(xpc_part, " remote_amos_page_pa = 0x%lx\n",
- part->remote_amos_page_pa);
-
- part->remote_vars_version = remote_vars->version;
- dev_dbg(xpc_part, " remote_vars_version = 0x%x\n",
- part->remote_vars_version);
-}
-
-/*
- * Prior code has determined the nasid which generated an IPI. Inspect
- * that nasid to determine if its partition needs to be activated or
- * deactivated.
- *
- * A partition is consider "awaiting activation" if our partition
- * flags indicate it is not active and it has a heartbeat. A
- * partition is considered "awaiting deactivation" if our partition
- * flags indicate it is active but it has no heartbeat or it is not
- * sending its heartbeat to us.
- *
- * To determine the heartbeat, the remote nasid must have a properly
- * initialized reserved page.
- */
-static void
-xpc_identify_act_IRQ_req(int nasid)
-{
- struct xpc_rsvd_page *remote_rp;
- struct xpc_vars *remote_vars;
- u64 remote_rp_pa;
- u64 remote_vars_pa;
- int remote_rp_version;
- int reactivate = 0;
- int stamp_diff;
- struct timespec remote_rp_stamp = { 0, 0 };
- short partid;
- struct xpc_partition *part;
- enum xp_retval ret;
-
- /* pull over the reserved page structure */
-
- remote_rp = (struct xpc_rsvd_page *)xpc_remote_copy_buffer;
-
- ret = xpc_get_remote_rp(nasid, NULL, remote_rp, &remote_rp_pa);
- if (ret != xpSuccess) {
- dev_warn(xpc_part, "unable to get reserved page from nasid %d, "
- "which sent interrupt, reason=%d\n", nasid, ret);
- return;
- }
-
- remote_vars_pa = remote_rp->vars_pa;
- remote_rp_version = remote_rp->version;
- if (XPC_SUPPORTS_RP_STAMP(remote_rp_version))
- remote_rp_stamp = remote_rp->stamp;
-
- partid = remote_rp->partid;
- part = &xpc_partitions[partid];
-
- /* pull over the cross partition variables */
-
- remote_vars = (struct xpc_vars *)xpc_remote_copy_buffer;
-
- ret = xpc_get_remote_vars(remote_vars_pa, remote_vars);
- if (ret != xpSuccess) {
-
- dev_warn(xpc_part, "unable to get XPC variables from nasid %d, "
- "which sent interrupt, reason=%d\n", nasid, ret);
-
- XPC_DEACTIVATE_PARTITION(part, ret);
- return;
- }
-
- part->act_IRQ_rcvd++;
-
- dev_dbg(xpc_part, "partid for nasid %d is %d; IRQs = %d; HB = "
- "%ld:0x%lx\n", (int)nasid, (int)partid, part->act_IRQ_rcvd,
- remote_vars->heartbeat, remote_vars->heartbeating_to_mask);
-
- if (xpc_partition_disengaged(part) &&
- part->act_state == XPC_P_INACTIVE) {
-
- xpc_update_partition_info(part, remote_rp_version,
- &remote_rp_stamp, remote_rp_pa,
- remote_vars_pa, remote_vars);
-
- if (XPC_SUPPORTS_DISENGAGE_REQUEST(part->remote_vars_version)) {
- if (xpc_partition_disengage_requested(1UL << partid)) {
- /*
- * Other side is waiting on us to disengage,
- * even though we already have.
- */
- return;
- }
- } else {
- /* other side doesn't support disengage requests */
- xpc_clear_partition_disengage_request(1UL << partid);
- }
-
- xpc_activate_partition(part);
- return;
- }
-
- DBUG_ON(part->remote_rp_version == 0);
- DBUG_ON(part->remote_vars_version == 0);
-
- if (!XPC_SUPPORTS_RP_STAMP(part->remote_rp_version)) {
- DBUG_ON(XPC_SUPPORTS_DISENGAGE_REQUEST(part->
- remote_vars_version));
-
- if (!XPC_SUPPORTS_RP_STAMP(remote_rp_version)) {
- DBUG_ON(XPC_SUPPORTS_DISENGAGE_REQUEST(remote_vars->
- version));
- /* see if the other side rebooted */
- if (part->remote_amos_page_pa ==
- remote_vars->amos_page_pa &&
- xpc_hb_allowed(sn_partition_id, remote_vars)) {
- /* doesn't look that way, so ignore the IPI */
- return;
- }
- }
-
- /*
- * Other side rebooted and previous XPC didn't support the
- * disengage request, so we don't need to do anything special.
- */
-
- xpc_update_partition_info(part, remote_rp_version,
- &remote_rp_stamp, remote_rp_pa,
- remote_vars_pa, remote_vars);
- part->reactivate_nasid = nasid;
- XPC_DEACTIVATE_PARTITION(part, xpReactivating);
- return;
- }
-
- DBUG_ON(!XPC_SUPPORTS_DISENGAGE_REQUEST(part->remote_vars_version));
-
- if (!XPC_SUPPORTS_RP_STAMP(remote_rp_version)) {
- DBUG_ON(!XPC_SUPPORTS_DISENGAGE_REQUEST(remote_vars->version));
-
- /*
- * Other side rebooted and previous XPC did support the
- * disengage request, but the new one doesn't.
- */
-
- xpc_clear_partition_engaged(1UL << partid);
- xpc_clear_partition_disengage_request(1UL << partid);
-
- xpc_update_partition_info(part, remote_rp_version,
- &remote_rp_stamp, remote_rp_pa,
- remote_vars_pa, remote_vars);
- reactivate = 1;
-
- } else {
- DBUG_ON(!XPC_SUPPORTS_DISENGAGE_REQUEST(remote_vars->version));
-
- stamp_diff = xpc_compare_stamps(&part->remote_rp_stamp,
- &remote_rp_stamp);
- if (stamp_diff != 0) {
- DBUG_ON(stamp_diff >= 0);
-
- /*
- * Other side rebooted and the previous XPC did support
- * the disengage request, as does the new one.
- */
-
- DBUG_ON(xpc_partition_engaged(1UL << partid));
- DBUG_ON(xpc_partition_disengage_requested(1UL <<
- partid));
-
- xpc_update_partition_info(part, remote_rp_version,
- &remote_rp_stamp,
- remote_rp_pa, remote_vars_pa,
- remote_vars);
- reactivate = 1;
- }
- }
-
- if (part->disengage_request_timeout > 0 &&
- !xpc_partition_disengaged(part)) {
- /* still waiting on other side to disengage from us */
- return;
- }
-
- if (reactivate) {
- part->reactivate_nasid = nasid;
- XPC_DEACTIVATE_PARTITION(part, xpReactivating);
-
- } else if (XPC_SUPPORTS_DISENGAGE_REQUEST(part->remote_vars_version) &&
- xpc_partition_disengage_requested(1UL << partid)) {
- XPC_DEACTIVATE_PARTITION(part, xpOtherGoingDown);
+ /* 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;
}
-}
-/*
- * Loop through the activation AMO variables and process any bits
- * which are set. Each bit indicates a nasid sending a partition
- * activation or deactivation request.
- *
- * Return #of IRQs detected.
- */
-int
-xpc_identify_act_IRQ_sender(void)
-{
- int word, bit;
- u64 nasid_mask;
- u64 nasid; /* remote nasid */
- int n_IRQs_detected = 0;
- AMO_t *act_amos;
-
- act_amos = xpc_vars->amos_page + XPC_ACTIVATE_IRQ_AMOS;
-
- /* scan through act AMO variable looking for non-zero entries */
- for (word = 0; word < xp_nasid_mask_words; word++) {
-
- if (xpc_exiting)
- break;
-
- nasid_mask = xpc_IPI_receive(&act_amos[word]);
- if (nasid_mask == 0) {
- /* no IRQs from nasids in this variable */
- continue;
- }
-
- dev_dbg(xpc_part, "AMO[%d] gave back 0x%lx\n", word,
- nasid_mask);
-
- /*
- * If this nasid has been added to the machine since
- * our partition was reset, this will retain the
- * remote nasid in our reserved pages machine mask.
- * This is used in the event of module reload.
- */
- xpc_mach_nasids[word] |= nasid_mask;
-
- /* locate the nasid(s) which sent interrupts */
+ if (remote_rp->SAL_partid == xp_partition_id)
+ return xpLocalPartid;
- for (bit = 0; bit < (8 * sizeof(u64)); bit++) {
- if (nasid_mask & (1UL << bit)) {
- n_IRQs_detected++;
- nasid = XPC_NASID_FROM_W_B(word, bit);
- dev_dbg(xpc_part, "interrupt from nasid %ld\n",
- nasid);
- xpc_identify_act_IRQ_req(nasid);
- }
- }
- }
- return n_IRQs_detected;
+ 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)
@@ -828,41 +264,37 @@ 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_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_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_cancel_partition_deactivation_request(part);
}
return disengaged;
}
@@ -879,8 +311,8 @@ xpc_mark_partition_active(struct xpc_partition *part)
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);
@@ -892,7 +324,7 @@ xpc_mark_partition_active(struct xpc_partition *part)
}
/*
- * 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,
@@ -902,16 +334,16 @@ 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_reactivate(part);
+ xpc_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);
@@ -920,22 +352,18 @@ xpc_deactivate_partition(const int line, struct xpc_partition *part,
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_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);
@@ -955,7 +383,7 @@ xpc_mark_partition_inactive(struct xpc_partition *part)
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;
}
@@ -974,28 +402,22 @@ xpc_discovery(void)
{
void *remote_rp_base;
struct xpc_rsvd_page *remote_rp;
- struct xpc_vars *remote_vars;
- u64 remote_rp_pa;
- u64 remote_vars_pa;
+ unsigned long remote_rp_pa;
int region;
int region_size;
int max_regions;
int nasid;
struct xpc_rsvd_page *rp;
- short partid;
- struct xpc_partition *part;
- u64 *discovered_nasids;
+ unsigned long *discovered_nasids;
enum xp_retval ret;
remote_rp = xpc_kmalloc_cacheline_aligned(XPC_RP_HEADER_SIZE +
- xp_nasid_mask_bytes,
+ xpc_nasid_mask_nbytes,
GFP_KERNEL, &remote_rp_base);
if (remote_rp == NULL)
return;
- remote_vars = (struct xpc_vars *)remote_rp;
-
- 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);
@@ -1010,7 +432,7 @@ xpc_discovery(void)
* 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:
@@ -1038,28 +460,28 @@ xpc_discovery(void)
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;
}
- /* pull over the reserved page structure */
+ /* pull over the rsvd page header & part_nasids mask */
ret = xpc_get_remote_rp(nasid, discovered_nasids,
remote_rp, &remote_rp_pa);
@@ -1074,72 +496,8 @@ xpc_discovery(void)
continue;
}
- remote_vars_pa = remote_rp->vars_pa;
-
- partid = remote_rp->partid;
- part = &xpc_partitions[partid];
-
- /* pull over the cross partition variables */
-
- ret = xpc_get_remote_vars(remote_vars_pa, remote_vars);
- if (ret != xpSuccess) {
- dev_dbg(xpc_part, "unable to get XPC variables "
- "from nasid %d, reason=%d\n", nasid,
- ret);
-
- XPC_DEACTIVATE_PARTITION(part, ret);
- continue;
- }
-
- if (part->act_state != XPC_P_INACTIVE) {
- dev_dbg(xpc_part, "partition %d on nasid %d is "
- "already activating\n", partid, nasid);
- break;
- }
-
- /*
- * Register the remote partition's AMOs with SAL so it
- * can handle and cleanup errors within that address
- * range should the remote partition go down. We don't
- * unregister this range because it is difficult to
- * tell when outstanding writes to the remote partition
- * are finished and thus when it is thus safe to
- * unregister. This should not result in wasted space
- * in the SAL xp_addr_region table because we should
- * get the same page for remote_act_amos_pa after
- * module reloads and system reboots.
- */
- if (sn_register_xp_addr_region
- (remote_vars->amos_page_pa, PAGE_SIZE, 1) < 0) {
- dev_dbg(xpc_part,
- "partition %d failed to "
- "register xp_addr region 0x%016lx\n",
- partid, remote_vars->amos_page_pa);
-
- XPC_SET_REASON(part, xpPhysAddrRegFailed,
- __LINE__);
- break;
- }
-
- /*
- * The remote nasid is valid and available.
- * Send an interrupt to that nasid to notify
- * it that we are ready to begin activation.
- */
- dev_dbg(xpc_part, "sending an interrupt to AMO 0x%lx, "
- "nasid %d, phys_cpuid 0x%x\n",
- remote_vars->amos_page_pa,
- remote_vars->act_nasid,
- remote_vars->act_phys_cpuid);
-
- if (XPC_SUPPORTS_DISENGAGE_REQUEST(remote_vars->
- version)) {
- part->remote_amos_page_pa =
- remote_vars->amos_page_pa;
- xpc_mark_partition_disengaged(part);
- xpc_cancel_partition_disengage_request(part);
- }
- xpc_IPI_send_activate(remote_vars);
+ xpc_request_partition_activation(remote_rp,
+ remote_rp_pa, nasid);
}
}
@@ -1155,20 +513,16 @@ enum xp_retval
xpc_initiate_partid_to_nasids(short partid, void *nasid_mask)
{
struct xpc_partition *part;
- u64 part_nasid_pa;
- int bte_res;
+ 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);
-
- part_nasid_pa = (u64)XPC_RP_PART_NASIDS(part->remote_rp_pa);
+ memset(nasid_mask, 0, xpc_nasid_mask_nbytes);
- bte_res = xp_bte_copy(part_nasid_pa, (u64)nasid_mask,
- xp_nasid_mask_bytes, (BTE_NOTIFY | BTE_WACQUIRE),
- NULL);
+ part_nasid_pa = (unsigned long)XPC_RP_PART_NASIDS(part->remote_rp_pa);
- return xpc_map_bte_errors(bte_res);
+ return xp_remote_memcpy(xp_pa(nasid_mask), part_nasid_pa,
+ xpc_nasid_mask_nbytes);
}