IB/ehca: Support large page MRs

Add support for MR pages larger than 4K on eHCA2. This reduces
firmware memory consumption.  If enabled via the mr_largepage module
parameter, the MR page size will be determined based on the MR length
and the hardware capabilities -- if the MR is >= 16M, 16M pages are
used, for example.
Signed-off-by: Joachim Fenkes <fenkes@de.ibm.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

drivers/infiniband/hw/ehca/ehca_classes.h

@@ -100,6 +100,11 @@ struct ehca_sport {
 	struct ehca_sma_attr saved_attr;
 };
 
+#define HCA_CAP_MR_PGSIZE_4K  1
+#define HCA_CAP_MR_PGSIZE_64K 2
+#define HCA_CAP_MR_PGSIZE_1M  4
+#define HCA_CAP_MR_PGSIZE_16M 8
+
 struct ehca_shca {
 	struct ib_device ib_device;
 	struct ibmebus_dev *ibmebus_dev;
@@ -115,6 +120,8 @@ struct ehca_shca {
 	struct h_galpas galpas;
 	struct mutex modify_mutex;
 	u64 hca_cap;
+	/* MR pgsize: bit 0-3 means 4K, 64K, 1M, 16M respectively */
+	u32 hca_cap_mr_pgsize;
 	int max_mtu;
 };
 
@@ -206,6 +213,7 @@ struct ehca_mr {
 	enum ehca_mr_flag flags;
 	u32 num_kpages;		/* number of kernel pages */
 	u32 num_hwpages;	/* number of hw pages to form MR */
+	u64 hwpage_size;	/* hw page size used for this MR */
 	int acl;		/* ACL (stored here for usage in reregister) */
 	u64 *start;		/* virtual start address (stored here for */
 				/* usage in reregister) */
@@ -240,6 +248,7 @@ struct ehca_mr_pginfo {
 	enum ehca_mr_pgi_type type;
 	u64 num_kpages;
 	u64 kpage_cnt;
+	u64 hwpage_size;     /* hw page size used for this MR */
 	u64 num_hwpages;     /* number of hw pages */
 	u64 hwpage_cnt;      /* counter for hw pages */
 	u64 next_hwpage;     /* next hw page in buffer/chunk/listelem */

drivers/infiniband/hw/ehca/ehca_main.c

@@ -63,6 +63,7 @@ int ehca_port_act_time = 30;
 int ehca_poll_all_eqs  = 1;
 int ehca_static_rate   = -1;
 int ehca_scaling_code  = 0;
+int ehca_mr_largepage  = 0;
 
 module_param_named(open_aqp1,     ehca_open_aqp1,     int, 0);
 module_param_named(debug_level,   ehca_debug_level,   int, 0);
@@ -72,7 +73,8 @@ module_param_named(use_hp_mr,     ehca_use_hp_mr,     int, 0);
 module_param_named(port_act_time, ehca_port_act_time, int, 0);
 module_param_named(poll_all_eqs,  ehca_poll_all_eqs,  int, 0);
 module_param_named(static_rate,   ehca_static_rate,   int, 0);
-module_param_named(scaling_code,   ehca_scaling_code,   int, 0);
+module_param_named(scaling_code,  ehca_scaling_code,  int, 0);
+module_param_named(mr_largepage,  ehca_mr_largepage,  int, 0);
 
 MODULE_PARM_DESC(open_aqp1,
 		 "AQP1 on startup (0: no (default), 1: yes)");
@@ -95,6 +97,9 @@ MODULE_PARM_DESC(static_rate,
 		 "set permanent static rate (default: disabled)");
 MODULE_PARM_DESC(scaling_code,
 		 "set scaling code (0: disabled/default, 1: enabled)");
+MODULE_PARM_DESC(mr_largepage,
+		 "use large page for MR (0: use PAGE_SIZE (default), "
+		 "1: use large page depending on MR size");
 
 DEFINE_RWLOCK(ehca_qp_idr_lock);
 DEFINE_RWLOCK(ehca_cq_idr_lock);
@@ -295,6 +300,8 @@ int ehca_sense_attributes(struct ehca_shca *shca)
 		if (EHCA_BMASK_GET(hca_cap_descr[i].mask, shca->hca_cap))
 			ehca_gen_dbg("   %s", hca_cap_descr[i].descr);
 
+	shca->hca_cap_mr_pgsize = rblock->memory_page_size_supported;
+
 	port = (struct hipz_query_port *)rblock;
 	h_ret = hipz_h_query_port(shca->ipz_hca_handle, 1, port);
 	if (h_ret != H_SUCCESS) {
@@ -590,6 +597,14 @@ static ssize_t ehca_show_adapter_handle(struct device *dev,
 }
 static DEVICE_ATTR(adapter_handle, S_IRUGO, ehca_show_adapter_handle, NULL);
 
+static ssize_t ehca_show_mr_largepage(struct device *dev,
+				      struct device_attribute *attr,
+				      char *buf)
+{
+	return sprintf(buf, "%d\n", ehca_mr_largepage);
+}
+static DEVICE_ATTR(mr_largepage, S_IRUGO, ehca_show_mr_largepage, NULL);
+
 static struct attribute *ehca_dev_attrs[] = {
 	&dev_attr_adapter_handle.attr,
 	&dev_attr_num_ports.attr,
@@ -606,6 +621,7 @@ static struct attribute *ehca_dev_attrs[] = {
 	&dev_attr_cur_mw.attr,
 	&dev_attr_max_pd.attr,
 	&dev_attr_max_ah.attr,
+	&dev_attr_mr_largepage.attr,
 	NULL
 };
 

drivers/infiniband/hw/ehca/ehca_mrmw.h

@@ -111,7 +111,7 @@ int ehca_mr_is_maxmr(u64 size,
 void ehca_mrmw_map_acl(int ib_acl,
 		       u32 *hipz_acl);
 
-void ehca_mrmw_set_pgsize_hipz_acl(u32 *hipz_acl);
+void ehca_mrmw_set_pgsize_hipz_acl(u32 pgsize, u32 *hipz_acl);
 
 void ehca_mrmw_reverse_map_acl(const u32 *hipz_acl,
 			       int *ib_acl);

drivers/infiniband/hw/ehca/hcp_if.c

@@ -427,7 +427,8 @@ u64 hipz_h_register_rpage(const struct ipz_adapter_handle adapter_handle,
 {
 	return ehca_plpar_hcall_norets(H_REGISTER_RPAGES,
 				       adapter_handle.handle,      /* r4  */
-				       queue_type | pagesize << 8, /* r5  */
+				       (u64)queue_type | ((u64)pagesize) << 8,
+				       /* r5  */
 				       resource_handle,	           /* r6  */
 				       logical_address_of_page,    /* r7  */
 				       count,	                   /* r8  */
@@ -724,6 +725,9 @@ u64 hipz_h_alloc_resource_mr(const struct ipz_adapter_handle adapter_handle,
 	u64 ret;
 	u64 outs[PLPAR_HCALL9_BUFSIZE];
 
+	ehca_gen_dbg("kernel PAGE_SIZE=%x access_ctrl=%016x "
+		     "vaddr=%lx length=%lx",
+		     (u32)PAGE_SIZE, access_ctrl, vaddr, length);
 	ret = ehca_plpar_hcall9(H_ALLOC_RESOURCE, outs,
 				adapter_handle.handle,            /* r4 */
 				5,                                /* r5 */
@@ -746,8 +750,22 @@ u64 hipz_h_register_rpage_mr(const struct ipz_adapter_handle adapter_handle,
 			     const u64 logical_address_of_page,
 			     const u64 count)
 {
+	extern int ehca_debug_level;
 	u64 ret;
 
+	if (unlikely(ehca_debug_level >= 2)) {
+		if (count > 1) {
+			u64 *kpage;
+			int i;
+			kpage = (u64 *)abs_to_virt(logical_address_of_page);
+			for (i = 0; i < count; i++)
+				ehca_gen_dbg("kpage[%d]=%p",
+					     i, (void *)kpage[i]);
+		} else
+			ehca_gen_dbg("kpage=%p",
+				     (void *)logical_address_of_page);
+	}
+
 	if ((count > 1) && (logical_address_of_page & (EHCA_PAGESIZE-1))) {
 		ehca_gen_err("logical_address_of_page not on a 4k boundary "
 			     "adapter_handle=%lx mr=%p mr_handle=%lx "