5 files changed, 214 insertions, 25 deletions

diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 94cd96b9b7bb..fbd6e6b7bbf2 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -193,7 +193,7 @@ static void pnv_smp_cpu_kill_self(void)
 		 * for coming online, which are handled via
 		 * generic_check_cpu_restart() calls.
 		 */
-		kvmppc_set_host_ipi(cpu, 0);
+		kvmppc_clear_host_ipi(cpu);
 
 		srr1 = pnv_cpu_offline(cpu);
 
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 36b846f6e74e..b53359258d99 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -56,6 +56,22 @@ EXPORT_SYMBOL(plpar_hcall);
 EXPORT_SYMBOL(plpar_hcall9);
 EXPORT_SYMBOL(plpar_hcall_norets);
 
+/*
+ * H_BLOCK_REMOVE supported block size for this page size in segment who's base
+ * page size is that page size.
+ *
+ * The first index is the segment base page size, the second one is the actual
+ * page size.
+ */
+static int hblkrm_size[MMU_PAGE_COUNT][MMU_PAGE_COUNT] __ro_after_init;
+
+/*
+ * Due to the involved complexity, and that the current hypervisor is only
+ * returning this value or 0, we are limiting the support of the H_BLOCK_REMOVE
+ * buffer size to 8 size block.
+ */
+#define HBLKRM_SUPPORTED_BLOCK_SIZE 8
+
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 static u8 dtl_mask = DTL_LOG_PREEMPT;
 #else
@@ -984,6 +1000,17 @@ static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn,
 #define HBLKR_CTRL_ERRNOTFOUND	0x8800000000000000UL
 #define HBLKR_CTRL_ERRBUSY	0xa000000000000000UL
 
+/*
+ * Returned true if we are supporting this block size for the specified segment
+ * base page size and actual page size.
+ *
+ * Currently, we only support 8 size block.
+ */
+static inline bool is_supported_hlbkrm(int bpsize, int psize)
+{
+	return (hblkrm_size[bpsize][psize] == HBLKRM_SUPPORTED_BLOCK_SIZE);
+}
+
 /**
  * H_BLOCK_REMOVE caller.
  * @idx should point to the latest @param entry set with a PTEX.
@@ -1143,7 +1170,8 @@ static inline void __pSeries_lpar_hugepage_invalidate(unsigned long *slot,
 	if (lock_tlbie)
 		spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags);
 
-	if (firmware_has_feature(FW_FEATURE_BLOCK_REMOVE))
+	/* Assuming THP size is 16M */
+	if (is_supported_hlbkrm(psize, MMU_PAGE_16M))
 		hugepage_block_invalidate(slot, vpn, count, psize, ssize);
 	else
 		hugepage_bulk_invalidate(slot, vpn, count, psize, ssize);
@@ -1312,6 +1340,137 @@ static void do_block_remove(unsigned long number, struct ppc64_tlb_batch *batch,
 }
 
 /*
+ * TLB Block Invalidate Characteristics
+ *
+ * These characteristics define the size of the block the hcall H_BLOCK_REMOVE
+ * is able to process for each couple segment base page size, actual page size.
+ *
+ * The ibm,get-system-parameter properties is returning a buffer with the
+ * following layout:
+ *
+ * [ 2 bytes size of the RTAS buffer (excluding these 2 bytes) ]
+ * -----------------
+ * TLB Block Invalidate Specifiers:
+ * [ 1 byte LOG base 2 of the TLB invalidate block size being specified ]
+ * [ 1 byte Number of page sizes (N) that are supported for the specified
+ *          TLB invalidate block size ]
+ * [ 1 byte Encoded segment base page size and actual page size
+ *          MSB=0 means 4k segment base page size and actual page size
+ *          MSB=1 the penc value in mmu_psize_def ]
+ * ...
+ * -----------------
+ * Next TLB Block Invalidate Specifiers...
+ * -----------------
+ * [ 0 ]
+ */
+static inline void set_hblkrm_bloc_size(int bpsize, int psize,
+					unsigned int block_size)
+{
+	if (block_size > hblkrm_size[bpsize][psize])
+		hblkrm_size[bpsize][psize] = block_size;
+}
+
+/*
+ * Decode the Encoded segment base page size and actual page size.
+ * PAPR specifies:
+ *   - bit 7 is the L bit
+ *   - bits 0-5 are the penc value
+ * If the L bit is 0, this means 4K segment base page size and actual page size
+ * otherwise the penc value should be read.
+ */
+#define HBLKRM_L_MASK		0x80
+#define HBLKRM_PENC_MASK	0x3f
+static inline void __init check_lp_set_hblkrm(unsigned int lp,
+					      unsigned int block_size)
+{
+	unsigned int bpsize, psize;
+
+	/* First, check the L bit, if not set, this means 4K */
+	if ((lp & HBLKRM_L_MASK) == 0) {
+		set_hblkrm_bloc_size(MMU_PAGE_4K, MMU_PAGE_4K, block_size);
+		return;
+	}
+
+	lp &= HBLKRM_PENC_MASK;
+	for (bpsize = 0; bpsize < MMU_PAGE_COUNT; bpsize++) {
+		struct mmu_psize_def *def = &mmu_psize_defs[bpsize];
+
+		for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
+			if (def->penc[psize] == lp) {
+				set_hblkrm_bloc_size(bpsize, psize, block_size);
+				return;
+			}
+		}
+	}
+}
+
+#define SPLPAR_TLB_BIC_TOKEN		50
+
+/*
+ * The size of the TLB Block Invalidate Characteristics is variable. But at the
+ * maximum it will be the number of possible page sizes *2 + 10 bytes.
+ * Currently MMU_PAGE_COUNT is 16, which means 42 bytes. Use a cache line size
+ * (128 bytes) for the buffer to get plenty of space.
+ */
+#define SPLPAR_TLB_BIC_MAXLENGTH	128
+
+void __init pseries_lpar_read_hblkrm_characteristics(void)
+{
+	unsigned char local_buffer[SPLPAR_TLB_BIC_MAXLENGTH];
+	int call_status, len, idx, bpsize;
+
+	spin_lock(&rtas_data_buf_lock);
+	memset(rtas_data_buf, 0, RTAS_DATA_BUF_SIZE);
+	call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1,
+				NULL,
+				SPLPAR_TLB_BIC_TOKEN,
+				__pa(rtas_data_buf),
+				RTAS_DATA_BUF_SIZE);
+	memcpy(local_buffer, rtas_data_buf, SPLPAR_TLB_BIC_MAXLENGTH);
+	local_buffer[SPLPAR_TLB_BIC_MAXLENGTH - 1] = '\0';
+	spin_unlock(&rtas_data_buf_lock);
+
+	if (call_status != 0) {
+		pr_warn("%s %s Error calling get-system-parameter (0x%x)\n",
+			__FILE__, __func__, call_status);
+		return;
+	}
+
+	/*
+	 * The first two (2) bytes of the data in the buffer are the length of
+	 * the returned data, not counting these first two (2) bytes.
+	 */
+	len = be16_to_cpu(*((u16 *)local_buffer)) + 2;
+	if (len > SPLPAR_TLB_BIC_MAXLENGTH) {
+		pr_warn("%s too large returned buffer %d", __func__, len);
+		return;
+	}
+
+	idx = 2;
+	while (idx < len) {
+		u8 block_shift = local_buffer[idx++];
+		u32 block_size;
+		unsigned int npsize;
+
+		if (!block_shift)
+			break;
+
+		block_size = 1 << block_shift;
+
+		for (npsize = local_buffer[idx++];
+		     npsize > 0 && idx < len; npsize--)
+			check_lp_set_hblkrm((unsigned int) local_buffer[idx++],
+					    block_size);
+	}
+
+	for (bpsize = 0; bpsize < MMU_PAGE_COUNT; bpsize++)
+		for (idx = 0; idx < MMU_PAGE_COUNT; idx++)
+			if (hblkrm_size[bpsize][idx])
+				pr_info("H_BLOCK_REMOVE supports base psize:%d psize:%d block size:%d",
+					bpsize, idx, hblkrm_size[bpsize][idx]);
+}
+
+/*
  * Take a spinlock around flushes to avoid bouncing the hypervisor tlbie
  * lock.
  */
@@ -1330,7 +1489,7 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local)
 	if (lock_tlbie)
 		spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags);
 
-	if (firmware_has_feature(FW_FEATURE_BLOCK_REMOVE)) {
+	if (is_supported_hlbkrm(batch->psize, batch->psize)) {
 		do_block_remove(number, batch, param);
 		goto out;
 	}
diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
index a5ac371a3f06..61883291defc 100644
--- a/arch/powerpc/platforms/pseries/papr_scm.c
+++ b/arch/powerpc/platforms/pseries/papr_scm.c
@@ -65,29 +65,21 @@ static int drc_pmem_bind(struct papr_scm_priv *p)
 		cond_resched();
 	} while (rc == H_BUSY);
 
-	if (rc) {
-		/* H_OVERLAP needs a separate error path */
-		if (rc == H_OVERLAP)
-			return -EBUSY;
-
-		dev_err(&p->pdev->dev, "bind err: %lld\n", rc);
-		return -ENXIO;
-	}
+	if (rc)
+		return rc;
 
 	p->bound_addr = saved;
-
-	dev_dbg(&p->pdev->dev, "bound drc %x to %pR\n", p->drc_index, &p->res);
-
-	return 0;
+	dev_dbg(&p->pdev->dev, "bound drc 0x%x to %pR\n", p->drc_index, &p->res);
+	return rc;
 }
 
-static int drc_pmem_unbind(struct papr_scm_priv *p)
+static void drc_pmem_unbind(struct papr_scm_priv *p)
 {
 	unsigned long ret[PLPAR_HCALL_BUFSIZE];
 	uint64_t token = 0;
 	int64_t rc;
 
-	dev_dbg(&p->pdev->dev, "unbind drc %x\n", p->drc_index);
+	dev_dbg(&p->pdev->dev, "unbind drc 0x%x\n", p->drc_index);
 
 	/* NB: unbind has the same retry requirements as drc_pmem_bind() */
 	do {
@@ -110,12 +102,48 @@ static int drc_pmem_unbind(struct papr_scm_priv *p)
 	if (rc)
 		dev_err(&p->pdev->dev, "unbind error: %lld\n", rc);
 	else
-		dev_dbg(&p->pdev->dev, "unbind drc %x complete\n",
+		dev_dbg(&p->pdev->dev, "unbind drc 0x%x complete\n",
 			p->drc_index);
 
-	return rc == H_SUCCESS ? 0 : -ENXIO;
+	return;
 }
 
+static int drc_pmem_query_n_bind(struct papr_scm_priv *p)
+{
+	unsigned long start_addr;
+	unsigned long end_addr;
+	unsigned long ret[PLPAR_HCALL_BUFSIZE];
+	int64_t rc;
+
+
+	rc = plpar_hcall(H_SCM_QUERY_BLOCK_MEM_BINDING, ret,
+			 p->drc_index, 0);
+	if (rc)
+		goto err_out;
+	start_addr = ret[0];
+
+	/* Make sure the full region is bound. */
+	rc = plpar_hcall(H_SCM_QUERY_BLOCK_MEM_BINDING, ret,
+			 p->drc_index, p->blocks - 1);
+	if (rc)
+		goto err_out;
+	end_addr = ret[0];
+
+	if ((end_addr - start_addr) != ((p->blocks - 1) * p->block_size))
+		goto err_out;
+
+	p->bound_addr = start_addr;
+	dev_dbg(&p->pdev->dev, "bound drc 0x%x to %pR\n", p->drc_index, &p->res);
+	return rc;
+
+err_out:
+	dev_info(&p->pdev->dev,
+		 "Failed to query, trying an unbind followed by bind");
+	drc_pmem_unbind(p);
+	return drc_pmem_bind(p);
+}
+
+
 static int papr_scm_meta_get(struct papr_scm_priv *p,
 			     struct nd_cmd_get_config_data_hdr *hdr)
 {
@@ -436,14 +464,14 @@ static int papr_scm_probe(struct platform_device *pdev)
 	rc = drc_pmem_bind(p);
 
 	/* If phyp says drc memory still bound then force unbound and retry */
-	if (rc == -EBUSY) {
-		dev_warn(&pdev->dev, "Retrying bind after unbinding\n");
-		drc_pmem_unbind(p);
-		rc = drc_pmem_bind(p);
-	}
+	if (rc == H_OVERLAP)
+		rc = drc_pmem_query_n_bind(p);
 
-	if (rc)
+	if (rc != H_SUCCESS) {
+		dev_err(&p->pdev->dev, "bind err: %d\n", rc);
+		rc = -ENXIO;
 		goto err;
+	}
 
 	/* setup the resource for the newly bound range */
 	p->res.start = p->bound_addr;
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index a6624d4bd9d0..13fa370a87e4 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -112,5 +112,6 @@ static inline unsigned long cmo_get_page_size(void)
 int dlpar_workqueue_init(void);
 
 void pseries_setup_rfi_flush(void);
+void pseries_lpar_read_hblkrm_characteristics(void);
 
 #endif /* _PSERIES_PSERIES_H */
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index f8adcd0e4589..0a40201f315f 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -744,6 +744,7 @@ static void __init pSeries_setup_arch(void)
 
 	pseries_setup_rfi_flush();
 	setup_stf_barrier();
+	pseries_lpar_read_hblkrm_characteristics();
 
 	/* By default, only probe PCI (can be overridden by rtas_pci) */
 	pci_add_flags(PCI_PROBE_ONLY);