8 files changed, 756 insertions, 20 deletions

diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 4e015c77e48e..283ee94224c6 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -475,6 +475,7 @@ config ACPI_REDUCED_HARDWARE_ONLY
 	  If you are unsure what to do, do not enable this option.
 
 source "drivers/acpi/nfit/Kconfig"
+source "drivers/acpi/hmat/Kconfig"
 
 source "drivers/acpi/apei/Kconfig"
 source "drivers/acpi/dptf/Kconfig"
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index bb857421c2e8..5d361e4e3405 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -80,6 +80,7 @@ obj-$(CONFIG_ACPI_PROCESSOR)	+= processor.o
 obj-$(CONFIG_ACPI)		+= container.o
 obj-$(CONFIG_ACPI_THERMAL)	+= thermal.o
 obj-$(CONFIG_ACPI_NFIT)		+= nfit/
+obj-$(CONFIG_ACPI_HMAT)		+= hmat/
 obj-$(CONFIG_ACPI)		+= acpi_memhotplug.o
 obj-$(CONFIG_ACPI_HOTPLUG_IOAPIC) += ioapic.o
 obj-$(CONFIG_ACPI_BATTERY)	+= battery.o
diff --git a/drivers/acpi/hmat/Kconfig b/drivers/acpi/hmat/Kconfig
new file mode 100644
index 000000000000..95a29964dbea
--- /dev/null
+++ b/drivers/acpi/hmat/Kconfig
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0
+config ACPI_HMAT
+	bool "ACPI Heterogeneous Memory Attribute Table Support"
+	depends on ACPI_NUMA
+	select HMEM_REPORTING
+	help
+	 If set, this option has the kernel parse and report the
+	 platform's ACPI HMAT (Heterogeneous Memory Attributes Table),
+	 register memory initiators with their targets, and export
+	 performance attributes through the node's sysfs device if
+	 provided.
diff --git a/drivers/acpi/hmat/Makefile b/drivers/acpi/hmat/Makefile
new file mode 100644
index 000000000000..e909051d3d00
--- /dev/null
+++ b/drivers/acpi/hmat/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_ACPI_HMAT) := hmat.o
diff --git a/drivers/acpi/hmat/hmat.c b/drivers/acpi/hmat/hmat.c
new file mode 100644
index 000000000000..96b7d39a97c6
--- /dev/null
+++ b/drivers/acpi/hmat/hmat.c
@@ -0,0 +1,666 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2019, Intel Corporation.
+ *
+ * Heterogeneous Memory Attributes Table (HMAT) representation
+ *
+ * This program parses and reports the platform's HMAT tables, and registers
+ * the applicable attributes with the node's interfaces.
+ */
+
+#include <linux/acpi.h>
+#include <linux/bitops.h>
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/list_sort.h>
+#include <linux/node.h>
+#include <linux/sysfs.h>
+
+static __initdata u8 hmat_revision;
+
+static __initdata LIST_HEAD(targets);
+static __initdata LIST_HEAD(initiators);
+static __initdata LIST_HEAD(localities);
+
+/*
+ * The defined enum order is used to prioritize attributes to break ties when
+ * selecting the best performing node.
+ */
+enum locality_types {
+	WRITE_LATENCY,
+	READ_LATENCY,
+	WRITE_BANDWIDTH,
+	READ_BANDWIDTH,
+};
+
+static struct memory_locality *localities_types[4];
+
+struct memory_target {
+	struct list_head node;
+	unsigned int memory_pxm;
+	unsigned int processor_pxm;
+	struct node_hmem_attrs hmem_attrs;
+};
+
+struct memory_initiator {
+	struct list_head node;
+	unsigned int processor_pxm;
+};
+
+struct memory_locality {
+	struct list_head node;
+	struct acpi_hmat_locality *hmat_loc;
+};
+
+static __init struct memory_initiator *find_mem_initiator(unsigned int cpu_pxm)
+{
+	struct memory_initiator *initiator;
+
+	list_for_each_entry(initiator, &initiators, node)
+		if (initiator->processor_pxm == cpu_pxm)
+			return initiator;
+	return NULL;
+}
+
+static __init struct memory_target *find_mem_target(unsigned int mem_pxm)
+{
+	struct memory_target *target;
+
+	list_for_each_entry(target, &targets, node)
+		if (target->memory_pxm == mem_pxm)
+			return target;
+	return NULL;
+}
+
+static __init void alloc_memory_initiator(unsigned int cpu_pxm)
+{
+	struct memory_initiator *initiator;
+
+	if (pxm_to_node(cpu_pxm) == NUMA_NO_NODE)
+		return;
+
+	initiator = find_mem_initiator(cpu_pxm);
+	if (initiator)
+		return;
+
+	initiator = kzalloc(sizeof(*initiator), GFP_KERNEL);
+	if (!initiator)
+		return;
+
+	initiator->processor_pxm = cpu_pxm;
+	list_add_tail(&initiator->node, &initiators);
+}
+
+static __init void alloc_memory_target(unsigned int mem_pxm)
+{
+	struct memory_target *target;
+
+	if (pxm_to_node(mem_pxm) == NUMA_NO_NODE)
+		return;
+
+	target = find_mem_target(mem_pxm);
+	if (target)
+		return;
+
+	target = kzalloc(sizeof(*target), GFP_KERNEL);
+	if (!target)
+		return;
+
+	target->memory_pxm = mem_pxm;
+	target->processor_pxm = PXM_INVAL;
+	list_add_tail(&target->node, &targets);
+}
+
+static __init const char *hmat_data_type(u8 type)
+{
+	switch (type) {
+	case ACPI_HMAT_ACCESS_LATENCY:
+		return "Access Latency";
+	case ACPI_HMAT_READ_LATENCY:
+		return "Read Latency";
+	case ACPI_HMAT_WRITE_LATENCY:
+		return "Write Latency";
+	case ACPI_HMAT_ACCESS_BANDWIDTH:
+		return "Access Bandwidth";
+	case ACPI_HMAT_READ_BANDWIDTH:
+		return "Read Bandwidth";
+	case ACPI_HMAT_WRITE_BANDWIDTH:
+		return "Write Bandwidth";
+	default:
+		return "Reserved";
+	}
+}
+
+static __init const char *hmat_data_type_suffix(u8 type)
+{
+	switch (type) {
+	case ACPI_HMAT_ACCESS_LATENCY:
+	case ACPI_HMAT_READ_LATENCY:
+	case ACPI_HMAT_WRITE_LATENCY:
+		return " nsec";
+	case ACPI_HMAT_ACCESS_BANDWIDTH:
+	case ACPI_HMAT_READ_BANDWIDTH:
+	case ACPI_HMAT_WRITE_BANDWIDTH:
+		return " MB/s";
+	default:
+		return "";
+	}
+}
+
+static __init u32 hmat_normalize(u16 entry, u64 base, u8 type)
+{
+	u32 value;
+
+	/*
+	 * Check for invalid and overflow values
+	 */
+	if (entry == 0xffff || !entry)
+		return 0;
+	else if (base > (UINT_MAX / (entry)))
+		return 0;
+
+	/*
+	 * Divide by the base unit for version 1, convert latency from
+	 * picosenonds to nanoseconds if revision 2.
+	 */
+	value = entry * base;
+	if (hmat_revision == 1) {
+		if (value < 10)
+			return 0;
+		value = DIV_ROUND_UP(value, 10);
+	} else if (hmat_revision == 2) {
+		switch (type) {
+		case ACPI_HMAT_ACCESS_LATENCY:
+		case ACPI_HMAT_READ_LATENCY:
+		case ACPI_HMAT_WRITE_LATENCY:
+			value = DIV_ROUND_UP(value, 1000);
+			break;
+		default:
+			break;
+		}
+	}
+	return value;
+}
+
+static __init void hmat_update_target_access(struct memory_target *target,
+					     u8 type, u32 value)
+{
+	switch (type) {
+	case ACPI_HMAT_ACCESS_LATENCY:
+		target->hmem_attrs.read_latency = value;
+		target->hmem_attrs.write_latency = value;
+		break;
+	case ACPI_HMAT_READ_LATENCY:
+		target->hmem_attrs.read_latency = value;
+		break;
+	case ACPI_HMAT_WRITE_LATENCY:
+		target->hmem_attrs.write_latency = value;
+		break;
+	case ACPI_HMAT_ACCESS_BANDWIDTH:
+		target->hmem_attrs.read_bandwidth = value;
+		target->hmem_attrs.write_bandwidth = value;
+		break;
+	case ACPI_HMAT_READ_BANDWIDTH:
+		target->hmem_attrs.read_bandwidth = value;
+		break;
+	case ACPI_HMAT_WRITE_BANDWIDTH:
+		target->hmem_attrs.write_bandwidth = value;
+		break;
+	default:
+		break;
+	}
+}
+
+static __init void hmat_add_locality(struct acpi_hmat_locality *hmat_loc)
+{
+	struct memory_locality *loc;
+
+	loc = kzalloc(sizeof(*loc), GFP_KERNEL);
+	if (!loc) {
+		pr_notice_once("Failed to allocate HMAT locality\n");
+		return;
+	}
+
+	loc->hmat_loc = hmat_loc;
+	list_add_tail(&loc->node, &localities);
+
+	switch (hmat_loc->data_type) {
+	case ACPI_HMAT_ACCESS_LATENCY:
+		localities_types[READ_LATENCY] = loc;
+		localities_types[WRITE_LATENCY] = loc;
+		break;
+	case ACPI_HMAT_READ_LATENCY:
+		localities_types[READ_LATENCY] = loc;
+		break;
+	case ACPI_HMAT_WRITE_LATENCY:
+		localities_types[WRITE_LATENCY] = loc;
+		break;
+	case ACPI_HMAT_ACCESS_BANDWIDTH:
+		localities_types[READ_BANDWIDTH] = loc;
+		localities_types[WRITE_BANDWIDTH] = loc;
+		break;
+	case ACPI_HMAT_READ_BANDWIDTH:
+		localities_types[READ_BANDWIDTH] = loc;
+		break;
+	case ACPI_HMAT_WRITE_BANDWIDTH:
+		localities_types[WRITE_BANDWIDTH] = loc;
+		break;
+	default:
+		break;
+	}
+}
+
+static __init int hmat_parse_locality(union acpi_subtable_headers *header,
+				      const unsigned long end)
+{
+	struct acpi_hmat_locality *hmat_loc = (void *)header;
+	struct memory_target *target;
+	unsigned int init, targ, total_size, ipds, tpds;
+	u32 *inits, *targs, value;
+	u16 *entries;
+	u8 type, mem_hier;
+
+	if (hmat_loc->header.length < sizeof(*hmat_loc)) {
+		pr_notice("HMAT: Unexpected locality header length: %d\n",
+			 hmat_loc->header.length);
+		return -EINVAL;
+	}
+
+	type = hmat_loc->data_type;
+	mem_hier = hmat_loc->flags & ACPI_HMAT_MEMORY_HIERARCHY;
+	ipds = hmat_loc->number_of_initiator_Pds;
+	tpds = hmat_loc->number_of_target_Pds;
+	total_size = sizeof(*hmat_loc) + sizeof(*entries) * ipds * tpds +
+		     sizeof(*inits) * ipds + sizeof(*targs) * tpds;
+	if (hmat_loc->header.length < total_size) {
+		pr_notice("HMAT: Unexpected locality header length:%d, minimum required:%d\n",
+			 hmat_loc->header.length, total_size);
+		return -EINVAL;
+	}
+
+	pr_info("HMAT: Locality: Flags:%02x Type:%s Initiator Domains:%d Target Domains:%d Base:%lld\n",
+		hmat_loc->flags, hmat_data_type(type), ipds, tpds,
+		hmat_loc->entry_base_unit);
+
+	inits = (u32 *)(hmat_loc + 1);
+	targs = inits + ipds;
+	entries = (u16 *)(targs + tpds);
+	for (init = 0; init < ipds; init++) {
+		alloc_memory_initiator(inits[init]);
+		for (targ = 0; targ < tpds; targ++) {
+			value = hmat_normalize(entries[init * tpds + targ],
+					       hmat_loc->entry_base_unit,
+					       type);
+			pr_info("  Initiator-Target[%d-%d]:%d%s\n",
+				inits[init], targs[targ], value,
+				hmat_data_type_suffix(type));
+
+			if (mem_hier == ACPI_HMAT_MEMORY) {
+				target = find_mem_target(targs[targ]);
+				if (target && target->processor_pxm == inits[init])
+					hmat_update_target_access(target, type, value);
+			}
+		}
+	}
+
+	if (mem_hier == ACPI_HMAT_MEMORY)
+		hmat_add_locality(hmat_loc);
+
+	return 0;
+}
+
+static __init int hmat_parse_cache(union acpi_subtable_headers *header,
+				   const unsigned long end)
+{
+	struct acpi_hmat_cache *cache = (void *)header;
+	struct node_cache_attrs cache_attrs;
+	u32 attrs;
+
+	if (cache->header.length < sizeof(*cache)) {
+		pr_notice("HMAT: Unexpected cache header length: %d\n",
+			 cache->header.length);
+		return -EINVAL;
+	}
+
+	attrs = cache->cache_attributes;
+	pr_info("HMAT: Cache: Domain:%d Size:%llu Attrs:%08x SMBIOS Handles:%d\n",
+		cache->memory_PD, cache->cache_size, attrs,
+		cache->number_of_SMBIOShandles);
+
+	cache_attrs.size = cache->cache_size;
+	cache_attrs.level = (attrs & ACPI_HMAT_CACHE_LEVEL) >> 4;
+	cache_attrs.line_size = (attrs & ACPI_HMAT_CACHE_LINE_SIZE) >> 16;
+
+	switch ((attrs & ACPI_HMAT_CACHE_ASSOCIATIVITY) >> 8) {
+	case ACPI_HMAT_CA_DIRECT_MAPPED:
+		cache_attrs.indexing = NODE_CACHE_DIRECT_MAP;
+		break;
+	case ACPI_HMAT_CA_COMPLEX_CACHE_INDEXING:
+		cache_attrs.indexing = NODE_CACHE_INDEXED;
+		break;
+	case ACPI_HMAT_CA_NONE:
+	default:
+		cache_attrs.indexing = NODE_CACHE_OTHER;
+		break;
+	}
+
+	switch ((attrs & ACPI_HMAT_WRITE_POLICY) >> 12) {
+	case ACPI_HMAT_CP_WB:
+		cache_attrs.write_policy = NODE_CACHE_WRITE_BACK;
+		break;
+	case ACPI_HMAT_CP_WT:
+		cache_attrs.write_policy = NODE_CACHE_WRITE_THROUGH;
+		break;
+	case ACPI_HMAT_CP_NONE:
+	default:
+		cache_attrs.write_policy = NODE_CACHE_WRITE_OTHER;
+		break;
+	}
+
+	node_add_cache(pxm_to_node(cache->memory_PD), &cache_attrs);
+	return 0;
+}
+
+static int __init hmat_parse_proximity_domain(union acpi_subtable_headers *header,
+					      const unsigned long end)
+{
+	struct acpi_hmat_proximity_domain *p = (void *)header;
+	struct memory_target *target = NULL;
+
+	if (p->header.length != sizeof(*p)) {
+		pr_notice("HMAT: Unexpected address range header length: %d\n",
+			 p->header.length);
+		return -EINVAL;
+	}
+
+	if (hmat_revision == 1)
+		pr_info("HMAT: Memory (%#llx length %#llx) Flags:%04x Processor Domain:%d Memory Domain:%d\n",
+			p->reserved3, p->reserved4, p->flags, p->processor_PD,
+			p->memory_PD);
+	else
+		pr_info("HMAT: Memory Flags:%04x Processor Domain:%d Memory Domain:%d\n",
+			p->flags, p->processor_PD, p->memory_PD);
+
+	if (p->flags & ACPI_HMAT_MEMORY_PD_VALID) {
+		target = find_mem_target(p->memory_PD);
+		if (!target) {
+			pr_debug("HMAT: Memory Domain missing from SRAT\n");
+			return -EINVAL;
+		}
+	}
+	if (target && p->flags & ACPI_HMAT_PROCESSOR_PD_VALID) {
+		int p_node = pxm_to_node(p->processor_PD);
+
+		if (p_node == NUMA_NO_NODE) {
+			pr_debug("HMAT: Invalid Processor Domain\n");
+			return -EINVAL;
+		}
+		target->processor_pxm = p_node;
+	}
+
+	return 0;
+}
+
+static int __init hmat_parse_subtable(union acpi_subtable_headers *header,
+				      const unsigned long end)
+{
+	struct acpi_hmat_structure *hdr = (void *)header;
+
+	if (!hdr)
+		return -EINVAL;
+
+	switch (hdr->type) {
+	case ACPI_HMAT_TYPE_PROXIMITY:
+		return hmat_parse_proximity_domain(header, end);
+	case ACPI_HMAT_TYPE_LOCALITY:
+		return hmat_parse_locality(header, end);
+	case ACPI_HMAT_TYPE_CACHE:
+		return hmat_parse_cache(header, end);
+	default:
+		return -EINVAL;
+	}
+}
+
+static __init int srat_parse_mem_affinity(union acpi_subtable_headers *header,
+					  const unsigned long end)
+{
+	struct acpi_srat_mem_affinity *ma = (void *)header;
+
+	if (!ma)
+		return -EINVAL;
+	if (!(ma->flags & ACPI_SRAT_MEM_ENABLED))
+		return 0;
+	alloc_memory_target(ma->proximity_domain);
+	return 0;
+}
+
+static __init u32 hmat_initiator_perf(struct memory_target *target,
+			       struct memory_initiator *initiator,
+			       struct acpi_hmat_locality *hmat_loc)
+{
+	unsigned int ipds, tpds, i, idx = 0, tdx = 0;
+	u32 *inits, *targs;
+	u16 *entries;
+
+	ipds = hmat_loc->number_of_initiator_Pds;
+	tpds = hmat_loc->number_of_target_Pds;
+	inits = (u32 *)(hmat_loc + 1);
+	targs = inits + ipds;
+	entries = (u16 *)(targs + tpds);
+
+	for (i = 0; i < ipds; i++) {
+		if (inits[i] == initiator->processor_pxm) {
+			idx = i;
+			break;
+		}
+	}
+
+	if (i == ipds)
+		return 0;
+
+	for (i = 0; i < tpds; i++) {
+		if (targs[i] == target->memory_pxm) {
+			tdx = i;
+			break;
+		}
+	}
+	if (i == tpds)
+		return 0;
+
+	return hmat_normalize(entries[idx * tpds + tdx],
+			      hmat_loc->entry_base_unit,
+			      hmat_loc->data_type);
+}
+
+static __init bool hmat_update_best(u8 type, u32 value, u32 *best)
+{
+	bool updated = false;
+
+	if (!value)
+		return false;
+
+	switch (type) {
+	case ACPI_HMAT_ACCESS_LATENCY:
+	case ACPI_HMAT_READ_LATENCY:
+	case ACPI_HMAT_WRITE_LATENCY:
+		if (!*best || *best > value) {
+			*best = value;
+			updated = true;
+		}
+		break;
+	case ACPI_HMAT_ACCESS_BANDWIDTH:
+	case ACPI_HMAT_READ_BANDWIDTH:
+	case ACPI_HMAT_WRITE_BANDWIDTH:
+		if (!*best || *best < value) {
+			*best = value;
+			updated = true;
+		}
+		break;
+	}
+
+	return updated;
+}
+
+static int initiator_cmp(void *priv, struct list_head *a, struct list_head *b)
+{
+	struct memory_initiator *ia;
+	struct memory_initiator *ib;
+	unsigned long *p_nodes = priv;
+
+	ia = list_entry(a, struct memory_initiator, node);
+	ib = list_entry(b, struct memory_initiator, node);
+
+	set_bit(ia->processor_pxm, p_nodes);
+	set_bit(ib->processor_pxm, p_nodes);
+
+	return ia->processor_pxm - ib->processor_pxm;
+}
+
+static __init void hmat_register_target_initiators(struct memory_target *target)
+{
+	static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
+	struct memory_initiator *initiator;
+	unsigned int mem_nid, cpu_nid;
+	struct memory_locality *loc = NULL;
+	u32 best = 0;
+	int i;
+
+	mem_nid = pxm_to_node(target->memory_pxm);
+	/*
+	 * If the Address Range Structure provides a local processor pxm, link
+	 * only that one. Otherwise, find the best performance attributes and
+	 * register all initiators that match.
+	 */
+	if (target->processor_pxm != PXM_INVAL) {
+		cpu_nid = pxm_to_node(target->processor_pxm);
+		register_memory_node_under_compute_node(mem_nid, cpu_nid, 0);
+		return;
+	}
+
+	if (list_empty(&localities))
+		return;
+
+	/*
+	 * We need the initiator list sorted so we can use bitmap_clear for
+	 * previously set initiators when we find a better memory accessor.
+	 * We'll also use the sorting to prime the candidate nodes with known
+	 * initiators.
+	 */
+	bitmap_zero(p_nodes, MAX_NUMNODES);
+	list_sort(p_nodes, &initiators, initiator_cmp);
+	for (i = WRITE_LATENCY; i <= READ_BANDWIDTH; i++) {
+		loc = localities_types[i];
+		if (!loc)
+			continue;
+
+		best = 0;
+		list_for_each_entry(initiator, &initiators, node) {
+			u32 value;
+
+			if (!test_bit(initiator->processor_pxm, p_nodes))
+				continue;
+
+			value = hmat_initiator_perf(target, initiator, loc->hmat_loc);
+			if (hmat_update_best(loc->hmat_loc->data_type, value, &best))
+				bitmap_clear(p_nodes, 0, initiator->processor_pxm);
+			if (value != best)
+				clear_bit(initiator->processor_pxm, p_nodes);
+		}
+		if (best)
+			hmat_update_target_access(target, loc->hmat_loc->data_type, best);
+	}
+
+	for_each_set_bit(i, p_nodes, MAX_NUMNODES) {
+		cpu_nid = pxm_to_node(i);
+		register_memory_node_under_compute_node(mem_nid, cpu_nid, 0);
+	}
+}
+
+static __init void hmat_register_target_perf(struct memory_target *target)
+{
+	unsigned mem_nid = pxm_to_node(target->memory_pxm);
+	node_set_perf_attrs(mem_nid, &target->hmem_attrs, 0);
+}
+
+static __init void hmat_register_targets(void)
+{
+	struct memory_target *target;
+
+	list_for_each_entry(target, &targets, node) {
+		hmat_register_target_initiators(target);
+		hmat_register_target_perf(target);
+	}
+}
+
+static __init void hmat_free_structures(void)
+{
+	struct memory_target *target, *tnext;
+	struct memory_locality *loc, *lnext;
+	struct memory_initiator *initiator, *inext;
+
+	list_for_each_entry_safe(target, tnext, &targets, node) {
+		list_del(&target->node);
+		kfree(target);
+	}
+
+	list_for_each_entry_safe(initiator, inext, &initiators, node) {
+		list_del(&initiator->node);
+		kfree(initiator);
+	}
+
+	list_for_each_entry_safe(loc, lnext, &localities, node) {
+		list_del(&loc->node);
+		kfree(loc);
+	}
+}
+
+static __init int hmat_init(void)
+{
+	struct acpi_table_header *tbl;
+	enum acpi_hmat_type i;
+	acpi_status status;
+
+	if (srat_disabled())
+		return 0;
+
+	status = acpi_get_table(ACPI_SIG_SRAT, 0, &tbl);
+	if (ACPI_FAILURE(status))
+		return 0;
+
+	if (acpi_table_parse_entries(ACPI_SIG_SRAT,
+				sizeof(struct acpi_table_srat),
+				ACPI_SRAT_TYPE_MEMORY_AFFINITY,
+				srat_parse_mem_affinity, 0) < 0)
+		goto out_put;
+	acpi_put_table(tbl);
+
+	status = acpi_get_table(ACPI_SIG_HMAT, 0, &tbl);
+	if (ACPI_FAILURE(status))
+		goto out_put;
+
+	hmat_revision = tbl->revision;
+	switch (hmat_revision) {
+	case 1:
+	case 2:
+		break;
+	default:
+		pr_notice("Ignoring HMAT: Unknown revision:%d\n", hmat_revision);
+		goto out_put;
+	}
+
+	for (i = ACPI_HMAT_TYPE_PROXIMITY; i < ACPI_HMAT_TYPE_RESERVED; i++) {
+		if (acpi_table_parse_entries(ACPI_SIG_HMAT,
+					     sizeof(struct acpi_table_hmat), i,
+					     hmat_parse_subtable, 0) < 0) {
+			pr_notice("Ignoring HMAT: Invalid table");
+			goto out_put;
+		}
+	}
+	hmat_register_targets();
+out_put:
+	hmat_free_structures();
+	acpi_put_table(tbl);
+	return 0;
+}
+subsys_initcall(hmat_init);
diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c
index 867f6e3f2b4f..30995834ad70 100644
--- a/drivers/acpi/numa.c
+++ b/drivers/acpi/numa.c
@@ -339,7 +339,7 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
 }
 
 static int __init
-acpi_parse_x2apic_affinity(struct acpi_subtable_header *header,
+acpi_parse_x2apic_affinity(union acpi_subtable_headers *header,
 			   const unsigned long end)
 {
 	struct acpi_srat_x2apic_cpu_affinity *processor_affinity;
@@ -348,7 +348,7 @@ acpi_parse_x2apic_affinity(struct acpi_subtable_header *header,
 	if (!processor_affinity)
 		return -EINVAL;
 
-	acpi_table_print_srat_entry(header);
+	acpi_table_print_srat_entry(&header->common);
 
 	/* let architecture-dependent part to do it */
 	acpi_numa_x2apic_affinity_init(processor_affinity);
@@ -357,7 +357,7 @@ acpi_parse_x2apic_affinity(struct acpi_subtable_header *header,
 }
 
 static int __init
-acpi_parse_processor_affinity(struct acpi_subtable_header *header,
+acpi_parse_processor_affinity(union acpi_subtable_headers *header,
 			      const unsigned long end)
 {
 	struct acpi_srat_cpu_affinity *processor_affinity;
@@ -366,7 +366,7 @@ acpi_parse_processor_affinity(struct acpi_subtable_header *header,
 	if (!processor_affinity)
 		return -EINVAL;
 
-	acpi_table_print_srat_entry(header);
+	acpi_table_print_srat_entry(&header->common);
 
 	/* let architecture-dependent part to do it */
 	acpi_numa_processor_affinity_init(processor_affinity);
@@ -375,7 +375,7 @@ acpi_parse_processor_affinity(struct acpi_subtable_header *header,
 }
 
 static int __init
-acpi_parse_gicc_affinity(struct acpi_subtable_header *header,
+acpi_parse_gicc_affinity(union acpi_subtable_headers *header,
 			 const unsigned long end)
 {
 	struct acpi_srat_gicc_affinity *processor_affinity;
@@ -384,7 +384,7 @@ acpi_parse_gicc_affinity(struct acpi_subtable_header *header,
 	if (!processor_affinity)
 		return -EINVAL;
 
-	acpi_table_print_srat_entry(header);
+	acpi_table_print_srat_entry(&header->common);
 
 	/* let architecture-dependent part to do it */
 	acpi_numa_gicc_affinity_init(processor_affinity);
@@ -395,7 +395,7 @@ acpi_parse_gicc_affinity(struct acpi_subtable_header *header,
 static int __initdata parsed_numa_memblks;
 
 static int __init
-acpi_parse_memory_affinity(struct acpi_subtable_header * header,
+acpi_parse_memory_affinity(union acpi_subtable_headers * header,
 			   const unsigned long end)
 {
 	struct acpi_srat_mem_affinity *memory_affinity;
@@ -404,7 +404,7 @@ acpi_parse_memory_affinity(struct acpi_subtable_header * header,
 	if (!memory_affinity)
 		return -EINVAL;
 
-	acpi_table_print_srat_entry(header);
+	acpi_table_print_srat_entry(&header->common);
 
 	/* let architecture-dependent part to do it */
 	if (!acpi_numa_memory_affinity_init(memory_affinity))
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index b845dc3e0ba9..566270d0e91a 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -2238,10 +2238,10 @@ static struct acpi_probe_entry *ape;
 static int acpi_probe_count;
 static DEFINE_MUTEX(acpi_probe_mutex);
 
-static int __init acpi_match_madt(struct acpi_subtable_header *header,
+static int __init acpi_match_madt(union acpi_subtable_headers *header,
 				  const unsigned long end)
 {
-	if (!ape->subtable_valid || ape->subtable_valid(header, ape))
+	if (!ape->subtable_valid || ape->subtable_valid(&header->common, ape))
 		if (!ape->probe_subtbl(header, end))
 			acpi_probe_count++;
 
diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c
index d7bf936b1646..3b5d04fd5e3e 100644
--- a/drivers/acpi/tables.c
+++ b/drivers/acpi/tables.c
@@ -49,6 +49,16 @@ static struct acpi_table_desc initial_tables[ACPI_MAX_TABLES] __initdata;
 
 static int acpi_apic_instance __initdata;
 
+enum acpi_subtable_type {
+	ACPI_SUBTABLE_COMMON,
+	ACPI_SUBTABLE_HMAT,
+};
+
+struct acpi_subtable_entry {
+	union acpi_subtable_headers *hdr;
+	enum acpi_subtable_type type;
+};
+
 /*
  * Disable table checksum verification for the early stage due to the size
  * limitation of the current x86 early mapping implementation.
@@ -217,6 +227,50 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header)
 	}
 }
 
+static unsigned long __init
+acpi_get_entry_type(struct acpi_subtable_entry *entry)
+{
+	switch (entry->type) {
+	case ACPI_SUBTABLE_COMMON:
+		return entry->hdr->common.type;
+	case ACPI_SUBTABLE_HMAT:
+		return entry->hdr->hmat.type;
+	}
+	return 0;
+}
+
+static unsigned long __init
+acpi_get_entry_length(struct acpi_subtable_entry *entry)
+{
+	switch (entry->type) {
+	case ACPI_SUBTABLE_COMMON:
+		return entry->hdr->common.length;
+	case ACPI_SUBTABLE_HMAT:
+		return entry->hdr->hmat.length;
+	}
+	return 0;
+}
+
+static unsigned long __init
+acpi_get_subtable_header_length(struct acpi_subtable_entry *entry)
+{
+	switch (entry->type) {
+	case ACPI_SUBTABLE_COMMON:
+		return sizeof(entry->hdr->common);
+	case ACPI_SUBTABLE_HMAT:
+		return sizeof(entry->hdr->hmat);
+	}
+	return 0;
+}
+
+static enum acpi_subtable_type __init
+acpi_get_subtable_type(char *id)
+{
+	if (strncmp(id, ACPI_SIG_HMAT, 4) == 0)
+		return ACPI_SUBTABLE_HMAT;
+	return ACPI_SUBTABLE_COMMON;
+}
+
 /**
  * acpi_parse_entries_array - for each proc_num find a suitable subtable
  *
@@ -245,8 +299,8 @@ static int __init acpi_parse_entries_array(char *id, unsigned long table_size,
 		struct acpi_subtable_proc *proc, int proc_num,
 		unsigned int max_entries)
 {
-	struct acpi_subtable_header *entry;
-	unsigned long table_end;
+	struct acpi_subtable_entry entry;
+	unsigned long table_end, subtable_len, entry_len;
 	int count = 0;
 	int errs = 0;
 	int i;
@@ -269,19 +323,20 @@ static int __init acpi_parse_entries_array(char *id, unsigned long table_size,
 
 	/* Parse all entries looking for a match. */
 
-	entry = (struct acpi_subtable_header *)
+	entry.type = acpi_get_subtable_type(id);
+	entry.hdr = (union acpi_subtable_headers *)
 	    ((unsigned long)table_header + table_size);
+	subtable_len = acpi_get_subtable_header_length(&entry);
 
-	while (((unsigned long)entry) + sizeof(struct acpi_subtable_header) <
-	       table_end) {
+	while (((unsigned long)entry.hdr) + subtable_len  < table_end) {
 		if (max_entries && count >= max_entries)
 			break;
 
 		for (i = 0; i < proc_num; i++) {
-			if (entry->type != proc[i].id)
+			if (acpi_get_entry_type(&entry) != proc[i].id)
 				continue;
 			if (!proc[i].handler ||
-			     (!errs && proc[i].handler(entry, table_end))) {
+			     (!errs && proc[i].handler(entry.hdr, table_end))) {
 				errs++;
 				continue;
 			}
@@ -296,13 +351,14 @@ static int __init acpi_parse_entries_array(char *id, unsigned long table_size,
 		 * If entry->length is 0, break from this loop to avoid
 		 * infinite loop.
 		 */
-		if (entry->length == 0) {
+		entry_len = acpi_get_entry_length(&entry);
+		if (entry_len == 0) {
 			pr_err("[%4.4s:0x%02x] Invalid zero length\n", id, proc->id);
 			return -EINVAL;
 		}
 
-		entry = (struct acpi_subtable_header *)
-		    ((unsigned long)entry + entry->length);
+		entry.hdr = (union acpi_subtable_headers *)
+		    ((unsigned long)entry.hdr + entry_len);
 	}
 
 	if (max_entries && count > max_entries) {