Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc-next

Pull sparc updates from David Miller:

 1) Add support for ADI (Application Data Integrity) found in more
    recent sparc64 cpus. Essentially this is keyed based access to
    virtual memory, and if the key encoded in the virual address is
    wrong you get a trap.

    The mm changes were reviewed by Andrew Morton and others.

    Work by Khalid Aziz.

 2) Validate DAX completion index range properly, from Rob Gardner.

 3) Add proper Kconfig deps for DAX driver. From Guenter Roeck.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc-next:
  sparc64: Make atomic_xchg() an inline function rather than a macro.
  sparc64: Properly range check DAX completion index
  sparc: Make auxiliary vectors for ADI available on 32-bit as well
  sparc64: Oracle DAX driver depends on SPARC64
  sparc64: Update signal delivery to use new helper functions
  sparc64: Add support for ADI (Application Data Integrity)
  mm: Allow arch code to override copy_highpage()
  mm: Clear arch specific VM flags on protection change
  mm: Add address parameter to arch_validate_prot()
  sparc64: Add auxiliary vectors to report platform ADI properties
  sparc64: Add handler for "Memory Corruption Detected" trap
  sparc64: Add HV fault type handlers for ADI related faults
  sparc64: Add support for ADI register fields, ASIs and traps
  mm, swap: Add infrastructure for saving page metadata on swap
  signals, sparc: Add signal codes for ADI violations

14 files changed, 643 insertions, 14 deletions

diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index cc97545737f0..76cb57750dda 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -69,6 +69,7 @@ obj-$(CONFIG_SPARC64)   += visemul.o
 obj-$(CONFIG_SPARC64)   += hvapi.o
 obj-$(CONFIG_SPARC64)   += sstate.o
 obj-$(CONFIG_SPARC64)   += mdesc.o
+obj-$(CONFIG_SPARC64)   += adi_64.o
 obj-$(CONFIG_SPARC64)	+= pcr.o
 obj-$(CONFIG_SPARC64)	+= nmi.o
 obj-$(CONFIG_SPARC64_SMP) += cpumap.o
diff --git a/arch/sparc/kernel/adi_64.c b/arch/sparc/kernel/adi_64.c
new file mode 100644
index 000000000000..d0a2ac975b42
--- /dev/null
+++ b/arch/sparc/kernel/adi_64.c
@@ -0,0 +1,397 @@
+/* adi_64.c: support for ADI (Application Data Integrity) feature on
+ * sparc m7 and newer processors. This feature is also known as
+ * SSM (Silicon Secured Memory).
+ *
+ * Copyright (C) 2016 Oracle and/or its affiliates. All rights reserved.
+ * Author: Khalid Aziz (khalid.aziz@oracle.com)
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/mm_types.h>
+#include <asm/mdesc.h>
+#include <asm/adi_64.h>
+#include <asm/mmu_64.h>
+#include <asm/pgtable_64.h>
+
+/* Each page of storage for ADI tags can accommodate tags for 128
+ * pages. When ADI enabled pages are being swapped out, it would be
+ * prudent to allocate at least enough tag storage space to accommodate
+ * SWAPFILE_CLUSTER number of pages. Allocate enough tag storage to
+ * store tags for four SWAPFILE_CLUSTER pages to reduce need for
+ * further allocations for same vma.
+ */
+#define TAG_STORAGE_PAGES	8
+
+struct adi_config adi_state;
+EXPORT_SYMBOL(adi_state);
+
+/* mdesc_adi_init() : Parse machine description provided by the
+ *	hypervisor to detect ADI capabilities
+ *
+ * Hypervisor reports ADI capabilities of platform in "hwcap-list" property
+ * for "cpu" node. If the platform supports ADI, "hwcap-list" property
+ * contains the keyword "adp". If the platform supports ADI, "platform"
+ * node will contain "adp-blksz", "adp-nbits" and "ue-on-adp" properties
+ * to describe the ADI capabilities.
+ */
+void __init mdesc_adi_init(void)
+{
+	struct mdesc_handle *hp = mdesc_grab();
+	const char *prop;
+	u64 pn, *val;
+	int len;
+
+	if (!hp)
+		goto adi_not_found;
+
+	pn = mdesc_node_by_name(hp, MDESC_NODE_NULL, "cpu");
+	if (pn == MDESC_NODE_NULL)
+		goto adi_not_found;
+
+	prop = mdesc_get_property(hp, pn, "hwcap-list", &len);
+	if (!prop)
+		goto adi_not_found;
+
+	/*
+	 * Look for "adp" keyword in hwcap-list which would indicate
+	 * ADI support
+	 */
+	adi_state.enabled = false;
+	while (len) {
+		int plen;
+
+		if (!strcmp(prop, "adp")) {
+			adi_state.enabled = true;
+			break;
+		}
+
+		plen = strlen(prop) + 1;
+		prop += plen;
+		len -= plen;
+	}
+
+	if (!adi_state.enabled)
+		goto adi_not_found;
+
+	/* Find the ADI properties in "platform" node. If all ADI
+	 * properties are not found, ADI support is incomplete and
+	 * do not enable ADI in the kernel.
+	 */
+	pn = mdesc_node_by_name(hp, MDESC_NODE_NULL, "platform");
+	if (pn == MDESC_NODE_NULL)
+		goto adi_not_found;
+
+	val = (u64 *) mdesc_get_property(hp, pn, "adp-blksz", &len);
+	if (!val)
+		goto adi_not_found;
+	adi_state.caps.blksz = *val;
+
+	val = (u64 *) mdesc_get_property(hp, pn, "adp-nbits", &len);
+	if (!val)
+		goto adi_not_found;
+	adi_state.caps.nbits = *val;
+
+	val = (u64 *) mdesc_get_property(hp, pn, "ue-on-adp", &len);
+	if (!val)
+		goto adi_not_found;
+	adi_state.caps.ue_on_adi = *val;
+
+	/* Some of the code to support swapping ADI tags is written
+	 * assumption that two ADI tags can fit inside one byte. If
+	 * this assumption is broken by a future architecture change,
+	 * that code will have to be revisited. If that were to happen,
+	 * disable ADI support so we do not get unpredictable results
+	 * with programs trying to use ADI and their pages getting
+	 * swapped out
+	 */
+	if (adi_state.caps.nbits > 4) {
+		pr_warn("WARNING: ADI tag size >4 on this platform. Disabling AADI support\n");
+		adi_state.enabled = false;
+	}
+
+	mdesc_release(hp);
+	return;
+
+adi_not_found:
+	adi_state.enabled = false;
+	adi_state.caps.blksz = 0;
+	adi_state.caps.nbits = 0;
+	if (hp)
+		mdesc_release(hp);
+}
+
+tag_storage_desc_t *find_tag_store(struct mm_struct *mm,
+				   struct vm_area_struct *vma,
+				   unsigned long addr)
+{
+	tag_storage_desc_t *tag_desc = NULL;
+	unsigned long i, max_desc, flags;
+
+	/* Check if this vma already has tag storage descriptor
+	 * allocated for it.
+	 */
+	max_desc = PAGE_SIZE/sizeof(tag_storage_desc_t);
+	if (mm->context.tag_store) {
+		tag_desc = mm->context.tag_store;
+		spin_lock_irqsave(&mm->context.tag_lock, flags);
+		for (i = 0; i < max_desc; i++) {
+			if ((addr >= tag_desc->start) &&
+			    ((addr + PAGE_SIZE - 1) <= tag_desc->end))
+				break;
+			tag_desc++;
+		}
+		spin_unlock_irqrestore(&mm->context.tag_lock, flags);
+
+		/* If no matching entries were found, this must be a
+		 * freshly allocated page
+		 */
+		if (i >= max_desc)
+			tag_desc = NULL;
+	}
+
+	return tag_desc;
+}
+
+tag_storage_desc_t *alloc_tag_store(struct mm_struct *mm,
+				    struct vm_area_struct *vma,
+				    unsigned long addr)
+{
+	unsigned char *tags;
+	unsigned long i, size, max_desc, flags;
+	tag_storage_desc_t *tag_desc, *open_desc;
+	unsigned long end_addr, hole_start, hole_end;
+
+	max_desc = PAGE_SIZE/sizeof(tag_storage_desc_t);
+	open_desc = NULL;
+	hole_start = 0;
+	hole_end = ULONG_MAX;
+	end_addr = addr + PAGE_SIZE - 1;
+
+	/* Check if this vma already has tag storage descriptor
+	 * allocated for it.
+	 */
+	spin_lock_irqsave(&mm->context.tag_lock, flags);
+	if (mm->context.tag_store) {
+		tag_desc = mm->context.tag_store;
+
+		/* Look for a matching entry for this address. While doing
+		 * that, look for the first open slot as well and find
+		 * the hole in already allocated range where this request
+		 * will fit in.
+		 */
+		for (i = 0; i < max_desc; i++) {
+			if (tag_desc->tag_users == 0) {
+				if (open_desc == NULL)
+					open_desc = tag_desc;
+			} else {
+				if ((addr >= tag_desc->start) &&
+				    (tag_desc->end >= (addr + PAGE_SIZE - 1))) {
+					tag_desc->tag_users++;
+					goto out;
+				}
+			}
+			if ((tag_desc->start > end_addr) &&
+			    (tag_desc->start < hole_end))
+				hole_end = tag_desc->start;
+			if ((tag_desc->end < addr) &&
+			    (tag_desc->end > hole_start))
+				hole_start = tag_desc->end;
+			tag_desc++;
+		}
+
+	} else {
+		size = sizeof(tag_storage_desc_t)*max_desc;
+		mm->context.tag_store = kzalloc(size, GFP_NOWAIT|__GFP_NOWARN);
+		if (mm->context.tag_store == NULL) {
+			tag_desc = NULL;
+			goto out;
+		}
+		tag_desc = mm->context.tag_store;
+		for (i = 0; i < max_desc; i++, tag_desc++)
+			tag_desc->tag_users = 0;
+		open_desc = mm->context.tag_store;
+		i = 0;
+	}
+
+	/* Check if we ran out of tag storage descriptors */
+	if (open_desc == NULL) {
+		tag_desc = NULL;
+		goto out;
+	}
+
+	/* Mark this tag descriptor slot in use and then initialize it */
+	tag_desc = open_desc;
+	tag_desc->tag_users = 1;
+
+	/* Tag storage has not been allocated for this vma and space
+	 * is available in tag storage descriptor. Since this page is
+	 * being swapped out, there is high probability subsequent pages
+	 * in the VMA will be swapped out as well. Allocate pages to
+	 * store tags for as many pages in this vma as possible but not
+	 * more than TAG_STORAGE_PAGES. Each byte in tag space holds
+	 * two ADI tags since each ADI tag is 4 bits. Each ADI tag
+	 * covers adi_blksize() worth of addresses. Check if the hole is
+	 * big enough to accommodate full address range for using
+	 * TAG_STORAGE_PAGES number of tag pages.
+	 */
+	size = TAG_STORAGE_PAGES * PAGE_SIZE;
+	end_addr = addr + (size*2*adi_blksize()) - 1;
+	/* Check for overflow. If overflow occurs, allocate only one page */
+	if (end_addr < addr) {
+		size = PAGE_SIZE;
+		end_addr = addr + (size*2*adi_blksize()) - 1;
+		/* If overflow happens with the minimum tag storage
+		 * allocation as well, adjust ending address for this
+		 * tag storage.
+		 */
+		if (end_addr < addr)
+			end_addr = ULONG_MAX;
+	}
+	if (hole_end < end_addr) {
+		/* Available hole is too small on the upper end of
+		 * address. Can we expand the range towards the lower
+		 * address and maximize use of this slot?
+		 */
+		unsigned long tmp_addr;
+
+		end_addr = hole_end - 1;
+		tmp_addr = end_addr - (size*2*adi_blksize()) + 1;
+		/* Check for underflow. If underflow occurs, allocate
+		 * only one page for storing ADI tags
+		 */
+		if (tmp_addr > addr) {
+			size = PAGE_SIZE;
+			tmp_addr = end_addr - (size*2*adi_blksize()) - 1;
+			/* If underflow happens with the minimum tag storage
+			 * allocation as well, adjust starting address for
+			 * this tag storage.
+			 */
+			if (tmp_addr > addr)
+				tmp_addr = 0;
+		}
+		if (tmp_addr < hole_start) {
+			/* Available hole is restricted on lower address
+			 * end as well
+			 */
+			tmp_addr = hole_start + 1;
+		}
+		addr = tmp_addr;
+		size = (end_addr + 1 - addr)/(2*adi_blksize());
+		size = (size + (PAGE_SIZE-adi_blksize()))/PAGE_SIZE;
+		size = size * PAGE_SIZE;
+	}
+	tags = kzalloc(size, GFP_NOWAIT|__GFP_NOWARN);
+	if (tags == NULL) {
+		tag_desc->tag_users = 0;
+		tag_desc = NULL;
+		goto out;
+	}
+	tag_desc->start = addr;
+	tag_desc->tags = tags;
+	tag_desc->end = end_addr;
+
+out:
+	spin_unlock_irqrestore(&mm->context.tag_lock, flags);
+	return tag_desc;
+}
+
+void del_tag_store(tag_storage_desc_t *tag_desc, struct mm_struct *mm)
+{
+	unsigned long flags;
+	unsigned char *tags = NULL;
+
+	spin_lock_irqsave(&mm->context.tag_lock, flags);
+	tag_desc->tag_users--;
+	if (tag_desc->tag_users == 0) {
+		tag_desc->start = tag_desc->end = 0;
+		/* Do not free up the tag storage space allocated
+		 * by the first descriptor. This is persistent
+		 * emergency tag storage space for the task.
+		 */
+		if (tag_desc != mm->context.tag_store) {
+			tags = tag_desc->tags;
+			tag_desc->tags = NULL;
+		}
+	}
+	spin_unlock_irqrestore(&mm->context.tag_lock, flags);
+	kfree(tags);
+}
+
+#define tag_start(addr, tag_desc)		\
+	((tag_desc)->tags + ((addr - (tag_desc)->start)/(2*adi_blksize())))
+
+/* Retrieve any saved ADI tags for the page being swapped back in and
+ * restore these tags to the newly allocated physical page.
+ */
+void adi_restore_tags(struct mm_struct *mm, struct vm_area_struct *vma,
+		      unsigned long addr, pte_t pte)
+{
+	unsigned char *tag;
+	tag_storage_desc_t *tag_desc;
+	unsigned long paddr, tmp, version1, version2;
+
+	/* Check if the swapped out page has an ADI version
+	 * saved. If yes, restore version tag to the newly
+	 * allocated page.
+	 */
+	tag_desc = find_tag_store(mm, vma, addr);
+	if (tag_desc == NULL)
+		return;
+
+	tag = tag_start(addr, tag_desc);
+	paddr = pte_val(pte) & _PAGE_PADDR_4V;
+	for (tmp = paddr; tmp < (paddr+PAGE_SIZE); tmp += adi_blksize()) {
+		version1 = (*tag) >> 4;
+		version2 = (*tag) & 0x0f;
+		*tag++ = 0;
+		asm volatile("stxa %0, [%1] %2\n\t"
+			:
+			: "r" (version1), "r" (tmp),
+			  "i" (ASI_MCD_REAL));
+		tmp += adi_blksize();
+		asm volatile("stxa %0, [%1] %2\n\t"
+			:
+			: "r" (version2), "r" (tmp),
+			  "i" (ASI_MCD_REAL));
+	}
+	asm volatile("membar #Sync\n\t");
+
+	/* Check and mark this tag space for release later if
+	 * the swapped in page was the last user of tag space
+	 */
+	del_tag_store(tag_desc, mm);
+}
+
+/* A page is about to be swapped out. Save any ADI tags associated with
+ * this physical page so they can be restored later when the page is swapped
+ * back in.
+ */
+int adi_save_tags(struct mm_struct *mm, struct vm_area_struct *vma,
+		  unsigned long addr, pte_t oldpte)
+{
+	unsigned char *tag;
+	tag_storage_desc_t *tag_desc;
+	unsigned long version1, version2, paddr, tmp;
+
+	tag_desc = alloc_tag_store(mm, vma, addr);
+	if (tag_desc == NULL)
+		return -1;
+
+	tag = tag_start(addr, tag_desc);
+	paddr = pte_val(oldpte) & _PAGE_PADDR_4V;
+	for (tmp = paddr; tmp < (paddr+PAGE_SIZE); tmp += adi_blksize()) {
+		asm volatile("ldxa [%1] %2, %0\n\t"
+				: "=r" (version1)
+				: "r" (tmp), "i" (ASI_MCD_REAL));
+		tmp += adi_blksize();
+		asm volatile("ldxa [%1] %2, %0\n\t"
+				: "=r" (version2)
+				: "r" (tmp), "i" (ASI_MCD_REAL));
+		*tag = (version1 << 4) | version2;
+		tag++;
+	}
+
+	return 0;
+}
diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h
index 7378567b601f..c746c0fd5d6b 100644
--- a/arch/sparc/kernel/entry.h
+++ b/arch/sparc/kernel/entry.h
@@ -160,6 +160,9 @@ void sun4v_resum_overflow(struct pt_regs *regs);
 void sun4v_nonresum_error(struct pt_regs *regs,
 			  unsigned long offset);
 void sun4v_nonresum_overflow(struct pt_regs *regs);
+void sun4v_mem_corrupt_detect_precise(struct pt_regs *regs,
+				      unsigned long addr,
+				      unsigned long context);
 
 extern unsigned long sun4v_err_itlb_vaddr;
 extern unsigned long sun4v_err_itlb_ctx;
diff --git a/arch/sparc/kernel/etrap_64.S b/arch/sparc/kernel/etrap_64.S
index 5c77a2e0e991..08cc41f64725 100644
--- a/arch/sparc/kernel/etrap_64.S
+++ b/arch/sparc/kernel/etrap_64.S
@@ -151,7 +151,32 @@ etrap_save:	save	%g2, -STACK_BIAS, %sp
 		stx	%g6, [%sp + PTREGS_OFF + PT_V9_G6]
 		stx	%g7, [%sp + PTREGS_OFF + PT_V9_G7]
 		or	%l7, %l0, %l7
-		sethi	%hi(TSTATE_TSO | TSTATE_PEF), %l0
+661:		sethi	%hi(TSTATE_TSO | TSTATE_PEF), %l0
+		/* If userspace is using ADI, it could potentially pass
+		 * a pointer with version tag embedded in it. To maintain
+		 * the ADI security, we must enable PSTATE.mcde. Userspace
+		 * would have already set TTE.mcd in an earlier call to
+		 * kernel and set the version tag for the address being
+		 * dereferenced. Setting PSTATE.mcde would ensure any
+		 * access to userspace data through a system call honors
+		 * ADI and does not allow a rogue app to bypass ADI by
+		 * using system calls. Setting PSTATE.mcde only affects
+		 * accesses to virtual addresses that have TTE.mcd set.
+		 * Set PMCDPER to ensure any exceptions caused by ADI
+		 * version tag mismatch are exposed before system call
+		 * returns to userspace. Setting PMCDPER affects only
+		 * writes to virtual addresses that have TTE.mcd set and
+		 * have a version tag set as well.
+		 */
+		.section .sun_m7_1insn_patch, "ax"
+		.word	661b
+		sethi	%hi(TSTATE_TSO | TSTATE_PEF | TSTATE_MCDE), %l0
+		.previous
+661:		nop
+		.section .sun_m7_1insn_patch, "ax"
+		.word	661b
+		.word 0xaf902001	/* wrpr %g0, 1, %pmcdper */
+		.previous
 		or	%l7, %l0, %l7
 		wrpr	%l2, %tnpc
 		wrpr	%l7, (TSTATE_PRIV | TSTATE_IE), %tstate
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index a41e6e16eb36..540bfc98472c 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -897,6 +897,7 @@ sparc64_boot_end:
 #include "syscalls.S"
 #include "helpers.S"
 #include "sun4v_tlb_miss.S"
+#include "sun4v_mcd.S"
 #include "sun4v_ivec.S"
 #include "ktlb.S"
 #include "tsb.S"
diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c
index 418592a09b41..39a2503fa3e1 100644
--- a/arch/sparc/kernel/mdesc.c
+++ b/arch/sparc/kernel/mdesc.c
@@ -22,6 +22,7 @@
 #include <linux/uaccess.h>
 #include <asm/oplib.h>
 #include <asm/smp.h>
+#include <asm/adi.h>
 
 /* Unlike the OBP device tree, the machine description is a full-on
  * DAG.  An arbitrary number of ARCs are possible from one
@@ -1345,5 +1346,6 @@ void __init sun4v_mdesc_init(void)
 
 	cur_mdesc = hp;
 
+	mdesc_adi_init();
 	report_platform_properties();
 }
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 318efd784a0b..454a8af28f13 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -670,6 +670,31 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 	return 0;
 }
 
+/* TIF_MCDPER in thread info flags for current task is updated lazily upon
+ * a context switch. Update this flag in current task's thread flags
+ * before dup so the dup'd task will inherit the current TIF_MCDPER flag.
+ */
+int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
+{
+	if (adi_capable()) {
+		register unsigned long tmp_mcdper;
+
+		__asm__ __volatile__(
+			".word 0x83438000\n\t"	/* rd  %mcdper, %g1 */
+			"mov %%g1, %0\n\t"
+			: "=r" (tmp_mcdper)
+			:
+			: "g1");
+		if (tmp_mcdper)
+			set_thread_flag(TIF_MCDPER);
+		else
+			clear_thread_flag(TIF_MCDPER);
+	}
+
+	*dst = *src;
+	return 0;
+}
+
 typedef struct {
 	union {
 		unsigned int	pr_regs[32];
diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S
index 0b21042ab181..f6528884a2c8 100644
--- a/arch/sparc/kernel/rtrap_64.S
+++ b/arch/sparc/kernel/rtrap_64.S
@@ -25,13 +25,31 @@
 		.align			32
 __handle_preemption:
 		call			SCHEDULE_USER
-		 wrpr			%g0, RTRAP_PSTATE, %pstate
+661:		 wrpr			%g0, RTRAP_PSTATE, %pstate
+		/* If userspace is using ADI, it could potentially pass
+		 * a pointer with version tag embedded in it. To maintain
+		 * the ADI security, we must re-enable PSTATE.mcde before
+		 * we continue execution in the kernel for another thread.
+		 */
+		.section .sun_m7_1insn_patch, "ax"
+		.word	661b
+		 wrpr			%g0, RTRAP_PSTATE|PSTATE_MCDE, %pstate
+		.previous
 		ba,pt			%xcc, __handle_preemption_continue
 		 wrpr			%g0, RTRAP_PSTATE_IRQOFF, %pstate
 
 __handle_user_windows:
 		call			fault_in_user_windows
-		 wrpr			%g0, RTRAP_PSTATE, %pstate
+661:		 wrpr			%g0, RTRAP_PSTATE, %pstate
+		/* If userspace is using ADI, it could potentially pass
+		 * a pointer with version tag embedded in it. To maintain
+		 * the ADI security, we must re-enable PSTATE.mcde before
+		 * we continue execution in the kernel for another thread.
+		 */
+		.section .sun_m7_1insn_patch, "ax"
+		.word	661b
+		 wrpr			%g0, RTRAP_PSTATE|PSTATE_MCDE, %pstate
+		.previous
 		ba,pt			%xcc, __handle_preemption_continue
 		 wrpr			%g0, RTRAP_PSTATE_IRQOFF, %pstate
 
@@ -48,7 +66,16 @@ __handle_signal:
 		add			%sp, PTREGS_OFF, %o0
 		mov			%l0, %o2
 		call			do_notify_resume
-		 wrpr			%g0, RTRAP_PSTATE, %pstate
+661:		 wrpr			%g0, RTRAP_PSTATE, %pstate
+		/* If userspace is using ADI, it could potentially pass
+		 * a pointer with version tag embedded in it. To maintain
+		 * the ADI security, we must re-enable PSTATE.mcde before
+		 * we continue execution in the kernel for another thread.
+		 */
+		.section .sun_m7_1insn_patch, "ax"
+		.word	661b
+		 wrpr			%g0, RTRAP_PSTATE|PSTATE_MCDE, %pstate
+		.previous
 		wrpr			%g0, RTRAP_PSTATE_IRQOFF, %pstate
 
 		/* Signal delivery can modify pt_regs tstate, so we must
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index 34f7a533a74f..7944b3ca216a 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -294,6 +294,8 @@ static void __init sun4v_patch(void)
 	case SUN4V_CHIP_SPARC_M7:
 	case SUN4V_CHIP_SPARC_M8:
 	case SUN4V_CHIP_SPARC_SN:
+		sun4v_patch_1insn_range(&__sun_m7_1insn_patch,
+					&__sun_m7_1insn_patch_end);
 		sun_m7_patch_2insn_range(&__sun_m7_2insn_patch,
 					 &__sun_m7_2insn_patch_end);
 		break;
diff --git a/arch/sparc/kernel/sun4v_mcd.S b/arch/sparc/kernel/sun4v_mcd.S
new file mode 100644
index 000000000000..d6c69ebca110
--- /dev/null
+++ b/arch/sparc/kernel/sun4v_mcd.S
@@ -0,0 +1,18 @@
+/* sun4v_mcd.S: Sun4v memory corruption detected precise exception handler
+ *
+ * Copyright (c) 2015 Oracle and/or its affiliates. All rights reserved.
+ * Authors: Bob Picco <bob.picco@oracle.com>,
+ *          Khalid Aziz <khalid.aziz@oracle.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+	.text
+	.align 32
+
+sun4v_mcd_detect_precise:
+	mov	%l4, %o1
+	mov 	%l5, %o2
+	call	sun4v_mem_corrupt_detect_precise
+	 add	%sp, PTREGS_OFF, %o0
+	ba,a,pt	%xcc, rtrap
+	 nop
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 0a56dc257cb9..462a21abd105 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -362,7 +362,6 @@ void sun4v_data_access_exception(struct pt_regs *regs, unsigned long addr, unsig
 {
 	unsigned short type = (type_ctx >> 16);
 	unsigned short ctx  = (type_ctx & 0xffff);
-	siginfo_t info;
 
 	if (notify_die(DIE_TRAP, "data access exception", regs,
 		       0, 0x8, SIGTRAP) == NOTIFY_STOP)
@@ -397,12 +396,29 @@ void sun4v_data_access_exception(struct pt_regs *regs, unsigned long addr, unsig
 	if (is_no_fault_exception(regs))
 		return;
 
-	info.si_signo = SIGSEGV;
-	info.si_errno = 0;
-	info.si_code = SEGV_MAPERR;
-	info.si_addr = (void __user *) addr;
-	info.si_trapno = 0;
-	force_sig_info(SIGSEGV, &info, current);
+	/* MCD (Memory Corruption Detection) disabled trap (TT=0x19) in HV
+	 * is vectored thorugh data access exception trap with fault type
+	 * set to HV_FAULT_TYPE_MCD_DIS. Check for MCD disabled trap.
+	 * Accessing an address with invalid ASI for the address, for
+	 * example setting an ADI tag on an address with ASI_MCD_PRIMARY
+	 * when TTE.mcd is not set for the VA, is also vectored into
+	 * kerbel by HV as data access exception with fault type set to
+	 * HV_FAULT_TYPE_INV_ASI.
+	 */
+	switch (type) {
+	case HV_FAULT_TYPE_INV_ASI:
+		force_sig_fault(SIGILL, ILL_ILLADR, (void __user *)addr, 0,
+				current);
+		break;
+	case HV_FAULT_TYPE_MCD_DIS:
+		force_sig_fault(SIGSEGV, SEGV_ACCADI, (void __user *)addr, 0,
+				current);
+		break;
+	default:
+		force_sig_fault(SIGSEGV, SEGV_MAPERR, (void __user *)addr, 0,
+				current);
+		break;
+	}
 }
 
 void sun4v_data_access_exception_tl1(struct pt_regs *regs, unsigned long addr, unsigned long type_ctx)
@@ -1847,6 +1863,7 @@ struct sun4v_error_entry {
 #define SUN4V_ERR_ATTRS_ASI		0x00000080
 #define SUN4V_ERR_ATTRS_PRIV_REG	0x00000100
 #define SUN4V_ERR_ATTRS_SPSTATE_MSK	0x00000600
+#define SUN4V_ERR_ATTRS_MCD		0x00000800
 #define SUN4V_ERR_ATTRS_SPSTATE_SHFT	9
 #define SUN4V_ERR_ATTRS_MODE_MSK	0x03000000
 #define SUN4V_ERR_ATTRS_MODE_SHFT	24
@@ -2044,6 +2061,50 @@ static void sun4v_log_error(struct pt_regs *regs, struct sun4v_error_entry *ent,
 	}
 }
 
+/* Handle memory corruption detected error which is vectored in
+ * through resumable error trap.
+ */
+void do_mcd_err(struct pt_regs *regs, struct sun4v_error_entry ent)
+{
+	if (notify_die(DIE_TRAP, "MCD error", regs, 0, 0x34,
+		       SIGSEGV) == NOTIFY_STOP)
+		return;
+
+	if (regs->tstate & TSTATE_PRIV) {
+		/* MCD exception could happen because the task was
+		 * running a system call with MCD enabled and passed a
+		 * non-versioned pointer or pointer with bad version
+		 * tag to the system call. In such cases, hypervisor
+		 * places the address of offending instruction in the
+		 * resumable error report. This is a deferred error,
+		 * so the read/write that caused the trap was potentially
+		 * retired long time back and we may have no choice
+		 * but to send SIGSEGV to the process.
+		 */
+		const struct exception_table_entry *entry;
+
+		entry = search_exception_tables(regs->tpc);
+		if (entry) {
+			/* Looks like a bad syscall parameter */
+#ifdef DEBUG_EXCEPTIONS
+			pr_emerg("Exception: PC<%016lx> faddr<UNKNOWN>\n",
+				 regs->tpc);
+			pr_emerg("EX_TABLE: insn<%016lx> fixup<%016lx>\n",
+				 ent.err_raddr, entry->fixup);
+#endif
+			regs->tpc = entry->fixup;
+			regs->tnpc = regs->tpc + 4;
+			return;
+		}
+	}
+
+	/* Send SIGSEGV to the userspace process with the right signal
+	 * code
+	 */
+	force_sig_fault(SIGSEGV, SEGV_ADIDERR, (void __user *)ent.err_raddr,
+			0, current);
+}
+
 /* We run with %pil set to PIL_NORMAL_MAX and PSTATE_IE enabled in %pstate.
  * Log the event and clear the first word of the entry.
  */
@@ -2081,6 +2142,14 @@ void sun4v_resum_error(struct pt_regs *regs, unsigned long offset)
 		goto out;
 	}
 
+	/* If this is a memory corruption detected error vectored in
+	 * by HV through resumable error trap, call the handler
+	 */
+	if (local_copy.err_attrs & SUN4V_ERR_ATTRS_MCD) {
+		do_mcd_err(regs, local_copy);
+		return;
+	}
+
 	sun4v_log_error(regs, &local_copy, cpu,
 			KERN_ERR "RESUMABLE ERROR",
 			&sun4v_resum_oflow_cnt);
@@ -2656,6 +2725,53 @@ void sun4v_do_mna(struct pt_regs *regs, unsigned long addr, unsigned long type_c
 	force_sig_info(SIGBUS, &info, current);
 }
 
+/* sun4v_mem_corrupt_detect_precise() - Handle precise exception on an ADI
+ * tag mismatch.
+ *
+ * ADI version tag mismatch on a load from memory always results in a
+ * precise exception. Tag mismatch on a store to memory will result in
+ * precise exception if MCDPER or PMCDPER is set to 1.
+ */
+void sun4v_mem_corrupt_detect_precise(struct pt_regs *regs, unsigned long addr,
+				      unsigned long context)
+{
+	if (notify_die(DIE_TRAP, "memory corruption precise exception", regs,
+		       0, 0x8, SIGSEGV) == NOTIFY_STOP)
+		return;
+
+	if (regs->tstate & TSTATE_PRIV) {
+		/* MCD exception could happen because the task was running
+		 * a system call with MCD enabled and passed a non-versioned
+		 * pointer or pointer with bad version tag to  the system
+		 * call.
+		 */
+		const struct exception_table_entry *entry;
+
+		entry = search_exception_tables(regs->tpc);
+		if (entry) {
+			/* Looks like a bad syscall parameter */
+#ifdef DEBUG_EXCEPTIONS
+			pr_emerg("Exception: PC<%016lx> faddr<UNKNOWN>\n",
+				 regs->tpc);
+			pr_emerg("EX_TABLE: insn<%016lx> fixup<%016lx>\n",
+				 regs->tpc, entry->fixup);
+#endif
+			regs->tpc = entry->fixup;
+			regs->tnpc = regs->tpc + 4;
+			return;
+		}
+		pr_emerg("%s: ADDR[%016lx] CTX[%lx], going.\n",
+			 __func__, addr, context);
+		die_if_kernel("MCD precise", regs);
+	}
+
+	if (test_thread_flag(TIF_32BIT)) {
+		regs->tpc &= 0xffffffff;
+		regs->tnpc &= 0xffffffff;
+	}
+	force_sig_fault(SIGSEGV, SEGV_ADIPERR, (void __user *)addr, 0, current);
+}
+
 void do_privop(struct pt_regs *regs)
 {
 	enum ctx_state prev_state = exception_enter();
diff --git a/arch/sparc/kernel/ttable_64.S b/arch/sparc/kernel/ttable_64.S
index 18685fe69b91..86e737e59c7e 100644
--- a/arch/sparc/kernel/ttable_64.S
+++ b/arch/sparc/kernel/ttable_64.S
@@ -26,8 +26,10 @@ tl0_ill:	membar #Sync
 		TRAP_7INSNS(do_illegal_instruction)
 tl0_privop:	TRAP(do_privop)
 tl0_resv012:	BTRAP(0x12) BTRAP(0x13) BTRAP(0x14) BTRAP(0x15) BTRAP(0x16) BTRAP(0x17)
-tl0_resv018:	BTRAP(0x18) BTRAP(0x19) BTRAP(0x1a) BTRAP(0x1b) BTRAP(0x1c) BTRAP(0x1d)
-tl0_resv01e:	BTRAP(0x1e) BTRAP(0x1f)
+tl0_resv018:	BTRAP(0x18) BTRAP(0x19)
+tl0_mcd:	SUN4V_MCD_PRECISE
+tl0_resv01b:	BTRAP(0x1b)
+tl0_resv01c:	BTRAP(0x1c) BTRAP(0x1d)	BTRAP(0x1e) BTRAP(0x1f)
 tl0_fpdis:	TRAP_NOSAVE(do_fpdis)
 tl0_fpieee:	TRAP_SAVEFPU(do_fpieee)
 tl0_fpother:	TRAP_NOSAVE(do_fpother_check_fitos)
diff --git a/arch/sparc/kernel/urtt_fill.S b/arch/sparc/kernel/urtt_fill.S
index 44183aa59168..e4cee7be5cd0 100644
--- a/arch/sparc/kernel/urtt_fill.S
+++ b/arch/sparc/kernel/urtt_fill.S
@@ -50,7 +50,12 @@ user_rtt_fill_fixup_common:
 		SET_GL(0)
 		.previous
 
-		wrpr	%g0, RTRAP_PSTATE, %pstate
+661:		wrpr	%g0, RTRAP_PSTATE, %pstate
+		.section		.sun_m7_1insn_patch, "ax"
+		.word			661b
+		/* Re-enable PSTATE.mcde to maintain ADI security */
+		wrpr	%g0, RTRAP_PSTATE|PSTATE_MCDE, %pstate
+		.previous
 
 		mov	%l1, %g6
 		ldx	[%g6 + TI_TASK], %g4
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index 5a2344574f39..61afd787bd0c 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -145,6 +145,11 @@ SECTIONS
 		*(.pause_3insn_patch)
 		__pause_3insn_patch_end = .;
 	}
+	.sun_m7_1insn_patch : {
+		__sun_m7_1insn_patch = .;
+		*(.sun_m7_1insn_patch)
+		__sun_m7_1insn_patch_end = .;
+	}
 	.sun_m7_2insn_patch : {
 		__sun_m7_2insn_patch = .;
 		*(.sun_m7_2insn_patch)