sparc64: Add support for ADI (Application Data Integrity)

ADI is a new feature supported on SPARC M7 and newer processors to allow
hardware to catch rogue accesses to memory. ADI is supported for data
fetches only and not instruction fetches. An app can enable ADI on its
data pages, set version tags on them and use versioned addresses to
access the data pages. Upper bits of the address contain the version
tag. On M7 processors, upper four bits (bits 63-60) contain the version
tag. If a rogue app attempts to access ADI enabled data pages, its
access is blocked and processor generates an exception. Please see
Documentation/sparc/adi.txt for further details.

This patch extends mprotect to enable ADI (TSTATE.mcde), enable/disable
MCD (Memory Corruption Detection) on selected memory ranges, enable
TTE.mcd in PTEs, return ADI parameters to userspace and save/restore ADI
version tags on page swap out/in or migration. ADI is not enabled by
default for any task. A task must explicitly enable ADI on a memory
range and set version tag for ADI to be effective for the task.

Signed-off-by: Khalid Aziz <khalid.aziz@oracle.com>
Cc: Khalid Aziz <khalid@gonehiking.org>
Reviewed-by: Anthony Yznaga <anthony.yznaga@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 395 insertions, 5 deletions

diff --git a/arch/sparc/kernel/adi_64.c b/arch/sparc/kernel/adi_64.c
index 8fb72585d9f1..d0a2ac975b42 100644
--- a/arch/sparc/kernel/adi_64.c
+++ b/arch/sparc/kernel/adi_64.c
@@ -8,10 +8,24 @@
  * 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
@@ -84,6 +98,19 @@ void __init mdesc_adi_init(void)
 		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;
 
@@ -94,3 +121,277 @@ adi_not_found:
 	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/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/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/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)