Merge tag 'please-pull-apei' into x86/ras

APEI is currently implemented so that it depends on x86 hardware.
The primary dependency is that GHES uses the x86 NMI for hardware
error notification and MCE for memory error handling. These patches
remove that dependency.

Other APEI features such as error reporting via external IRQ, error
serialization, or error injection, do not require changes to use them
on non-x86 architectures.

The following patch set eliminates the APEI Kconfig x86 dependency
by making these changes:
- treat NMI notification as GHES architecture - HAVE_ACPI_APEI_NMI
- group and wrap around #ifdef CONFIG_HAVE_ACPI_APEI_NMI code which
  is used only for NMI path
- identify architectural boxes and abstract it accordingly (tlb flush and MCE)
- rework ioremap for both IRQ and NMI context

NMI code is kept in ghes.c file since NMI and IRQ context are tightly coupled.

Note, these patches introduce no functional changes for x86. The NMI notification
feature is hard selected for x86. Architectures that want to use this
feature should also provide NMI code infrastructure.

6 files changed, 127 insertions, 36 deletions

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 7cfcc1b8e101..7a638aa3545b 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -930,7 +930,7 @@ config LOCKDEP
 	bool
 	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
 	select STACKTRACE
-	select FRAME_POINTER if !MIPS && !PPC && !ARM_UNWIND && !S390 && !MICROBLAZE && !ARC
+	select FRAME_POINTER if !MIPS && !PPC && !ARM_UNWIND && !S390 && !MICROBLAZE && !ARC && !SCORE
 	select KALLSYMS
 	select KALLSYMS_ALL
 
@@ -1408,7 +1408,7 @@ config FAULT_INJECTION_STACKTRACE_FILTER
 	depends on FAULT_INJECTION_DEBUG_FS && STACKTRACE_SUPPORT
 	depends on !X86_64
 	select STACKTRACE
-	select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND && !ARC
+	select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND && !ARC && !SCORE
 	help
 	  Provide stacktrace filter for fault-injection capabilities
 
diff --git a/lib/cpumask.c b/lib/cpumask.c
index c101230658eb..b6513a9f2892 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -191,7 +191,7 @@ int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp)
 
 	i %= num_online_cpus();
 
-	if (!cpumask_of_node(numa_node)) {
+	if (numa_node == -1 || !cpumask_of_node(numa_node)) {
 		/* Use all online cpu's for non numa aware system */
 		cpumask_copy(mask, cpu_online_mask);
 	} else {
diff --git a/lib/iovec.c b/lib/iovec.c
index 454baa88bf27..7a7c2da4cddf 100644
--- a/lib/iovec.c
+++ b/lib/iovec.c
@@ -51,3 +51,58 @@ int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len)
 	return 0;
 }
 EXPORT_SYMBOL(memcpy_toiovec);
+
+/*
+ *	Copy kernel to iovec. Returns -EFAULT on error.
+ */
+
+int memcpy_toiovecend(const struct iovec *iov, unsigned char *kdata,
+		      int offset, int len)
+{
+	int copy;
+	for (; len > 0; ++iov) {
+		/* Skip over the finished iovecs */
+		if (unlikely(offset >= iov->iov_len)) {
+			offset -= iov->iov_len;
+			continue;
+		}
+		copy = min_t(unsigned int, iov->iov_len - offset, len);
+		if (copy_to_user(iov->iov_base + offset, kdata, copy))
+			return -EFAULT;
+		offset = 0;
+		kdata += copy;
+		len -= copy;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(memcpy_toiovecend);
+
+/*
+ *	Copy iovec to kernel. Returns -EFAULT on error.
+ */
+
+int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
+			int offset, int len)
+{
+	/* Skip over the finished iovecs */
+	while (offset >= iov->iov_len) {
+		offset -= iov->iov_len;
+		iov++;
+	}
+
+	while (len > 0) {
+		u8 __user *base = iov->iov_base + offset;
+		int copy = min_t(unsigned int, len, iov->iov_len - offset);
+
+		offset = 0;
+		if (copy_from_user(kdata, base, copy))
+			return -EFAULT;
+		len -= copy;
+		kdata += copy;
+		iov++;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(memcpy_fromiovecend);
diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c
index df6839e3ce08..7a85967060a5 100644
--- a/lib/lz4/lz4_decompress.c
+++ b/lib/lz4/lz4_decompress.c
@@ -72,6 +72,8 @@ static int lz4_uncompress(const char *source, char *dest, int osize)
 			len = *ip++;
 			for (; len == 255; length += 255)
 				len = *ip++;
+			if (unlikely(length > (size_t)(length + len)))
+				goto _output_error;
 			length += len;
 		}
 
@@ -106,6 +108,8 @@ static int lz4_uncompress(const char *source, char *dest, int osize)
 		if (length == ML_MASK) {
 			for (; *ip == 255; length += 255)
 				ip++;
+			if (unlikely(length > (size_t)(length + *ip)))
+				goto _output_error;
 			length += *ip++;
 		}
 
@@ -155,7 +159,7 @@ static int lz4_uncompress(const char *source, char *dest, int osize)
 
 	/* write overflow error detected */
 _output_error:
-	return (int) (-(((char *)ip) - source));
+	return -1;
 }
 
 static int lz4_uncompress_unknownoutputsize(const char *source, char *dest,
@@ -188,6 +192,8 @@ static int lz4_uncompress_unknownoutputsize(const char *source, char *dest,
 			int s = 255;
 			while ((ip < iend) && (s == 255)) {
 				s = *ip++;
+				if (unlikely(length > (size_t)(length + s)))
+					goto _output_error;
 				length += s;
 			}
 		}
@@ -228,6 +234,8 @@ static int lz4_uncompress_unknownoutputsize(const char *source, char *dest,
 		if (length == ML_MASK) {
 			while (ip < iend) {
 				int s = *ip++;
+				if (unlikely(length > (size_t)(length + s)))
+					goto _output_error;
 				length += s;
 				if (s == 255)
 					continue;
@@ -280,7 +288,7 @@ static int lz4_uncompress_unknownoutputsize(const char *source, char *dest,
 
 	/* write overflow error detected */
 _output_error:
-	return (int) (-(((char *) ip) - source));
+	return -1;
 }
 
 int lz4_decompress(const unsigned char *src, size_t *src_len,
diff --git a/lib/lzo/lzo1x_decompress_safe.c b/lib/lzo/lzo1x_decompress_safe.c
index 569985d522d5..8563081e8da3 100644
--- a/lib/lzo/lzo1x_decompress_safe.c
+++ b/lib/lzo/lzo1x_decompress_safe.c
@@ -19,11 +19,31 @@
 #include <linux/lzo.h>
 #include "lzodefs.h"
 
-#define HAVE_IP(x)      ((size_t)(ip_end - ip) >= (size_t)(x))
-#define HAVE_OP(x)      ((size_t)(op_end - op) >= (size_t)(x))
-#define NEED_IP(x)      if (!HAVE_IP(x)) goto input_overrun
-#define NEED_OP(x)      if (!HAVE_OP(x)) goto output_overrun
-#define TEST_LB(m_pos)  if ((m_pos) < out) goto lookbehind_overrun
+#define HAVE_IP(t, x)					\
+	(((size_t)(ip_end - ip) >= (size_t)(t + x)) &&	\
+	 (((t + x) >= t) && ((t + x) >= x)))
+
+#define HAVE_OP(t, x)					\
+	(((size_t)(op_end - op) >= (size_t)(t + x)) &&	\
+	 (((t + x) >= t) && ((t + x) >= x)))
+
+#define NEED_IP(t, x)					\
+	do {						\
+		if (!HAVE_IP(t, x))			\
+			goto input_overrun;		\
+	} while (0)
+
+#define NEED_OP(t, x)					\
+	do {						\
+		if (!HAVE_OP(t, x))			\
+			goto output_overrun;		\
+	} while (0)
+
+#define TEST_LB(m_pos)					\
+	do {						\
+		if ((m_pos) < out)			\
+			goto lookbehind_overrun;	\
+	} while (0)
 
 int lzo1x_decompress_safe(const unsigned char *in, size_t in_len,
 			  unsigned char *out, size_t *out_len)
@@ -58,14 +78,14 @@ int lzo1x_decompress_safe(const unsigned char *in, size_t in_len,
 					while (unlikely(*ip == 0)) {
 						t += 255;
 						ip++;
-						NEED_IP(1);
+						NEED_IP(1, 0);
 					}
 					t += 15 + *ip++;
 				}
 				t += 3;
 copy_literal_run:
 #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
-				if (likely(HAVE_IP(t + 15) && HAVE_OP(t + 15))) {
+				if (likely(HAVE_IP(t, 15) && HAVE_OP(t, 15))) {
 					const unsigned char *ie = ip + t;
 					unsigned char *oe = op + t;
 					do {
@@ -81,8 +101,8 @@ copy_literal_run:
 				} else
 #endif
 				{
-					NEED_OP(t);
-					NEED_IP(t + 3);
+					NEED_OP(t, 0);
+					NEED_IP(t, 3);
 					do {
 						*op++ = *ip++;
 					} while (--t > 0);
@@ -95,7 +115,7 @@ copy_literal_run:
 				m_pos -= t >> 2;
 				m_pos -= *ip++ << 2;
 				TEST_LB(m_pos);
-				NEED_OP(2);
+				NEED_OP(2, 0);
 				op[0] = m_pos[0];
 				op[1] = m_pos[1];
 				op += 2;
@@ -119,10 +139,10 @@ copy_literal_run:
 				while (unlikely(*ip == 0)) {
 					t += 255;
 					ip++;
-					NEED_IP(1);
+					NEED_IP(1, 0);
 				}
 				t += 31 + *ip++;
-				NEED_IP(2);
+				NEED_IP(2, 0);
 			}
 			m_pos = op - 1;
 			next = get_unaligned_le16(ip);
@@ -137,10 +157,10 @@ copy_literal_run:
 				while (unlikely(*ip == 0)) {
 					t += 255;
 					ip++;
-					NEED_IP(1);
+					NEED_IP(1, 0);
 				}
 				t += 7 + *ip++;
-				NEED_IP(2);
+				NEED_IP(2, 0);
 			}
 			next = get_unaligned_le16(ip);
 			ip += 2;
@@ -154,7 +174,7 @@ copy_literal_run:
 #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
 		if (op - m_pos >= 8) {
 			unsigned char *oe = op + t;
-			if (likely(HAVE_OP(t + 15))) {
+			if (likely(HAVE_OP(t, 15))) {
 				do {
 					COPY8(op, m_pos);
 					op += 8;
@@ -164,7 +184,7 @@ copy_literal_run:
 					m_pos += 8;
 				} while (op < oe);
 				op = oe;
-				if (HAVE_IP(6)) {
+				if (HAVE_IP(6, 0)) {
 					state = next;
 					COPY4(op, ip);
 					op += next;
@@ -172,7 +192,7 @@ copy_literal_run:
 					continue;
 				}
 			} else {
-				NEED_OP(t);
+				NEED_OP(t, 0);
 				do {
 					*op++ = *m_pos++;
 				} while (op < oe);
@@ -181,7 +201,7 @@ copy_literal_run:
 #endif
 		{
 			unsigned char *oe = op + t;
-			NEED_OP(t);
+			NEED_OP(t, 0);
 			op[0] = m_pos[0];
 			op[1] = m_pos[1];
 			op += 2;
@@ -194,15 +214,15 @@ match_next:
 		state = next;
 		t = next;
 #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
-		if (likely(HAVE_IP(6) && HAVE_OP(4))) {
+		if (likely(HAVE_IP(6, 0) && HAVE_OP(4, 0))) {
 			COPY4(op, ip);
 			op += t;
 			ip += t;
 		} else
 #endif
 		{
-			NEED_IP(t + 3);
-			NEED_OP(t);
+			NEED_IP(t, 3);
+			NEED_OP(t, 0);
 			while (t > 0) {
 				*op++ = *ip++;
 				t--;
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 649d097853a1..4abda074ea45 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -86,6 +86,7 @@ static unsigned int io_tlb_index;
  * We need to save away the original address corresponding to a mapped entry
  * for the sync operations.
  */
+#define INVALID_PHYS_ADDR (~(phys_addr_t)0)
 static phys_addr_t *io_tlb_orig_addr;
 
 /*
@@ -188,12 +189,14 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
 	io_tlb_list = memblock_virt_alloc(
 				PAGE_ALIGN(io_tlb_nslabs * sizeof(int)),
 				PAGE_SIZE);
-	for (i = 0; i < io_tlb_nslabs; i++)
- 		io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
-	io_tlb_index = 0;
 	io_tlb_orig_addr = memblock_virt_alloc(
 				PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)),
 				PAGE_SIZE);
+	for (i = 0; i < io_tlb_nslabs; i++) {
+		io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
+		io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
+	}
+	io_tlb_index = 0;
 
 	if (verbose)
 		swiotlb_print_info();
@@ -313,10 +316,6 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
 	if (!io_tlb_list)
 		goto cleanup3;
 
-	for (i = 0; i < io_tlb_nslabs; i++)
- 		io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
-	io_tlb_index = 0;
-
 	io_tlb_orig_addr = (phys_addr_t *)
 		__get_free_pages(GFP_KERNEL,
 				 get_order(io_tlb_nslabs *
@@ -324,7 +323,11 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
 	if (!io_tlb_orig_addr)
 		goto cleanup4;
 
-	memset(io_tlb_orig_addr, 0, io_tlb_nslabs * sizeof(phys_addr_t));
+	for (i = 0; i < io_tlb_nslabs; i++) {
+		io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
+		io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
+	}
+	io_tlb_index = 0;
 
 	swiotlb_print_info();
 
@@ -556,7 +559,8 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
 	/*
 	 * First, sync the memory before unmapping the entry
 	 */
-	if (orig_addr && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
+	if (orig_addr != INVALID_PHYS_ADDR &&
+	    ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
 		swiotlb_bounce(orig_addr, tlb_addr, size, DMA_FROM_DEVICE);
 
 	/*
@@ -573,8 +577,10 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
 		 * Step 1: return the slots to the free list, merging the
 		 * slots with superceeding slots
 		 */
-		for (i = index + nslots - 1; i >= index; i--)
+		for (i = index + nslots - 1; i >= index; i--) {
 			io_tlb_list[i] = ++count;
+			io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
+		}
 		/*
 		 * Step 2: merge the returned slots with the preceding slots,
 		 * if available (non zero)
@@ -593,6 +599,8 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
 	int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT;
 	phys_addr_t orig_addr = io_tlb_orig_addr[index];
 
+	if (orig_addr == INVALID_PHYS_ADDR)
+		return;
 	orig_addr += (unsigned long)tlb_addr & ((1 << IO_TLB_SHIFT) - 1);
 
 	switch (target) {