Merge branch 'akpm/master'

18 files changed, 312 insertions, 58 deletions

diff --git a/CREDITS b/CREDITS
index 9fbd2c77b546..c375943c6d8e 100644
--- a/CREDITS
+++ b/CREDITS
@@ -4128,6 +4128,13 @@ D: MD driver
 D: EISA/sysfs subsystem
 S: France
 
+N: Marcel Selhorst
+E: tpmdd@selhorst.net
+D: TPM driver
+
+N: Ashley Lai
+E: ashleydlai@gmail.com
+D: IBM VTPM driver
 
 # Don't add your name here, unless you really _are_ after Marc
 # alphabetically. Leonard used to be very proud of being the 
diff --git a/MAINTAINERS b/MAINTAINERS
index 00c3b8ec9862..02441c2e8c55 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13690,23 +13690,14 @@ F:	drivers/platform/x86/toshiba-wmi.c
 
 TPM DEVICE DRIVER
 M:	Peter Huewe <peterhuewe@gmx.de>
-M:	Marcel Selhorst <tpmdd@selhorst.net>
 M:	Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
 R:	Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
-W:	http://tpmdd.sourceforge.net
-L:	tpmdd-devel@lists.sourceforge.net (moderated for non-subscribers)
-Q:	https://patchwork.kernel.org/project/tpmdd-devel/list/
+L:	linux-integrity@vger.kernel.org
+Q:	https://patchwork.kernel.org/project/linux-integrity/list/
 T:	git git://git.infradead.org/users/jjs/linux-tpmdd.git
 S:	Maintained
 F:	drivers/char/tpm/
 
-TPM IBM_VTPM DEVICE DRIVER
-M:	Ashley Lai <ashleydlai@gmail.com>
-W:	http://tpmdd.sourceforge.net
-L:	tpmdd-devel@lists.sourceforge.net (moderated for non-subscribers)
-S:	Maintained
-F:	drivers/char/tpm/tpm_ibmvtpm*
-
 TRACING
 M:	Steven Rostedt <rostedt@goodmis.org>
 M:	Ingo Molnar <mingo@redhat.com>
diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h
index 3ad8f6988363..82f9bf702804 100644
--- a/arch/ia64/include/asm/topology.h
+++ b/arch/ia64/include/asm/topology.h
@@ -34,13 +34,6 @@
 			       &node_to_cpu_mask[node])
 
 /*
- * Returns the number of the node containing Node 'nid'.
- * Not implemented here. Multi-level hierarchies detected with
- * the help of node_distance().
- */
-#define parent_node(nid) (nid)
-
-/*
  * Determines the node for a given pci bus
  */
 #define pcibus_to_node(bus) PCI_CONTROLLER(bus)->node
diff --git a/arch/sh/include/asm/topology.h b/arch/sh/include/asm/topology.h
index 358e3f516ef6..6931f5084abe 100644
--- a/arch/sh/include/asm/topology.h
+++ b/arch/sh/include/asm/topology.h
@@ -4,7 +4,6 @@
 #ifdef CONFIG_NUMA
 
 #define cpu_to_node(cpu)	((void)(cpu),0)
-#define parent_node(node)	((void)(node),0)
 
 #define cpumask_of_node(node)	((void)node, cpu_online_mask)
 
diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h
index ad5293f89680..0fcc9a031492 100644
--- a/arch/sparc/include/asm/topology_64.h
+++ b/arch/sparc/include/asm/topology_64.h
@@ -10,8 +10,6 @@ static inline int cpu_to_node(int cpu)
 	return numa_cpu_lookup_table[cpu];
 }
 
-#define parent_node(node)	(node)
-
 #define cpumask_of_node(node) ((node) == -1 ?				\
 			       cpu_all_mask :				\
 			       &numa_cpumask_lookup_table[node])
diff --git a/arch/sparc/lib/NG4memset.S b/arch/sparc/lib/NG4memset.S
index 7c0c81f18837..c07834f3a6fc 100644
--- a/arch/sparc/lib/NG4memset.S
+++ b/arch/sparc/lib/NG4memset.S
@@ -13,14 +13,14 @@
 	.globl		NG4memset
 NG4memset:
 	andcc		%o1, 0xff, %o4
-	be,pt		%icc, 1f
+	be,pt		%xcc, 1f
 	 mov		%o2, %o1
 	sllx		%o4, 8, %g1
 	or		%g1, %o4, %o2
 	sllx		%o2, 16, %g1
 	or		%g1, %o2, %o2
 	sllx		%o2, 32, %g1
-	ba,pt		%icc, 1f
+	ba,pt		%xcc, 1f
 	 or		%g1, %o2, %o4
 	.size		NG4memset,.-NG4memset
 
@@ -29,7 +29,7 @@ NG4memset:
 NG4bzero:
 	clr		%o4
 1:	cmp		%o1, 16
-	ble		%icc, .Ltiny
+	ble		%xcc, .Ltiny
 	 mov		%o0, %o3
 	sub		%g0, %o0, %g1
 	and		%g1, 0x7, %g1
@@ -37,7 +37,7 @@ NG4bzero:
 	 sub		%o1, %g1, %o1
 1:	stb		%o4, [%o0 + 0x00]
 	subcc		%g1, 1, %g1
-	bne,pt		%icc, 1b
+	bne,pt		%xcc, 1b
 	 add		%o0, 1, %o0
 .Laligned8:
 	cmp		%o1, 64 + (64 - 8)
@@ -48,7 +48,7 @@ NG4bzero:
 	 sub		%o1, %g1, %o1
 1:	stx		%o4, [%o0 + 0x00]
 	subcc		%g1, 8, %g1
-	bne,pt		%icc, 1b
+	bne,pt		%xcc, 1b
 	 add		%o0, 0x8, %o0
 .Laligned64:
 	andn		%o1, 64 - 1, %g1
@@ -58,30 +58,30 @@ NG4bzero:
 1:	stxa		%o4, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P
 	subcc		%g1, 0x40, %g1
 	stxa		%o4, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
-	bne,pt		%icc, 1b
+	bne,pt		%xcc, 1b
 	 add		%o0, 0x40, %o0
 .Lpostloop:
 	cmp		%o1, 8
-	bl,pn		%icc, .Ltiny
+	bl,pn		%xcc, .Ltiny
 	 membar		#StoreStore|#StoreLoad
 .Lmedium:
 	andn		%o1, 0x7, %g1
 	sub		%o1, %g1, %o1
 1:	stx		%o4, [%o0 + 0x00]
 	subcc		%g1, 0x8, %g1
-	bne,pt		%icc, 1b
+	bne,pt		%xcc, 1b
 	 add		%o0, 0x08, %o0
 	andcc		%o1, 0x4, %g1
-	be,pt		%icc, .Ltiny
+	be,pt		%xcc, .Ltiny
 	 sub		%o1, %g1, %o1
 	stw		%o4, [%o0 + 0x00]
 	add		%o0, 0x4, %o0
 .Ltiny:
 	cmp		%o1, 0
-	be,pn		%icc, .Lexit
+	be,pn		%xcc, .Lexit
 1:	 subcc		%o1, 1, %o1
 	stb		%o4, [%o0 + 0x00]
-	bne,pt		%icc, 1b
+	bne,pt		%xcc, 1b
 	 add		%o0, 1, %o0
 .Lexit:
 	retl
@@ -99,8 +99,8 @@ NG4bzero:
 	stxa		%o4, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
 	stxa		%o4, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P
 	stxa		%o4, [%o0 + %o5] ASI_BLK_INIT_QUAD_LDD_P
-	bne,pt		%icc, 1b
+	bne,pt		%xcc, 1b
 	 add		%o0, 0x30, %o0
-	ba,a,pt		%icc, .Lpostloop
+	ba,a,pt		%xcc, .Lpostloop
 	 nop
 	.size		NG4bzero,.-NG4bzero
diff --git a/arch/tile/include/asm/topology.h b/arch/tile/include/asm/topology.h
index b11d5fcd2c41..635a0a4596f0 100644
--- a/arch/tile/include/asm/topology.h
+++ b/arch/tile/include/asm/topology.h
@@ -29,12 +29,6 @@ static inline int cpu_to_node(int cpu)
 	return cpu_2_node[cpu];
 }
 
-/*
- * Returns the number of the node containing Node 'node'.
- * This architecture is flat, so it is a pretty simple function!
- */
-#define parent_node(node) (node)
-
 /* Returns a bitmask of CPUs on Node 'node'. */
 static inline const struct cpumask *cpumask_of_node(int node)
 {
diff --git a/drivers/pcmcia/sa1111_badge4.c b/drivers/pcmcia/sa1111_badge4.c
index 2f490930430d..93a5c7423d80 100644
--- a/drivers/pcmcia/sa1111_badge4.c
+++ b/drivers/pcmcia/sa1111_badge4.c
@@ -144,6 +144,7 @@ int pcmcia_badge4_init(struct sa1111_dev *dev)
 				 sa11xx_drv_pcmcia_add_one);
 }
 
+#ifndef MODULE
 static int __init pcmv_setup(char *s)
 {
 	int v[4];
@@ -158,3 +159,4 @@ static int __init pcmv_setup(char *s)
 }
 
 __setup("pcmv=", pcmv_setup);
+#endif
diff --git a/include/asm-generic/topology.h b/include/asm-generic/topology.h
index 5d2add1a6c96..238873739550 100644
--- a/include/asm-generic/topology.h
+++ b/include/asm-generic/topology.h
@@ -44,9 +44,6 @@
 #define cpu_to_mem(cpu)		((void)(cpu),0)
 #endif
 
-#ifndef parent_node
-#define parent_node(node)	((void)(node),0)
-#endif
 #ifndef cpumask_of_node
   #ifdef CONFIG_NEED_MULTIPLE_NODES
     #define cpumask_of_node(node)	((node) == 0 ? cpu_online_mask : cpu_none_mask)
diff --git a/include/linux/crc-ccitt.h b/include/linux/crc-ccitt.h
index f52696a1ff0d..7cd45a4bc224 100644
--- a/include/linux/crc-ccitt.h
+++ b/include/linux/crc-ccitt.h
@@ -4,12 +4,19 @@
 #include <linux/types.h>
 
 extern u16 const crc_ccitt_table[256];
+extern u16 const crc_ccitt_false_table[256];
 
 extern u16 crc_ccitt(u16 crc, const u8 *buffer, size_t len);
+extern u16 crc_ccitt_false(u16 crc, const u8 *buffer, size_t len);
 
 static inline u16 crc_ccitt_byte(u16 crc, const u8 c)
 {
 	return (crc >> 8) ^ crc_ccitt_table[(crc ^ c) & 0xff];
 }
 
+static inline u16 crc_ccitt_false_byte(u16 crc, const u8 c)
+{
+    return (crc << 8) ^ crc_ccitt_false_table[(crc >> 8) ^ c];
+}
+
 #endif /* _LINUX_CRC_CCITT_H */
diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h
index d29e1e21bf3f..b1d861caca16 100644
--- a/include/linux/iopoll.h
+++ b/include/linux/iopoll.h
@@ -42,18 +42,21 @@
  */
 #define readx_poll_timeout(op, addr, val, cond, sleep_us, timeout_us)	\
 ({ \
-	ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); \
-	might_sleep_if(sleep_us); \
+	u64 __timeout_us = (timeout_us); \
+	unsigned long __sleep_us = (sleep_us); \
+	ktime_t __timeout = ktime_add_us(ktime_get(), __timeout_us); \
+	might_sleep_if((__sleep_us) != 0); \
 	for (;;) { \
 		(val) = op(addr); \
 		if (cond) \
 			break; \
-		if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \
+		if (__timeout_us && \
+		    ktime_compare(ktime_get(), __timeout) > 0) { \
 			(val) = op(addr); \
 			break; \
 		} \
-		if (sleep_us) \
-			usleep_range((sleep_us >> 2) + 1, sleep_us); \
+		if (__sleep_us) \
+			usleep_range((__sleep_us >> 2) + 1, __sleep_us); \
 	} \
 	(cond) ? 0 : -ETIMEDOUT; \
 })
@@ -77,17 +80,20 @@
  */
 #define readx_poll_timeout_atomic(op, addr, val, cond, delay_us, timeout_us) \
 ({ \
-	ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); \
+	u64 __timeout_us = (timeout_us); \
+	unsigned long __delay_us = (delay_us); \
+	ktime_t __timeout = ktime_add_us(ktime_get(), __timeout_us); \
 	for (;;) { \
 		(val) = op(addr); \
 		if (cond) \
 			break; \
-		if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \
+		if (__timeout_us && \
+		    ktime_compare(ktime_get(), __timeout) > 0) { \
 			(val) = op(addr); \
 			break; \
 		} \
-		if (delay_us) \
-			udelay(delay_us);	\
+		if (__delay_us) \
+			udelay(__delay_us);	\
 	} \
 	(cond) ? 0 : -ETIMEDOUT; \
 })
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index 1e369f0e921d..5bacecc5f51b 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -120,22 +120,24 @@ struct reg_sequence {
  */
 #define regmap_read_poll_timeout(map, addr, val, cond, sleep_us, timeout_us) \
 ({ \
-	ktime_t __timeout = ktime_add_us(ktime_get(), timeout_us); \
+	u64 __timeout_us = (timeout_us); \
+	unsigned long __sleep_us = (sleep_us); \
+	ktime_t __timeout = ktime_add_us(ktime_get(), __timeout_us); \
 	int __ret; \
-	might_sleep_if(sleep_us); \
+	might_sleep_if(__sleep_us); \
 	for (;;) { \
 		__ret = regmap_read((map), (addr), &(val)); \
 		if (__ret) \
 			break; \
 		if (cond) \
 			break; \
-		if ((timeout_us) && \
+		if (__timeout_us && \
 		    ktime_compare(ktime_get(), __timeout) > 0) { \
 			__ret = regmap_read((map), (addr), &(val)); \
 			break; \
 		} \
-		if (sleep_us) \
-			usleep_range(((sleep_us) >> 2) + 1, sleep_us); \
+		if (__sleep_us) \
+			usleep_range((__sleep_us >> 2) + 1, __sleep_us); \
 	} \
 	__ret ?: ((cond) ? 0 : -ETIMEDOUT); \
 })
diff --git a/lib/crc-ccitt.c b/lib/crc-ccitt.c
index 7f6dd68d2d09..d873b34039ff 100644
--- a/lib/crc-ccitt.c
+++ b/lib/crc-ccitt.c
@@ -51,8 +51,49 @@ u16 const crc_ccitt_table[256] = {
 };
 EXPORT_SYMBOL(crc_ccitt_table);
 
+/*
+ * Similar table to calculate CRC16 variant known as CRC-CCITT-FALSE
+ * Reflected bits order, does not augment final value.
+ */
+u16 const crc_ccitt_false_table[256] = {
+    0x0000, 0x1021, 0x2042, 0x3063, 0x4084, 0x50A5, 0x60C6, 0x70E7,
+    0x8108, 0x9129, 0xA14A, 0xB16B, 0xC18C, 0xD1AD, 0xE1CE, 0xF1EF,
+    0x1231, 0x0210, 0x3273, 0x2252, 0x52B5, 0x4294, 0x72F7, 0x62D6,
+    0x9339, 0x8318, 0xB37B, 0xA35A, 0xD3BD, 0xC39C, 0xF3FF, 0xE3DE,
+    0x2462, 0x3443, 0x0420, 0x1401, 0x64E6, 0x74C7, 0x44A4, 0x5485,
+    0xA56A, 0xB54B, 0x8528, 0x9509, 0xE5EE, 0xF5CF, 0xC5AC, 0xD58D,
+    0x3653, 0x2672, 0x1611, 0x0630, 0x76D7, 0x66F6, 0x5695, 0x46B4,
+    0xB75B, 0xA77A, 0x9719, 0x8738, 0xF7DF, 0xE7FE, 0xD79D, 0xC7BC,
+    0x48C4, 0x58E5, 0x6886, 0x78A7, 0x0840, 0x1861, 0x2802, 0x3823,
+    0xC9CC, 0xD9ED, 0xE98E, 0xF9AF, 0x8948, 0x9969, 0xA90A, 0xB92B,
+    0x5AF5, 0x4AD4, 0x7AB7, 0x6A96, 0x1A71, 0x0A50, 0x3A33, 0x2A12,
+    0xDBFD, 0xCBDC, 0xFBBF, 0xEB9E, 0x9B79, 0x8B58, 0xBB3B, 0xAB1A,
+    0x6CA6, 0x7C87, 0x4CE4, 0x5CC5, 0x2C22, 0x3C03, 0x0C60, 0x1C41,
+    0xEDAE, 0xFD8F, 0xCDEC, 0xDDCD, 0xAD2A, 0xBD0B, 0x8D68, 0x9D49,
+    0x7E97, 0x6EB6, 0x5ED5, 0x4EF4, 0x3E13, 0x2E32, 0x1E51, 0x0E70,
+    0xFF9F, 0xEFBE, 0xDFDD, 0xCFFC, 0xBF1B, 0xAF3A, 0x9F59, 0x8F78,
+    0x9188, 0x81A9, 0xB1CA, 0xA1EB, 0xD10C, 0xC12D, 0xF14E, 0xE16F,
+    0x1080, 0x00A1, 0x30C2, 0x20E3, 0x5004, 0x4025, 0x7046, 0x6067,
+    0x83B9, 0x9398, 0xA3FB, 0xB3DA, 0xC33D, 0xD31C, 0xE37F, 0xF35E,
+    0x02B1, 0x1290, 0x22F3, 0x32D2, 0x4235, 0x5214, 0x6277, 0x7256,
+    0xB5EA, 0xA5CB, 0x95A8, 0x8589, 0xF56E, 0xE54F, 0xD52C, 0xC50D,
+    0x34E2, 0x24C3, 0x14A0, 0x0481, 0x7466, 0x6447, 0x5424, 0x4405,
+    0xA7DB, 0xB7FA, 0x8799, 0x97B8, 0xE75F, 0xF77E, 0xC71D, 0xD73C,
+    0x26D3, 0x36F2, 0x0691, 0x16B0, 0x6657, 0x7676, 0x4615, 0x5634,
+    0xD94C, 0xC96D, 0xF90E, 0xE92F, 0x99C8, 0x89E9, 0xB98A, 0xA9AB,
+    0x5844, 0x4865, 0x7806, 0x6827, 0x18C0, 0x08E1, 0x3882, 0x28A3,
+    0xCB7D, 0xDB5C, 0xEB3F, 0xFB1E, 0x8BF9, 0x9BD8, 0xABBB, 0xBB9A,
+    0x4A75, 0x5A54, 0x6A37, 0x7A16, 0x0AF1, 0x1AD0, 0x2AB3, 0x3A92,
+    0xFD2E, 0xED0F, 0xDD6C, 0xCD4D, 0xBDAA, 0xAD8B, 0x9DE8, 0x8DC9,
+    0x7C26, 0x6C07, 0x5C64, 0x4C45, 0x3CA2, 0x2C83, 0x1CE0, 0x0CC1,
+    0xEF1F, 0xFF3E, 0xCF5D, 0xDF7C, 0xAF9B, 0xBFBA, 0x8FD9, 0x9FF8,
+    0x6E17, 0x7E36, 0x4E55, 0x5E74, 0x2E93, 0x3EB2, 0x0ED1, 0x1EF0
+};
+EXPORT_SYMBOL(crc_ccitt_false_table);
+
 /**
- *	crc_ccitt - recompute the CRC for the data buffer
+ *	crc_ccitt - recompute the CRC (CRC-CCITT variant) for the data
+ *	buffer
  *	@crc: previous CRC value
  *	@buffer: data pointer
  *	@len: number of bytes in the buffer
@@ -65,5 +106,20 @@ u16 crc_ccitt(u16 crc, u8 const *buffer, size_t len)
 }
 EXPORT_SYMBOL(crc_ccitt);
 
+/**
+ *	crc_ccitt_false - recompute the CRC (CRC-CCITT-FALSE variant)
+ *	for the data buffer
+ *	@crc: previous CRC value
+ *	@buffer: data pointer
+ *	@len: number of bytes in the buffer
+ */
+u16 crc_ccitt_false(u16 crc, u8 const *buffer, size_t len)
+{
+	while (len--)
+		crc = crc_ccitt_false_byte(crc, *buffer++);
+	return crc;
+}
+EXPORT_SYMBOL(crc_ccitt_false);
+
 MODULE_DESCRIPTION("CRC-CCITT calculations");
 MODULE_LICENSE("GPL");
diff --git a/mm/Kconfig b/mm/Kconfig
index 9c4bdddd80c2..03ff7703d322 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -756,3 +756,12 @@ config PERCPU_STATS
 	  This feature collects and exposes statistics via debugfs. The
 	  information includes global and per chunk statistics, which can
 	  be used to help understand percpu memory usage.
+
+config GUP_BENCHMARK
+	bool "Enable infrastructure for get_user_pages_fast() benchmarking"
+	default n
+	help
+	  Provides /sys/kernel/debug/gup_benchmark that helps with testing
+	  performance of get_user_pages_fast().
+
+	  See tools/testing/selftests/vm/gup_benchmark.c
diff --git a/mm/Makefile b/mm/Makefile
index e3ac3aeb533b..5246deed3878 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -81,6 +81,7 @@ obj-$(CONFIG_PAGE_COUNTER) += page_counter.o
 obj-$(CONFIG_MEMCG) += memcontrol.o vmpressure.o
 obj-$(CONFIG_MEMCG_SWAP) += swap_cgroup.o
 obj-$(CONFIG_CGROUP_HUGETLB) += hugetlb_cgroup.o
+obj-$(CONFIG_GUP_BENCHMARK) += gup_benchmark.o
 obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o
 obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o
 obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o
diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c
new file mode 100644
index 000000000000..5c8e2abeaa15
--- /dev/null
+++ b/mm/gup_benchmark.c
@@ -0,0 +1,100 @@
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/ktime.h>
+#include <linux/debugfs.h>
+
+#define GUP_FAST_BENCHMARK	_IOWR('g', 1, struct gup_benchmark)
+
+struct gup_benchmark {
+	__u64 delta_usec;
+	__u64 addr;
+	__u64 size;
+	__u32 nr_pages_per_call;
+	__u32 flags;
+};
+
+static int __gup_benchmark_ioctl(unsigned int cmd,
+		struct gup_benchmark *gup)
+{
+	ktime_t start_time, end_time;
+	unsigned long i, nr, nr_pages, addr, next;
+	struct page **pages;
+
+	nr_pages = gup->size / PAGE_SIZE;
+	pages = kvmalloc(sizeof(void *) * nr_pages, GFP_KERNEL);
+	if (!pages)
+		return -ENOMEM;
+
+	i = 0;
+	nr = gup->nr_pages_per_call;
+	start_time = ktime_get();
+	for (addr = gup->addr; addr < gup->addr + gup->size; addr = next) {
+		if (nr != gup->nr_pages_per_call)
+			break;
+
+		next = addr + nr * PAGE_SIZE;
+		if (next > gup->addr + gup->size) {
+			next = gup->addr + gup->size;
+			nr = (next - addr) / PAGE_SIZE;
+		}
+
+		nr = get_user_pages_fast(addr, nr, gup->flags & 1, pages + i);
+		i += nr;
+	}
+	end_time = ktime_get();
+
+	gup->delta_usec = ktime_us_delta(end_time, start_time);
+	gup->size = addr - gup->addr;
+
+	for (i = 0; i < nr_pages; i++) {
+		if (!pages[i])
+			break;
+		put_page(pages[i]);
+	}
+
+	kvfree(pages);
+	return 0;
+}
+
+static long gup_benchmark_ioctl(struct file *filep, unsigned int cmd,
+		unsigned long arg)
+{
+	struct gup_benchmark gup;
+	int ret;
+
+	if (cmd != GUP_FAST_BENCHMARK)
+		return -EINVAL;
+
+	if (copy_from_user(&gup, (void __user *)arg, sizeof(gup)))
+		return -EFAULT;
+
+	ret = __gup_benchmark_ioctl(cmd, &gup);
+	if (ret)
+		return ret;
+
+	if (copy_to_user((void __user *)arg, &gup, sizeof(gup)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static const struct file_operations gup_benchmark_fops = {
+	.open = nonseekable_open,
+	.unlocked_ioctl = gup_benchmark_ioctl,
+};
+
+static int gup_benchmark_init(void)
+{
+	void *ret;
+
+	ret = debugfs_create_file_unsafe("gup_benchmark", 0600, NULL, NULL,
+			&gup_benchmark_fops);
+	if (!ret)
+		pr_warn("Failed to create gup_benchmark in debugfs");
+
+	return 0;
+}
+
+late_initcall(gup_benchmark_init);
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index cbb29e41ef2b..084212d9e3e2 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -17,6 +17,7 @@ TEST_GEN_FILES += transhuge-stress
 TEST_GEN_FILES += userfaultfd
 TEST_GEN_FILES += mlock-random-test
 TEST_GEN_FILES += virtual_address_range
+TEST_GEN_FILES += gup_benchmark
 
 TEST_PROGS := run_vmtests
 
diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
new file mode 100644
index 000000000000..36df55132036
--- /dev/null
+++ b/tools/testing/selftests/vm/gup_benchmark.c
@@ -0,0 +1,91 @@
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/prctl.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+
+#include <linux/types.h>
+
+#define MB (1UL << 20)
+#define PAGE_SIZE sysconf(_SC_PAGESIZE)
+
+#define GUP_FAST_BENCHMARK	_IOWR('g', 1, struct gup_benchmark)
+
+struct gup_benchmark {
+	__u64 delta_usec;
+	__u64 addr;
+	__u64 size;
+	__u32 nr_pages_per_call;
+	__u32 flags;
+};
+
+int main(int argc, char **argv)
+{
+	struct gup_benchmark gup;
+	unsigned long size = 128 * MB;
+	int i, fd, opt, nr_pages = 1, thp = -1, repeats = 1, write = 0;
+	char *p;
+
+	while ((opt = getopt(argc, argv, "m:r:n:tT")) != -1) {
+		switch (opt) {
+		case 'm':
+			size = atoi(optarg) * MB;
+			break;
+		case 'r':
+			repeats = atoi(optarg);
+			break;
+		case 'n':
+			nr_pages = atoi(optarg);
+			break;
+		case 't':
+			thp = 1;
+			break;
+		case 'T':
+			thp = 0;
+			break;
+		case 'w':
+			write = 1;
+		default:
+			return -1;
+		}
+	}
+
+	gup.nr_pages_per_call = nr_pages;
+	gup.flags = write;
+
+	fd = open("/sys/kernel/debug/gup_benchmark", O_RDWR);
+	if (fd == -1)
+		perror("open"), exit(1);
+
+	p = mmap(NULL, size, PROT_READ | PROT_WRITE,
+			MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+	if (p == MAP_FAILED)
+		perror("mmap"), exit(1);
+	gup.addr = (unsigned long)p;
+
+	if (thp == 1)
+		madvise(p, size, MADV_HUGEPAGE);
+	else if (thp == 0)
+		madvise(p, size, MADV_NOHUGEPAGE);
+
+	for (; (unsigned long)p < gup.addr + size; p += PAGE_SIZE)
+		p[0] = 0;
+
+	for (i = 0; i < repeats; i++) {
+		gup.size = size;
+		if (ioctl(fd, GUP_FAST_BENCHMARK, &gup))
+			perror("ioctl"), exit(1);
+
+		printf("Time: %lld us", gup.delta_usec);
+		if (gup.size != size)
+			printf(", truncated (size: %lld)", gup.size);
+		printf("\n");
+	}
+
+	return 0;
+}