Merge "Merge android-4.4.129 (b1c4836) into msm-4.4"

Documentation/device-mapper/verity.txt

@@ -109,6 +109,17 @@ fec_start <offset>
     This is the offset, in <data_block_size> blocks, from the start of the
     FEC device to the beginning of the encoding data.
 
+check_at_most_once
+    Verify data blocks only the first time they are read from the data device,
+    rather than every time.  This reduces the overhead of dm-verity so that it
+    can be used on systems that are memory and/or CPU constrained.  However, it
+    provides a reduced level of security because only offline tampering of the
+    data device's content will be detected, not online tampering.
+
+    Hash blocks are still verified each time they are read from the hash device,
+    since verification of hash blocks is less performance critical than data
+    blocks, and a hash block will not be verified any more after all the data
+    blocks it covers have been verified anyway.
 
 Theory of operation
 ===================

Makefile

@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 4
-SUBLEVEL = 128
+SUBLEVEL = 129
 EXTRAVERSION =
 NAME = Blurry Fish Butt
 

arch/arm/boot/dts/at91sam9g25.dtsi

@@ -21,7 +21,7 @@
 				atmel,mux-mask = <
 				      /*    A         B          C     */
 				       0xffffffff 0xffe0399f 0xc000001c  /* pioA */
-				       0x0007ffff 0x8000fe3f 0x00000000  /* pioB */
+				       0x0007ffff 0x00047e3f 0x00000000  /* pioB */
 				       0x80000000 0x07c0ffff 0xb83fffff  /* pioC */
 				       0x003fffff 0x003f8000 0x00000000  /* pioD */
 				      >;

arch/arm/boot/dts/sama5d4.dtsi

@@ -1354,7 +1354,7 @@
 			pinctrl@fc06a000 {
 				#address-cells = <1>;
 				#size-cells = <1>;
-				compatible = "atmel,at91sam9x5-pinctrl", "atmel,at91rm9200-pinctrl", "simple-bus";
+				compatible = "atmel,sama5d3-pinctrl", "atmel,at91sam9x5-pinctrl", "simple-bus";
 				ranges = <0xfc068000 0xfc068000 0x100
 					  0xfc06a000 0xfc06a000 0x4000>;
 				/* WARNING: revisit as pin spec has changed */

arch/mips/include/asm/uaccess.h

@@ -1238,6 +1238,13 @@ __clear_user(void __user *addr, __kernel_size_t size)
 {
 	__kernel_size_t res;
 
+#ifdef CONFIG_CPU_MICROMIPS
+/* micromips memset / bzero also clobbers t7 & t8 */
+#define bzero_clobbers "$4", "$5", "$6", __UA_t0, __UA_t1, "$15", "$24", "$31"
+#else
+#define bzero_clobbers "$4", "$5", "$6", __UA_t0, __UA_t1, "$31"
+#endif /* CONFIG_CPU_MICROMIPS */
+
 	if (eva_kernel_access()) {
 		__asm__ __volatile__(
 			"move\t$4, %1\n\t"
@@ -1247,7 +1254,7 @@ __clear_user(void __user *addr, __kernel_size_t size)
 			"move\t%0, $6"
 			: "=r" (res)
 			: "r" (addr), "r" (size)
-			: "$4", "$5", "$6", __UA_t0, __UA_t1, "$31");
+			: bzero_clobbers);
 	} else {
 		might_fault();
 		__asm__ __volatile__(
@@ -1258,7 +1265,7 @@ __clear_user(void __user *addr, __kernel_size_t size)
 			"move\t%0, $6"
 			: "=r" (res)
 			: "r" (addr), "r" (size)
-			: "$4", "$5", "$6", __UA_t0, __UA_t1, "$31");
+			: bzero_clobbers);
 	}
 
 	return res;

arch/mips/lib/memset.S

@@ -218,7 +218,7 @@
 1:	PTR_ADDIU	a0, 1			/* fill bytewise */
 	R10KCBARRIER(0(ra))
 	bne		t1, a0, 1b
-	sb		a1, -1(a0)
+	 EX(sb, a1, -1(a0), .Lsmall_fixup\@)
 
 2:	jr		ra			/* done */
 	move		a2, zero
@@ -249,13 +249,18 @@
 	PTR_L		t0, TI_TASK($28)
 	andi		a2, STORMASK
 	LONG_L		t0, THREAD_BUADDR(t0)
-	LONG_ADDU	a2, t1
+	LONG_ADDU	a2, a0
 	jr		ra
 	LONG_SUBU	a2, t0
 
 .Llast_fixup\@:
 	jr		ra
-	andi		v1, a2, STORMASK
+	 nop
+
+.Lsmall_fixup\@:
+	PTR_SUBU	a2, t1, a0
+	jr		ra
+	 PTR_ADDIU	a2, 1
 
 	.endm
 

arch/parisc/kernel/drivers.c

@@ -648,6 +648,10 @@ static int match_pci_device(struct device *dev, int index,
 					(modpath->mod == PCI_FUNC(devfn)));
 	}
 
+	/* index might be out of bounds for bc[] */
+	if (index >= 6)
+		return 0;
+
 	id = PCI_SLOT(pdev->devfn) | (PCI_FUNC(pdev->devfn) << 5);
 	return (modpath->bc[index] == id);
 }

arch/powerpc/include/asm/barrier.h

@@ -36,7 +36,8 @@
 
 #define smp_store_mb(var, value)	do { WRITE_ONCE(var, value); mb(); } while (0)
 
-#ifdef __SUBARCH_HAS_LWSYNC
+/* The sub-arch has lwsync */
+#if defined(__powerpc64__) || defined(CONFIG_PPC_E500MC)
 #    define SMPWMB      LWSYNC
 #else
 #    define SMPWMB      eieio

arch/powerpc/include/asm/opal.h

@@ -21,6 +21,9 @@
 /* We calculate number of sg entries based on PAGE_SIZE */
 #define SG_ENTRIES_PER_NODE ((PAGE_SIZE - 16) / sizeof(struct opal_sg_entry))
 
+/* Default time to sleep or delay between OPAL_BUSY/OPAL_BUSY_EVENT loops */
+#define OPAL_BUSY_DELAY_MS	10
+
 /* /sys/firmware/opal */
 extern struct kobject *opal_kobj;
 

arch/powerpc/include/asm/synch.h

@@ -5,10 +5,6 @@
 #include <linux/stringify.h>
 #include <asm/feature-fixups.h>
 
-#if defined(__powerpc64__) || defined(CONFIG_PPC_E500MC)
-#define __SUBARCH_HAS_LWSYNC
-#endif
-
 #ifndef __ASSEMBLY__
 extern unsigned int __start___lwsync_fixup, __stop___lwsync_fixup;
 extern void do_lwsync_fixups(unsigned long value, void *fixup_start,

arch/powerpc/kernel/eeh_pe.c

@@ -788,7 +788,8 @@ static void eeh_restore_bridge_bars(struct eeh_dev *edev)
 	eeh_ops->write_config(pdn, 15*4, 4, edev->config_space[15]);
 
 	/* PCI Command: 0x4 */
-	eeh_ops->write_config(pdn, PCI_COMMAND, 4, edev->config_space[1]);
+	eeh_ops->write_config(pdn, PCI_COMMAND, 4, edev->config_space[1] |
+			      PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER);
 
 	/* Check the PCIe link is ready */
 	eeh_bridge_check_link(edev);

arch/powerpc/lib/feature-fixups.c

@@ -53,7 +53,7 @@ static int patch_alt_instruction(unsigned int *src, unsigned int *dest,
 		unsigned int *target = (unsigned int *)branch_target(src);
 
 		/* Branch within the section doesn't need translating */
-		if (target < alt_start || target >= alt_end) {
+		if (target < alt_start || target > alt_end) {
 			instr = translate_branch(dest, src);
 			if (!instr)
 				return 1;

arch/powerpc/platforms/powernv/opal-nvram.c

@@ -11,6 +11,7 @@
 
 #define DEBUG
 
+#include <linux/delay.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/of.h>
@@ -56,9 +57,17 @@ static ssize_t opal_nvram_write(char *buf, size_t count, loff_t *index)
 
 	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
 		rc = opal_write_nvram(__pa(buf), count, off);
-		if (rc == OPAL_BUSY_EVENT)
+		if (rc == OPAL_BUSY_EVENT) {
+			msleep(OPAL_BUSY_DELAY_MS);
 			opal_poll_events(NULL);
+		} else if (rc == OPAL_BUSY) {
+			msleep(OPAL_BUSY_DELAY_MS);
 		}
+	}
+
+	if (rc)
+		return -EIO;
+
 	*index += count;
 	return count;
 }

arch/s390/hypfs/inode.c

@@ -318,7 +318,7 @@ static void hypfs_kill_super(struct super_block *sb)
 
 	if (sb->s_root)
 		hypfs_delete_tree(sb->s_root);
-	if (sb_info->update_file)
+	if (sb_info && sb_info->update_file)
 		hypfs_remove(sb_info->update_file);
 	kfree(sb->s_fs_info);
 	sb->s_fs_info = NULL;

arch/s390/kernel/ipl.c

@@ -798,6 +798,7 @@ static ssize_t reipl_generic_loadparm_store(struct ipl_parameter_block *ipb,
 	/* copy and convert to ebcdic */
 	memcpy(ipb->hdr.loadparm, buf, lp_len);
 	ASCEBC(ipb->hdr.loadparm, LOADPARM_LEN);
+	ipb->hdr.flags |= DIAG308_FLAGS_LP_VALID;
 	return len;
 }
 

arch/um/os-Linux/signal.c

@@ -140,7 +140,7 @@ static void (*handlers[_NSIG])(int sig, struct siginfo *si, mcontext_t *mc) = {
 
 static void hard_handler(int sig, siginfo_t *si, void *p)
 {
-	struct ucontext *uc = p;
+	ucontext_t *uc = p;
 	mcontext_t *mc = &uc->uc_mcontext;
 	unsigned long pending = 1UL << sig;
 

arch/x86/um/stub_segv.c

@@ -10,7 +10,7 @@
 void __attribute__ ((__section__ (".__syscall_stub")))
 stub_segv_handler(int sig, siginfo_t *info, void *p)
 {
-	struct ucontext *uc = p;
+	ucontext_t *uc = p;
 
 	GET_FAULTINFO_FROM_MC(*((struct faultinfo *) STUB_DATA),
 			      &uc->uc_mcontext);

drivers/acpi/video_detect.c

@@ -205,6 +205,15 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
 			  "3570R/370R/470R/450R/510R/4450RV"),
 		},
 	},
+	{
+	 /* https://bugzilla.redhat.com/show_bug.cgi?id=1557060 */
+	 .callback = video_detect_force_video,
+	 .ident = "SAMSUNG 670Z5E",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "670Z5E"),
+		},
+	},
 	{
 	 /* https://bugzilla.redhat.com/show_bug.cgi?id=1094948 */
 	 .callback = video_detect_force_video,

drivers/base/regmap/regmap.c

@@ -1582,7 +1582,7 @@ int regmap_raw_write(struct regmap *map, unsigned int reg,
 		return -EINVAL;
 	if (val_len % map->format.val_bytes)
 		return -EINVAL;
-	if (map->max_raw_write && map->max_raw_write > val_len)
+	if (map->max_raw_write && map->max_raw_write < val_len)
 		return -E2BIG;
 
 	map->lock(map->lock_arg);

drivers/block/loop.c

@@ -1121,11 +1121,15 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	if (info->lo_encrypt_type) {
 		unsigned int type = info->lo_encrypt_type;
 
-		if (type >= MAX_LO_CRYPT)
+		if (type >= MAX_LO_CRYPT) {
-			return -EINVAL;
+			err = -EINVAL;
+			goto exit;
+		}
 		xfer = xfer_funcs[type];
-		if (xfer == NULL)
+		if (xfer == NULL) {
-			return -EINVAL;
+			err = -EINVAL;
+			goto exit;
+		}
 	} else
 		xfer = NULL;
 

drivers/char/random.c

@@ -724,7 +724,7 @@ retry:
 
 static int credit_entropy_bits_safe(struct entropy_store *r, int nbits)
 {
-	const int nbits_max = (int)(~0U >> (ENTROPY_SHIFT + 1));
+	const int nbits_max = r->poolinfo->poolwords * 32;
 
 	if (nbits < 0)
 		return -EINVAL;

drivers/clk/bcm/clk-bcm2835.c

@@ -891,9 +891,7 @@ static void bcm2835_pll_off(struct clk_hw *hw)
 	const struct bcm2835_pll_data *data = pll->data;
 
 	spin_lock(&cprman->regs_lock);
-	cprman_write(cprman, data->cm_ctrl_reg,
+	cprman_write(cprman, data->cm_ctrl_reg, CM_PLL_ANARST);
-		     cprman_read(cprman, data->cm_ctrl_reg) |
-		     CM_PLL_ANARST);
 	cprman_write(cprman, data->a2w_ctrl_reg,
 		     cprman_read(cprman, data->a2w_ctrl_reg) |
 		     A2W_PLL_CTRL_PWRDN);
@@ -929,6 +927,10 @@ static int bcm2835_pll_on(struct clk_hw *hw)
 		cpu_relax();
 	}
 
+	cprman_write(cprman, data->a2w_ctrl_reg,
+		     cprman_read(cprman, data->a2w_ctrl_reg) |
+		     A2W_PLL_CTRL_PRST_DISABLE);
+
 	return 0;
 }
 

drivers/clk/mvebu/armada-38x.c

@@ -46,10 +46,11 @@ static u32 __init armada_38x_get_tclk_freq(void __iomem *sar)
 }
 
 static const u32 armada_38x_cpu_frequencies[] __initconst = {
-	0, 0, 0, 0,
+	666 * 1000 * 1000,  0, 800 * 1000 * 1000, 0,
-	1066 * 1000 * 1000, 0, 0, 0,
+	1066 * 1000 * 1000, 0, 1200 * 1000 * 1000, 0,
 	1332 * 1000 * 1000, 0, 0, 0,
-	1600 * 1000 * 1000,
+	1600 * 1000 * 1000, 0, 0, 0,
+	1866 * 1000 * 1000, 0, 0, 2000 * 1000 * 1000,
 };
 
 static u32 __init armada_38x_get_cpu_freq(void __iomem *sar)
@@ -75,11 +76,11 @@ static const struct coreclk_ratio armada_38x_coreclk_ratios[] __initconst = {
 };
 
 static const int armada_38x_cpu_l2_ratios[32][2] __initconst = {
-	{0, 1}, {0, 1}, {0, 1}, {0, 1},
+	{1, 2}, {0, 1}, {1, 2}, {0, 1},
+	{1, 2}, {0, 1}, {1, 2}, {0, 1},
 	{1, 2}, {0, 1}, {0, 1}, {0, 1},
 	{1, 2}, {0, 1}, {0, 1}, {0, 1},
-	{1, 2}, {0, 1}, {0, 1}, {0, 1},
+	{1, 2}, {0, 1}, {0, 1}, {1, 2},
-	{0, 1}, {0, 1}, {0, 1}, {0, 1},
 	{0, 1}, {0, 1}, {0, 1}, {0, 1},
 	{0, 1}, {0, 1}, {0, 1}, {0, 1},
 	{0, 1}, {0, 1}, {0, 1}, {0, 1},
@@ -90,7 +91,7 @@ static const int armada_38x_cpu_ddr_ratios[32][2] __initconst = {
 	{1, 2}, {0, 1}, {0, 1}, {0, 1},
 	{1, 2}, {0, 1}, {0, 1}, {0, 1},
 	{1, 2}, {0, 1}, {0, 1}, {0, 1},
-	{0, 1}, {0, 1}, {0, 1}, {0, 1},
+	{1, 2}, {0, 1}, {0, 1}, {7, 15},
 	{0, 1}, {0, 1}, {0, 1}, {0, 1},
 	{0, 1}, {0, 1}, {0, 1}, {0, 1},
 	{0, 1}, {0, 1}, {0, 1}, {0, 1},

drivers/dma/at_xdmac.c

@@ -1473,10 +1473,10 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	for (retry = 0; retry < AT_XDMAC_RESIDUE_MAX_RETRIES; retry++) {
 		check_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
 		rmb();
-		initd = !!(at_xdmac_chan_read(atchan, AT_XDMAC_CC) & AT_XDMAC_CC_INITD);
-		rmb();
 		cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC);
 		rmb();
+		initd = !!(at_xdmac_chan_read(atchan, AT_XDMAC_CC) & AT_XDMAC_CC_INITD);
+		rmb();
 		cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
 		rmb();
 

drivers/gpu/drm/radeon/radeon_object.c

@@ -238,9 +238,10 @@ int radeon_bo_create(struct radeon_device *rdev,
 	 * may be slow
 	 * See https://bugs.freedesktop.org/show_bug.cgi?id=88758
 	 */
-
+#ifndef CONFIG_COMPILE_TEST
 #warning Please enable CONFIG_MTRR and CONFIG_X86_PAT for better performance \
 	 thanks to write-combining
+#endif
 
 	if (bo->flags & RADEON_GEM_GTT_WC)
 		DRM_INFO_ONCE("Please enable CONFIG_MTRR and CONFIG_X86_PAT for "

drivers/gpu/drm/radeon/si_dpm.c

@@ -5964,9 +5964,9 @@ static void si_set_pcie_lane_width_in_smc(struct radeon_device *rdev,
 {
 	u32 lane_width;
 	u32 new_lane_width =
-		(radeon_new_state->caps & ATOM_PPLIB_PCIE_LINK_WIDTH_MASK) >> ATOM_PPLIB_PCIE_LINK_WIDTH_SHIFT;
+		((radeon_new_state->caps & ATOM_PPLIB_PCIE_LINK_WIDTH_MASK) >> ATOM_PPLIB_PCIE_LINK_WIDTH_SHIFT) + 1;
 	u32 current_lane_width =
-		(radeon_current_state->caps & ATOM_PPLIB_PCIE_LINK_WIDTH_MASK) >> ATOM_PPLIB_PCIE_LINK_WIDTH_SHIFT;
+		((radeon_current_state->caps & ATOM_PPLIB_PCIE_LINK_WIDTH_MASK) >> ATOM_PPLIB_PCIE_LINK_WIDTH_SHIFT) + 1;
 
 	if (new_lane_width != current_lane_width) {
 		radeon_set_pcie_lanes(rdev, new_lane_width);

drivers/hid/hid-core.c

@@ -1331,7 +1331,7 @@ u8 *hid_alloc_report_buf(struct hid_report *report, gfp_t flags)
 	 * of implement() working on 8 byte chunks
 	 */
 
-	int len = hid_report_len(report) + 7;
+	u32 len = hid_report_len(report) + 7;
 
 	return kmalloc(len, flags);
 }
@@ -1396,7 +1396,7 @@ void __hid_request(struct hid_device *hid, struct hid_report *report,
 {
 	char *buf;
 	int ret;
-	int len;
+	u32 len;
 
 	buf = hid_alloc_report_buf(report, GFP_KERNEL);
 	if (!buf)
@@ -1422,14 +1422,14 @@ out:
 }
 EXPORT_SYMBOL_GPL(__hid_request);
 
-int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, int size,
+int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size,
 		int interrupt)
 {
 	struct hid_report_enum *report_enum = hid->report_enum + type;
 	struct hid_report *report;
 	struct hid_driver *hdrv;
 	unsigned int a;
-	int rsize, csize = size;
+	u32 rsize, csize = size;
 	u8 *cdata = data;
 	int ret = 0;
 
@@ -1487,7 +1487,7 @@ EXPORT_SYMBOL_GPL(hid_report_raw_event);
  *
  * This is data entry for lower layers.
  */
-int hid_input_report(struct hid_device *hid, int type, u8 *data, int size, int interrupt)
+int hid_input_report(struct hid_device *hid, int type, u8 *data, u32 size, int interrupt)
 {
 	struct hid_report_enum *report_enum;
 	struct hid_driver *hdrv;

drivers/hid/hid-input.c

@@ -1258,7 +1258,8 @@ static void hidinput_led_worker(struct work_struct *work)
 					      led_work);
 	struct hid_field *field;
 	struct hid_report *report;
-	int len, ret;
+	int ret;
+	u32 len;
 	__u8 *buf;
 
 	field = hidinput_get_led_field(hid);

drivers/hid/hid-multitouch.c

@@ -314,7 +314,8 @@ static struct attribute_group mt_attribute_group = {
 static void mt_get_feature(struct hid_device *hdev, struct hid_report *report)
 {
 	struct mt_device *td = hid_get_drvdata(hdev);
-	int ret, size = hid_report_len(report);
+	int ret;
+	u32 size = hid_report_len(report);
 	u8 *buf;
 
 	/*
@@ -919,7 +920,7 @@ static void mt_set_input_mode(struct hid_device *hdev)
 	struct hid_report_enum *re;
 	struct mt_class *cls = &td->mtclass;
 	char *buf;
-	int report_len;
+	u32 report_len;
 
 	if (td->inputmode < 0)
 		return;

drivers/hid/hid-rmi.c

@@ -110,8 +110,8 @@ struct rmi_data {
 	u8 *writeReport;
 	u8 *readReport;
 
-	int input_report_size;
+	u32 input_report_size;
-	int output_report_size;
+	u32 output_report_size;
 
 	unsigned long flags;
 

drivers/hid/hidraw.c

@@ -197,6 +197,11 @@ static ssize_t hidraw_get_report(struct file *file, char __user *buffer, size_t
 	int ret = 0, len;
 	unsigned char report_number;
 
+	if (!hidraw_table[minor] || !hidraw_table[minor]->exist) {
+		ret = -ENODEV;
+		goto out;
+	}
+
 	dev = hidraw_table[minor]->hid;
 
 	if (!dev->ll_driver->raw_request) {

drivers/hid/i2c-hid/i2c-hid.c

@@ -137,10 +137,10 @@ struct i2c_hid {
 						   * register of the HID
 						   * descriptor. */
 	unsigned int		bufsize;	/* i2c buffer size */
-	char			*inbuf;		/* Input buffer */
+	u8			*inbuf;		/* Input buffer */
-	char			*rawbuf;	/* Raw Input buffer */
+	u8			*rawbuf;	/* Raw Input buffer */
-	char			*cmdbuf;	/* Command buffer */
+	u8			*cmdbuf;	/* Command buffer */
-	char			*argsbuf;	/* Command arguments buffer */
+	u8			*argsbuf;	/* Command arguments buffer */
 
 	unsigned long		flags;		/* device flags */
 
@@ -387,7 +387,8 @@ static int i2c_hid_hwreset(struct i2c_client *client)
 
 static void i2c_hid_get_input(struct i2c_hid *ihid)
 {
-	int ret, ret_size;
+	int ret;
+	u32 ret_size;
 	int size = le16_to_cpu(ihid->hdesc.wMaxInputLength);
 
 	if (size > ihid->bufsize)
@@ -412,7 +413,7 @@ static void i2c_hid_get_input(struct i2c_hid *ihid)
 		return;
 	}
 
-	if (ret_size > size) {
+	if ((ret_size > size) || (ret_size <= 2)) {
 		dev_err(&ihid->client->dev, "%s: incomplete report (%d/%d)\n",
 			__func__, size, ret_size);
 		return;

drivers/hwmon/ina2xx.c

@@ -447,6 +447,7 @@ static int ina2xx_probe(struct i2c_client *client,
 
 	/* set the device type */
 	data->config = &ina2xx_config[id->driver_data];
+	mutex_init(&data->config_lock);
 
 	if (of_property_read_u32(dev->of_node, "shunt-resistor", &val) < 0) {
 		struct ina2xx_platform_data *pdata = dev_get_platdata(dev);
@@ -473,8 +474,6 @@ static int ina2xx_probe(struct i2c_client *client,
 		return -ENODEV;
 	}
 
-	mutex_init(&data->config_lock);
-
 	data->groups[group++] = &ina2xx_group;
 	if (id->driver_data == ina226)
 		data->groups[group++] = &ina226_group;

drivers/infiniband/core/ucma.c

@@ -1230,6 +1230,9 @@ static int ucma_set_ib_path(struct ucma_context *ctx,
 	if (!optlen)
 		return -EINVAL;
 
+	if (!ctx->cm_id->device)
+		return -EINVAL;
+
 	memset(&sa_path, 0, sizeof(sa_path));
 
 	ib_sa_unpack_path(path_data->path_rec, &sa_path);

drivers/infiniband/ulp/srp/ib_srp.c

@@ -2581,9 +2581,11 @@ static int srp_abort(struct scsi_cmnd *scmnd)
 		ret = FAST_IO_FAIL;
 	else
 		ret = FAILED;
+	if (ret == SUCCESS) {
 		srp_free_req(ch, req, scmnd, 0);
 		scmnd->result = DID_ABORT << 16;
 		scmnd->scsi_done(scmnd);
+	}
 
 	return ret;
 }
@@ -3309,12 +3311,10 @@ static ssize_t srp_create_target(struct device *dev,
 				      num_online_nodes());
 		const int ch_end = ((node_idx + 1) * target->ch_count /
 				    num_online_nodes());
-		const int cv_start = (node_idx * ibdev->num_comp_vectors /
+		const int cv_start = node_idx * ibdev->num_comp_vectors /
-				      num_online_nodes() + target->comp_vector)
+				     num_online_nodes();
-				     % ibdev->num_comp_vectors;
+		const int cv_end = (node_idx + 1) * ibdev->num_comp_vectors /
-		const int cv_end = ((node_idx + 1) * ibdev->num_comp_vectors /
+				   num_online_nodes();
-				    num_online_nodes() + target->comp_vector)
-				   % ibdev->num_comp_vectors;
 		int cpu_idx = 0;
 
 		for_each_online_cpu(cpu) {

drivers/iommu/intel-svm.c

@@ -389,6 +389,7 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 				pasid_max - 1, GFP_KERNEL);
 		if (ret < 0) {
 			kfree(svm);
+			kfree(sdev);
 			goto out;
 		}
 		svm->pasid = ret;

drivers/md/dm-verity-target.c

@@ -19,6 +19,7 @@
 
 #include <linux/module.h>
 #include <linux/reboot.h>
+#include <linux/vmalloc.h>
 
 #define DM_MSG_PREFIX			"verity"
 
@@ -32,6 +33,7 @@
 #define DM_VERITY_OPT_LOGGING		"ignore_corruption"
 #define DM_VERITY_OPT_RESTART		"restart_on_corruption"
 #define DM_VERITY_OPT_IGN_ZEROES	"ignore_zero_blocks"
+#define DM_VERITY_OPT_AT_MOST_ONCE	"check_at_most_once"
 
 #define DM_VERITY_OPTS_MAX		(2 + DM_VERITY_OPTS_FEC)
 
@@ -398,6 +400,18 @@ static int verity_bv_zero(struct dm_verity *v, struct dm_verity_io *io,
 	return 0;
 }
 
+/*
+ * Moves the bio iter one data block forward.
+ */
+static inline void verity_bv_skip_block(struct dm_verity *v,
+					struct dm_verity_io *io,
+					struct bvec_iter *iter)
+{
+	struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_bio_data_size);
+
+	bio_advance_iter(bio, iter, 1 << v->data_dev_block_bits);
+}
+
 /*
  * Verify one "dm_verity_io" structure.
  */
@@ -410,9 +424,16 @@ static int verity_verify_io(struct dm_verity_io *io)
 
 	for (b = 0; b < io->n_blocks; b++) {
 		int r;
+		sector_t cur_block = io->block + b;
 		struct shash_desc *desc = verity_io_hash_desc(v, io);
 
-		r = verity_hash_for_block(v, io, io->block + b,
+		if (v->validated_blocks &&
+		    likely(test_bit(cur_block, v->validated_blocks))) {
+			verity_bv_skip_block(v, io, &io->iter);
+			continue;
+		}
+
+		r = verity_hash_for_block(v, io, cur_block,
 					  verity_io_want_digest(v, io),
 					  &is_zero);
 		if (unlikely(r < 0))
@@ -445,13 +466,16 @@ static int verity_verify_io(struct dm_verity_io *io)
 			return r;
 
 		if (likely(memcmp(verity_io_real_digest(v, io),
-				  verity_io_want_digest(v, io), v->digest_size) == 0))
+				  verity_io_want_digest(v, io), v->digest_size) == 0)) {
+			if (v->validated_blocks)
+				set_bit(cur_block, v->validated_blocks);
 			continue;
+		}
 		else if (verity_fec_decode(v, io, DM_VERITY_BLOCK_TYPE_DATA,
-					   io->block + b, NULL, &start) == 0)
+					   cur_block, NULL, &start) == 0)
 			continue;
 		else if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_DATA,
-					   io->block + b))
+					   cur_block))
 			return -EIO;
 	}
 
@@ -645,6 +669,8 @@ void verity_status(struct dm_target *ti, status_type_t type,
 			args += DM_VERITY_OPTS_FEC;
 		if (v->zero_digest)
 			args++;
+		if (v->validated_blocks)
+			args++;
 		if (!args)
 			return;
 		DMEMIT(" %u", args);
@@ -663,6 +689,8 @@ void verity_status(struct dm_target *ti, status_type_t type,
 		}
 		if (v->zero_digest)
 			DMEMIT(" " DM_VERITY_OPT_IGN_ZEROES);
+		if (v->validated_blocks)
+			DMEMIT(" " DM_VERITY_OPT_AT_MOST_ONCE);
 		sz = verity_fec_status_table(v, sz, result, maxlen);
 		break;
 	}
@@ -716,6 +744,7 @@ void verity_dtr(struct dm_target *ti)
 	if (v->bufio)
 		dm_bufio_client_destroy(v->bufio);
 
+	vfree(v->validated_blocks);
 	kfree(v->salt);
 	kfree(v->root_digest);
 	kfree(v->zero_digest);
@@ -737,6 +766,26 @@ void verity_dtr(struct dm_target *ti)
 }
 EXPORT_SYMBOL_GPL(verity_dtr);
 
+static int verity_alloc_most_once(struct dm_verity *v)
+{
+	struct dm_target *ti = v->ti;
+
+	/* the bitset can only handle INT_MAX blocks */
+	if (v->data_blocks > INT_MAX) {
+		ti->error = "device too large to use check_at_most_once";
+		return -E2BIG;
+	}
+
+	v->validated_blocks = vzalloc(BITS_TO_LONGS(v->data_blocks) *
+				       sizeof(unsigned long));
+	if (!v->validated_blocks) {
+		ti->error = "failed to allocate bitset for check_at_most_once";
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
 static int verity_alloc_zero_digest(struct dm_verity *v)
 {
 	int r = -ENOMEM;
@@ -806,6 +855,12 @@ static int verity_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v)
 			}
 			continue;
 
+		} else if (!strcasecmp(arg_name, DM_VERITY_OPT_AT_MOST_ONCE)) {
+			r = verity_alloc_most_once(v);
+			if (r)
+				return r;
+			continue;
+
 		} else if (verity_is_fec_opt_arg(arg_name)) {
 			r = verity_fec_parse_opt_args(as, v, &argc, arg_name);
 			if (r)
@@ -1074,7 +1129,7 @@ EXPORT_SYMBOL_GPL(verity_ctr);
 
 static struct target_type verity_target = {
 	.name		= "verity",
-	.version	= {1, 3, 0},
+	.version	= {1, 4, 0},
 	.module		= THIS_MODULE,
 	.ctr		= verity_ctr,
 	.dtr		= verity_dtr,

drivers/md/dm-verity.h

@@ -63,6 +63,7 @@ struct dm_verity {
 	sector_t hash_level_block[DM_VERITY_MAX_LEVELS];
 
 	struct dm_verity_fec *fec;	/* forward error correction */
+	unsigned long *validated_blocks; /* bitset blocks validated */
 };
 
 struct dm_verity_io {

drivers/media/v4l2-core/v4l2-compat-ioctl32.c

@@ -101,7 +101,7 @@ static int get_v4l2_window32(struct v4l2_window __user *kp,
 static int put_v4l2_window32(struct v4l2_window __user *kp,
 			     struct v4l2_window32 __user *up)
 {
-	struct v4l2_clip __user *kclips = kp->clips;
+	struct v4l2_clip __user *kclips;
 	struct v4l2_clip32 __user *uclips;
 	compat_caddr_t p;
 	u32 clipcount;
@@ -116,6 +116,8 @@ static int put_v4l2_window32(struct v4l2_window __user *kp,
 	if (!clipcount)
 		return 0;
 
+	if (get_user(kclips, &kp->clips))
+		return -EFAULT;
 	if (get_user(p, &up->clips))
 		return -EFAULT;
 	uclips = compat_ptr(p);

drivers/mmc/host/jz4740_mmc.c

@@ -368,9 +368,9 @@ static void jz4740_mmc_set_irq_enabled(struct jz4740_mmc_host *host,
 		host->irq_mask &= ~irq;
 	else
 		host->irq_mask |= irq;
-	spin_unlock_irqrestore(&host->lock, flags);
 
 	writew(host->irq_mask, host->base + JZ_REG_MMC_IMASK);
+	spin_unlock_irqrestore(&host->lock, flags);
 }
 
 static void jz4740_mmc_clock_enable(struct jz4740_mmc_host *host,

drivers/mtd/ubi/block.c

@@ -244,7 +244,7 @@ static int ubiblock_open(struct block_device *bdev, fmode_t mode)
 	 * in any case.
 	 */
 	if (mode & FMODE_WRITE) {
-		ret = -EPERM;
+		ret = -EROFS;
 		goto out_unlock;
 	}
 

drivers/mtd/ubi/build.c

@@ -951,6 +951,17 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num,
 		return -EINVAL;
 	}
 
+	/*
+	 * Both UBI and UBIFS have been designed for SLC NAND and NOR flashes.
+	 * MLC NAND is different and needs special care, otherwise UBI or UBIFS
+	 * will die soon and you will lose all your data.
+	 */
+	if (mtd->type == MTD_MLCNANDFLASH) {
+		pr_err("ubi: refuse attaching mtd%d - MLC NAND is not supported\n",
+			mtd->index);
+		return -EINVAL;
+	}
+
 	if (ubi_num == UBI_DEV_NUM_AUTO) {
 		/* Search for an empty slot in the @ubi_devices array */
 		for (ubi_num = 0; ubi_num < UBI_MAX_DEVICES; ubi_num++)

drivers/mtd/ubi/fastmap-wl.c

@@ -360,7 +360,6 @@ static void ubi_fastmap_close(struct ubi_device *ubi)
 {
 	int i;
 
-	flush_work(&ubi->fm_work);
 	return_unused_pool_pebs(ubi, &ubi->fm_pool);
 	return_unused_pool_pebs(ubi, &ubi->fm_wl_pool);
 

drivers/net/slip/slhc.c

@@ -509,6 +509,10 @@ slhc_uncompress(struct slcompress *comp, unsigned char *icp, int isize)
 		if(x < 0 || x > comp->rslot_limit)
 			goto bad;
 
+		/* Check if the cstate is initialized */
+		if (!comp->rstate[x].initialized)
+			goto bad;
+
 		comp->flags &=~ SLF_TOSS;
 		comp->recv_current = x;
 	} else {
@@ -673,6 +677,7 @@ slhc_remember(struct slcompress *comp, unsigned char *icp, int isize)
 	if (cs->cs_tcp.doff > 5)
 	  memcpy(cs->cs_tcpopt, icp + ihl*4 + sizeof(struct tcphdr), (cs->cs_tcp.doff - 5) * 4);
 	cs->cs_hsize = ihl*2 + cs->cs_tcp.doff*2;
+	cs->initialized = true;
 	/* Put headers back on packet
 	 * Neither header checksum is recalculated
 	 */

drivers/net/usb/cdc_ether.c

@@ -704,6 +704,12 @@ static const struct usb_device_id	products[] = {
 				      USB_CDC_SUBCLASS_ETHERNET,
 				      USB_CDC_PROTO_NONE),
 	.driver_info = (unsigned long)&wwan_info,
+}, {
+	/* Cinterion AHS3 modem by GEMALTO */
+	USB_DEVICE_AND_INTERFACE_INFO(0x1e2d, 0x0055, USB_CLASS_COMM,
+				      USB_CDC_SUBCLASS_ETHERNET,
+				      USB_CDC_PROTO_NONE),
+	.driver_info = (unsigned long)&wwan_info,
 }, {
 	/* Telit modules */
 	USB_VENDOR_AND_INTERFACE_INFO(0x1bc7, USB_CLASS_COMM,

drivers/net/usb/lan78xx.c

@@ -618,6 +618,7 @@ static int lan78xx_read_otp(struct lan78xx_net *dev, u32 offset,
 			offset += 0x100;
 		else
 			ret = -EINVAL;
+		if (!ret)
 			ret = lan78xx_read_raw_otp(dev, offset, length, data);
 	}
 

drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c

@@ -1454,6 +1454,7 @@ static int rtl8187_probe(struct usb_interface *intf,
 		goto err_free_dev;
 	}
 	mutex_init(&priv->io_mutex);
+	mutex_init(&priv->conf_mutex);
 
 	SET_IEEE80211_DEV(dev, &intf->dev);
 	usb_set_intfdata(intf, dev);
@@ -1627,7 +1628,6 @@ static int rtl8187_probe(struct usb_interface *intf,
 		printk(KERN_ERR "rtl8187: Cannot register device\n");
 		goto err_free_dmabuf;
 	}
-	mutex_init(&priv->conf_mutex);
 	skb_queue_head_init(&priv->b_tx_status.queue);
 
 	wiphy_info(dev->wiphy, "hwaddr %pM, %s V%d + %s, rfkill mask %d\n",

drivers/net/xen-netfront.c

@@ -2024,7 +2024,10 @@ static void netback_changed(struct xenbus_device *dev,
 	case XenbusStateInitialised:
 	case XenbusStateReconfiguring:
 	case XenbusStateReconfigured:
+		break;
+
 	case XenbusStateUnknown:
+		wake_up_all(&module_unload_q);
 		break;
 
 	case XenbusStateInitWait:
@@ -2155,7 +2158,9 @@ static int xennet_remove(struct xenbus_device *dev)
 		xenbus_switch_state(dev, XenbusStateClosing);
 		wait_event(module_unload_q,
 			   xenbus_read_driver_state(dev->otherend) ==
-			   XenbusStateClosing);
+			   XenbusStateClosing ||
+			   xenbus_read_driver_state(dev->otherend) ==
+			   XenbusStateUnknown);
 
 		xenbus_switch_state(dev, XenbusStateClosed);
 		wait_event(module_unload_q,

drivers/pci/hotplug/acpiphp_glue.c

@@ -587,6 +587,7 @@ static unsigned int get_slot_status(struct acpiphp_slot *slot)
 {
 	unsigned long long sta = 0;
 	struct acpiphp_func *func;
+	u32 dvid;
 
 	list_for_each_entry(func, &slot->funcs, sibling) {
 		if (func->flags & FUNC_HAS_STA) {
@@ -597,19 +598,27 @@ static unsigned int get_slot_status(struct acpiphp_slot *slot)
 			if (ACPI_SUCCESS(status) && sta)
 				break;
 		} else {
-			u32 dvid;
+			if (pci_bus_read_dev_vendor_id(slot->bus,
-
+					PCI_DEVFN(slot->device, func->function),
-			pci_bus_read_config_dword(slot->bus,
+					&dvid, 0)) {
-						  PCI_DEVFN(slot->device,
-							    func->function),
-						  PCI_VENDOR_ID, &dvid);
-			if (dvid != 0xffffffff) {
 				sta = ACPI_STA_ALL;
 				break;
 			}
 		}
 	}
 
+	if (!sta) {
+		/*
+		 * Check for the slot itself since it may be that the
+		 * ACPI slot is a device below PCIe upstream port so in
+		 * that case it may not even be reachable yet.
+		 */
+		if (pci_bus_read_dev_vendor_id(slot->bus,
+				PCI_DEVFN(slot->device, 0), &dvid, 0)) {
+			sta = ACPI_STA_ALL;
+		}
+	}
+
 	return (unsigned int)sta;
 }
 

drivers/s390/cio/qdio_main.c

@@ -126,7 +126,7 @@ static inline int qdio_check_ccq(struct qdio_q *q, unsigned int ccq)
 static int qdio_do_eqbs(struct qdio_q *q, unsigned char *state,
 			int start, int count, int auto_ack)
 {
-	int rc, tmp_count = count, tmp_start = start, nr = q->nr, retried = 0;
+	int rc, tmp_count = count, tmp_start = start, nr = q->nr;
 	unsigned int ccq = 0;
 
 	qperf_inc(q, eqbs);
@@ -149,13 +149,6 @@ again:
 		qperf_inc(q, eqbs_partial);
 		DBF_DEV_EVENT(DBF_WARN, q->irq_ptr, "EQBS part:%02x",
 			tmp_count);
-		/*
-		 * Retry once, if that fails bail out and process the
-		 * extracted buffers before trying again.
-		 */
-		if (!retried++)
-			goto again;
-		else
 		return count - tmp_count;
 	}
 
@@ -212,7 +205,10 @@ again:
 	return 0;
 }
 
-/* returns number of examined buffers and their common state in *state */
+/*
+ * Returns number of examined buffers and their common state in *state.
+ * Requested number of buffers-to-examine must be > 0.
+ */
 static inline int get_buf_states(struct qdio_q *q, unsigned int bufnr,
 				 unsigned char *state, unsigned int count,
 				 int auto_ack, int merge_pending)
@@ -223,17 +219,23 @@ static inline int get_buf_states(struct qdio_q *q, unsigned int bufnr,
 	if (is_qebsm(q))
 		return qdio_do_eqbs(q, state, bufnr, count, auto_ack);
 
-	for (i = 0; i < count; i++) {
+	/* get initial state: */
-		if (!__state) {
 	__state = q->slsb.val[bufnr];
 	if (merge_pending && __state == SLSB_P_OUTPUT_PENDING)
 		__state = SLSB_P_OUTPUT_EMPTY;
-		} else if (merge_pending) {
+
-			if ((q->slsb.val[bufnr] & __state) != __state)
+	for (i = 1; i < count; i++) {
-				break;
-		} else if (q->slsb.val[bufnr] != __state)
-			break;
 		bufnr = next_buf(bufnr);
+
+		/* merge PENDING into EMPTY: */
+		if (merge_pending &&
+		    q->slsb.val[bufnr] == SLSB_P_OUTPUT_PENDING &&
+		    __state == SLSB_P_OUTPUT_EMPTY)
+			continue;
+
+		/* stop if next state differs from initial state: */
+		if (q->slsb.val[bufnr] != __state)
+			break;
 	}
 	*state = __state;
 	return i;

drivers/thermal/imx_thermal.c

@@ -589,6 +589,9 @@ static int imx_thermal_probe(struct platform_device *pdev)
 	regmap_write(map, TEMPSENSE0 + REG_CLR, TEMPSENSE0_POWER_DOWN);
 	regmap_write(map, TEMPSENSE0 + REG_SET, TEMPSENSE0_MEASURE_TEMP);
 
+	data->irq_enabled = true;
+	data->mode = THERMAL_DEVICE_ENABLED;
+
 	ret = devm_request_threaded_irq(&pdev->dev, data->irq,
 			imx_thermal_alarm_irq, imx_thermal_alarm_irq_thread,
 			0, "imx_thermal", data);
@@ -600,9 +603,6 @@ static int imx_thermal_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	data->irq_enabled = true;
-	data->mode = THERMAL_DEVICE_ENABLED;
-
 	return 0;
 }
 

drivers/thunderbolt/nhi.c

@@ -627,6 +627,7 @@ static const struct dev_pm_ops nhi_pm_ops = {
 					    * we just disable hotplug, the
 					    * pci-tunnels stay alive.
 					    */
+	.thaw_noirq = nhi_resume_noirq,
 	.restore_noirq = nhi_resume_noirq,
 };
 

drivers/tty/n_tty.c

@@ -2238,6 +2238,12 @@ static ssize_t n_tty_read(struct tty_struct *tty, struct file *file,
 				}
 				if (tty_hung_up_p(file))
 					break;
+				/*
+				 * Abort readers for ttys which never actually
+				 * get hung up.  See __tty_hangup().
+				 */
+				if (test_bit(TTY_HUPPING, &tty->flags))
+					break;
 				if (!timeout)
 					break;
 				if (file->f_flags & O_NONBLOCK) {

drivers/tty/tty_io.c

@@ -702,6 +702,14 @@ static void __tty_hangup(struct tty_struct *tty, int exit_session)
 		return;
 	}
 
+	/*
+	 * Some console devices aren't actually hung up for technical and
+	 * historical reasons, which can lead to indefinite interruptible
+	 * sleep in n_tty_read().  The following explicitly tells
+	 * n_tty_read() to abort readers.
+	 */
+	set_bit(TTY_HUPPING, &tty->flags);
+
 	/* inuse_filps is protected by the single tty lock,
 	   this really needs to change if we want to flush the
 	   workqueue with the lock held */
@@ -757,6 +765,7 @@ static void __tty_hangup(struct tty_struct *tty, int exit_session)
 	 * can't yet guarantee all that.
 	 */
 	set_bit(TTY_HUPPED, &tty->flags);
+	clear_bit(TTY_HUPPING, &tty->flags);
 	tty_unlock(tty);
 
 	if (f)

drivers/usb/core/generic.c

@@ -242,8 +242,13 @@ static int generic_suspend(struct usb_device *udev, pm_message_t msg)
 	if (!udev->parent)
 		rc = hcd_bus_suspend(udev, msg);
 
-	/* Non-root devices don't need to do anything for FREEZE or PRETHAW */
+	/*
-	else if (msg.event == PM_EVENT_FREEZE || msg.event == PM_EVENT_PRETHAW)
+	 * Non-root USB2 devices don't need to do anything for FREEZE
+	 * or PRETHAW. USB3 devices don't support global suspend and
+	 * needs to be selectively suspended.
+	 */
+	else if ((msg.event == PM_EVENT_FREEZE || msg.event == PM_EVENT_PRETHAW)
+		 && (udev->speed < USB_SPEED_SUPER))
 		rc = 0;
 	else
 		rc = usb_port_suspend(udev, msg);

drivers/usb/dwc3/dwc3-pci.c

@@ -167,7 +167,7 @@ static int dwc3_pci_probe(struct pci_dev *pci,
 	ret = platform_device_add_resources(dwc3, res, ARRAY_SIZE(res));
 	if (ret) {
 		dev_err(dev, "couldn't add resources to dwc3 device\n");
-		return ret;
+		goto err;
 	}
 
 	pci_set_drvdata(pci, dwc3);

drivers/usb/musb/musb_gadget_ep0.c

@@ -114,15 +114,19 @@ static int service_tx_status_request(
 		}
 
 		is_in = epnum & USB_DIR_IN;
-		if (is_in) {
 		epnum &= 0x0f;
-			ep = &musb->endpoints[epnum].ep_in;
+		if (epnum >= MUSB_C_NUM_EPS) {
-		} else {
+			handled = -EINVAL;
-			ep = &musb->endpoints[epnum].ep_out;
+			break;
 		}
+
+		if (is_in)
+			ep = &musb->endpoints[epnum].ep_in;
+		else
+			ep = &musb->endpoints[epnum].ep_out;
 		regs = musb->endpoints[epnum].regs;
 
-		if (epnum >= MUSB_C_NUM_EPS || !ep->desc) {
+		if (!ep->desc) {
 			handled = -EINVAL;
 			break;
 		}

drivers/vfio/pci/vfio_pci_config.c

@@ -752,6 +752,62 @@ static int __init init_pci_cap_pcix_perm(struct perm_bits *perm)
 	return 0;
 }
 
+static int vfio_exp_config_write(struct vfio_pci_device *vdev, int pos,
+				 int count, struct perm_bits *perm,
+				 int offset, __le32 val)
+{
+	__le16 *ctrl = (__le16 *)(vdev->vconfig + pos -
+				  offset + PCI_EXP_DEVCTL);
+	int readrq = le16_to_cpu(*ctrl) & PCI_EXP_DEVCTL_READRQ;
+
+	count = vfio_default_config_write(vdev, pos, count, perm, offset, val);
+	if (count < 0)
+		return count;
+
+	/*
+	 * The FLR bit is virtualized, if set and the device supports PCIe
+	 * FLR, issue a reset_function.  Regardless, clear the bit, the spec
+	 * requires it to be always read as zero.  NB, reset_function might
+	 * not use a PCIe FLR, we don't have that level of granularity.
+	 */
+	if (*ctrl & cpu_to_le16(PCI_EXP_DEVCTL_BCR_FLR)) {
+		u32 cap;
+		int ret;
+
+		*ctrl &= ~cpu_to_le16(PCI_EXP_DEVCTL_BCR_FLR);
+
+		ret = pci_user_read_config_dword(vdev->pdev,
+						 pos - offset + PCI_EXP_DEVCAP,
+						 &cap);
+
+		if (!ret && (cap & PCI_EXP_DEVCAP_FLR))
+			pci_try_reset_function(vdev->pdev);
+	}
+
+	/*
+	 * MPS is virtualized to the user, writes do not change the physical
+	 * register since determining a proper MPS value requires a system wide
+	 * device view.  The MRRS is largely independent of MPS, but since the
+	 * user does not have that system-wide view, they might set a safe, but
+	 * inefficiently low value.  Here we allow writes through to hardware,
+	 * but we set the floor to the physical device MPS setting, so that
+	 * we can at least use full TLPs, as defined by the MPS value.
+	 *
+	 * NB, if any devices actually depend on an artificially low MRRS
+	 * setting, this will need to be revisited, perhaps with a quirk
+	 * though pcie_set_readrq().
+	 */
+	if (readrq != (le16_to_cpu(*ctrl) & PCI_EXP_DEVCTL_READRQ)) {
+		readrq = 128 <<
+			((le16_to_cpu(*ctrl) & PCI_EXP_DEVCTL_READRQ) >> 12);
+		readrq = max(readrq, pcie_get_mps(vdev->pdev));
+
+		pcie_set_readrq(vdev->pdev, readrq);
+	}
+
+	return count;
+}
+
 /* Permissions for PCI Express capability */
 static int __init init_pci_cap_exp_perm(struct perm_bits *perm)
 {
@@ -759,26 +815,67 @@ static int __init init_pci_cap_exp_perm(struct perm_bits *perm)
 	if (alloc_perm_bits(perm, PCI_CAP_EXP_ENDPOINT_SIZEOF_V2))
 		return -ENOMEM;
 
+	perm->writefn = vfio_exp_config_write;
+
 	p_setb(perm, PCI_CAP_LIST_NEXT, (u8)ALL_VIRT, NO_WRITE);
 
 	/*
-	 * Allow writes to device control fields (includes FLR!)
+	 * Allow writes to device control fields, except devctl_phantom,
-	 * but not to devctl_phantom which could confuse IOMMU
+	 * which could confuse IOMMU, MPS, which can break communication
-	 * or to the ARI bit in devctl2 which is set at probe time
+	 * with other physical devices, and the ARI bit in devctl2, which
+	 * is set at probe time.  FLR and MRRS get virtualized via our
+	 * writefn.
 	 */
-	p_setw(perm, PCI_EXP_DEVCTL, NO_VIRT, ~PCI_EXP_DEVCTL_PHANTOM);
+	p_setw(perm, PCI_EXP_DEVCTL,
+	       PCI_EXP_DEVCTL_BCR_FLR | PCI_EXP_DEVCTL_PAYLOAD |
+	       PCI_EXP_DEVCTL_READRQ, ~PCI_EXP_DEVCTL_PHANTOM);
 	p_setw(perm, PCI_EXP_DEVCTL2, NO_VIRT, ~PCI_EXP_DEVCTL2_ARI);
 	return 0;
 }
 
+static int vfio_af_config_write(struct vfio_pci_device *vdev, int pos,
+				int count, struct perm_bits *perm,
+				int offset, __le32 val)
+{
+	u8 *ctrl = vdev->vconfig + pos - offset + PCI_AF_CTRL;
+
+	count = vfio_default_config_write(vdev, pos, count, perm, offset, val);
+	if (count < 0)
+		return count;
+
+	/*
+	 * The FLR bit is virtualized, if set and the device supports AF
+	 * FLR, issue a reset_function.  Regardless, clear the bit, the spec
+	 * requires it to be always read as zero.  NB, reset_function might
+	 * not use an AF FLR, we don't have that level of granularity.
+	 */
+	if (*ctrl & PCI_AF_CTRL_FLR) {
+		u8 cap;
+		int ret;
+
+		*ctrl &= ~PCI_AF_CTRL_FLR;
+
+		ret = pci_user_read_config_byte(vdev->pdev,
+						pos - offset + PCI_AF_CAP,
+						&cap);
+
+		if (!ret && (cap & PCI_AF_CAP_FLR) && (cap & PCI_AF_CAP_TP))
+			pci_try_reset_function(vdev->pdev);
+	}
+
+	return count;
+}
+
 /* Permissions for Advanced Function capability */
 static int __init init_pci_cap_af_perm(struct perm_bits *perm)
 {
 	if (alloc_perm_bits(perm, pci_cap_length[PCI_CAP_ID_AF]))
 		return -ENOMEM;
 
+	perm->writefn = vfio_af_config_write;
+
 	p_setb(perm, PCI_CAP_LIST_NEXT, (u8)ALL_VIRT, NO_WRITE);
-	p_setb(perm, PCI_AF_CTRL, NO_VIRT, PCI_AF_CTRL_FLR);
+	p_setb(perm, PCI_AF_CTRL, PCI_AF_CTRL_FLR, PCI_AF_CTRL_FLR);
 	return 0;
 }
 

drivers/watchdog/f71808e_wdt.c

@@ -450,7 +450,7 @@ static bool watchdog_is_running(void)
 
 	is_running = (superio_inb(watchdog.sioaddr, SIO_REG_ENABLE) & BIT(0))
 		&& (superio_inb(watchdog.sioaddr, F71808FG_REG_WDT_CONF)
-			& F71808FG_FLAG_WD_EN);
+			& BIT(F71808FG_FLAG_WD_EN));
 
 	superio_exit(watchdog.sioaddr);
 

fs/autofs4/root.c

@@ -746,7 +746,7 @@ static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, umode_t m
 
 	autofs4_del_active(dentry);
 
-	inode = autofs4_get_inode(dir->i_sb, S_IFDIR | 0555);
+	inode = autofs4_get_inode(dir->i_sb, S_IFDIR | mode);
 	if (!inode)
 		return -ENOMEM;
 	d_add(dentry, inode);

fs/crypto/bio.c

@@ -25,15 +25,8 @@
 #include <linux/namei.h>
 #include "fscrypt_private.h"
 
-/*
+static void __fscrypt_decrypt_bio(struct bio *bio, bool done)
- * Call fscrypt_decrypt_page on every single page, reusing the encryption
- * context.
- */
-static void completion_pages(struct work_struct *work)
 {
-	struct fscrypt_ctx *ctx =
-		container_of(work, struct fscrypt_ctx, r.work);
-	struct bio *bio = ctx->r.bio;
 	struct bio_vec *bv;
 	int i;
 
@@ -45,22 +38,38 @@ static void completion_pages(struct work_struct *work)
 		if (ret) {
 			WARN_ON_ONCE(1);
 			SetPageError(page);
-		} else {
+		} else if (done) {
 			SetPageUptodate(page);
 		}
+		if (done)
 			unlock_page(page);
 	}
+}
+
+void fscrypt_decrypt_bio(struct bio *bio)
+{
+	__fscrypt_decrypt_bio(bio, false);
+}
+EXPORT_SYMBOL(fscrypt_decrypt_bio);
+
+static void completion_pages(struct work_struct *work)
+{
+	struct fscrypt_ctx *ctx =
+		container_of(work, struct fscrypt_ctx, r.work);
+	struct bio *bio = ctx->r.bio;
+
+	__fscrypt_decrypt_bio(bio, true);
 	fscrypt_release_ctx(ctx);
 	bio_put(bio);
 }
 
-void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *ctx, struct bio *bio)
+void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, struct bio *bio)
 {
 	INIT_WORK(&ctx->r.work, completion_pages);
 	ctx->r.bio = bio;
-	queue_work(fscrypt_read_workqueue, &ctx->r.work);
+	fscrypt_enqueue_decrypt_work(&ctx->r.work);
 }
-EXPORT_SYMBOL(fscrypt_decrypt_bio_pages);
+EXPORT_SYMBOL(fscrypt_enqueue_decrypt_bio);
 
 void fscrypt_pullback_bio_page(struct page **page, bool restore)
 {

fs/crypto/crypto.c

@@ -45,12 +45,18 @@ static mempool_t *fscrypt_bounce_page_pool = NULL;
 static LIST_HEAD(fscrypt_free_ctxs);
 static DEFINE_SPINLOCK(fscrypt_ctx_lock);
 
-struct workqueue_struct *fscrypt_read_workqueue;
+static struct workqueue_struct *fscrypt_read_workqueue;
 static DEFINE_MUTEX(fscrypt_init_mutex);
 
 static struct kmem_cache *fscrypt_ctx_cachep;
 struct kmem_cache *fscrypt_info_cachep;
 
+void fscrypt_enqueue_decrypt_work(struct work_struct *work)
+{
+	queue_work(fscrypt_read_workqueue, work);
+}
+EXPORT_SYMBOL(fscrypt_enqueue_decrypt_work);
+
 /**
  * fscrypt_release_ctx() - Releases an encryption context
  * @ctx: The encryption context to release.

fs/crypto/fscrypt_private.h

@@ -107,7 +107,6 @@ static inline bool fscrypt_valid_enc_modes(u32 contents_mode,
 /* crypto.c */
 extern struct kmem_cache *fscrypt_info_cachep;
 extern int fscrypt_initialize(unsigned int cop_flags);
-extern struct workqueue_struct *fscrypt_read_workqueue;
 extern int fscrypt_do_page_crypto(const struct inode *inode,
 				  fscrypt_direction_t rw, u64 lblk_num,
 				  struct page *src_page,

fs/ext4/balloc.c

@@ -242,8 +242,6 @@ static int ext4_init_block_bitmap(struct super_block *sb,
 	 */
 	ext4_mark_bitmap_end(num_clusters_in_group(sb, block_group),
 			     sb->s_blocksize * 8, bh->b_data);
-	ext4_block_bitmap_csum_set(sb, block_group, gdp, bh);
-	ext4_group_desc_csum_set(sb, block_group, gdp);
 	return 0;
 }
 
@@ -447,6 +445,7 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
 		err = ext4_init_block_bitmap(sb, bh, block_group, desc);
 		set_bitmap_uptodate(bh);
 		set_buffer_uptodate(bh);
+		set_buffer_verified(bh);
 		ext4_unlock_group(sb, block_group);
 		unlock_buffer(bh);
 		if (err) {

fs/ext4/ialloc.c

@@ -63,44 +63,6 @@ void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap)
 		memset(bitmap + (i >> 3), 0xff, (end_bit - i) >> 3);
 }
 
-/* Initializes an uninitialized inode bitmap */
-static int ext4_init_inode_bitmap(struct super_block *sb,
-				       struct buffer_head *bh,
-				       ext4_group_t block_group,
-				       struct ext4_group_desc *gdp)
-{
-	struct ext4_group_info *grp;
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	J_ASSERT_BH(bh, buffer_locked(bh));
-
-	/* If checksum is bad mark all blocks and inodes use to prevent
-	 * allocation, essentially implementing a per-group read-only flag. */
-	if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
-		grp = ext4_get_group_info(sb, block_group);
-		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
-			percpu_counter_sub(&sbi->s_freeclusters_counter,
-					   grp->bb_free);
-		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
-		if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
-			int count;
-			count = ext4_free_inodes_count(sb, gdp);
-			percpu_counter_sub(&sbi->s_freeinodes_counter,
-					   count);
-		}
-		set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
-		return -EFSBADCRC;
-	}
-
-	memset(bh->b_data, 0, (EXT4_INODES_PER_GROUP(sb) + 7) / 8);
-	ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8,
-			bh->b_data);
-	ext4_inode_bitmap_csum_set(sb, block_group, gdp, bh,
-				   EXT4_INODES_PER_GROUP(sb) / 8);
-	ext4_group_desc_csum_set(sb, block_group, gdp);
-
-	return 0;
-}
-
 void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate)
 {
 	if (uptodate) {
@@ -184,17 +146,14 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 
 	ext4_lock_group(sb, block_group);
 	if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
-		err = ext4_init_inode_bitmap(sb, bh, block_group, desc);
+		memset(bh->b_data, 0, (EXT4_INODES_PER_GROUP(sb) + 7) / 8);
+		ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb),
+				     sb->s_blocksize * 8, bh->b_data);
 		set_bitmap_uptodate(bh);
 		set_buffer_uptodate(bh);
 		set_buffer_verified(bh);
 		ext4_unlock_group(sb, block_group);
 		unlock_buffer(bh);
-		if (err) {
-			ext4_error(sb, "Failed to init inode bitmap for group "
-				   "%u: %d", block_group, err);
-			goto out;
-		}
 		return bh;
 	}
 	ext4_unlock_group(sb, block_group);

fs/ext4/inline.c

@@ -377,7 +377,7 @@ out:
 static int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
 				    unsigned int len)
 {
-	int ret, size;
+	int ret, size, no_expand;
 	struct ext4_inode_info *ei = EXT4_I(inode);
 
 	if (!ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA))
@@ -387,15 +387,14 @@ static int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
 	if (size < len)
 		return -ENOSPC;
 
-	down_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_lock_xattr(inode, &no_expand);
 
 	if (ei->i_inline_off)
 		ret = ext4_update_inline_data(handle, inode, len);
 	else
 		ret = ext4_create_inline_data(handle, inode, len);
 
-	up_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_unlock_xattr(inode, &no_expand);
-
 	return ret;
 }
 
@@ -537,7 +536,7 @@ static int ext4_convert_inline_data_to_extent(struct address_space *mapping,
 					      struct inode *inode,
 					      unsigned flags)
 {
-	int ret, needed_blocks;
+	int ret, needed_blocks, no_expand;
 	handle_t *handle = NULL;
 	int retries = 0, sem_held = 0;
 	struct page *page = NULL;
@@ -577,7 +576,7 @@ retry:
 		goto out;
 	}
 
-	down_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_lock_xattr(inode, &no_expand);
 	sem_held = 1;
 	/* If some one has already done this for us, just exit. */
 	if (!ext4_has_inline_data(inode)) {
@@ -613,7 +612,7 @@ retry:
 		page_cache_release(page);
 		page = NULL;
 		ext4_orphan_add(handle, inode);
-		up_write(&EXT4_I(inode)->xattr_sem);
+		ext4_write_unlock_xattr(inode, &no_expand);
 		sem_held = 0;
 		ext4_journal_stop(handle);
 		handle = NULL;
@@ -639,7 +638,7 @@ out:
 		page_cache_release(page);
 	}
 	if (sem_held)
-		up_write(&EXT4_I(inode)->xattr_sem);
+		ext4_write_unlock_xattr(inode, &no_expand);
 	if (handle)
 		ext4_journal_stop(handle);
 	brelse(iloc.bh);
@@ -732,7 +731,7 @@ convert:
 int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len,
 			       unsigned copied, struct page *page)
 {
-	int ret;
+	int ret, no_expand;
 	void *kaddr;
 	struct ext4_iloc iloc;
 
@@ -750,7 +749,7 @@ int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len,
 		goto out;
 	}
 
-	down_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_lock_xattr(inode, &no_expand);
 	BUG_ON(!ext4_has_inline_data(inode));
 
 	kaddr = kmap_atomic(page);
@@ -760,7 +759,7 @@ int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len,
 	/* clear page dirty so that writepages wouldn't work for us. */
 	ClearPageDirty(page);
 
-	up_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_unlock_xattr(inode, &no_expand);
 	brelse(iloc.bh);
 out:
 	return copied;
@@ -771,7 +770,7 @@ ext4_journalled_write_inline_data(struct inode *inode,
 				  unsigned len,
 				  struct page *page)
 {
-	int ret;
+	int ret, no_expand;
 	void *kaddr;
 	struct ext4_iloc iloc;
 
@@ -781,11 +780,11 @@ ext4_journalled_write_inline_data(struct inode *inode,
 		return NULL;
 	}
 
-	down_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_lock_xattr(inode, &no_expand);
 	kaddr = kmap_atomic(page);
 	ext4_write_inline_data(inode, &iloc, kaddr, 0, len);
 	kunmap_atomic(kaddr);
-	up_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_unlock_xattr(inode, &no_expand);
 
 	return iloc.bh;
 }
@@ -1268,7 +1267,7 @@ out:
 int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname,
 			      struct inode *dir, struct inode *inode)
 {
-	int ret, inline_size;
+	int ret, inline_size, no_expand;
 	void *inline_start;
 	struct ext4_iloc iloc;
 
@@ -1276,7 +1275,7 @@ int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname,
 	if (ret)
 		return ret;
 
-	down_write(&EXT4_I(dir)->xattr_sem);
+	ext4_write_lock_xattr(dir, &no_expand);
 	if (!ext4_has_inline_data(dir))
 		goto out;
 
@@ -1322,7 +1321,7 @@ int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname,
 
 out:
 	ext4_mark_inode_dirty(handle, dir);
-	up_write(&EXT4_I(dir)->xattr_sem);
+	ext4_write_unlock_xattr(dir, &no_expand);
 	brelse(iloc.bh);
 	return ret;
 }
@@ -1682,7 +1681,7 @@ int ext4_delete_inline_entry(handle_t *handle,
 			     struct buffer_head *bh,
 			     int *has_inline_data)
 {
-	int err, inline_size;
+	int err, inline_size, no_expand;
 	struct ext4_iloc iloc;
 	void *inline_start;
 
@@ -1690,7 +1689,7 @@ int ext4_delete_inline_entry(handle_t *handle,
 	if (err)
 		return err;
 
-	down_write(&EXT4_I(dir)->xattr_sem);
+	ext4_write_lock_xattr(dir, &no_expand);
 	if (!ext4_has_inline_data(dir)) {
 		*has_inline_data = 0;
 		goto out;
@@ -1725,7 +1724,7 @@ int ext4_delete_inline_entry(handle_t *handle,
 
 	ext4_show_inline_dir(dir, iloc.bh, inline_start, inline_size);
 out:
-	up_write(&EXT4_I(dir)->xattr_sem);
+	ext4_write_unlock_xattr(dir, &no_expand);
 	brelse(iloc.bh);
 	if (err != -ENOENT)
 		ext4_std_error(dir->i_sb, err);
@@ -1824,11 +1823,11 @@ out:
 
 int ext4_destroy_inline_data(handle_t *handle, struct inode *inode)
 {
-	int ret;
+	int ret, no_expand;
 
-	down_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_lock_xattr(inode, &no_expand);
 	ret = ext4_destroy_inline_data_nolock(handle, inode);
-	up_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_unlock_xattr(inode, &no_expand);
 
 	return ret;
 }
@@ -1913,7 +1912,7 @@ out:
 void ext4_inline_data_truncate(struct inode *inode, int *has_inline)
 {
 	handle_t *handle;
-	int inline_size, value_len, needed_blocks;
+	int inline_size, value_len, needed_blocks, no_expand;
 	size_t i_size;
 	void *value = NULL;
 	struct ext4_xattr_ibody_find is = {
@@ -1930,7 +1929,7 @@ void ext4_inline_data_truncate(struct inode *inode, int *has_inline)
 	if (IS_ERR(handle))
 		return;
 
-	down_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_lock_xattr(inode, &no_expand);
 	if (!ext4_has_inline_data(inode)) {
 		*has_inline = 0;
 		ext4_journal_stop(handle);
@@ -1988,7 +1987,7 @@ out_error:
 	up_write(&EXT4_I(inode)->i_data_sem);
 out:
 	brelse(is.iloc.bh);
-	up_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_unlock_xattr(inode, &no_expand);
 	kfree(value);
 	if (inode->i_nlink)
 		ext4_orphan_del(handle, inode);
@@ -2004,7 +2003,7 @@ out:
 
 int ext4_convert_inline_data(struct inode *inode)
 {
-	int error, needed_blocks;
+	int error, needed_blocks, no_expand;
 	handle_t *handle;
 	struct ext4_iloc iloc;
 
@@ -2026,15 +2025,10 @@ int ext4_convert_inline_data(struct inode *inode)
 		goto out_free;
 	}
 
-	down_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_lock_xattr(inode, &no_expand);
-	if (!ext4_has_inline_data(inode)) {
+	if (ext4_has_inline_data(inode))
-		up_write(&EXT4_I(inode)->xattr_sem);
-		goto out;
-	}
-
 		error = ext4_convert_inline_data_nolock(handle, inode, &iloc);
-	up_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_unlock_xattr(inode, &no_expand);
-out:
 	ext4_journal_stop(handle);
 out_free:
 	brelse(iloc.bh);

fs/ext4/inode.c

@@ -1545,6 +1545,8 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd,
 			BUG_ON(!PageLocked(page));
 			BUG_ON(PageWriteback(page));
 			if (invalidate) {
+				if (page_mapped(page))
+					clear_page_dirty_for_io(page);
 				block_invalidatepage(page, 0, PAGE_CACHE_SIZE);
 				ClearPageUptodate(page);
 			}
@@ -3297,6 +3299,9 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	 * case, we allocate an io_end structure to hook to the iocb.
 	 */
 	iocb->private = NULL;
+	if (overwrite) {
+		get_block_func = ext4_get_block_write_nolock;
+	} else {
 		ext4_inode_aio_set(inode, NULL);
 		if (!is_sync_kiocb(iocb)) {
 			io_end = ext4_init_io_end(inode, GFP_NOFS);
@@ -3305,7 +3310,8 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 				goto retake_lock;
 			}
 			/*
-		 * Grab reference for DIO. Will be dropped in ext4_end_io_dio()
+			 * Grab reference for DIO. Will be dropped in
+			 * ext4_end_io_dio()
 			 */
 			iocb->private = ext4_get_io_end(io_end);
 			/*
@@ -3316,10 +3322,6 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 			 */
 			ext4_inode_aio_set(inode, io_end);
 		}
-
-	if (overwrite) {
-		get_block_func = ext4_get_block_write_nolock;
-	} else {
 		get_block_func = ext4_get_block_write;
 		dio_flags = DIO_LOCKING;
 	}
@@ -4317,6 +4319,12 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 		goto bad_inode;
 	raw_inode = ext4_raw_inode(&iloc);
 
+	if ((ino == EXT4_ROOT_INO) && (raw_inode->i_links_count == 0)) {
+		EXT4_ERROR_INODE(inode, "root inode unallocated");
+		ret = -EFSCORRUPTED;
+		goto bad_inode;
+	}
+
 	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
 		ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize);
 		if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize >

fs/ext4/super.c

@@ -2130,6 +2130,8 @@ static int ext4_check_descriptors(struct super_block *sb,
 			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
 				 "Block bitmap for group %u overlaps "
 				 "superblock", i);
+			if (!(sb->s_flags & MS_RDONLY))
+				return 0;
 		}
 		if (block_bitmap < first_block || block_bitmap > last_block) {
 			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
@@ -2142,6 +2144,8 @@ static int ext4_check_descriptors(struct super_block *sb,
 			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
 				 "Inode bitmap for group %u overlaps "
 				 "superblock", i);
+			if (!(sb->s_flags & MS_RDONLY))
+				return 0;
 		}
 		if (inode_bitmap < first_block || inode_bitmap > last_block) {
 			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
@@ -2154,6 +2158,8 @@ static int ext4_check_descriptors(struct super_block *sb,
 			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
 				 "Inode table for group %u overlaps "
 				 "superblock", i);
+			if (!(sb->s_flags & MS_RDONLY))
+				return 0;
 		}
 		if (inode_table < first_block ||
 		    inode_table + sbi->s_itb_per_group - 1 > last_block) {

fs/ext4/xattr.c

@@ -1143,16 +1143,14 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 	struct ext4_xattr_block_find bs = {
 		.s = { .not_found = -ENODATA, },
 	};
-	unsigned long no_expand;
+	int no_expand;
 	int error;
 
 	if (!name)
 		return -EINVAL;
 	if (strlen(name) > 255)
 		return -ERANGE;
-	down_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_lock_xattr(inode, &no_expand);
-	no_expand = ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND);
-	ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
 
 	error = ext4_reserve_inode_write(handle, inode, &is.iloc);
 	if (error)
@@ -1213,7 +1211,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 		ext4_xattr_update_super_block(handle, inode->i_sb);
 		inode->i_ctime = ext4_current_time(inode);
 		if (!value)
-			ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
+			no_expand = 0;
 		error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
 		/*
 		 * The bh is consumed by ext4_mark_iloc_dirty, even with
@@ -1227,9 +1225,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 cleanup:
 	brelse(is.iloc.bh);
 	brelse(bs.bh);
-	if (no_expand == 0)
+	ext4_write_unlock_xattr(inode, &no_expand);
-		ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
-	up_write(&EXT4_I(inode)->xattr_sem);
 	return error;
 }
 
@@ -1313,12 +1309,11 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
 	int error = 0, tried_min_extra_isize = 0;
 	int s_min_extra_isize = le16_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize);
 	int isize_diff;	/* How much do we need to grow i_extra_isize */
+	int no_expand;
+
+	if (ext4_write_trylock_xattr(inode, &no_expand) == 0)
+		return 0;
 
-	down_write(&EXT4_I(inode)->xattr_sem);
-	/*
-	 * Set EXT4_STATE_NO_EXPAND to avoid recursion when marking inode dirty
-	 */
-	ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
 retry:
 	isize_diff = new_extra_isize - EXT4_I(inode)->i_extra_isize;
 	if (EXT4_I(inode)->i_extra_isize >= new_extra_isize)
@@ -1512,8 +1507,7 @@ retry:
 	}
 	brelse(bh);
 out:
-	ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
+	ext4_write_unlock_xattr(inode, &no_expand);
-	up_write(&EXT4_I(inode)->xattr_sem);
 	return 0;
 
 cleanup:
@@ -1525,10 +1519,10 @@ cleanup:
 	kfree(bs);
 	brelse(bh);
 	/*
-	 * We deliberately leave EXT4_STATE_NO_EXPAND set here since inode
+	 * Inode size expansion failed; don't try again
-	 * size expansion failed.
 	 */
-	up_write(&EXT4_I(inode)->xattr_sem);
+	no_expand = 1;
+	ext4_write_unlock_xattr(inode, &no_expand);
 	return error;
 }
 

fs/ext4/xattr.h

@@ -101,6 +101,38 @@ extern const struct xattr_handler ext4_xattr_security_handler;
 
 #define EXT4_XATTR_NAME_ENCRYPTION_CONTEXT "c"
 
+/*
+ * The EXT4_STATE_NO_EXPAND is overloaded and used for two purposes.
+ * The first is to signal that there the inline xattrs and data are
+ * taking up so much space that we might as well not keep trying to
+ * expand it.  The second is that xattr_sem is taken for writing, so
+ * we shouldn't try to recurse into the inode expansion.  For this
+ * second case, we need to make sure that we take save and restore the
+ * NO_EXPAND state flag appropriately.
+ */
+static inline void ext4_write_lock_xattr(struct inode *inode, int *save)
+{
+	down_write(&EXT4_I(inode)->xattr_sem);
+	*save = ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND);
+	ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
+}
+
+static inline int ext4_write_trylock_xattr(struct inode *inode, int *save)
+{
+	if (down_write_trylock(&EXT4_I(inode)->xattr_sem) == 0)
+		return 0;
+	*save = ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND);
+	ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
+	return 1;
+}
+
+static inline void ext4_write_unlock_xattr(struct inode *inode, int *save)
+{
+	if (*save == 0)
+		ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
+	up_write(&EXT4_I(inode)->xattr_sem);
+}
+
 extern ssize_t ext4_listxattr(struct dentry *, char *, size_t);
 
 extern int ext4_xattr_get(struct inode *, int, const char *, void *, size_t);

fs/f2fs/checkpoint.c

@@ -386,7 +386,7 @@ static int f2fs_set_meta_page_dirty(struct page *page)
 	if (!PageUptodate(page))
 		SetPageUptodate(page);
 	if (!PageDirty(page)) {
-		f2fs_set_page_dirty_nobuffers(page);
+		__set_page_dirty_nobuffers(page);
 		inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META);
 		SetPagePrivate(page);
 		f2fs_trace_pid(page);

fs/f2fs/data.c

@@ -19,8 +19,6 @@
 #include <linux/bio.h>
 #include <linux/prefetch.h>
 #include <linux/uio.h>
-#include <linux/mm.h>
-#include <linux/memcontrol.h>
 #include <linux/cleancache.h>
 
 #include "f2fs.h"
@@ -30,6 +28,11 @@
 #include <trace/events/f2fs.h>
 #include <trace/events/android_fs.h>
 
+#define NUM_PREALLOC_POST_READ_CTXS	128
+
+static struct kmem_cache *bio_post_read_ctx_cache;
+static mempool_t *bio_post_read_ctx_pool;
+
 static bool __is_cp_guaranteed(struct page *page)
 {
 	struct address_space *mapping = page->mapping;
@@ -50,11 +53,77 @@ static bool __is_cp_guaranteed(struct page *page)
 	return false;
 }
 
-static void f2fs_read_end_io(struct bio *bio)
+/* postprocessing steps for read bios */
+enum bio_post_read_step {
+	STEP_INITIAL = 0,
+	STEP_DECRYPT,
+};
+
+struct bio_post_read_ctx {
+	struct bio *bio;
+	struct work_struct work;
+	unsigned int cur_step;
+	unsigned int enabled_steps;
+};
+
+static void __read_end_io(struct bio *bio)
 {
-	struct bio_vec *bvec;
+	struct page *page;
+	struct bio_vec *bv;
 	int i;
 
+	bio_for_each_segment_all(bv, bio, i) {
+		page = bv->bv_page;
+
+		/* PG_error was set if any post_read step failed */
+		if (bio->bi_error || PageError(page)) {
+			ClearPageUptodate(page);
+			SetPageError(page);
+		} else {
+			SetPageUptodate(page);
+		}
+		unlock_page(page);
+	}
+	if (bio->bi_private)
+		mempool_free(bio->bi_private, bio_post_read_ctx_pool);
+	bio_put(bio);
+}
+
+static void bio_post_read_processing(struct bio_post_read_ctx *ctx);
+
+static void decrypt_work(struct work_struct *work)
+{
+	struct bio_post_read_ctx *ctx =
+		container_of(work, struct bio_post_read_ctx, work);
+
+	fscrypt_decrypt_bio(ctx->bio);
+
+	bio_post_read_processing(ctx);
+}
+
+static void bio_post_read_processing(struct bio_post_read_ctx *ctx)
+{
+	switch (++ctx->cur_step) {
+	case STEP_DECRYPT:
+		if (ctx->enabled_steps & (1 << STEP_DECRYPT)) {
+			INIT_WORK(&ctx->work, decrypt_work);
+			fscrypt_enqueue_decrypt_work(&ctx->work);
+			return;
+		}
+		ctx->cur_step++;
+		/* fall-through */
+	default:
+		__read_end_io(ctx->bio);
+	}
+}
+
+static bool f2fs_bio_post_read_required(struct bio *bio)
+{
+	return bio->bi_private && !bio->bi_error;
+}
+
+static void f2fs_read_end_io(struct bio *bio)
+{
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 	if (time_to_inject(F2FS_P_SB(bio->bi_io_vec->bv_page), FAULT_IO)) {
 		f2fs_show_injection_info(FAULT_IO);
@@ -62,28 +131,15 @@ static void f2fs_read_end_io(struct bio *bio)
 	}
 #endif
 
-	if (f2fs_bio_encrypted(bio)) {
+	if (f2fs_bio_post_read_required(bio)) {
-		if (bio->bi_error) {
+		struct bio_post_read_ctx *ctx = bio->bi_private;
-			fscrypt_release_ctx(bio->bi_private);
+
-		} else {
+		ctx->cur_step = STEP_INITIAL;
-			fscrypt_decrypt_bio_pages(bio->bi_private, bio);
+		bio_post_read_processing(ctx);
 		return;
 	}
-	}
 
-	bio_for_each_segment_all(bvec, bio, i) {
+	__read_end_io(bio);
-		struct page *page = bvec->bv_page;
-
-		if (!bio->bi_error) {
-			if (!PageUptodate(page))
-				SetPageUptodate(page);
-		} else {
-			ClearPageUptodate(page);
-			SetPageError(page);
-		}
-		unlock_page(page);
-	}
-	bio_put(bio);
 }
 
 static void f2fs_write_end_io(struct bio *bio)
@@ -480,29 +536,33 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
 							 unsigned nr_pages)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct fscrypt_ctx *ctx = NULL;
 	struct bio *bio;
+	struct bio_post_read_ctx *ctx;
+	unsigned int post_read_steps = 0;
 
-	if (f2fs_encrypted_file(inode)) {
+	bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES), false);
-		ctx = fscrypt_get_ctx(inode, GFP_NOFS);
+	if (!bio)
-		if (IS_ERR(ctx))
+		return ERR_PTR(-ENOMEM);
-			return ERR_CAST(ctx);
+	f2fs_target_device(sbi, blkaddr, bio);
+	bio->bi_end_io = f2fs_read_end_io;
+	bio_set_op_attrs(bio, REQ_OP_READ, 0);
+
+	if (f2fs_encrypted_file(inode))
+		post_read_steps |= 1 << STEP_DECRYPT;
+	if (post_read_steps) {
+		ctx = mempool_alloc(bio_post_read_ctx_pool, GFP_NOFS);
+		if (!ctx) {
+			bio_put(bio);
+			return ERR_PTR(-ENOMEM);
+		}
+		ctx->bio = bio;
+		ctx->enabled_steps = post_read_steps;
+		bio->bi_private = ctx;
 
 		/* wait the page to be moved by cleaning */
 		f2fs_wait_on_block_writeback(sbi, blkaddr);
 	}
 
-	bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES), false);
-	if (!bio) {
-		if (ctx)
-			fscrypt_release_ctx(ctx);
-		return ERR_PTR(-ENOMEM);
-	}
-	f2fs_target_device(sbi, blkaddr, bio);
-	bio->bi_end_io = f2fs_read_end_io;
-	bio->bi_private = ctx;
-	bio_set_op_attrs(bio, REQ_OP_READ, 0);
-
 	return bio;
 }
 
@@ -1523,7 +1583,7 @@ static int encrypt_one_page(struct f2fs_io_info *fio)
 	if (!f2fs_encrypted_file(inode))
 		return 0;
 
-	/* wait for GCed encrypted page writeback */
+	/* wait for GCed page writeback via META_MAPPING */
 	f2fs_wait_on_block_writeback(fio->sbi, fio->old_blkaddr);
 
 retry_encrypt:
@@ -1673,6 +1733,7 @@ got_it:
 			goto out_writepage;
 
 		set_page_writeback(page);
+		ClearPageError(page);
 		f2fs_put_dnode(&dn);
 		if (fio->need_lock == LOCK_REQ)
 			f2fs_unlock_op(fio->sbi);
@@ -1695,6 +1756,7 @@ got_it:
 		goto out_writepage;
 
 	set_page_writeback(page);
+	ClearPageError(page);
 
 	/* LFS mode write path */
 	write_data_page(&dn, fio);
@@ -2235,8 +2297,8 @@ repeat:
 
 	f2fs_wait_on_page_writeback(page, DATA, false);
 
-	/* wait for GCed encrypted page writeback */
+	/* wait for GCed page writeback via META_MAPPING */
-	if (f2fs_encrypted_file(inode))
+	if (f2fs_post_read_required(inode))
 		f2fs_wait_on_block_writeback(sbi, blkaddr);
 
 	if (len == PAGE_SIZE || PageUptodate(page))
@@ -2449,37 +2511,6 @@ int f2fs_release_page(struct page *page, gfp_t wait)
 	return 1;
 }
 
-/*
- * This was copied from __set_page_dirty_buffers which gives higher performance
- * in very high speed storages. (e.g., pmem)
- */
-void f2fs_set_page_dirty_nobuffers(struct page *page)
-{
-	struct address_space *mapping = page->mapping;
-	struct mem_cgroup *memcg;
-	unsigned long flags;
-
-	if (unlikely(!mapping))
-		return;
-
-	spin_lock(&mapping->private_lock);
-	memcg = mem_cgroup_begin_page_stat(page);
-	SetPageDirty(page);
-	spin_unlock(&mapping->private_lock);
-
-	spin_lock_irqsave(&mapping->tree_lock, flags);
-	WARN_ON_ONCE(!PageUptodate(page));
-	account_page_dirtied(page, mapping, memcg);
-	radix_tree_tag_set(&mapping->page_tree,
-			page_index(page), PAGECACHE_TAG_DIRTY);
-	spin_unlock_irqrestore(&mapping->tree_lock, flags);
-
-	mem_cgroup_end_page_stat(memcg);
-
-	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
-	return;
-}
-
 static int f2fs_set_data_page_dirty(struct page *page)
 {
 	struct address_space *mapping = page->mapping;
@@ -2503,7 +2534,7 @@ static int f2fs_set_data_page_dirty(struct page *page)
 	}
 
 	if (!PageDirty(page)) {
-		f2fs_set_page_dirty_nobuffers(page);
+		__set_page_dirty_nobuffers(page);
 		update_dirty_page(inode, page);
 		return 1;
 	}
@@ -2596,3 +2627,27 @@ const struct address_space_operations f2fs_dblock_aops = {
 	.migratepage    = f2fs_migrate_page,
 #endif
 };
+
+int __init f2fs_init_post_read_processing(void)
+{
+	bio_post_read_ctx_cache = KMEM_CACHE(bio_post_read_ctx, 0);
+	if (!bio_post_read_ctx_cache)
+		goto fail;
+	bio_post_read_ctx_pool =
+		mempool_create_slab_pool(NUM_PREALLOC_POST_READ_CTXS,
+					 bio_post_read_ctx_cache);
+	if (!bio_post_read_ctx_pool)
+		goto fail_free_cache;
+	return 0;
+
+fail_free_cache:
+	kmem_cache_destroy(bio_post_read_ctx_cache);
+fail:
+	return -ENOMEM;
+}
+
+void __exit f2fs_destroy_post_read_processing(void)
+{
+	mempool_destroy(bio_post_read_ctx_pool);
+	kmem_cache_destroy(bio_post_read_ctx_cache);
+}

fs/f2fs/f2fs.h

@@ -1673,7 +1673,7 @@ static inline bool f2fs_has_xattr_block(unsigned int ofs)
 }
 
 static inline bool __allow_reserved_blocks(struct f2fs_sb_info *sbi,
-					struct inode *inode)
+					struct inode *inode, bool cap)
 {
 	if (!inode)
 		return true;
@@ -1686,7 +1686,7 @@ static inline bool __allow_reserved_blocks(struct f2fs_sb_info *sbi,
 	if (!gid_eq(F2FS_OPTION(sbi).s_resgid, GLOBAL_ROOT_GID) &&
 					in_group_p(F2FS_OPTION(sbi).s_resgid))
 		return true;
-	if (capable(CAP_SYS_RESOURCE))
+	if (cap && capable(CAP_SYS_RESOURCE))
 		return true;
 	return false;
 }
@@ -1721,7 +1721,7 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi,
 	avail_user_block_count = sbi->user_block_count -
 					sbi->current_reserved_blocks;
 
-	if (!__allow_reserved_blocks(sbi, inode))
+	if (!__allow_reserved_blocks(sbi, inode, true))
 		avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks;
 
 	if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) {
@@ -1928,7 +1928,7 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi,
 	valid_block_count = sbi->total_valid_block_count +
 					sbi->current_reserved_blocks + 1;
 
-	if (!__allow_reserved_blocks(sbi, inode))
+	if (!__allow_reserved_blocks(sbi, inode, false))
 		valid_block_count += F2FS_OPTION(sbi).root_reserved_blocks;
 
 	if (unlikely(valid_block_count > sbi->user_block_count)) {
@@ -2937,6 +2937,8 @@ void destroy_checkpoint_caches(void);
 /*
  * data.c
  */
+int f2fs_init_post_read_processing(void);
+void f2fs_destroy_post_read_processing(void);
 void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type);
 void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
 				struct inode *inode, nid_t ino, pgoff_t idx,
@@ -2968,7 +2970,6 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			u64 start, u64 len);
 bool should_update_inplace(struct inode *inode, struct f2fs_io_info *fio);
 bool should_update_outplace(struct inode *inode, struct f2fs_io_info *fio);
-void f2fs_set_page_dirty_nobuffers(struct page *page);
 int __f2fs_write_data_pages(struct address_space *mapping,
 						struct writeback_control *wbc,
 						enum iostat_type io_type);
@@ -3297,9 +3298,13 @@ static inline void f2fs_set_encrypted_inode(struct inode *inode)
 #endif
 }
 
-static inline bool f2fs_bio_encrypted(struct bio *bio)
+/*
+ * Returns true if the reads of the inode's data need to undergo some
+ * postprocessing step, like decryption or authenticity verification.
+ */
+static inline bool f2fs_post_read_required(struct inode *inode)
 {
-	return bio->bi_private != NULL;
+	return f2fs_encrypted_file(inode);
 }
 
 #define F2FS_FEATURE_FUNCS(name, flagname) \
@@ -3367,7 +3372,7 @@ static inline bool f2fs_may_encrypt(struct inode *inode)
 
 static inline bool f2fs_force_buffered_io(struct inode *inode, int rw)
 {
-	return (f2fs_encrypted_file(inode) ||
+	return (f2fs_post_read_required(inode) ||
 			(rw == WRITE && test_opt(F2FS_I_SB(inode), LFS)) ||
 			F2FS_I_SB(inode)->s_ndevs);
 }

fs/f2fs/file.c

@@ -113,8 +113,8 @@ mapped:
 	/* fill the page */
 	f2fs_wait_on_page_writeback(page, DATA, false);
 
-	/* wait for GCed encrypted page writeback */
+	/* wait for GCed page writeback via META_MAPPING */
-	if (f2fs_encrypted_file(inode))
+	if (f2fs_post_read_required(inode))
 		f2fs_wait_on_block_writeback(sbi, dn.data_blkaddr);
 
 out_sem:

fs/f2fs/gc.c

@@ -850,8 +850,8 @@ next_step:
 			if (IS_ERR(inode) || is_bad_inode(inode))
 				continue;
 
-			/* if encrypted inode, let's go phase 3 */
+			/* if inode uses special I/O path, let's go phase 3 */
-			if (f2fs_encrypted_file(inode)) {
+			if (f2fs_post_read_required(inode)) {
 				add_gc_inode(gc_list, inode);
 				continue;
 			}
@@ -899,7 +899,7 @@ next_step:
 
 			start_bidx = start_bidx_of_node(nofs, inode)
 								+ ofs_in_node;
-			if (f2fs_encrypted_file(inode))
+			if (f2fs_post_read_required(inode))
 				move_data_block(inode, start_bidx, segno, off);
 			else
 				move_data_page(inode, start_bidx, gc_type,

fs/f2fs/inline.c

@@ -26,7 +26,7 @@ bool f2fs_may_inline_data(struct inode *inode)
 	if (i_size_read(inode) > MAX_INLINE_DATA(inode))
 		return false;
 
-	if (f2fs_encrypted_file(inode))
+	if (f2fs_post_read_required(inode))
 		return false;
 
 	return true;

fs/f2fs/namei.c

@@ -294,8 +294,8 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 
 	alloc_nid_done(sbi, ino);
 
-	d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
+	d_instantiate(dentry, inode);
 
 	if (IS_DIRSYNC(dir))
 		f2fs_sync_fs(sbi->sb, 1);
@@ -594,8 +594,8 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 	err = page_symlink(inode, disk_link.name, disk_link.len);
 
 err_out:
-	d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
+	d_instantiate(dentry, inode);
 
 	/*
 	 * Let's flush symlink data in order to avoid broken symlink as much as
@@ -658,8 +658,8 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 	alloc_nid_done(sbi, inode->i_ino);
 
-	d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
+	d_instantiate(dentry, inode);
 
 	if (IS_DIRSYNC(dir))
 		f2fs_sync_fs(sbi->sb, 1);
@@ -710,8 +710,8 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
 
 	alloc_nid_done(sbi, inode->i_ino);
 
-	d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
+	d_instantiate(dentry, inode);
 
 	if (IS_DIRSYNC(dir))
 		f2fs_sync_fs(sbi->sb, 1);

fs/f2fs/node.c

@@ -1775,7 +1775,7 @@ static int f2fs_set_node_page_dirty(struct page *page)
 	if (!PageUptodate(page))
 		SetPageUptodate(page);
 	if (!PageDirty(page)) {
-		f2fs_set_page_dirty_nobuffers(page);
+		__set_page_dirty_nobuffers(page);
 		inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES);
 		SetPagePrivate(page);
 		f2fs_trace_pid(page);

fs/f2fs/super.c

@@ -3100,8 +3100,13 @@ static int __init init_f2fs_fs(void)
 	err = f2fs_create_root_stats();
 	if (err)
 		goto free_filesystem;
+	err = f2fs_init_post_read_processing();
+	if (err)
+		goto free_root_stats;
 	return 0;
 
+free_root_stats:
+	f2fs_destroy_root_stats();
 free_filesystem:
 	unregister_filesystem(&f2fs_fs_type);
 free_shrinker:
@@ -3124,6 +3129,7 @@ fail:
 
 static void __exit exit_f2fs_fs(void)
 {
+	f2fs_destroy_post_read_processing();
 	f2fs_destroy_root_stats();
 	unregister_filesystem(&f2fs_fs_type);
 	unregister_shrinker(&f2fs_shrinker_info);

fs/fs-writeback.c

@@ -747,11 +747,12 @@ int inode_congested(struct inode *inode, int cong_bits)
 	 */
 	if (inode && inode_to_wb_is_valid(inode)) {
 		struct bdi_writeback *wb;
-		bool locked, congested;
+		struct wb_lock_cookie lock_cookie = {};
+		bool congested;
 
-		wb = unlocked_inode_to_wb_begin(inode, &locked);
+		wb = unlocked_inode_to_wb_begin(inode, &lock_cookie);
 		congested = wb_congested(wb, cong_bits);
-		unlocked_inode_to_wb_end(inode, locked);
+		unlocked_inode_to_wb_end(inode, &lock_cookie);
 		return congested;
 	}
 

fs/jbd2/journal.c

@@ -914,7 +914,7 @@ out:
 }
 
 /*
- * This is a variaon of __jbd2_update_log_tail which checks for validity of
+ * This is a variation of __jbd2_update_log_tail which checks for validity of
  * provided log tail and locks j_checkpoint_mutex. So it is safe against races
  * with other threads updating log tail.
  */
@@ -1384,6 +1384,9 @@ int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid,
 	journal_superblock_t *sb = journal->j_superblock;
 	int ret;
 
+	if (is_journal_aborted(journal))
+		return -EIO;
+
 	BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
 	jbd_debug(1, "JBD2: updating superblock (start %lu, seq %u)\n",
 		  tail_block, tail_tid);

fs/jffs2/super.c

@@ -345,7 +345,7 @@ static void jffs2_put_super (struct super_block *sb)
 static void jffs2_kill_sb(struct super_block *sb)
 {
 	struct jffs2_sb_info *c = JFFS2_SB_INFO(sb);
-	if (!(sb->s_flags & MS_RDONLY))
+	if (c && !(sb->s_flags & MS_RDONLY))
 		jffs2_stop_garbage_collect_thread(c);
 	kill_mtd_super(sb);
 	kfree(c);

fs/namei.c

@@ -219,9 +219,10 @@ getname_kernel(const char * filename)
 	if (len <= EMBEDDED_NAME_MAX) {
 		result->name = (char *)result->iname;
 	} else if (len <= PATH_MAX) {
+		const size_t size = offsetof(struct filename, iname[1]);
 		struct filename *tmp;
 
-		tmp = kmalloc(sizeof(*tmp), GFP_KERNEL);
+		tmp = kmalloc(size, GFP_KERNEL);
 		if (unlikely(!tmp)) {
 			__putname(result);
 			return ERR_PTR(-ENOMEM);

fs/namespace.c

@@ -1036,7 +1036,8 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 			goto out_free;
 	}
 
-	mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~(MNT_WRITE_HOLD|MNT_MARKED);
+	mnt->mnt.mnt_flags = old->mnt.mnt_flags;
+	mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL);
 	/* Don't allow unprivileged users to change mount flags */
 	if (flag & CL_UNPRIVILEGED) {
 		mnt->mnt.mnt_flags |= MNT_LOCK_ATIME;

fs/notify/fanotify/fanotify.c

@@ -92,7 +92,7 @@ static bool fanotify_should_send_event(struct fsnotify_mark *inode_mark,
 				       u32 event_mask,
 				       void *data, int data_type)
 {
-	__u32 marks_mask, marks_ignored_mask;
+	__u32 marks_mask = 0, marks_ignored_mask = 0;
 	struct path *path = data;
 
 	pr_debug("%s: inode_mark=%p vfsmnt_mark=%p mask=%x data=%p"
@@ -108,24 +108,20 @@ static bool fanotify_should_send_event(struct fsnotify_mark *inode_mark,
 	    !d_can_lookup(path->dentry))
 		return false;
 
-	if (inode_mark && vfsmnt_mark) {
-		marks_mask = (vfsmnt_mark->mask | inode_mark->mask);
-		marks_ignored_mask = (vfsmnt_mark->ignored_mask | inode_mark->ignored_mask);
-	} else if (inode_mark) {
 	/*
 	 * if the event is for a child and this inode doesn't care about
 	 * events on the child, don't send it!
 	 */
-		if ((event_mask & FS_EVENT_ON_CHILD) &&
+	if (inode_mark &&
-		    !(inode_mark->mask & FS_EVENT_ON_CHILD))
+	    (!(event_mask & FS_EVENT_ON_CHILD) ||
-			return false;
+	     (inode_mark->mask & FS_EVENT_ON_CHILD))) {
-		marks_mask = inode_mark->mask;
+		marks_mask |= inode_mark->mask;
-		marks_ignored_mask = inode_mark->ignored_mask;
+		marks_ignored_mask |= inode_mark->ignored_mask;
-	} else if (vfsmnt_mark) {
+	}
-		marks_mask = vfsmnt_mark->mask;
+
-		marks_ignored_mask = vfsmnt_mark->ignored_mask;
+	if (vfsmnt_mark) {
-	} else {
+		marks_mask |= vfsmnt_mark->mask;
-		BUG();
+		marks_ignored_mask |= vfsmnt_mark->ignored_mask;
 	}
 
 	if (d_is_dir(path->dentry) &&

fs/reiserfs/journal.c

@@ -2643,7 +2643,7 @@ static int journal_init_dev(struct super_block *super,
 	if (IS_ERR(journal->j_dev_bd)) {
 		result = PTR_ERR(journal->j_dev_bd);
 		journal->j_dev_bd = NULL;
-		reiserfs_warning(super,
+		reiserfs_warning(super, "sh-457",
 				 "journal_init_dev: Cannot open '%s': %i",
 				 jdev_name, result);
 		return result;

fs/ubifs/super.c

@@ -1728,8 +1728,11 @@ static void ubifs_remount_ro(struct ubifs_info *c)
 
 	dbg_save_space_info(c);
 
-	for (i = 0; i < c->jhead_cnt; i++)
+	for (i = 0; i < c->jhead_cnt; i++) {
-		ubifs_wbuf_sync(&c->jheads[i].wbuf);
+		err = ubifs_wbuf_sync(&c->jheads[i].wbuf);
+		if (err)
+			ubifs_ro_mode(c, err);
+	}
 
 	c->mst_node->flags &= ~cpu_to_le32(UBIFS_MST_DIRTY);
 	c->mst_node->flags |= cpu_to_le32(UBIFS_MST_NO_ORPHS);
@@ -1795,8 +1798,11 @@ static void ubifs_put_super(struct super_block *sb)
 			int err;
 
 			/* Synchronize write-buffers */
-			for (i = 0; i < c->jhead_cnt; i++)
+			for (i = 0; i < c->jhead_cnt; i++) {
-				ubifs_wbuf_sync(&c->jheads[i].wbuf);
+				err = ubifs_wbuf_sync(&c->jheads[i].wbuf);
+				if (err)
+					ubifs_ro_mode(c, err);
+			}
 
 			/*
 			 * We are being cleanly unmounted which means the

include/linux/backing-dev-defs.h

@@ -193,6 +193,11 @@ static inline void set_bdi_congested(struct backing_dev_info *bdi, int sync)
 	set_wb_congested(bdi->wb.congested, sync);
 }
 
+struct wb_lock_cookie {
+	bool locked;
+	unsigned long flags;
+};
+
 #ifdef CONFIG_CGROUP_WRITEBACK
 
 /**

include/linux/backing-dev.h

@@ -374,7 +374,7 @@ static inline struct bdi_writeback *inode_to_wb(struct inode *inode)
 /**
  * unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction
  * @inode: target inode
- * @lockedp: temp bool output param, to be passed to the end function
+ * @cookie: output param, to be passed to the end function
  *
  * The caller wants to access the wb associated with @inode but isn't
  * holding inode->i_lock, mapping->tree_lock or wb->list_lock.  This
@@ -382,12 +382,12 @@ static inline struct bdi_writeback *inode_to_wb(struct inode *inode)
  * association doesn't change until the transaction is finished with
  * unlocked_inode_to_wb_end().
  *
- * The caller must call unlocked_inode_to_wb_end() with *@lockdep
+ * The caller must call unlocked_inode_to_wb_end() with *@cookie afterwards and
- * afterwards and can't sleep during transaction.  IRQ may or may not be
+ * can't sleep during the transaction.  IRQs may or may not be disabled on
- * disabled on return.
+ * return.
  */
 static inline struct bdi_writeback *
-unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
+unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie)
 {
 	rcu_read_lock();
 
@@ -395,10 +395,10 @@ unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
 	 * Paired with store_release in inode_switch_wb_work_fn() and
 	 * ensures that we see the new wb if we see cleared I_WB_SWITCH.
 	 */
-	*lockedp = smp_load_acquire(&inode->i_state) & I_WB_SWITCH;
+	cookie->locked = smp_load_acquire(&inode->i_state) & I_WB_SWITCH;
 
-	if (unlikely(*lockedp))
+	if (unlikely(cookie->locked))
-		spin_lock_irq(&inode->i_mapping->tree_lock);
+		spin_lock_irqsave(&inode->i_mapping->tree_lock, cookie->flags);
 
 	/*
 	 * Protected by either !I_WB_SWITCH + rcu_read_lock() or tree_lock.
@@ -410,12 +410,14 @@ unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
 /**
  * unlocked_inode_to_wb_end - end inode wb access transaction
  * @inode: target inode
- * @locked: *@lockedp from unlocked_inode_to_wb_begin()
+ * @cookie: @cookie from unlocked_inode_to_wb_begin()
  */
-static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked)
+static inline void unlocked_inode_to_wb_end(struct inode *inode,
+					    struct wb_lock_cookie *cookie)
 {
-	if (unlikely(locked))
+	if (unlikely(cookie->locked))
-		spin_unlock_irq(&inode->i_mapping->tree_lock);
+		spin_unlock_irqrestore(&inode->i_mapping->tree_lock,
+				       cookie->flags);
 
 	rcu_read_unlock();
 }
@@ -462,12 +464,13 @@ static inline struct bdi_writeback *inode_to_wb(struct inode *inode)
 }
 
 static inline struct bdi_writeback *
-unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
+unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie)
 {
 	return inode_to_wb(inode);
 }
 
-static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked)
+static inline void unlocked_inode_to_wb_end(struct inode *inode,
+					    struct wb_lock_cookie *cookie)
 {
 }
 

include/linux/fscrypt_notsupp.h

@@ -24,6 +24,10 @@ static inline bool fscrypt_dummy_context_enabled(struct inode *inode)
 }
 
 /* crypto.c */
+static inline void fscrypt_enqueue_decrypt_work(struct work_struct *work)
+{
+}
+
 static inline struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *inode,
 						  gfp_t gfp_flags)
 {
@@ -160,10 +164,13 @@ static inline bool fscrypt_match_name(const struct fscrypt_name *fname,
 }
 
 /* bio.c */
-static inline void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *ctx,
+static inline void fscrypt_decrypt_bio(struct bio *bio)
+{
+}
+
+static inline void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx,
 					       struct bio *bio)
 {
-	return;
 }
 
 static inline void fscrypt_pullback_bio_page(struct page **page, bool restore)

include/linux/fscrypt_supp.h

@@ -58,6 +58,7 @@ static inline bool fscrypt_dummy_context_enabled(struct inode *inode)
 }
 
 /* crypto.c */
+extern void fscrypt_enqueue_decrypt_work(struct work_struct *);
 extern struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *, gfp_t);
 extern void fscrypt_release_ctx(struct fscrypt_ctx *);
 extern struct page *fscrypt_encrypt_page(const struct inode *, struct page *,
@@ -187,7 +188,9 @@ static inline bool fscrypt_match_name(const struct fscrypt_name *fname,
 }
 
 /* bio.c */
-extern void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *, struct bio *);
+extern void fscrypt_decrypt_bio(struct bio *);
+extern void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx,
+					struct bio *bio);
 extern void fscrypt_pullback_bio_page(struct page **, bool);
 extern int fscrypt_zeroout_range(const struct inode *, pgoff_t, sector_t,
 				 unsigned int);

include/linux/hid.h

@@ -793,7 +793,7 @@ extern int hidinput_connect(struct hid_device *hid, unsigned int force);
 extern void hidinput_disconnect(struct hid_device *);
 
 int hid_set_field(struct hid_field *, unsigned, __s32);
-int hid_input_report(struct hid_device *, int type, u8 *, int, int);
+int hid_input_report(struct hid_device *, int type, u8 *, u32, int);
 int hidinput_find_field(struct hid_device *hid, unsigned int type, unsigned int code, struct hid_field **field);
 struct hid_field *hidinput_get_led_field(struct hid_device *hid);
 unsigned int hidinput_count_leds(struct hid_device *hid);
@@ -1098,13 +1098,13 @@ static inline void hid_hw_wait(struct hid_device *hdev)
  *
  * @report: the report we want to know the length
  */
-static inline int hid_report_len(struct hid_report *report)
+static inline u32 hid_report_len(struct hid_report *report)
 {
 	/* equivalent to DIV_ROUND_UP(report->size, 8) + !!(report->id > 0) */
 	return ((report->size - 1) >> 3) + 1 + (report->id > 0);
 }
 
-int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, int size,
+int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size,
 		int interrupt);
 
 /* HID quirks API */

include/linux/mm.h

@@ -241,10 +241,14 @@ extern pgprot_t protection_map[16];
  * ->fault function. The vma's ->fault is responsible for returning a bitmask
  * of VM_FAULT_xxx flags that give details about how the fault was handled.
  *
+ * MM layer fills up gfp_mask for page allocations but fault handler might
+ * alter it if its implementation requires a different allocation context.
+ *
  * pgoff should be used in favour of virtual_address, if possible.
  */
 struct vm_fault {
 	unsigned int flags;		/* FAULT_FLAG_xxx flags */
+	gfp_t gfp_mask;			/* gfp mask to be used for allocations */
 	pgoff_t pgoff;			/* Logical page offset based on vma */
 	void __user *virtual_address;	/* Faulting virtual address */
 

include/linux/tty.h

@@ -342,6 +342,7 @@ struct tty_file_private {
 #define TTY_PTY_LOCK 		16	/* pty private */
 #define TTY_NO_WRITE_SPLIT 	17	/* Preserve write boundaries to driver */
 #define TTY_HUPPED 		18	/* Post driver->hangup() */
+#define TTY_HUPPING		19	/* Hangup in progress */
 #define TTY_LDISC_HALTED	22	/* Line discipline is halted */
 
 #define TTY_WRITE_FLUSH(tty) tty_write_flush((tty))

include/net/slhc_vj.h

@@ -127,6 +127,7 @@ typedef __u32 int32;
  */
 struct cstate {
 	byte_t	cs_this;	/* connection id number (xmit) */
+	bool	initialized;	/* true if initialized */
 	struct cstate *next;	/* next in ring (xmit) */
 	struct iphdr cs_ip;	/* ip/tcp hdr from most recent packet */
 	struct tcphdr cs_tcp;

include/sound/pcm_oss.h

@@ -57,6 +57,7 @@ struct snd_pcm_oss_runtime {
 	char *buffer;				/* vmallocated period */
 	size_t buffer_used;			/* used length from period buffer */
 	struct mutex params_lock;
+	atomic_t rw_ref;		/* concurrent read/write accesses */
 #ifdef CONFIG_SND_PCM_OSS_PLUGINS
 	struct snd_pcm_plugin *plugin_first;
 	struct snd_pcm_plugin *plugin_last;

ipc/shm.c

@@ -198,6 +198,12 @@ static int __shm_open(struct vm_area_struct *vma)
 	if (IS_ERR(shp))
 		return PTR_ERR(shp);
 
+	if (shp->shm_file != sfd->file) {
+		/* ID was reused */
+		shm_unlock(shp);
+		return -EINVAL;
+	}
+
 	shp->shm_atim = get_seconds();
 	shp->shm_lprid = task_tgid_vnr(current);
 	shp->shm_nattch++;
@@ -414,8 +420,9 @@ static int shm_mmap(struct file *file, struct vm_area_struct *vma)
 	int ret;
 
 	/*
-	 * In case of remap_file_pages() emulation, the file can represent
+	 * In case of remap_file_pages() emulation, the file can represent an
-	 * removed IPC ID: propogate shm_lock() error to caller.
+	 * IPC ID that was removed, and possibly even reused by another shm
+	 * segment already.  Propagate this case as an error to caller.
 	 */
 	ret =__shm_open(vma);
 	if (ret)
@@ -439,6 +446,7 @@ static int shm_release(struct inode *ino, struct file *file)
 	struct shm_file_data *sfd = shm_file_data(file);
 
 	put_ipc_ns(sfd->ns);
+	fput(sfd->file);
 	shm_file_data(file) = NULL;
 	kfree(sfd);
 	return 0;
@@ -1198,7 +1206,16 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg,
 	file->f_mapping = shp->shm_file->f_mapping;
 	sfd->id = shp->shm_perm.id;
 	sfd->ns = get_ipc_ns(ns);
-	sfd->file = shp->shm_file;
+	/*
+	 * We need to take a reference to the real shm file to prevent the
+	 * pointer from becoming stale in cases where the lifetime of the outer
+	 * file extends beyond that of the shm segment.  It's not usually
+	 * possible, but it can happen during remap_file_pages() emulation as
+	 * that unmaps the memory, then does ->mmap() via file reference only.
+	 * We'll deny the ->mmap() if the shm segment was since removed, but to
+	 * detect shm ID reuse we need to compare the file pointers.
+	 */
+	sfd->file = get_file(shp->shm_file);
 	sfd->vm_ops = NULL;
 
 	err = security_mmap_file(file, prot, flags);

kernel/resource.c

@@ -611,7 +611,8 @@ static int __find_resource(struct resource *root, struct resource *old,
 			alloc.start = constraint->alignf(constraint->alignf_data, &avail,
 					size, constraint->align);
 			alloc.end = alloc.start + size - 1;
-			if (resource_contains(&avail, &alloc)) {
+			if (alloc.start <= alloc.end &&
+			    resource_contains(&avail, &alloc)) {
 				new->start = alloc.start;
 				new->end = alloc.end;
 				return 0;

kernel/time/hrtimer.c

@@ -435,6 +435,7 @@ void destroy_hrtimer_on_stack(struct hrtimer *timer)
 {
 	debug_object_free(timer, &hrtimer_debug_descr);
 }
+EXPORT_SYMBOL_GPL(destroy_hrtimer_on_stack);
 
 #else
 static inline void debug_hrtimer_init(struct hrtimer *timer) { }

mm/filemap.c

@@ -573,7 +573,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 	VM_BUG_ON_PAGE(!PageLocked(new), new);
 	VM_BUG_ON_PAGE(new->mapping, new);
 
-	error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
+	error = radix_tree_preload(gfp_mask & GFP_RECLAIM_MASK);
 	if (!error) {
 		struct address_space *mapping = old->mapping;
 		void (*freepage)(struct page *);
@@ -632,7 +632,7 @@ static int __add_to_page_cache_locked(struct page *page,
 			return error;
 	}
 
-	error = radix_tree_maybe_preload(gfp_mask & ~__GFP_HIGHMEM);
+	error = radix_tree_maybe_preload(gfp_mask & GFP_RECLAIM_MASK);
 	if (error) {
 		if (!huge)
 			mem_cgroup_cancel_charge(page, memcg);
@@ -1194,8 +1194,7 @@ no_page:
 		if (fgp_flags & FGP_ACCESSED)
 			__SetPageReferenced(page);
 
-		err = add_to_page_cache_lru(page, mapping, offset,
+		err = add_to_page_cache_lru(page, mapping, offset, gfp_mask);
-				gfp_mask & GFP_RECLAIM_MASK);
 		if (unlikely(err)) {
 			page_cache_release(page);
 			page = NULL;
@@ -1829,19 +1828,18 @@ EXPORT_SYMBOL(generic_file_read_iter);
  * This adds the requested page to the page cache if it isn't already there,
  * and schedules an I/O to read in its contents from disk.
  */
-static int page_cache_read(struct file *file, pgoff_t offset)
+static int page_cache_read(struct file *file, pgoff_t offset, gfp_t gfp_mask)
 {
 	struct address_space *mapping = file->f_mapping;
 	struct page *page;
 	int ret;
 
 	do {
-		page = page_cache_alloc_cold(mapping);
+		page = __page_cache_alloc(gfp_mask|__GFP_COLD);
 		if (!page)
 			return -ENOMEM;
 
-		ret = add_to_page_cache_lru(page, mapping, offset,
+		ret = add_to_page_cache_lru(page, mapping, offset, gfp_mask);
-				mapping_gfp_constraint(mapping, GFP_KERNEL));
 		if (ret == 0)
 			ret = mapping->a_ops->readpage(file, page);
 		else if (ret == -EEXIST)
@@ -2022,7 +2020,7 @@ no_cached_page:
 	 * We're only likely to ever get here if MADV_RANDOM is in
 	 * effect.
 	 */
-	error = page_cache_read(file, offset);
+	error = page_cache_read(file, offset, vmf->gfp_mask);
 
 	/*
 	 * The page we want has now been added to the page cache.