Merge 6e4dc3d592 ("Merge tag 'for-linus-5.10-1' of git://github.com/cminyard/linux-ipmi") into android-mainline

Steps on the way to 5.10-rc1

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: Idbd0577a495237bf5628333110e2c98a77b39c77

Documentation/trace/histogram.rst

@@ -1495,7 +1495,7 @@ Extended error information
     #
 
     { stacktrace:
-             _do_fork+0x18e/0x330
+             kernel_clone+0x18e/0x330
              kernel_thread+0x29/0x30
              kthreadd+0x154/0x1b0
              ret_from_fork+0x3f/0x70
@@ -1588,7 +1588,7 @@ Extended error information
              SYSC_sendto+0xef/0x170
     } hitcount:         88
     { stacktrace:
-             _do_fork+0x18e/0x330
+             kernel_clone+0x18e/0x330
              SyS_clone+0x19/0x20
              entry_SYSCALL_64_fastpath+0x12/0x6a
     } hitcount:        244

arch/h8300/kernel/process.c

@@ -172,5 +172,5 @@ asmlinkage int sys_clone(unsigned long __user *args)
 	kargs.exit_signal	= (lower_32_bits(clone_flags) & CSIGNAL);
 	kargs.stack		= newsp;
 
-	return _do_fork(&kargs);
+	return kernel_clone(&kargs);
 }

arch/ia64/kernel/process.c

@@ -271,7 +271,7 @@ ia64_load_extra (struct task_struct *task)
  *
  *	<clone syscall>	        <some kernel call frames>
  *	sys_clone		   :
- *	_do_fork		_do_fork
+ *	kernel_clone		kernel_clone
  *	copy_thread		copy_thread
  *
  * This means that the stack layout is as follows:
@@ -411,7 +411,7 @@ asmlinkage long ia64_clone(unsigned long clone_flags, unsigned long stack_start,
 		.tls		= tls,
 	};
 
-	return _do_fork(&args);
+	return kernel_clone(&args);
 }
 
 static void

arch/m68k/kernel/process.c

@@ -107,10 +107,10 @@ void flush_thread(void)
  * on top of pt_regs, which means that sys_clone() arguments would be
  * buried.  We could, of course, copy them, but it's too costly for no
  * good reason - generic clone() would have to copy them *again* for
- * _do_fork() anyway.  So in this case it's actually better to pass pt_regs *
+ * kernel_clone() anyway.  So in this case it's actually better to pass pt_regs *
- * and extract arguments for _do_fork() from there.  Eventually we might
+ * and extract arguments for kernel_clone() from there.  Eventually we might
- * go for calling _do_fork() directly from the wrapper, but only after we
+ * go for calling kernel_clone() directly from the wrapper, but only after we
- * are finished with _do_fork() prototype conversion.
+ * are finished with kernel_clone() prototype conversion.
  */
 asmlinkage int m68k_clone(struct pt_regs *regs)
 {
@@ -125,7 +125,7 @@ asmlinkage int m68k_clone(struct pt_regs *regs)
 		.tls		= regs->d5,
 	};
 
-	return _do_fork(&args);
+	return kernel_clone(&args);
 }
 
 /*

arch/nios2/kernel/process.c

@@ -266,5 +266,5 @@ asmlinkage int nios2_clone(unsigned long clone_flags, unsigned long newsp,
 		.tls		= tls,
 	};
 
-	return _do_fork(&args);
+	return kernel_clone(&args);
 }

arch/sparc/kernel/process.c

@@ -25,7 +25,7 @@ asmlinkage long sparc_fork(struct pt_regs *regs)
 		.stack		= regs->u_regs[UREG_FP],
 	};
 
-	ret = _do_fork(&args);
+	ret = kernel_clone(&args);
 
 	/* If we get an error and potentially restart the system
 	 * call, we're screwed because copy_thread() clobbered
@@ -50,7 +50,7 @@ asmlinkage long sparc_vfork(struct pt_regs *regs)
 		.stack		= regs->u_regs[UREG_FP],
 	};
 
-	ret = _do_fork(&args);
+	ret = kernel_clone(&args);
 
 	/* If we get an error and potentially restart the system
 	 * call, we're screwed because copy_thread() clobbered
@@ -96,7 +96,7 @@ asmlinkage long sparc_clone(struct pt_regs *regs)
 	else
 		args.stack = regs->u_regs[UREG_FP];
 
-	ret = _do_fork(&args);
+	ret = kernel_clone(&args);
 
 	/* If we get an error and potentially restart the system
 	 * call, we're screwed because copy_thread() clobbered

arch/x86/kernel/sys_ia32.c

@@ -251,6 +251,6 @@ COMPAT_SYSCALL_DEFINE5(ia32_clone, unsigned long, clone_flags,
 		.tls		= tls_val,
 	};
 
-	return _do_fork(&args);
+	return kernel_clone(&args);
 }
 #endif /* CONFIG_IA32_EMULATION */

drivers/char/ipmi/ipmi_bt_sm.c

@@ -213,8 +213,10 @@ static int bt_start_transaction(struct si_sm_data *bt,
 	if (bt->state == BT_STATE_LONG_BUSY)
 		return IPMI_NODE_BUSY_ERR;
 
-	if (bt->state != BT_STATE_IDLE)
+	if (bt->state != BT_STATE_IDLE) {
+		dev_warn(bt->io->dev, "BT in invalid state %d\n", bt->state);
 		return IPMI_NOT_IN_MY_STATE_ERR;
+	}
 
 	if (bt_debug & BT_DEBUG_MSG) {
 		dev_dbg(bt->io->dev, "+++++++++++++++++ New command\n");

drivers/char/ipmi/ipmi_kcs_sm.c

@@ -17,6 +17,8 @@
  * that document.
  */
 
+#define DEBUG /* So dev_dbg() is always available. */
+
 #include <linux/kernel.h> /* For printk. */
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -187,8 +189,8 @@ static inline void start_error_recovery(struct si_sm_data *kcs, char *reason)
 	(kcs->error_retries)++;
 	if (kcs->error_retries > MAX_ERROR_RETRIES) {
 		if (kcs_debug & KCS_DEBUG_ENABLE)
-			printk(KERN_DEBUG "ipmi_kcs_sm: kcs hosed: %s\n",
+			dev_dbg(kcs->io->dev, "ipmi_kcs_sm: kcs hosed: %s\n",
-			       reason);
+				reason);
 		kcs->state = KCS_HOSED;
 	} else {
 		kcs->error0_timeout = jiffies + ERROR0_OBF_WAIT_JIFFIES;
@@ -268,11 +270,13 @@ static int start_kcs_transaction(struct si_sm_data *kcs, unsigned char *data,
 	if (size > MAX_KCS_WRITE_SIZE)
 		return IPMI_REQ_LEN_EXCEEDED_ERR;
 
-	if ((kcs->state != KCS_IDLE) && (kcs->state != KCS_HOSED))
+	if ((kcs->state != KCS_IDLE) && (kcs->state != KCS_HOSED)) {
+		dev_warn(kcs->io->dev, "KCS in invalid state %d\n", kcs->state);
 		return IPMI_NOT_IN_MY_STATE_ERR;
+	}
 
 	if (kcs_debug & KCS_DEBUG_MSG) {
-		printk(KERN_DEBUG "start_kcs_transaction -");
+		dev_dbg(kcs->io->dev, "%s -", __func__);
 		for (i = 0; i < size; i++)
 			pr_cont(" %02x", data[i]);
 		pr_cont("\n");
@@ -331,7 +335,8 @@ static enum si_sm_result kcs_event(struct si_sm_data *kcs, long time)
 	status = read_status(kcs);
 
 	if (kcs_debug & KCS_DEBUG_STATES)
-		printk(KERN_DEBUG "KCS: State = %d, %x\n", kcs->state, status);
+		dev_dbg(kcs->io->dev,
+			"KCS: State = %d, %x\n", kcs->state, status);
 
 	/* All states wait for ibf, so just do it here. */
 	if (!check_ibf(kcs, status, time))

drivers/char/ipmi/ipmi_msghandler.c

@@ -34,12 +34,13 @@
 #include <linux/uuid.h>
 #include <linux/nospec.h>
 #include <linux/vmalloc.h>
+#include <linux/delay.h>
 
 #define IPMI_DRIVER_VERSION "39.2"
 
 static struct ipmi_recv_msg *ipmi_alloc_recv_msg(void);
 static int ipmi_init_msghandler(void);
-static void smi_recv_tasklet(unsigned long);
+static void smi_recv_tasklet(struct tasklet_struct *t);
 static void handle_new_recv_msgs(struct ipmi_smi *intf);
 static void need_waiter(struct ipmi_smi *intf);
 static int handle_one_recv_msg(struct ipmi_smi *intf,
@@ -60,6 +61,7 @@ enum ipmi_panic_event_op {
 #else
 #define IPMI_PANIC_DEFAULT IPMI_SEND_PANIC_EVENT_NONE
 #endif
+
 static enum ipmi_panic_event_op ipmi_send_panic_event = IPMI_PANIC_DEFAULT;
 
 static int panic_op_write_handler(const char *val,
@@ -89,19 +91,19 @@ static int panic_op_read_handler(char *buffer, const struct kernel_param *kp)
 {
 	switch (ipmi_send_panic_event) {
 	case IPMI_SEND_PANIC_EVENT_NONE:
-		strcpy(buffer, "none");
+		strcpy(buffer, "none\n");
 		break;
 
 	case IPMI_SEND_PANIC_EVENT:
-		strcpy(buffer, "event");
+		strcpy(buffer, "event\n");
 		break;
 
 	case IPMI_SEND_PANIC_EVENT_STRING:
-		strcpy(buffer, "string");
+		strcpy(buffer, "string\n");
 		break;
 
 	default:
-		strcpy(buffer, "???");
+		strcpy(buffer, "???\n");
 		break;
 	}
 
@@ -317,6 +319,7 @@ struct bmc_device {
 	int                    dyn_guid_set;
 	struct kref	       usecount;
 	struct work_struct     remove_work;
+	unsigned char	       cc; /* completion code */
 };
 #define to_bmc_device(x) container_of((x), struct bmc_device, pdev.dev)
 
@@ -2381,6 +2384,8 @@ static void bmc_device_id_handler(struct ipmi_smi *intf,
 			msg->msg.data, msg->msg.data_len, &intf->bmc->fetch_id);
 	if (rv) {
 		dev_warn(intf->si_dev, "device id demangle failed: %d\n", rv);
+		/* record completion code when error */
+		intf->bmc->cc = msg->msg.data[0];
 		intf->bmc->dyn_id_set = 0;
 	} else {
 		/*
@@ -2426,23 +2431,39 @@ send_get_device_id_cmd(struct ipmi_smi *intf)
 static int __get_device_id(struct ipmi_smi *intf, struct bmc_device *bmc)
 {
 	int rv;
-
+	unsigned int retry_count = 0;
-	bmc->dyn_id_set = 2;
 
 	intf->null_user_handler = bmc_device_id_handler;
 
+retry:
+	bmc->cc = 0;
+	bmc->dyn_id_set = 2;
+
 	rv = send_get_device_id_cmd(intf);
 	if (rv)
-		return rv;
+		goto out_reset_handler;
 
 	wait_event(intf->waitq, bmc->dyn_id_set != 2);
 
-	if (!bmc->dyn_id_set)
+	if (!bmc->dyn_id_set) {
+		if ((bmc->cc == IPMI_DEVICE_IN_FW_UPDATE_ERR
+		     || bmc->cc ==  IPMI_DEVICE_IN_INIT_ERR
+		     || bmc->cc ==  IPMI_NOT_IN_MY_STATE_ERR)
+		     && ++retry_count <= GET_DEVICE_ID_MAX_RETRY) {
+			msleep(500);
+			dev_warn(intf->si_dev,
+			    "BMC returned 0x%2.2x, retry get bmc device id\n",
+			    bmc->cc);
+			goto retry;
+		}
+
 		rv = -EIO; /* Something went wrong in the fetch. */
+	}
 
 	/* dyn_id_set makes the id data available. */
 	smp_rmb();
 
+out_reset_handler:
 	intf->null_user_handler = NULL;
 
 	return rv;
@@ -3245,7 +3266,6 @@ channel_handler(struct ipmi_smi *intf, struct ipmi_recv_msg *msg)
 		/* It's the one we want */
 		if (msg->msg.data[0] != 0) {
 			/* Got an error from the channel, just go on. */
-
 			if (msg->msg.data[0] == IPMI_INVALID_COMMAND_ERR) {
 				/*
 				 * If the MC does not support this
@@ -3329,6 +3349,7 @@ static int __scan_channels(struct ipmi_smi *intf, struct ipmi_device_id *id)
 			dev_warn(intf->si_dev,
 				 "Error sending channel information for channel 0, %d\n",
 				 rv);
+			intf->null_user_handler = NULL;
 			return -EIO;
 		}
 
@@ -3430,9 +3451,8 @@ int ipmi_add_smi(struct module         *owner,
 	intf->curr_seq = 0;
 	spin_lock_init(&intf->waiting_rcv_msgs_lock);
 	INIT_LIST_HEAD(&intf->waiting_rcv_msgs);
-	tasklet_init(&intf->recv_tasklet,
+	tasklet_setup(&intf->recv_tasklet,
-		     smi_recv_tasklet,
+		     smi_recv_tasklet);
-		     (unsigned long) intf);
 	atomic_set(&intf->watchdog_pretimeouts_to_deliver, 0);
 	spin_lock_init(&intf->xmit_msgs_lock);
 	INIT_LIST_HEAD(&intf->xmit_msgs);
@@ -4467,10 +4487,10 @@ static void handle_new_recv_msgs(struct ipmi_smi *intf)
 	}
 }
 
-static void smi_recv_tasklet(unsigned long val)
+static void smi_recv_tasklet(struct tasklet_struct *t)
 {
 	unsigned long flags = 0; /* keep us warning-free. */
-	struct ipmi_smi *intf = (struct ipmi_smi *) val;
+	struct ipmi_smi *intf = from_tasklet(intf, t, recv_tasklet);
 	int run_to_completion = intf->run_to_completion;
 	struct ipmi_smi_msg *newmsg = NULL;
 
@@ -4542,7 +4562,7 @@ void ipmi_smi_msg_received(struct ipmi_smi *intf,
 		spin_unlock_irqrestore(&intf->xmit_msgs_lock, flags);
 
 	if (run_to_completion)
-		smi_recv_tasklet((unsigned long) intf);
+		smi_recv_tasklet(&intf->recv_tasklet);
 	else
 		tasklet_schedule(&intf->recv_tasklet);
 }

drivers/char/ipmi/ipmi_si_intf.c

@@ -1316,6 +1316,7 @@ static int try_get_dev_id(struct smi_info *smi_info)
 	unsigned char         *resp;
 	unsigned long         resp_len;
 	int                   rv = 0;
+	unsigned int          retry_count = 0;
 
 	resp = kmalloc(IPMI_MAX_MSG_LENGTH, GFP_KERNEL);
 	if (!resp)
@@ -1327,6 +1328,8 @@ static int try_get_dev_id(struct smi_info *smi_info)
 	 */
 	msg[0] = IPMI_NETFN_APP_REQUEST << 2;
 	msg[1] = IPMI_GET_DEVICE_ID_CMD;
+
+retry:
 	smi_info->handlers->start_transaction(smi_info->si_sm, msg, 2);
 
 	rv = wait_for_msg_done(smi_info);
@@ -1339,6 +1342,20 @@ static int try_get_dev_id(struct smi_info *smi_info)
 	/* Check and record info from the get device id, in case we need it. */
 	rv = ipmi_demangle_device_id(resp[0] >> 2, resp[1],
 			resp + 2, resp_len - 2, &smi_info->device_id);
+	if (rv) {
+		/* record completion code */
+		unsigned char cc = *(resp + 2);
+
+		if ((cc == IPMI_DEVICE_IN_FW_UPDATE_ERR
+		    || cc == IPMI_DEVICE_IN_INIT_ERR
+		    || cc == IPMI_NOT_IN_MY_STATE_ERR)
+		    && ++retry_count <= GET_DEVICE_ID_MAX_RETRY) {
+			dev_warn(smi_info->io.dev,
+			    "BMC returned 0x%2.2x, retry get bmc device id\n",
+			    cc);
+			goto retry;
+		}
+	}
 
 out:
 	kfree(resp);
@@ -1963,7 +1980,7 @@ static int try_smi_init(struct smi_info *new_smi)
 	/* Do this early so it's available for logs. */
 	if (!new_smi->io.dev) {
 		pr_err("IPMI interface added with no device\n");
-		rv = EIO;
+		rv = -EIO;
 		goto out_err;
 	}
 

drivers/char/ipmi/ipmi_smic_sm.c

@@ -21,6 +21,8 @@
  * 2001 Hewlett-Packard Company
  */
 
+#define DEBUG /* So dev_dbg() is always available. */
+
 #include <linux/kernel.h> /* For printk. */
 #include <linux/string.h>
 #include <linux/module.h>
@@ -126,11 +128,14 @@ static int start_smic_transaction(struct si_sm_data *smic,
 	if (size > MAX_SMIC_WRITE_SIZE)
 		return IPMI_REQ_LEN_EXCEEDED_ERR;
 
-	if ((smic->state != SMIC_IDLE) && (smic->state != SMIC_HOSED))
+	if ((smic->state != SMIC_IDLE) && (smic->state != SMIC_HOSED)) {
+		dev_warn(smic->io->dev,
+			 "SMIC in invalid state %d\n", smic->state);
 		return IPMI_NOT_IN_MY_STATE_ERR;
+	}
 
 	if (smic_debug & SMIC_DEBUG_MSG) {
-		printk(KERN_DEBUG "start_smic_transaction -");
+		dev_dbg(smic->io->dev, "%s -", __func__);
 		for (i = 0; i < size; i++)
 			pr_cont(" %02x", data[i]);
 		pr_cont("\n");
@@ -152,7 +157,7 @@ static int smic_get_result(struct si_sm_data *smic,
 	int i;
 
 	if (smic_debug & SMIC_DEBUG_MSG) {
-		printk(KERN_DEBUG "smic_get result -");
+		dev_dbg(smic->io->dev, "smic_get result -");
 		for (i = 0; i < smic->read_pos; i++)
 			pr_cont(" %02x", smic->read_data[i]);
 		pr_cont("\n");
@@ -324,9 +329,9 @@ static enum si_sm_result smic_event(struct si_sm_data *smic, long time)
 	}
 	if (smic->state != SMIC_IDLE) {
 		if (smic_debug & SMIC_DEBUG_STATES)
-			printk(KERN_DEBUG
+			dev_dbg(smic->io->dev,
-			       "smic_event - smic->smic_timeout = %ld, time = %ld\n",
+				"%s - smic->smic_timeout = %ld, time = %ld\n",
-			       smic->smic_timeout, time);
+				__func__, smic->smic_timeout, time);
 		/*
 		 * FIXME: smic_event is sometimes called with time >
 		 * SMIC_RETRY_TIMEOUT
@@ -345,8 +350,9 @@ static enum si_sm_result smic_event(struct si_sm_data *smic, long time)
 
 	status = read_smic_status(smic);
 	if (smic_debug & SMIC_DEBUG_STATES)
-		printk(KERN_DEBUG "smic_event - state = %d, flags = 0x%02x, status = 0x%02x\n",
+		dev_dbg(smic->io->dev,
-		       smic->state, flags, status);
+			"%s - state = %d, flags = 0x%02x, status = 0x%02x\n",
+			__func__, smic->state, flags, status);
 
 	switch (smic->state) {
 	case SMIC_IDLE:
@@ -436,8 +442,9 @@ static enum si_sm_result smic_event(struct si_sm_data *smic, long time)
 		data = read_smic_data(smic);
 		if (data != 0) {
 			if (smic_debug & SMIC_DEBUG_ENABLE)
-				printk(KERN_DEBUG "SMIC_WRITE_END: data = %02x\n",
+				dev_dbg(smic->io->dev,
-				       data);
+					"SMIC_WRITE_END: data = %02x\n",
+					data);
 			start_error_recovery(smic,
 					     "state = SMIC_WRITE_END, "
 					     "data != SUCCESS");
@@ -516,8 +523,9 @@ static enum si_sm_result smic_event(struct si_sm_data *smic, long time)
 		/* data register holds an error code */
 		if (data != 0) {
 			if (smic_debug & SMIC_DEBUG_ENABLE)
-				printk(KERN_DEBUG "SMIC_READ_END: data = %02x\n",
+				dev_dbg(smic->io->dev,
-				       data);
+					"SMIC_READ_END: data = %02x\n",
+					data);
 			start_error_recovery(smic,
 					     "state = SMIC_READ_END, "
 					     "data != SUCCESS");
@@ -533,7 +541,8 @@ static enum si_sm_result smic_event(struct si_sm_data *smic, long time)
 
 	default:
 		if (smic_debug & SMIC_DEBUG_ENABLE) {
-			printk(KERN_DEBUG "smic->state = %d\n", smic->state);
+			dev_dbg(smic->io->dev,
+				"smic->state = %d\n", smic->state);
 			start_error_recovery(smic, "state = UNKNOWN");
 			return SI_SM_CALL_WITH_DELAY;
 		}

drivers/misc/kgdbts.c

@@ -33,16 +33,16 @@
  * You can also specify optional tests:
  * N## = Go to sleep with interrupts of for ## seconds
  *       to test the HW NMI watchdog
- * F## = Break at do_fork for ## iterations
+ * F## = Break at kernel_clone for ## iterations
  * S## = Break at sys_open for ## iterations
  * I## = Run the single step test ## iterations
  *
- * NOTE: that the do_fork and sys_open tests are mutually exclusive.
+ * NOTE: that the kernel_clone and sys_open tests are mutually exclusive.
  *
  * To invoke the kgdb test suite from boot you use a kernel start
  * argument as follows:
  * 	kgdbts=V1 kgdbwait
- * Or if you wanted to perform the NMI test for 6 seconds and do_fork
+ * Or if you wanted to perform the NMI test for 6 seconds and kernel_clone
  * test for 100 forks, you could use:
  * 	kgdbts=V1N6F100 kgdbwait
  *
@@ -74,7 +74,7 @@
  * echo kgdbts=V1S10000 > /sys/module/kgdbts/parameters/kgdbts
  * fg # and hit control-c
  * fg # and hit control-c
- * ## This tests break points on do_fork
+ * ## This tests break points on kernel_clone
  * while [ 1 ] ; do date > /dev/null ; done &
  * while [ 1 ] ; do date > /dev/null ; done &
  * echo kgdbts=V1F1000 > /sys/module/kgdbts/parameters/kgdbts
@@ -209,8 +209,8 @@ static unsigned long lookup_addr(char *arg)
 		addr = (unsigned long)kgdbts_break_test;
 	else if (!strcmp(arg, "sys_open"))
 		addr = (unsigned long)do_sys_open;
-	else if (!strcmp(arg, "do_fork"))
+	else if (!strcmp(arg, "kernel_clone"))
-		addr = (unsigned long)_do_fork;
+		addr = (unsigned long)kernel_clone;
 	else if (!strcmp(arg, "hw_break_val"))
 		addr = (unsigned long)&hw_break_val;
 	addr = (unsigned long) dereference_function_descriptor((void *)addr);
@@ -310,7 +310,7 @@ static int check_and_rewind_pc(char *put_str, char *arg)
 
 	if (arch_needs_sstep_emulation && sstep_addr &&
 	    ip + offset == sstep_addr &&
-	    ((!strcmp(arg, "sys_open") || !strcmp(arg, "do_fork")))) {
+	    ((!strcmp(arg, "sys_open") || !strcmp(arg, "kernel_clone")))) {
 		/* This is special case for emulated single step */
 		v2printk("Emul: rewind hit single step bp\n");
 		restart_from_top_after_write = 1;
@@ -596,19 +596,19 @@ static struct test_struct singlestep_break_test[] = {
 };
 
 /*
- * Test for hitting a breakpoint at do_fork for what ever the number
+ * Test for hitting a breakpoint at kernel_clone for what ever the number
  * of iterations required by the variable repeat_test.
  */
-static struct test_struct do_fork_test[] = {
+static struct test_struct do_kernel_clone_test[] = {
 	{ "?", "S0*" }, /* Clear break points */
-	{ "do_fork", "OK", sw_break, }, /* set sw breakpoint */
+	{ "kernel_clone", "OK", sw_break, }, /* set sw breakpoint */
 	{ "c", "T0*", NULL, get_thread_id_continue }, /* Continue */
-	{ "do_fork", "OK", sw_rem_break }, /*remove breakpoint */
+	{ "kernel_clone", "OK", sw_rem_break }, /*remove breakpoint */
-	{ "g", "do_fork", NULL, check_and_rewind_pc }, /* check location */
+	{ "g", "kernel_clone", NULL, check_and_rewind_pc }, /* check location */
 	{ "write", "OK", write_regs, emul_reset }, /* Write registers */
 	{ "s", "T0*", emul_sstep_get, emul_sstep_put }, /* Single step */
-	{ "g", "do_fork", NULL, check_single_step },
+	{ "g", "kernel_clone", NULL, check_single_step },
-	{ "do_fork", "OK", sw_break, }, /* set sw breakpoint */
+	{ "kernel_clone", "OK", sw_break, }, /* set sw breakpoint */
 	{ "7", "T0*", skip_back_repeat_test }, /* Loop based on repeat_test */
 	{ "D", "OK", NULL, final_ack_set }, /* detach and unregister I/O */
 	{ "", "", get_cont_catch, put_cont_catch },
@@ -935,11 +935,11 @@ static void run_bad_read_test(void)
 	kgdb_breakpoint();
 }
 
-static void run_do_fork_test(void)
+static void run_kernel_clone_test(void)
 {
 	init_simple_test();
-	ts.tst = do_fork_test;
+	ts.tst = do_kernel_clone_test;
-	ts.name = "do_fork_test";
+	ts.name = "do_kernel_clone_test";
 	/* Activate test with initial breakpoint */
 	kgdb_breakpoint();
 }
@@ -967,7 +967,7 @@ static void run_singlestep_break_test(void)
 static void kgdbts_run_tests(void)
 {
 	char *ptr;
-	int fork_test = 0;
+	int clone_test = 0;
 	int do_sys_open_test = 0;
 	int sstep_test = 1000;
 	int nmi_sleep = 0;
@@ -981,7 +981,7 @@ static void kgdbts_run_tests(void)
 
 	ptr = strchr(config, 'F');
 	if (ptr)
-		fork_test = simple_strtol(ptr + 1, NULL, 10);
+		clone_test = simple_strtol(ptr + 1, NULL, 10);
 	ptr = strchr(config, 'S');
 	if (ptr)
 		do_sys_open_test = simple_strtol(ptr + 1, NULL, 10);
@@ -1025,16 +1025,16 @@ static void kgdbts_run_tests(void)
 		run_nmi_sleep_test(nmi_sleep);
 	}
 
-	/* If the do_fork test is run it will be the last test that is
+	/* If the kernel_clone test is run it will be the last test that is
 	 * executed because a kernel thread will be spawned at the very
 	 * end to unregister the debug hooks.
 	 */
-	if (fork_test) {
+	if (clone_test) {
-		repeat_test = fork_test;
+		repeat_test = clone_test;
-		printk(KERN_INFO "kgdbts:RUN do_fork for %i breakpoints\n",
+		printk(KERN_INFO "kgdbts:RUN kernel_clone for %i breakpoints\n",
 			repeat_test);
 		kthread_run(kgdbts_unreg_thread, NULL, "kgdbts_unreg");
-		run_do_fork_test();
+		run_kernel_clone_test();
 		return;
 	}
 

fs/d_path.c

@@ -102,6 +102,8 @@ restart:
 
 		if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) {
 			struct mount *parent = READ_ONCE(mnt->mnt_parent);
+			struct mnt_namespace *mnt_ns;
+
 			/* Escaped? */
 			if (dentry != vfsmnt->mnt_root) {
 				bptr = *buffer;
@@ -116,7 +118,9 @@ restart:
 				vfsmnt = &mnt->mnt;
 				continue;
 			}
-			if (is_mounted(vfsmnt) && !is_anon_ns(mnt->mnt_ns))
+			mnt_ns = READ_ONCE(mnt->mnt_ns);
+			/* open-coded is_mounted() to use local mnt_ns */
+			if (!IS_ERR_OR_NULL(mnt_ns) && !is_anon_ns(mnt_ns))
 				error = 1;	// absolute root
 			else
 				error = 2;	// detached or not attached yet

fs/dax.c

@@ -1037,18 +1037,18 @@ static vm_fault_t dax_load_hole(struct xa_state *xas,
 	return ret;
 }
 
-int dax_iomap_zero(loff_t pos, unsigned offset, unsigned size,
+s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap)
-		   struct iomap *iomap)
 {
 	sector_t sector = iomap_sector(iomap, pos & PAGE_MASK);
 	pgoff_t pgoff;
 	long rc, id;
 	void *kaddr;
 	bool page_aligned = false;
-
+	unsigned offset = offset_in_page(pos);
+	unsigned size = min_t(u64, PAGE_SIZE - offset, length);
 
 	if (IS_ALIGNED(sector << SECTOR_SHIFT, PAGE_SIZE) &&
-	    IS_ALIGNED(size, PAGE_SIZE))
+	    (size == PAGE_SIZE))
 		page_aligned = true;
 
 	rc = bdev_dax_pgoff(iomap->bdev, sector, PAGE_SIZE, &pgoff);
@@ -1058,8 +1058,7 @@ int dax_iomap_zero(loff_t pos, unsigned offset, unsigned size,
 	id = dax_read_lock();
 
 	if (page_aligned)
-		rc = dax_zero_page_range(iomap->dax_dev, pgoff,
+		rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1);
-					 size >> PAGE_SHIFT);
 	else
 		rc = dax_direct_access(iomap->dax_dev, pgoff, 1, &kaddr, NULL);
 	if (rc < 0) {
@@ -1072,7 +1071,7 @@ int dax_iomap_zero(loff_t pos, unsigned offset, unsigned size,
 		dax_flush(iomap->dax_dev, kaddr + offset, size);
 	}
 	dax_read_unlock(id);
-	return 0;
+	return size;
 }
 
 static loff_t

fs/iomap/buffered-io.c

@@ -22,18 +22,25 @@
 #include "../internal.h"
 
 /*
- * Structure allocated for each page when block size < PAGE_SIZE to track
+ * Structure allocated for each page or THP when block size < page size
- * sub-page uptodate status and I/O completions.
+ * to track sub-page uptodate status and I/O completions.
  */
 struct iomap_page {
-	atomic_t		read_count;
+	atomic_t		read_bytes_pending;
-	atomic_t		write_count;
+	atomic_t		write_bytes_pending;
 	spinlock_t		uptodate_lock;
-	DECLARE_BITMAP(uptodate, PAGE_SIZE / 512);
+	unsigned long		uptodate[];
 };
 
 static inline struct iomap_page *to_iomap_page(struct page *page)
 {
+	/*
+	 * per-block data is stored in the head page.  Callers should
+	 * not be dealing with tail pages (and if they are, they can
+	 * call thp_head() first.
+	 */
+	VM_BUG_ON_PGFLAGS(PageTail(page), page);
+
 	if (page_has_private(page))
 		return (struct iomap_page *)page_private(page);
 	return NULL;
@@ -45,20 +52,16 @@ static struct iomap_page *
 iomap_page_create(struct inode *inode, struct page *page)
 {
 	struct iomap_page *iop = to_iomap_page(page);
+	unsigned int nr_blocks = i_blocks_per_page(inode, page);
 
-	if (iop || i_blocksize(inode) == PAGE_SIZE)
+	if (iop || nr_blocks <= 1)
 		return iop;
 
-	iop = kmalloc(sizeof(*iop), GFP_NOFS | __GFP_NOFAIL);
+	iop = kzalloc(struct_size(iop, uptodate, BITS_TO_LONGS(nr_blocks)),
-	atomic_set(&iop->read_count, 0);
+			GFP_NOFS | __GFP_NOFAIL);
-	atomic_set(&iop->write_count, 0);
 	spin_lock_init(&iop->uptodate_lock);
-	bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE);
+	if (PageUptodate(page))
-
+		bitmap_fill(iop->uptodate, nr_blocks);
-	/*
-	 * migrate_page_move_mapping() assumes that pages with private data have
-	 * their count elevated by 1.
-	 */
 	attach_page_private(page, iop);
 	return iop;
 }
@@ -67,11 +70,14 @@ static void
 iomap_page_release(struct page *page)
 {
 	struct iomap_page *iop = detach_page_private(page);
+	unsigned int nr_blocks = i_blocks_per_page(page->mapping->host, page);
 
 	if (!iop)
 		return;
-	WARN_ON_ONCE(atomic_read(&iop->read_count));
+	WARN_ON_ONCE(atomic_read(&iop->read_bytes_pending));
-	WARN_ON_ONCE(atomic_read(&iop->write_count));
+	WARN_ON_ONCE(atomic_read(&iop->write_bytes_pending));
+	WARN_ON_ONCE(bitmap_full(iop->uptodate, nr_blocks) !=
+			PageUptodate(page));
 	kfree(iop);
 }
 
@@ -142,19 +148,11 @@ iomap_iop_set_range_uptodate(struct page *page, unsigned off, unsigned len)
 	struct inode *inode = page->mapping->host;
 	unsigned first = off >> inode->i_blkbits;
 	unsigned last = (off + len - 1) >> inode->i_blkbits;
-	bool uptodate = true;
 	unsigned long flags;
-	unsigned int i;
 
 	spin_lock_irqsave(&iop->uptodate_lock, flags);
-	for (i = 0; i < PAGE_SIZE / i_blocksize(inode); i++) {
+	bitmap_set(iop->uptodate, first, last - first + 1);
-		if (i >= first && i <= last)
+	if (bitmap_full(iop->uptodate, i_blocks_per_page(inode, page)))
-			set_bit(i, iop->uptodate);
-		else if (!test_bit(i, iop->uptodate))
-			uptodate = false;
-	}
-
-	if (uptodate)
 		SetPageUptodate(page);
 	spin_unlock_irqrestore(&iop->uptodate_lock, flags);
 }
@@ -171,13 +169,6 @@ iomap_set_range_uptodate(struct page *page, unsigned off, unsigned len)
 		SetPageUptodate(page);
 }
 
-static void
-iomap_read_finish(struct iomap_page *iop, struct page *page)
-{
-	if (!iop || atomic_dec_and_test(&iop->read_count))
-		unlock_page(page);
-}
-
 static void
 iomap_read_page_end_io(struct bio_vec *bvec, int error)
 {
@@ -191,7 +182,8 @@ iomap_read_page_end_io(struct bio_vec *bvec, int error)
 		iomap_set_range_uptodate(page, bvec->bv_offset, bvec->bv_len);
 	}
 
-	iomap_read_finish(iop, page);
+	if (!iop || atomic_sub_and_test(bvec->bv_len, &iop->read_bytes_pending))
+		unlock_page(page);
 }
 
 static void
@@ -271,30 +263,19 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 	}
 
 	ctx->cur_page_in_bio = true;
+	if (iop)
+		atomic_add(plen, &iop->read_bytes_pending);
 
-	/*
+	/* Try to merge into a previous segment if we can */
-	 * Try to merge into a previous segment if we can.
-	 */
 	sector = iomap_sector(iomap, pos);
-	if (ctx->bio && bio_end_sector(ctx->bio) == sector)
+	if (ctx->bio && bio_end_sector(ctx->bio) == sector) {
+		if (__bio_try_merge_page(ctx->bio, page, plen, poff,
+				&same_page))
+			goto done;
 		is_contig = true;
-
-	if (is_contig &&
-	    __bio_try_merge_page(ctx->bio, page, plen, poff, &same_page)) {
-		if (!same_page && iop)
-			atomic_inc(&iop->read_count);
-		goto done;
 	}
 
-	/*
+	if (!is_contig || bio_full(ctx->bio, plen)) {
-	 * If we start a new segment we need to increase the read count, and we
-	 * need to do so before submitting any previous full bio to make sure
-	 * that we don't prematurely unlock the page.
-	 */
-	if (iop)
-		atomic_inc(&iop->read_count);
-
-	if (!ctx->bio || !is_contig || bio_full(ctx->bio, plen)) {
 		gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL);
 		gfp_t orig_gfp = gfp;
 		int nr_vecs = (length + PAGE_SIZE - 1) >> PAGE_SHIFT;
@@ -571,13 +552,13 @@ __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, int flags,
 {
 	struct iomap_page *iop = iomap_page_create(inode, page);
 	loff_t block_size = i_blocksize(inode);
-	loff_t block_start = pos & ~(block_size - 1);
+	loff_t block_start = round_down(pos, block_size);
-	loff_t block_end = (pos + len + block_size - 1) & ~(block_size - 1);
+	loff_t block_end = round_up(pos + len, block_size);
 	unsigned from = offset_in_page(pos), to = from + len, poff, plen;
-	int status;
 
 	if (PageUptodate(page))
 		return 0;
+	ClearPageError(page);
 
 	do {
 		iomap_adjust_read_range(inode, iop, &block_start,
@@ -594,14 +575,13 @@ __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, int flags,
 			if (WARN_ON_ONCE(flags & IOMAP_WRITE_F_UNSHARE))
 				return -EIO;
 			zero_user_segments(page, poff, from, to, poff + plen);
-			iomap_set_range_uptodate(page, poff, plen);
+		} else {
-			continue;
+			int status = iomap_read_page_sync(block_start, page,
+					poff, plen, srcmap);
+			if (status)
+				return status;
 		}
-
+		iomap_set_range_uptodate(page, poff, plen);
-		status = iomap_read_page_sync(block_start, page, poff, plen,
-				srcmap);
-		if (status)
-			return status;
 	} while ((block_start += plen) < block_end);
 
 	return 0;
@@ -685,9 +665,8 @@ iomap_set_page_dirty(struct page *page)
 }
 EXPORT_SYMBOL_GPL(iomap_set_page_dirty);
 
-static int
+static size_t __iomap_write_end(struct inode *inode, loff_t pos, size_t len,
-__iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
+		size_t copied, struct page *page)
-		unsigned copied, struct page *page)
 {
 	flush_dcache_page(page);
 
@@ -709,15 +688,15 @@ __iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
 	return copied;
 }
 
-static int
+static size_t iomap_write_end_inline(struct inode *inode, struct page *page,
-iomap_write_end_inline(struct inode *inode, struct page *page,
+		struct iomap *iomap, loff_t pos, size_t copied)
-		struct iomap *iomap, loff_t pos, unsigned copied)
 {
 	void *addr;
 
 	WARN_ON_ONCE(!PageUptodate(page));
 	BUG_ON(pos + copied > PAGE_SIZE - offset_in_page(iomap->inline_data));
 
+	flush_dcache_page(page);
 	addr = kmap_atomic(page);
 	memcpy(iomap->inline_data + pos, addr + pos, copied);
 	kunmap_atomic(addr);
@@ -726,13 +705,14 @@ iomap_write_end_inline(struct inode *inode, struct page *page,
 	return copied;
 }
 
-static int
+/* Returns the number of bytes copied.  May be 0.  Cannot be an errno. */
-iomap_write_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied,
+static size_t iomap_write_end(struct inode *inode, loff_t pos, size_t len,
-		struct page *page, struct iomap *iomap, struct iomap *srcmap)
+		size_t copied, struct page *page, struct iomap *iomap,
+		struct iomap *srcmap)
 {
 	const struct iomap_page_ops *page_ops = iomap->page_ops;
 	loff_t old_size = inode->i_size;
-	int ret;
+	size_t ret;
 
 	if (srcmap->type == IOMAP_INLINE) {
 		ret = iomap_write_end_inline(inode, page, iomap, pos, copied);
@@ -811,13 +791,8 @@ again:
 
 		copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
 
-		flush_dcache_page(page);
+		copied = iomap_write_end(inode, pos, bytes, copied, page, iomap,
-
-		status = iomap_write_end(inode, pos, bytes, copied, page, iomap,
 				srcmap);
-		if (unlikely(status < 0))
-			break;
-		copied = status;
 
 		cond_resched();
 
@@ -891,11 +866,8 @@ iomap_unshare_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 
 		status = iomap_write_end(inode, pos, bytes, bytes, page, iomap,
 				srcmap);
-		if (unlikely(status <= 0)) {
+		if (WARN_ON_ONCE(status == 0))
-			if (WARN_ON_ONCE(status == 0))
+			return -EIO;
-				return -EIO;
-			return status;
-		}
 
 		cond_resched();
 
@@ -928,11 +900,13 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
 }
 EXPORT_SYMBOL_GPL(iomap_file_unshare);
 
-static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset,
+static s64 iomap_zero(struct inode *inode, loff_t pos, u64 length,
-		unsigned bytes, struct iomap *iomap, struct iomap *srcmap)
+		struct iomap *iomap, struct iomap *srcmap)
 {
 	struct page *page;
 	int status;
+	unsigned offset = offset_in_page(pos);
+	unsigned bytes = min_t(u64, PAGE_SIZE - offset, length);
 
 	status = iomap_write_begin(inode, pos, bytes, 0, &page, iomap, srcmap);
 	if (status)
@@ -944,38 +918,33 @@ static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset,
 	return iomap_write_end(inode, pos, bytes, bytes, page, iomap, srcmap);
 }
 
-static loff_t
+static loff_t iomap_zero_range_actor(struct inode *inode, loff_t pos,
-iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count,
+		loff_t length, void *data, struct iomap *iomap,
-		void *data, struct iomap *iomap, struct iomap *srcmap)
+		struct iomap *srcmap)
 {
 	bool *did_zero = data;
 	loff_t written = 0;
-	int status;
 
 	/* already zeroed?  we're done. */
 	if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)
-		return count;
+		return length;
 
 	do {
-		unsigned offset, bytes;
+		s64 bytes;
-
-		offset = offset_in_page(pos);
-		bytes = min_t(loff_t, PAGE_SIZE - offset, count);
 
 		if (IS_DAX(inode))
-			status = dax_iomap_zero(pos, offset, bytes, iomap);
+			bytes = dax_iomap_zero(pos, length, iomap);
 		else
-			status = iomap_zero(inode, pos, offset, bytes, iomap,
+			bytes = iomap_zero(inode, pos, length, iomap, srcmap);
-					srcmap);
+		if (bytes < 0)
-		if (status < 0)
+			return bytes;
-			return status;
 
 		pos += bytes;
-		count -= bytes;
+		length -= bytes;
 		written += bytes;
 		if (did_zero)
 			*did_zero = true;
-	} while (count > 0);
+	} while (length > 0);
 
 	return written;
 }
@@ -1070,7 +1039,7 @@ EXPORT_SYMBOL_GPL(iomap_page_mkwrite);
 
 static void
 iomap_finish_page_writeback(struct inode *inode, struct page *page,
-		int error)
+		int error, unsigned int len)
 {
 	struct iomap_page *iop = to_iomap_page(page);
 
@@ -1079,10 +1048,10 @@ iomap_finish_page_writeback(struct inode *inode, struct page *page,
 		mapping_set_error(inode->i_mapping, -EIO);
 	}
 
-	WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE && !iop);
+	WARN_ON_ONCE(i_blocks_per_page(inode, page) > 1 && !iop);
-	WARN_ON_ONCE(iop && atomic_read(&iop->write_count) <= 0);
+	WARN_ON_ONCE(iop && atomic_read(&iop->write_bytes_pending) <= 0);
 
-	if (!iop || atomic_dec_and_test(&iop->write_count))
+	if (!iop || atomic_sub_and_test(len, &iop->write_bytes_pending))
 		end_page_writeback(page);
 }
 
@@ -1116,7 +1085,8 @@ iomap_finish_ioend(struct iomap_ioend *ioend, int error)
 
 		/* walk each page on bio, ending page IO on them */
 		bio_for_each_segment_all(bv, bio, iter_all)
-			iomap_finish_page_writeback(inode, bv->bv_page, error);
+			iomap_finish_page_writeback(inode, bv->bv_page, error,
+					bv->bv_len);
 		bio_put(bio);
 	}
 	/* The ioend has been freed by bio_put() */
@@ -1332,8 +1302,8 @@ iomap_add_to_ioend(struct inode *inode, loff_t offset, struct page *page,
 
 	merged = __bio_try_merge_page(wpc->ioend->io_bio, page, len, poff,
 			&same_page);
-	if (iop && !same_page)
+	if (iop)
-		atomic_inc(&iop->write_count);
+		atomic_add(len, &iop->write_bytes_pending);
 
 	if (!merged) {
 		if (bio_full(wpc->ioend->io_bio, len)) {
@@ -1375,8 +1345,8 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc,
 	int error = 0, count = 0, i;
 	LIST_HEAD(submit_list);
 
-	WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE && !iop);
+	WARN_ON_ONCE(i_blocks_per_page(inode, page) > 1 && !iop);
-	WARN_ON_ONCE(iop && atomic_read(&iop->write_count) != 0);
+	WARN_ON_ONCE(iop && atomic_read(&iop->write_bytes_pending) != 0);
 
 	/*
 	 * Walk through the page to find areas to write back. If we run off the

fs/iomap/direct-io.c

@@ -77,7 +77,7 @@ static void iomap_dio_submit_bio(struct iomap_dio *dio, struct iomap *iomap,
 		dio->submit.cookie = submit_bio(bio);
 }
 
-static ssize_t iomap_dio_complete(struct iomap_dio *dio)
+ssize_t iomap_dio_complete(struct iomap_dio *dio)
 {
 	const struct iomap_dio_ops *dops = dio->dops;
 	struct kiocb *iocb = dio->iocb;
@@ -109,7 +109,7 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio)
 	 * ->end_io() when necessary, otherwise a racing buffer read would cache
 	 * zeros from unwritten extents.
 	 */
-	if (!dio->error &&
+	if (!dio->error && dio->size &&
 	    (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) {
 		int err;
 		err = invalidate_inode_pages2_range(inode->i_mapping,
@@ -119,6 +119,7 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio)
 			dio_warn_stale_pagecache(iocb->ki_filp);
 	}
 
+	inode_dio_end(file_inode(iocb->ki_filp));
 	/*
 	 * If this is a DSYNC write, make sure we push it to stable storage now
 	 * that we've written data.
@@ -126,11 +127,11 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio)
 	if (ret > 0 && (dio->flags & IOMAP_DIO_NEED_SYNC))
 		ret = generic_write_sync(iocb, ret);
 
-	inode_dio_end(file_inode(iocb->ki_filp));
 	kfree(dio);
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(iomap_dio_complete);
 
 static void iomap_dio_complete_work(struct work_struct *work)
 {
@@ -396,6 +397,16 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 		return iomap_dio_bio_actor(inode, pos, length, dio, iomap);
 	case IOMAP_INLINE:
 		return iomap_dio_inline_actor(inode, pos, length, dio, iomap);
+	case IOMAP_DELALLOC:
+		/*
+		 * DIO is not serialised against mmap() access at all, and so
+		 * if the page_mkwrite occurs between the writeback and the
+		 * iomap_apply() call in the DIO path, then it will see the
+		 * DELALLOC block that the page-mkwrite allocated.
+		 */
+		pr_warn_ratelimited("Direct I/O collision with buffered writes! File: %pD4 Comm: %.20s\n",
+				    dio->iocb->ki_filp, current->comm);
+		return -EIO;
 	default:
 		WARN_ON_ONCE(1);
 		return -EIO;
@@ -414,8 +425,8 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
  * Returns -ENOTBLK In case of a page invalidation invalidation failure for
  * writes.  The callers needs to fall back to buffered I/O in this case.
  */
-ssize_t
+struct iomap_dio *
-iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
+__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
 		bool wait_for_completion)
 {
@@ -429,14 +440,14 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	struct iomap_dio *dio;
 
 	if (!count)
-		return 0;
+		return NULL;
 
 	if (WARN_ON(is_sync_kiocb(iocb) && !wait_for_completion))
-		return -EIO;
+		return ERR_PTR(-EIO);
 
 	dio = kmalloc(sizeof(*dio), GFP_KERNEL);
 	if (!dio)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	dio->iocb = iocb;
 	atomic_set(&dio->ref, 1);
@@ -566,7 +577,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	dio->wait_for_completion = wait_for_completion;
 	if (!atomic_dec_and_test(&dio->ref)) {
 		if (!wait_for_completion)
-			return -EIOCBQUEUED;
+			return ERR_PTR(-EIOCBQUEUED);
 
 		for (;;) {
 			set_current_state(TASK_UNINTERRUPTIBLE);
@@ -582,10 +593,26 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		__set_current_state(TASK_RUNNING);
 	}
 
-	return iomap_dio_complete(dio);
+	return dio;
 
 out_free_dio:
 	kfree(dio);
-	return ret;
+	if (ret)
+		return ERR_PTR(ret);
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(__iomap_dio_rw);
+
+ssize_t
+iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
+		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
+		bool wait_for_completion)
+{
+	struct iomap_dio *dio;
+
+	dio = __iomap_dio_rw(iocb, iter, ops, dops, wait_for_completion);
+	if (IS_ERR_OR_NULL(dio))
+		return PTR_ERR_OR_ZERO(dio);
+	return iomap_dio_complete(dio);
 }
 EXPORT_SYMBOL_GPL(iomap_dio_rw);

fs/jfs/jfs_metapage.c

@@ -473,7 +473,7 @@ static int metapage_readpage(struct file *fp, struct page *page)
 	struct inode *inode = page->mapping->host;
 	struct bio *bio = NULL;
 	int block_offset;
-	int blocks_per_page = PAGE_SIZE >> inode->i_blkbits;
+	int blocks_per_page = i_blocks_per_page(inode, page);
 	sector_t page_start;	/* address of page in fs blocks */
 	sector_t pblock;
 	int xlen;

fs/xfs/kmem.c

@@ -93,25 +93,3 @@ kmem_alloc_large(size_t size, xfs_km_flags_t flags)
 		return ptr;
 	return __kmem_vmalloc(size, flags);
 }
-
-void *
-kmem_realloc(const void *old, size_t newsize, xfs_km_flags_t flags)
-{
-	int	retries = 0;
-	gfp_t	lflags = kmem_flags_convert(flags);
-	void	*ptr;
-
-	trace_kmem_realloc(newsize, flags, _RET_IP_);
-
-	do {
-		ptr = krealloc(old, newsize, lflags);
-		if (ptr || (flags & KM_MAYFAIL))
-			return ptr;
-		if (!(++retries % 100))
-			xfs_err(NULL,
-	"%s(%u) possible memory allocation deadlock size %zu in %s (mode:0x%x)",
-				current->comm, current->pid,
-				newsize, __func__, lflags);
-		congestion_wait(BLK_RW_ASYNC, HZ/50);
-	} while (1);
-}

fs/xfs/kmem.h

@@ -59,7 +59,6 @@ kmem_flags_convert(xfs_km_flags_t flags)
 extern void *kmem_alloc(size_t, xfs_km_flags_t);
 extern void *kmem_alloc_io(size_t size, int align_mask, xfs_km_flags_t flags);
 extern void *kmem_alloc_large(size_t size, xfs_km_flags_t);
-extern void *kmem_realloc(const void *, size_t, xfs_km_flags_t);
 static inline void  kmem_free(const void *ptr)
 {
 	kvfree(ptr);
@@ -72,12 +71,6 @@ kmem_zalloc(size_t size, xfs_km_flags_t flags)
 	return kmem_alloc(size, flags | KM_ZERO);
 }
 
-static inline void *
-kmem_zalloc_large(size_t size, xfs_km_flags_t flags)
-{
-	return kmem_alloc_large(size, flags | KM_ZERO);
-}
-
 /*
  * Zone interfaces
  */

fs/xfs/libxfs/xfs_ag.c

@@ -333,6 +333,11 @@ xfs_agiblock_init(
 	}
 	for (bucket = 0; bucket < XFS_AGI_UNLINKED_BUCKETS; bucket++)
 		agi->agi_unlinked[bucket] = cpu_to_be32(NULLAGINO);
+	if (xfs_sb_version_hasinobtcounts(&mp->m_sb)) {
+		agi->agi_iblocks = cpu_to_be32(1);
+		if (xfs_sb_version_hasfinobt(&mp->m_sb))
+			agi->agi_fblocks = cpu_to_be32(1);
+	}
 }
 
 typedef void (*aghdr_init_work_f)(struct xfs_mount *mp, struct xfs_buf *bp,

fs/xfs/libxfs/xfs_attr.c

@@ -428,7 +428,7 @@ xfs_attr_set(
 		 */
 		if (XFS_IFORK_Q(dp) == 0) {
 			int sf_size = sizeof(struct xfs_attr_sf_hdr) +
-				XFS_ATTR_SF_ENTSIZE_BYNAME(args->namelen,
+				xfs_attr_sf_entsize_byname(args->namelen,
 						args->valuelen);
 
 			error = xfs_bmap_add_attrfork(dp, sf_size, rsvd);
@@ -523,6 +523,14 @@ out_trans_cancel:
  * External routines when attribute list is inside the inode
  *========================================================================*/
 
+static inline int xfs_attr_sf_totsize(struct xfs_inode *dp)
+{
+	struct xfs_attr_shortform *sf;
+
+	sf = (struct xfs_attr_shortform *)dp->i_afp->if_u1.if_data;
+	return be16_to_cpu(sf->hdr.totsize);
+}
+
 /*
  * Add a name to the shortform attribute list structure
  * This is the external routine.
@@ -555,8 +563,8 @@ xfs_attr_shortform_addname(xfs_da_args_t *args)
 	    args->valuelen >= XFS_ATTR_SF_ENTSIZE_MAX)
 		return -ENOSPC;
 
-	newsize = XFS_ATTR_SF_TOTSIZE(args->dp);
+	newsize = xfs_attr_sf_totsize(args->dp);
-	newsize += XFS_ATTR_SF_ENTSIZE_BYNAME(args->namelen, args->valuelen);
+	newsize += xfs_attr_sf_entsize_byname(args->namelen, args->valuelen);
 
 	forkoff = xfs_attr_shortform_bytesfit(args->dp, newsize);
 	if (!forkoff)

fs/xfs/libxfs/xfs_attr_leaf.c

@@ -684,9 +684,9 @@ xfs_attr_sf_findname(
 	sf = (struct xfs_attr_shortform *)args->dp->i_afp->if_u1.if_data;
 	sfe = &sf->list[0];
 	end = sf->hdr.count;
-	for (i = 0; i < end; sfe = XFS_ATTR_SF_NEXTENTRY(sfe),
+	for (i = 0; i < end; sfe = xfs_attr_sf_nextentry(sfe),
 			     base += size, i++) {
-		size = XFS_ATTR_SF_ENTSIZE(sfe);
+		size = xfs_attr_sf_entsize(sfe);
 		if (!xfs_attr_match(args, sfe->namelen, sfe->nameval,
 				    sfe->flags))
 			continue;
@@ -728,15 +728,15 @@ xfs_attr_shortform_add(
 
 	ifp = dp->i_afp;
 	ASSERT(ifp->if_flags & XFS_IFINLINE);
-	sf = (xfs_attr_shortform_t *)ifp->if_u1.if_data;
+	sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
 	if (xfs_attr_sf_findname(args, &sfe, NULL) == -EEXIST)
 		ASSERT(0);
 
 	offset = (char *)sfe - (char *)sf;
-	size = XFS_ATTR_SF_ENTSIZE_BYNAME(args->namelen, args->valuelen);
+	size = xfs_attr_sf_entsize_byname(args->namelen, args->valuelen);
 	xfs_idata_realloc(dp, size, XFS_ATTR_FORK);
-	sf = (xfs_attr_shortform_t *)ifp->if_u1.if_data;
+	sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
-	sfe = (xfs_attr_sf_entry_t *)((char *)sf + offset);
+	sfe = (struct xfs_attr_sf_entry *)((char *)sf + offset);
 
 	sfe->namelen = args->namelen;
 	sfe->valuelen = args->valuelen;
@@ -787,12 +787,12 @@ xfs_attr_shortform_remove(
 
 	dp = args->dp;
 	mp = dp->i_mount;
-	sf = (xfs_attr_shortform_t *)dp->i_afp->if_u1.if_data;
+	sf = (struct xfs_attr_shortform *)dp->i_afp->if_u1.if_data;
 
 	error = xfs_attr_sf_findname(args, &sfe, &base);
 	if (error != -EEXIST)
 		return error;
-	size = XFS_ATTR_SF_ENTSIZE(sfe);
+	size = xfs_attr_sf_entsize(sfe);
 
 	/*
 	 * Fix up the attribute fork data, covering the hole
@@ -837,8 +837,8 @@ xfs_attr_shortform_remove(
 int
 xfs_attr_shortform_lookup(xfs_da_args_t *args)
 {
-	xfs_attr_shortform_t *sf;
+	struct xfs_attr_shortform *sf;
-	xfs_attr_sf_entry_t *sfe;
+	struct xfs_attr_sf_entry *sfe;
 	int i;
 	struct xfs_ifork *ifp;
 
@@ -846,10 +846,10 @@ xfs_attr_shortform_lookup(xfs_da_args_t *args)
 
 	ifp = args->dp->i_afp;
 	ASSERT(ifp->if_flags & XFS_IFINLINE);
-	sf = (xfs_attr_shortform_t *)ifp->if_u1.if_data;
+	sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
 	sfe = &sf->list[0];
 	for (i = 0; i < sf->hdr.count;
-				sfe = XFS_ATTR_SF_NEXTENTRY(sfe), i++) {
+				sfe = xfs_attr_sf_nextentry(sfe), i++) {
 		if (xfs_attr_match(args, sfe->namelen, sfe->nameval,
 				sfe->flags))
 			return -EEXIST;
@@ -873,10 +873,10 @@ xfs_attr_shortform_getvalue(
 	int			i;
 
 	ASSERT(args->dp->i_afp->if_flags == XFS_IFINLINE);
-	sf = (xfs_attr_shortform_t *)args->dp->i_afp->if_u1.if_data;
+	sf = (struct xfs_attr_shortform *)args->dp->i_afp->if_u1.if_data;
 	sfe = &sf->list[0];
 	for (i = 0; i < sf->hdr.count;
-				sfe = XFS_ATTR_SF_NEXTENTRY(sfe), i++) {
+				sfe = xfs_attr_sf_nextentry(sfe), i++) {
 		if (xfs_attr_match(args, sfe->namelen, sfe->nameval,
 				sfe->flags))
 			return xfs_attr_copy_value(args,
@@ -908,12 +908,12 @@ xfs_attr_shortform_to_leaf(
 
 	dp = args->dp;
 	ifp = dp->i_afp;
-	sf = (xfs_attr_shortform_t *)ifp->if_u1.if_data;
+	sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
 	size = be16_to_cpu(sf->hdr.totsize);
 	tmpbuffer = kmem_alloc(size, 0);
 	ASSERT(tmpbuffer != NULL);
 	memcpy(tmpbuffer, ifp->if_u1.if_data, size);
-	sf = (xfs_attr_shortform_t *)tmpbuffer;
+	sf = (struct xfs_attr_shortform *)tmpbuffer;
 
 	xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
 	xfs_bmap_local_to_extents_empty(args->trans, dp, XFS_ATTR_FORK);
@@ -951,7 +951,7 @@ xfs_attr_shortform_to_leaf(
 		ASSERT(error != -ENOSPC);
 		if (error)
 			goto out;
-		sfe = XFS_ATTR_SF_NEXTENTRY(sfe);
+		sfe = xfs_attr_sf_nextentry(sfe);
 	}
 	error = 0;
 	*leaf_bp = bp;
@@ -992,9 +992,8 @@ xfs_attr_shortform_allfit(
 			return 0;
 		if (be16_to_cpu(name_loc->valuelen) >= XFS_ATTR_SF_ENTSIZE_MAX)
 			return 0;
-		bytes += sizeof(struct xfs_attr_sf_entry) - 1
+		bytes += xfs_attr_sf_entsize_byname(name_loc->namelen,
-				+ name_loc->namelen
+					be16_to_cpu(name_loc->valuelen));
-				+ be16_to_cpu(name_loc->valuelen);
 	}
 	if ((dp->i_mount->m_flags & XFS_MOUNT_ATTR2) &&
 	    (dp->i_df.if_format != XFS_DINODE_FMT_BTREE) &&
@@ -1039,7 +1038,7 @@ xfs_attr_shortform_verify(
 		 * xfs_attr_sf_entry is defined with a 1-byte variable
 		 * array at the end, so we must subtract that off.
 		 */
-		if (((char *)sfep + sizeof(*sfep) - 1) >= endp)
+		if (((char *)sfep + sizeof(*sfep)) >= endp)
 			return __this_address;
 
 		/* Don't allow names with known bad length. */
@@ -1051,7 +1050,7 @@ xfs_attr_shortform_verify(
 		 * within the data buffer.  The next entry starts after the
 		 * name component, so nextentry is an acceptable test.
 		 */
-		next_sfep = XFS_ATTR_SF_NEXTENTRY(sfep);
+		next_sfep = xfs_attr_sf_nextentry(sfep);
 		if ((char *)next_sfep > endp)
 			return __this_address;
 

fs/xfs/libxfs/xfs_attr_sf.h

@@ -13,7 +13,6 @@
  * to fit into the literal area of the inode.
  */
 typedef struct xfs_attr_sf_hdr xfs_attr_sf_hdr_t;
-typedef struct xfs_attr_sf_entry xfs_attr_sf_entry_t;
 
 /*
  * We generate this then sort it, attr_list() must return things in hash-order.
@@ -27,16 +26,26 @@ typedef struct xfs_attr_sf_sort {
 	unsigned char	*name;		/* name value, pointer into buffer */
 } xfs_attr_sf_sort_t;
 
-#define XFS_ATTR_SF_ENTSIZE_BYNAME(nlen,vlen)	/* space name/value uses */ \
-	(((int)sizeof(xfs_attr_sf_entry_t)-1 + (nlen)+(vlen)))
 #define XFS_ATTR_SF_ENTSIZE_MAX			/* max space for name&value */ \
 	((1 << (NBBY*(int)sizeof(uint8_t))) - 1)
-#define XFS_ATTR_SF_ENTSIZE(sfep)		/* space an entry uses */ \
+
-	((int)sizeof(xfs_attr_sf_entry_t)-1 + (sfep)->namelen+(sfep)->valuelen)
+/* space name/value uses */
-#define XFS_ATTR_SF_NEXTENTRY(sfep)		/* next entry in struct */ \
+static inline int xfs_attr_sf_entsize_byname(uint8_t nlen, uint8_t vlen)
-	((xfs_attr_sf_entry_t *)((char *)(sfep) + XFS_ATTR_SF_ENTSIZE(sfep)))
+{
-#define XFS_ATTR_SF_TOTSIZE(dp)			/* total space in use */ \
+	return sizeof(struct xfs_attr_sf_entry) + nlen + vlen;
-	(be16_to_cpu(((xfs_attr_shortform_t *)	\
+}
-		((dp)->i_afp->if_u1.if_data))->hdr.totsize))
+
+/* space an entry uses */
+static inline int xfs_attr_sf_entsize(struct xfs_attr_sf_entry *sfep)
+{
+	return struct_size(sfep, nameval, sfep->namelen + sfep->valuelen);
+}
+
+/* next entry in struct */
+static inline struct xfs_attr_sf_entry *
+xfs_attr_sf_nextentry(struct xfs_attr_sf_entry *sfep)
+{
+	return (void *)sfep + xfs_attr_sf_entsize(sfep);
+}
 
 #endif	/* __XFS_ATTR_SF_H__ */

fs/xfs/libxfs/xfs_da_format.h

@@ -579,7 +579,7 @@ xfs_dir2_block_leaf_p(struct xfs_dir2_block_tail *btp)
 /*
  * Entries are packed toward the top as tight as possible.
  */
-typedef struct xfs_attr_shortform {
+struct xfs_attr_shortform {
 	struct xfs_attr_sf_hdr {	/* constant-structure header block */
 		__be16	totsize;	/* total bytes in shortform list */
 		__u8	count;	/* count of active entries */
@@ -589,9 +589,9 @@ typedef struct xfs_attr_shortform {
 		uint8_t namelen;	/* actual length of name (no NULL) */
 		uint8_t valuelen;	/* actual length of value (no NULL) */
 		uint8_t flags;	/* flags bits (see xfs_attr_leaf.h) */
-		uint8_t nameval[1];	/* name & value bytes concatenated */
+		uint8_t nameval[];	/* name & value bytes concatenated */
 	} list[1];			/* variable sized array */
-} xfs_attr_shortform_t;
+};
 
 typedef struct xfs_attr_leaf_map {	/* RLE map of free bytes */
 	__be16	base;			  /* base of free region */

fs/xfs/libxfs/xfs_dquot_buf.c

@@ -69,6 +69,13 @@ xfs_dquot_verify(
 	    ddq_type != XFS_DQTYPE_GROUP)
 		return __this_address;
 
+	if ((ddq->d_type & XFS_DQTYPE_BIGTIME) &&
+	    !xfs_sb_version_hasbigtime(&mp->m_sb))
+		return __this_address;
+
+	if ((ddq->d_type & XFS_DQTYPE_BIGTIME) && !ddq->d_id)
+		return __this_address;
+
 	if (id != -1 && id != be32_to_cpu(ddq->d_id))
 		return __this_address;
 
@@ -288,3 +295,31 @@ const struct xfs_buf_ops xfs_dquot_buf_ra_ops = {
 	.verify_read = xfs_dquot_buf_readahead_verify,
 	.verify_write = xfs_dquot_buf_write_verify,
 };
+
+/* Convert an on-disk timer value into an incore timer value. */
+time64_t
+xfs_dquot_from_disk_ts(
+	struct xfs_disk_dquot	*ddq,
+	__be32			dtimer)
+{
+	uint32_t		t = be32_to_cpu(dtimer);
+
+	if (t != 0 && (ddq->d_type & XFS_DQTYPE_BIGTIME))
+		return xfs_dq_bigtime_to_unix(t);
+
+	return t;
+}
+
+/* Convert an incore timer value into an on-disk timer value. */
+__be32
+xfs_dquot_to_disk_ts(
+	struct xfs_dquot	*dqp,
+	time64_t		timer)
+{
+	uint32_t		t = timer;
+
+	if (timer != 0 && (dqp->q_type & XFS_DQTYPE_BIGTIME))
+		t = xfs_dq_unix_to_bigtime(timer);
+
+	return cpu_to_be32(t);
+}

fs/xfs/libxfs/xfs_format.h

@@ -449,10 +449,12 @@ xfs_sb_has_compat_feature(
 #define XFS_SB_FEAT_RO_COMPAT_FINOBT   (1 << 0)		/* free inode btree */
 #define XFS_SB_FEAT_RO_COMPAT_RMAPBT   (1 << 1)		/* reverse map btree */
 #define XFS_SB_FEAT_RO_COMPAT_REFLINK  (1 << 2)		/* reflinked files */
+#define XFS_SB_FEAT_RO_COMPAT_INOBTCNT (1 << 3)		/* inobt block counts */
 #define XFS_SB_FEAT_RO_COMPAT_ALL \
 		(XFS_SB_FEAT_RO_COMPAT_FINOBT | \
 		 XFS_SB_FEAT_RO_COMPAT_RMAPBT | \
-		 XFS_SB_FEAT_RO_COMPAT_REFLINK)
+		 XFS_SB_FEAT_RO_COMPAT_REFLINK| \
+		 XFS_SB_FEAT_RO_COMPAT_INOBTCNT)
 #define XFS_SB_FEAT_RO_COMPAT_UNKNOWN	~XFS_SB_FEAT_RO_COMPAT_ALL
 static inline bool
 xfs_sb_has_ro_compat_feature(
@@ -465,10 +467,12 @@ xfs_sb_has_ro_compat_feature(
 #define XFS_SB_FEAT_INCOMPAT_FTYPE	(1 << 0)	/* filetype in dirent */
 #define XFS_SB_FEAT_INCOMPAT_SPINODES	(1 << 1)	/* sparse inode chunks */
 #define XFS_SB_FEAT_INCOMPAT_META_UUID	(1 << 2)	/* metadata UUID */
+#define XFS_SB_FEAT_INCOMPAT_BIGTIME	(1 << 3)	/* large timestamps */
 #define XFS_SB_FEAT_INCOMPAT_ALL \
 		(XFS_SB_FEAT_INCOMPAT_FTYPE|	\
 		 XFS_SB_FEAT_INCOMPAT_SPINODES|	\
-		 XFS_SB_FEAT_INCOMPAT_META_UUID)
+		 XFS_SB_FEAT_INCOMPAT_META_UUID| \
+		 XFS_SB_FEAT_INCOMPAT_BIGTIME)
 
 #define XFS_SB_FEAT_INCOMPAT_UNKNOWN	~XFS_SB_FEAT_INCOMPAT_ALL
 static inline bool
@@ -563,6 +567,23 @@ static inline bool xfs_sb_version_hasreflink(struct xfs_sb *sbp)
 		(sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_REFLINK);
 }
 
+static inline bool xfs_sb_version_hasbigtime(struct xfs_sb *sbp)
+{
+	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 &&
+		(sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_BIGTIME);
+}
+
+/*
+ * Inode btree block counter.  We record the number of inobt and finobt blocks
+ * in the AGI header so that we can skip the finobt walk at mount time when
+ * setting up per-AG reservations.
+ */
+static inline bool xfs_sb_version_hasinobtcounts(struct xfs_sb *sbp)
+{
+	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 &&
+		(sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_INOBTCNT);
+}
+
 /*
  * end of superblock version macros
  */
@@ -765,6 +786,9 @@ typedef struct xfs_agi {
 	__be32		agi_free_root; /* root of the free inode btree */
 	__be32		agi_free_level;/* levels in free inode btree */
 
+	__be32		agi_iblocks;	/* inobt blocks used */
+	__be32		agi_fblocks;	/* finobt blocks used */
+
 	/* structure must be padded to 64 bit alignment */
 } xfs_agi_t;
 
@@ -785,7 +809,8 @@ typedef struct xfs_agi {
 #define	XFS_AGI_ALL_BITS_R1	((1 << XFS_AGI_NUM_BITS_R1) - 1)
 #define	XFS_AGI_FREE_ROOT	(1 << 11)
 #define	XFS_AGI_FREE_LEVEL	(1 << 12)
-#define	XFS_AGI_NUM_BITS_R2	13
+#define	XFS_AGI_IBLOCKS		(1 << 13) /* both inobt/finobt block counters */
+#define	XFS_AGI_NUM_BITS_R2	14
 
 /* disk block (xfs_daddr_t) in the AG */
 #define XFS_AGI_DADDR(mp)	((xfs_daddr_t)(2 << (mp)->m_sectbb_log))
@@ -831,10 +856,87 @@ struct xfs_agfl {
 	    ASSERT(xfs_daddr_to_agno(mp, d) == \
 		   xfs_daddr_to_agno(mp, (d) + (len) - 1)))
 
-typedef struct xfs_timestamp {
+/*
+ * XFS Timestamps
+ * ==============
+ *
+ * Traditional ondisk inode timestamps consist of signed 32-bit counters for
+ * seconds and nanoseconds; time zero is the Unix epoch, Jan  1 00:00:00 UTC
+ * 1970, which means that the timestamp epoch is the same as the Unix epoch.
+ * Therefore, the ondisk min and max defined here can be used directly to
+ * constrain the incore timestamps on a Unix system.  Note that we actually
+ * encode a __be64 value on disk.
+ *
+ * When the bigtime feature is enabled, ondisk inode timestamps become an
+ * unsigned 64-bit nanoseconds counter.  This means that the bigtime inode
+ * timestamp epoch is the start of the classic timestamp range, which is
+ * Dec 31 20:45:52 UTC 1901.  Because the epochs are not the same, callers
+ * /must/ use the bigtime conversion functions when encoding and decoding raw
+ * timestamps.
+ */
+typedef __be64 xfs_timestamp_t;
+
+/* Legacy timestamp encoding format. */
+struct xfs_legacy_timestamp {
 	__be32		t_sec;		/* timestamp seconds */
 	__be32		t_nsec;		/* timestamp nanoseconds */
-} xfs_timestamp_t;
+};
+
+/*
+ * Smallest possible ondisk seconds value with traditional timestamps.  This
+ * corresponds exactly with the incore timestamp Dec 13 20:45:52 UTC 1901.
+ */
+#define XFS_LEGACY_TIME_MIN	((int64_t)S32_MIN)
+
+/*
+ * Largest possible ondisk seconds value with traditional timestamps.  This
+ * corresponds exactly with the incore timestamp Jan 19 03:14:07 UTC 2038.
+ */
+#define XFS_LEGACY_TIME_MAX	((int64_t)S32_MAX)
+
+/*
+ * Smallest possible ondisk seconds value with bigtime timestamps.  This
+ * corresponds (after conversion to a Unix timestamp) with the traditional
+ * minimum timestamp of Dec 13 20:45:52 UTC 1901.
+ */
+#define XFS_BIGTIME_TIME_MIN	((int64_t)0)
+
+/*
+ * Largest supported ondisk seconds value with bigtime timestamps.  This
+ * corresponds (after conversion to a Unix timestamp) with an incore timestamp
+ * of Jul  2 20:20:24 UTC 2486.
+ *
+ * We round down the ondisk limit so that the bigtime quota and inode max
+ * timestamps will be the same.
+ */
+#define XFS_BIGTIME_TIME_MAX	((int64_t)((-1ULL / NSEC_PER_SEC) & ~0x3ULL))
+
+/*
+ * Bigtime epoch is set exactly to the minimum time value that a traditional
+ * 32-bit timestamp can represent when using the Unix epoch as a reference.
+ * Hence the Unix epoch is at a fixed offset into the supported bigtime
+ * timestamp range.
+ *
+ * The bigtime epoch also matches the minimum value an on-disk 32-bit XFS
+ * timestamp can represent so we will not lose any fidelity in converting
+ * to/from unix and bigtime timestamps.
+ *
+ * The following conversion factor converts a seconds counter from the Unix
+ * epoch to the bigtime epoch.
+ */
+#define XFS_BIGTIME_EPOCH_OFFSET	(-(int64_t)S32_MIN)
+
+/* Convert a timestamp from the Unix epoch to the bigtime epoch. */
+static inline uint64_t xfs_unix_to_bigtime(time64_t unix_seconds)
+{
+	return (uint64_t)unix_seconds + XFS_BIGTIME_EPOCH_OFFSET;
+}
+
+/* Convert a timestamp from the bigtime epoch to the Unix epoch. */
+static inline time64_t xfs_bigtime_to_unix(uint64_t ondisk_seconds)
+{
+	return (time64_t)ondisk_seconds - XFS_BIGTIME_EPOCH_OFFSET;
+}
 
 /*
  * On-disk inode structure.
@@ -1061,12 +1163,22 @@ static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev)
 #define XFS_DIFLAG2_DAX_BIT	0	/* use DAX for this inode */
 #define XFS_DIFLAG2_REFLINK_BIT	1	/* file's blocks may be shared */
 #define XFS_DIFLAG2_COWEXTSIZE_BIT   2  /* copy on write extent size hint */
+#define XFS_DIFLAG2_BIGTIME_BIT	3	/* big timestamps */
+
 #define XFS_DIFLAG2_DAX		(1 << XFS_DIFLAG2_DAX_BIT)
 #define XFS_DIFLAG2_REFLINK     (1 << XFS_DIFLAG2_REFLINK_BIT)
 #define XFS_DIFLAG2_COWEXTSIZE  (1 << XFS_DIFLAG2_COWEXTSIZE_BIT)
+#define XFS_DIFLAG2_BIGTIME	(1 << XFS_DIFLAG2_BIGTIME_BIT)
 
 #define XFS_DIFLAG2_ANY \
-	(XFS_DIFLAG2_DAX | XFS_DIFLAG2_REFLINK | XFS_DIFLAG2_COWEXTSIZE)
+	(XFS_DIFLAG2_DAX | XFS_DIFLAG2_REFLINK | XFS_DIFLAG2_COWEXTSIZE | \
+	 XFS_DIFLAG2_BIGTIME)
+
+static inline bool xfs_dinode_has_bigtime(const struct xfs_dinode *dip)
+{
+	return dip->di_version >= 3 &&
+	       (dip->di_flags2 & cpu_to_be64(XFS_DIFLAG2_BIGTIME));
+}
 
 /*
  * Inode number format:
@@ -1152,13 +1264,98 @@ static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev)
 #define XFS_DQTYPE_USER		0x01		/* user dquot record */
 #define XFS_DQTYPE_PROJ		0x02		/* project dquot record */
 #define XFS_DQTYPE_GROUP	0x04		/* group dquot record */
+#define XFS_DQTYPE_BIGTIME	0x80		/* large expiry timestamps */
 
 /* bitmask to determine if this is a user/group/project dquot */
 #define XFS_DQTYPE_REC_MASK	(XFS_DQTYPE_USER | \
 				 XFS_DQTYPE_PROJ | \
 				 XFS_DQTYPE_GROUP)
 
-#define XFS_DQTYPE_ANY		(XFS_DQTYPE_REC_MASK)
+#define XFS_DQTYPE_ANY		(XFS_DQTYPE_REC_MASK | \
+				 XFS_DQTYPE_BIGTIME)
+
+/*
+ * XFS Quota Timers
+ * ================
+ *
+ * Traditional quota grace period expiration timers are an unsigned 32-bit
+ * seconds counter; time zero is the Unix epoch, Jan  1 00:00:01 UTC 1970.
+ * Note that an expiration value of zero means that the quota limit has not
+ * been reached, and therefore no expiration has been set.  Therefore, the
+ * ondisk min and max defined here can be used directly to constrain the incore
+ * quota expiration timestamps on a Unix system.
+ *
+ * When bigtime is enabled, we trade two bits of precision to expand the
+ * expiration timeout range to match that of big inode timestamps.  The min and
+ * max recorded here are the on-disk limits, not a Unix timestamp.
+ *
+ * The grace period for each quota type is stored in the root dquot (id = 0)
+ * and is applied to a non-root dquot when it exceeds the soft or hard limits.
+ * The length of quota grace periods are unsigned 32-bit quantities measured in
+ * units of seconds.  A value of zero means to use the default period.
+ */
+
+/*
+ * Smallest possible ondisk quota expiration value with traditional timestamps.
+ * This corresponds exactly with the incore expiration Jan  1 00:00:01 UTC 1970.
+ */
+#define XFS_DQ_LEGACY_EXPIRY_MIN	((int64_t)1)
+
+/*
+ * Largest possible ondisk quota expiration value with traditional timestamps.
+ * This corresponds exactly with the incore expiration Feb  7 06:28:15 UTC 2106.
+ */
+#define XFS_DQ_LEGACY_EXPIRY_MAX	((int64_t)U32_MAX)
+
+/*
+ * Smallest possible ondisk quota expiration value with bigtime timestamps.
+ * This corresponds (after conversion to a Unix timestamp) with the incore
+ * expiration of Jan  1 00:00:04 UTC 1970.
+ */
+#define XFS_DQ_BIGTIME_EXPIRY_MIN	(XFS_DQ_LEGACY_EXPIRY_MIN)
+
+/*
+ * Largest supported ondisk quota expiration value with bigtime timestamps.
+ * This corresponds (after conversion to a Unix timestamp) with an incore
+ * expiration of Jul  2 20:20:24 UTC 2486.
+ *
+ * The ondisk field supports values up to -1U, which corresponds to an incore
+ * expiration in 2514.  This is beyond the maximum the bigtime inode timestamp,
+ * so we cap the maximum bigtime quota expiration to the max inode timestamp.
+ */
+#define XFS_DQ_BIGTIME_EXPIRY_MAX	((int64_t)4074815106U)
+
+/*
+ * The following conversion factors assist in converting a quota expiration
+ * timestamp between the incore and ondisk formats.
+ */
+#define XFS_DQ_BIGTIME_SHIFT	(2)
+#define XFS_DQ_BIGTIME_SLACK	((int64_t)(1ULL << XFS_DQ_BIGTIME_SHIFT) - 1)
+
+/* Convert an incore quota expiration timestamp to an ondisk bigtime value. */
+static inline uint32_t xfs_dq_unix_to_bigtime(time64_t unix_seconds)
+{
+	/*
+	 * Round the expiration timestamp up to the nearest bigtime timestamp
+	 * that we can store, to give users the most time to fix problems.
+	 */
+	return ((uint64_t)unix_seconds + XFS_DQ_BIGTIME_SLACK) >>
+			XFS_DQ_BIGTIME_SHIFT;
+}
+
+/* Convert an ondisk bigtime quota expiration value to an incore timestamp. */
+static inline time64_t xfs_dq_bigtime_to_unix(uint32_t ondisk_seconds)
+{
+	return (time64_t)ondisk_seconds << XFS_DQ_BIGTIME_SHIFT;
+}
+
+/*
+ * Default quota grace periods, ranging from zero (use the compiled defaults)
+ * to ~136 years.  These are applied to a non-root dquot that has exceeded
+ * either limit.
+ */
+#define XFS_DQ_GRACE_MIN		((int64_t)0)
+#define XFS_DQ_GRACE_MAX		((int64_t)U32_MAX)
 
 /*
  * This is the main portion of the on-disk representation of quota information

fs/xfs/libxfs/xfs_fs.h

@@ -249,6 +249,7 @@ typedef struct xfs_fsop_resblks {
 #define XFS_FSOP_GEOM_FLAGS_SPINODES	(1 << 18) /* sparse inode chunks   */
 #define XFS_FSOP_GEOM_FLAGS_RMAPBT	(1 << 19) /* reverse mapping btree */
 #define XFS_FSOP_GEOM_FLAGS_REFLINK	(1 << 20) /* files can share blocks */
+#define XFS_FSOP_GEOM_FLAGS_BIGTIME	(1 << 21) /* 64-bit nsec timestamps */
 
 /*
  * Minimum and maximum sizes need for growth checks.

fs/xfs/libxfs/xfs_ialloc.c

@@ -2473,6 +2473,7 @@ xfs_ialloc_log_agi(
 		offsetof(xfs_agi_t, agi_unlinked),
 		offsetof(xfs_agi_t, agi_free_root),
 		offsetof(xfs_agi_t, agi_free_level),
+		offsetof(xfs_agi_t, agi_iblocks),
 		sizeof(xfs_agi_t)
 	};
 #ifdef DEBUG
@@ -2806,6 +2807,10 @@ xfs_ialloc_setup_geometry(
 	uint64_t		icount;
 	uint			inodes;
 
+	igeo->new_diflags2 = 0;
+	if (xfs_sb_version_hasbigtime(&mp->m_sb))
+		igeo->new_diflags2 |= XFS_DIFLAG2_BIGTIME;
+
 	/* Compute inode btree geometry. */
 	igeo->agino_log = sbp->sb_inopblog + sbp->sb_agblklog;
 	igeo->inobt_mxr[0] = xfs_inobt_maxrecs(mp, sbp->sb_blocksize, 1);

fs/xfs/libxfs/xfs_ialloc_btree.c

@@ -67,6 +67,25 @@ xfs_finobt_set_root(
 			   XFS_AGI_FREE_ROOT | XFS_AGI_FREE_LEVEL);
 }
 
+/* Update the inode btree block counter for this btree. */
+static inline void
+xfs_inobt_mod_blockcount(
+	struct xfs_btree_cur	*cur,
+	int			howmuch)
+{
+	struct xfs_buf		*agbp = cur->bc_ag.agbp;
+	struct xfs_agi		*agi = agbp->b_addr;
+
+	if (!xfs_sb_version_hasinobtcounts(&cur->bc_mp->m_sb))
+		return;
+
+	if (cur->bc_btnum == XFS_BTNUM_FINO)
+		be32_add_cpu(&agi->agi_fblocks, howmuch);
+	else if (cur->bc_btnum == XFS_BTNUM_INO)
+		be32_add_cpu(&agi->agi_iblocks, howmuch);
+	xfs_ialloc_log_agi(cur->bc_tp, agbp, XFS_AGI_IBLOCKS);
+}
+
 STATIC int
 __xfs_inobt_alloc_block(
 	struct xfs_btree_cur	*cur,
@@ -102,6 +121,7 @@ __xfs_inobt_alloc_block(
 
 	new->s = cpu_to_be32(XFS_FSB_TO_AGBNO(args.mp, args.fsbno));
 	*stat = 1;
+	xfs_inobt_mod_blockcount(cur, 1);
 	return 0;
 }
 
@@ -134,6 +154,7 @@ __xfs_inobt_free_block(
 	struct xfs_buf		*bp,
 	enum xfs_ag_resv_type	resv)
 {
+	xfs_inobt_mod_blockcount(cur, -1);
 	return xfs_free_extent(cur->bc_tp,
 			XFS_DADDR_TO_FSB(cur->bc_mp, XFS_BUF_ADDR(bp)), 1,
 			&XFS_RMAP_OINFO_INOBT, resv);
@@ -480,19 +501,29 @@ xfs_inobt_commit_staged_btree(
 {
 	struct xfs_agi		*agi = agbp->b_addr;
 	struct xbtree_afakeroot	*afake = cur->bc_ag.afake;
+	int			fields;
 
 	ASSERT(cur->bc_flags & XFS_BTREE_STAGING);
 
 	if (cur->bc_btnum == XFS_BTNUM_INO) {
+		fields = XFS_AGI_ROOT | XFS_AGI_LEVEL;
 		agi->agi_root = cpu_to_be32(afake->af_root);
 		agi->agi_level = cpu_to_be32(afake->af_levels);
-		xfs_ialloc_log_agi(tp, agbp, XFS_AGI_ROOT | XFS_AGI_LEVEL);
+		if (xfs_sb_version_hasinobtcounts(&cur->bc_mp->m_sb)) {
+			agi->agi_iblocks = cpu_to_be32(afake->af_blocks);
+			fields |= XFS_AGI_IBLOCKS;
+		}
+		xfs_ialloc_log_agi(tp, agbp, fields);
 		xfs_btree_commit_afakeroot(cur, tp, agbp, &xfs_inobt_ops);
 	} else {
+		fields = XFS_AGI_FREE_ROOT | XFS_AGI_FREE_LEVEL;
 		agi->agi_free_root = cpu_to_be32(afake->af_root);
 		agi->agi_free_level = cpu_to_be32(afake->af_levels);
-		xfs_ialloc_log_agi(tp, agbp, XFS_AGI_FREE_ROOT |
+		if (xfs_sb_version_hasinobtcounts(&cur->bc_mp->m_sb)) {
-					     XFS_AGI_FREE_LEVEL);
+			agi->agi_fblocks = cpu_to_be32(afake->af_blocks);
+			fields |= XFS_AGI_IBLOCKS;
+		}
+		xfs_ialloc_log_agi(tp, agbp, fields);
 		xfs_btree_commit_afakeroot(cur, tp, agbp, &xfs_finobt_ops);
 	}
 }
@@ -673,6 +704,28 @@ xfs_inobt_count_blocks(
 	return error;
 }
 
+/* Read finobt block count from AGI header. */
+static int
+xfs_finobt_read_blocks(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	xfs_agnumber_t		agno,
+	xfs_extlen_t		*tree_blocks)
+{
+	struct xfs_buf		*agbp;
+	struct xfs_agi		*agi;
+	int			error;
+
+	error = xfs_ialloc_read_agi(mp, tp, agno, &agbp);
+	if (error)
+		return error;
+
+	agi = agbp->b_addr;
+	*tree_blocks = be32_to_cpu(agi->agi_fblocks);
+	xfs_trans_brelse(tp, agbp);
+	return 0;
+}
+
 /*
  * Figure out how many blocks to reserve and how many are used by this btree.
  */
@@ -690,7 +743,11 @@ xfs_finobt_calc_reserves(
 	if (!xfs_sb_version_hasfinobt(&mp->m_sb))
 		return 0;
 
-	error = xfs_inobt_count_blocks(mp, tp, agno, XFS_BTNUM_FINO, &tree_len);
+	if (xfs_sb_version_hasinobtcounts(&mp->m_sb))
+		error = xfs_finobt_read_blocks(mp, tp, agno, &tree_len);
+	else
+		error = xfs_inobt_count_blocks(mp, tp, agno, XFS_BTNUM_FINO,
+				&tree_len);
 	if (error)
 		return error;
 

fs/xfs/libxfs/xfs_iext_tree.c

@@ -603,7 +603,7 @@ xfs_iext_realloc_root(
 	if (new_size / sizeof(struct xfs_iext_rec) == RECS_PER_LEAF)
 		new_size = NODE_SIZE;
 
-	new = kmem_realloc(ifp->if_u1.if_root, new_size, KM_NOFS);
+	new = krealloc(ifp->if_u1.if_root, new_size, GFP_NOFS | __GFP_NOFAIL);
 	memset(new + ifp->if_bytes, 0, new_size - ifp->if_bytes);
 	ifp->if_u1.if_root = new;
 	cur->leaf = new;

fs/xfs/libxfs/xfs_inode_buf.c

@@ -157,6 +157,36 @@ xfs_imap_to_bp(
 	return 0;
 }
 
+static inline struct timespec64 xfs_inode_decode_bigtime(uint64_t ts)
+{
+	struct timespec64	tv;
+	uint32_t		n;
+
+	tv.tv_sec = xfs_bigtime_to_unix(div_u64_rem(ts, NSEC_PER_SEC, &n));
+	tv.tv_nsec = n;
+
+	return tv;
+}
+
+/* Convert an ondisk timestamp to an incore timestamp. */
+struct timespec64
+xfs_inode_from_disk_ts(
+	struct xfs_dinode		*dip,
+	const xfs_timestamp_t		ts)
+{
+	struct timespec64		tv;
+	struct xfs_legacy_timestamp	*lts;
+
+	if (xfs_dinode_has_bigtime(dip))
+		return xfs_inode_decode_bigtime(be64_to_cpu(ts));
+
+	lts = (struct xfs_legacy_timestamp *)&ts;
+	tv.tv_sec = (int)be32_to_cpu(lts->t_sec);
+	tv.tv_nsec = (int)be32_to_cpu(lts->t_nsec);
+
+	return tv;
+}
+
 int
 xfs_inode_from_disk(
 	struct xfs_inode	*ip,
@@ -211,12 +241,9 @@ xfs_inode_from_disk(
 	 * a time before epoch is converted to a time long after epoch
 	 * on 64 bit systems.
 	 */
-	inode->i_atime.tv_sec = (int)be32_to_cpu(from->di_atime.t_sec);
+	inode->i_atime = xfs_inode_from_disk_ts(from, from->di_atime);
-	inode->i_atime.tv_nsec = (int)be32_to_cpu(from->di_atime.t_nsec);
+	inode->i_mtime = xfs_inode_from_disk_ts(from, from->di_mtime);
-	inode->i_mtime.tv_sec = (int)be32_to_cpu(from->di_mtime.t_sec);
+	inode->i_ctime = xfs_inode_from_disk_ts(from, from->di_ctime);
-	inode->i_mtime.tv_nsec = (int)be32_to_cpu(from->di_mtime.t_nsec);
-	inode->i_ctime.tv_sec = (int)be32_to_cpu(from->di_ctime.t_sec);
-	inode->i_ctime.tv_nsec = (int)be32_to_cpu(from->di_ctime.t_nsec);
 
 	to->di_size = be64_to_cpu(from->di_size);
 	to->di_nblocks = be64_to_cpu(from->di_nblocks);
@@ -229,8 +256,7 @@ xfs_inode_from_disk(
 	if (xfs_sb_version_has_v3inode(&ip->i_mount->m_sb)) {
 		inode_set_iversion_queried(inode,
 					   be64_to_cpu(from->di_changecount));
-		to->di_crtime.tv_sec = be32_to_cpu(from->di_crtime.t_sec);
+		to->di_crtime = xfs_inode_from_disk_ts(from, from->di_crtime);
-		to->di_crtime.tv_nsec = be32_to_cpu(from->di_crtime.t_nsec);
 		to->di_flags2 = be64_to_cpu(from->di_flags2);
 		to->di_cowextsize = be32_to_cpu(from->di_cowextsize);
 	}
@@ -252,6 +278,25 @@ out_destroy_data_fork:
 	return error;
 }
 
+/* Convert an incore timestamp to an ondisk timestamp. */
+static inline xfs_timestamp_t
+xfs_inode_to_disk_ts(
+	struct xfs_inode		*ip,
+	const struct timespec64		tv)
+{
+	struct xfs_legacy_timestamp	*lts;
+	xfs_timestamp_t			ts;
+
+	if (xfs_inode_has_bigtime(ip))
+		return cpu_to_be64(xfs_inode_encode_bigtime(tv));
+
+	lts = (struct xfs_legacy_timestamp *)&ts;
+	lts->t_sec = cpu_to_be32(tv.tv_sec);
+	lts->t_nsec = cpu_to_be32(tv.tv_nsec);
+
+	return ts;
+}
+
 void
 xfs_inode_to_disk(
 	struct xfs_inode	*ip,
@@ -271,12 +316,9 @@ xfs_inode_to_disk(
 	to->di_projid_hi = cpu_to_be16(from->di_projid >> 16);
 
 	memset(to->di_pad, 0, sizeof(to->di_pad));
-	to->di_atime.t_sec = cpu_to_be32(inode->i_atime.tv_sec);
+	to->di_atime = xfs_inode_to_disk_ts(ip, inode->i_atime);
-	to->di_atime.t_nsec = cpu_to_be32(inode->i_atime.tv_nsec);
+	to->di_mtime = xfs_inode_to_disk_ts(ip, inode->i_mtime);
-	to->di_mtime.t_sec = cpu_to_be32(inode->i_mtime.tv_sec);
+	to->di_ctime = xfs_inode_to_disk_ts(ip, inode->i_ctime);
-	to->di_mtime.t_nsec = cpu_to_be32(inode->i_mtime.tv_nsec);
-	to->di_ctime.t_sec = cpu_to_be32(inode->i_ctime.tv_sec);
-	to->di_ctime.t_nsec = cpu_to_be32(inode->i_ctime.tv_nsec);
 	to->di_nlink = cpu_to_be32(inode->i_nlink);
 	to->di_gen = cpu_to_be32(inode->i_generation);
 	to->di_mode = cpu_to_be16(inode->i_mode);
@@ -295,8 +337,7 @@ xfs_inode_to_disk(
 	if (xfs_sb_version_has_v3inode(&ip->i_mount->m_sb)) {
 		to->di_version = 3;
 		to->di_changecount = cpu_to_be64(inode_peek_iversion(inode));
-		to->di_crtime.t_sec = cpu_to_be32(from->di_crtime.tv_sec);
+		to->di_crtime = xfs_inode_to_disk_ts(ip, from->di_crtime);
-		to->di_crtime.t_nsec = cpu_to_be32(from->di_crtime.tv_nsec);
 		to->di_flags2 = cpu_to_be64(from->di_flags2);
 		to->di_cowextsize = cpu_to_be32(from->di_cowextsize);
 		to->di_ino = cpu_to_be64(ip->i_ino);
@@ -310,58 +351,6 @@ xfs_inode_to_disk(
 	}
 }
 
-void
-xfs_log_dinode_to_disk(
-	struct xfs_log_dinode	*from,
-	struct xfs_dinode	*to)
-{
-	to->di_magic = cpu_to_be16(from->di_magic);
-	to->di_mode = cpu_to_be16(from->di_mode);
-	to->di_version = from->di_version;
-	to->di_format = from->di_format;
-	to->di_onlink = 0;
-	to->di_uid = cpu_to_be32(from->di_uid);
-	to->di_gid = cpu_to_be32(from->di_gid);
-	to->di_nlink = cpu_to_be32(from->di_nlink);
-	to->di_projid_lo = cpu_to_be16(from->di_projid_lo);
-	to->di_projid_hi = cpu_to_be16(from->di_projid_hi);
-	memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));
-
-	to->di_atime.t_sec = cpu_to_be32(from->di_atime.t_sec);
-	to->di_atime.t_nsec = cpu_to_be32(from->di_atime.t_nsec);
-	to->di_mtime.t_sec = cpu_to_be32(from->di_mtime.t_sec);
-	to->di_mtime.t_nsec = cpu_to_be32(from->di_mtime.t_nsec);
-	to->di_ctime.t_sec = cpu_to_be32(from->di_ctime.t_sec);
-	to->di_ctime.t_nsec = cpu_to_be32(from->di_ctime.t_nsec);
-
-	to->di_size = cpu_to_be64(from->di_size);
-	to->di_nblocks = cpu_to_be64(from->di_nblocks);
-	to->di_extsize = cpu_to_be32(from->di_extsize);
-	to->di_nextents = cpu_to_be32(from->di_nextents);
-	to->di_anextents = cpu_to_be16(from->di_anextents);
-	to->di_forkoff = from->di_forkoff;
-	to->di_aformat = from->di_aformat;
-	to->di_dmevmask = cpu_to_be32(from->di_dmevmask);
-	to->di_dmstate = cpu_to_be16(from->di_dmstate);
-	to->di_flags = cpu_to_be16(from->di_flags);
-	to->di_gen = cpu_to_be32(from->di_gen);
-
-	if (from->di_version == 3) {
-		to->di_changecount = cpu_to_be64(from->di_changecount);
-		to->di_crtime.t_sec = cpu_to_be32(from->di_crtime.t_sec);
-		to->di_crtime.t_nsec = cpu_to_be32(from->di_crtime.t_nsec);
-		to->di_flags2 = cpu_to_be64(from->di_flags2);
-		to->di_cowextsize = cpu_to_be32(from->di_cowextsize);
-		to->di_ino = cpu_to_be64(from->di_ino);
-		to->di_lsn = cpu_to_be64(from->di_lsn);
-		memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
-		uuid_copy(&to->di_uuid, &from->di_uuid);
-		to->di_flushiter = 0;
-	} else {
-		to->di_flushiter = cpu_to_be16(from->di_flushiter);
-	}
-}
-
 static xfs_failaddr_t
 xfs_dinode_verify_fork(
 	struct xfs_dinode	*dip,
@@ -568,6 +557,11 @@ xfs_dinode_verify(
 	if (fa)
 		return fa;
 
+	/* bigtime iflag can only happen on bigtime filesystems */
+	if (xfs_dinode_has_bigtime(dip) &&
+	    !xfs_sb_version_hasbigtime(&mp->m_sb))
+		return __this_address;
+
 	return NULL;
 }
 

fs/xfs/libxfs/xfs_inode_buf.h

@@ -32,6 +32,11 @@ struct xfs_icdinode {
 	struct timespec64 di_crtime;	/* time created */
 };
 
+static inline bool xfs_icdinode_has_bigtime(const struct xfs_icdinode *icd)
+{
+	return icd->di_flags2 & XFS_DIFLAG2_BIGTIME;
+}
+
 /*
  * Inode location information.  Stored in the inode and passed to
  * xfs_imap_to_bp() to get a buffer and dinode for a given inode.
@@ -49,8 +54,6 @@ void	xfs_dinode_calc_crc(struct xfs_mount *, struct xfs_dinode *);
 void	xfs_inode_to_disk(struct xfs_inode *ip, struct xfs_dinode *to,
 			  xfs_lsn_t lsn);
 int	xfs_inode_from_disk(struct xfs_inode *ip, struct xfs_dinode *from);
-void	xfs_log_dinode_to_disk(struct xfs_log_dinode *from,
-			       struct xfs_dinode *to);
 
 xfs_failaddr_t xfs_dinode_verify(struct xfs_mount *mp, xfs_ino_t ino,
 			   struct xfs_dinode *dip);
@@ -60,4 +63,12 @@ xfs_failaddr_t xfs_inode_validate_cowextsize(struct xfs_mount *mp,
 		uint32_t cowextsize, uint16_t mode, uint16_t flags,
 		uint64_t flags2);
 
+static inline uint64_t xfs_inode_encode_bigtime(struct timespec64 tv)
+{
+	return xfs_unix_to_bigtime(tv.tv_sec) * NSEC_PER_SEC + tv.tv_nsec;
+}
+
+struct timespec64 xfs_inode_from_disk_ts(struct xfs_dinode *dip,
+		const xfs_timestamp_t ts);
+
 #endif	/* __XFS_INODE_BUF_H__ */

fs/xfs/libxfs/xfs_inode_fork.c

@@ -386,8 +386,8 @@ xfs_iroot_realloc(
 		cur_max = xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, 0);
 		new_max = cur_max + rec_diff;
 		new_size = XFS_BMAP_BROOT_SPACE_CALC(mp, new_max);
-		ifp->if_broot = kmem_realloc(ifp->if_broot, new_size,
+		ifp->if_broot = krealloc(ifp->if_broot, new_size,
-				KM_NOFS);
+					 GFP_NOFS | __GFP_NOFAIL);
 		op = (char *)XFS_BMAP_BROOT_PTR_ADDR(mp, ifp->if_broot, 1,
 						     ifp->if_broot_bytes);
 		np = (char *)XFS_BMAP_BROOT_PTR_ADDR(mp, ifp->if_broot, 1,
@@ -496,8 +496,8 @@ xfs_idata_realloc(
 	 * in size so that it can be logged and stay on word boundaries.
 	 * We enforce that here.
 	 */
-	ifp->if_u1.if_data = kmem_realloc(ifp->if_u1.if_data,
+	ifp->if_u1.if_data = krealloc(ifp->if_u1.if_data, roundup(new_size, 4),
-			roundup(new_size, 4), KM_NOFS);
+				      GFP_NOFS | __GFP_NOFAIL);
 	ifp->if_bytes = new_size;
 }
 

fs/xfs/libxfs/xfs_log_format.h

@@ -368,10 +368,13 @@ static inline int xfs_ilog_fdata(int w)
  * directly mirrors the xfs_dinode structure as it must contain all the same
  * information.
  */
-typedef struct xfs_ictimestamp {
+typedef uint64_t xfs_ictimestamp_t;
+
+/* Legacy timestamp encoding format. */
+struct xfs_legacy_ictimestamp {
 	int32_t		t_sec;		/* timestamp seconds */
 	int32_t		t_nsec;		/* timestamp nanoseconds */
-} xfs_ictimestamp_t;
+};
 
 /*
  * Define the format of the inode core that is logged. This structure must be

fs/xfs/libxfs/xfs_log_recover.h

@@ -121,7 +121,6 @@ struct xlog_recover {
 void xlog_buf_readahead(struct xlog *log, xfs_daddr_t blkno, uint len,
 		const struct xfs_buf_ops *ops);
 bool xlog_is_buffer_cancelled(struct xlog *log, xfs_daddr_t blkno, uint len);
-void xlog_recover_iodone(struct xfs_buf *bp);
 
 void xlog_recover_release_intent(struct xlog *log, unsigned short intent_type,
 		uint64_t intent_id);

fs/xfs/libxfs/xfs_quota_defs.h

@@ -23,7 +23,8 @@ typedef uint8_t		xfs_dqtype_t;
 #define XFS_DQTYPE_STRINGS \
 	{ XFS_DQTYPE_USER,	"USER" }, \
 	{ XFS_DQTYPE_PROJ,	"PROJ" }, \
-	{ XFS_DQTYPE_GROUP,	"GROUP" }
+	{ XFS_DQTYPE_GROUP,	"GROUP" }, \
+	{ XFS_DQTYPE_BIGTIME,	"BIGTIME" }
 
 /*
  * flags for q_flags field in the dquot.
@@ -143,4 +144,9 @@ extern int xfs_calc_dquots_per_chunk(unsigned int nbblks);
 extern void xfs_dqblk_repair(struct xfs_mount *mp, struct xfs_dqblk *dqb,
 		xfs_dqid_t id, xfs_dqtype_t type);
 
+struct xfs_dquot;
+time64_t xfs_dquot_from_disk_ts(struct xfs_disk_dquot *ddq,
+		__be32 dtimer);
+__be32 xfs_dquot_to_disk_ts(struct xfs_dquot *ddq, time64_t timer);
+
 #endif	/* __XFS_QUOTA_H__ */

fs/xfs/libxfs/xfs_sb.c

@@ -954,7 +954,7 @@ xfs_log_sb(
 	struct xfs_trans	*tp)
 {
 	struct xfs_mount	*mp = tp->t_mountp;
-	struct xfs_buf		*bp = xfs_trans_getsb(tp, mp);
+	struct xfs_buf		*bp = xfs_trans_getsb(tp);
 
 	mp->m_sb.sb_icount = percpu_counter_sum(&mp->m_icount);
 	mp->m_sb.sb_ifree = percpu_counter_sum(&mp->m_ifree);
@@ -1084,7 +1084,7 @@ xfs_sync_sb_buf(
 	if (error)
 		return error;
 
-	bp = xfs_trans_getsb(tp, mp);
+	bp = xfs_trans_getsb(tp);
 	xfs_log_sb(tp);
 	xfs_trans_bhold(tp, bp);
 	xfs_trans_set_sync(tp);
@@ -1166,6 +1166,8 @@ xfs_fs_geometry(
 		geo->flags |= XFS_FSOP_GEOM_FLAGS_RMAPBT;
 	if (xfs_sb_version_hasreflink(sbp))
 		geo->flags |= XFS_FSOP_GEOM_FLAGS_REFLINK;
+	if (xfs_sb_version_hasbigtime(sbp))
+		geo->flags |= XFS_FSOP_GEOM_FLAGS_BIGTIME;
 	if (xfs_sb_version_hassector(sbp))
 		geo->logsectsize = sbp->sb_logsectsize;
 	else

fs/xfs/libxfs/xfs_shared.h

@@ -176,6 +176,9 @@ struct xfs_ino_geometry {
 	unsigned int	ialloc_align;
 
 	unsigned int	agino_log;	/* #bits for agino in inum */
+
+	/* precomputed value for di_flags2 */
+	uint64_t	new_diflags2;
 };
 
 #endif /* __XFS_SHARED_H__ */

fs/xfs/libxfs/xfs_trans_inode.c

@@ -131,6 +131,17 @@ xfs_trans_log_inode(
 			iversion_flags = XFS_ILOG_CORE;
 	}
 
+	/*
+	 * If we're updating the inode core or the timestamps and it's possible
+	 * to upgrade this inode to bigtime format, do so now.
+	 */
+	if ((flags & (XFS_ILOG_CORE | XFS_ILOG_TIMESTAMP)) &&
+	    xfs_sb_version_hasbigtime(&ip->i_mount->m_sb) &&
+	    !xfs_inode_has_bigtime(ip)) {
+		ip->i_d.di_flags2 |= XFS_DIFLAG2_BIGTIME;
+		flags |= XFS_ILOG_CORE;
+	}
+
 	/*
 	 * Record the specific change for fdatasync optimisation. This allows
 	 * fdatasync to skip log forces for inodes that are only timestamp
@@ -177,9 +188,9 @@ xfs_trans_log_inode(
 
 	/*
 	 * Always OR in the bits from the ili_last_fields field.  This is to
-	 * coordinate with the xfs_iflush() and xfs_iflush_done() routines in
+	 * coordinate with the xfs_iflush() and xfs_buf_inode_iodone() routines
-	 * the eventual clearing of the ili_fields bits.  See the big comment in
+	 * in the eventual clearing of the ili_fields bits.  See the big comment
-	 * xfs_iflush() for an explanation of this coordination mechanism.
+	 * in xfs_iflush() for an explanation of this coordination mechanism.
 	 */
 	iip->ili_fields |= (flags | iip->ili_last_fields | iversion_flags);
 	spin_unlock(&iip->ili_lock);

fs/xfs/scrub/agheader.c

@@ -781,6 +781,35 @@ xchk_agi_xref_icounts(
 		xchk_block_xref_set_corrupt(sc, sc->sa.agi_bp);
 }
 
+/* Check agi_[fi]blocks against tree size */
+static inline void
+xchk_agi_xref_fiblocks(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_agi		*agi = sc->sa.agi_bp->b_addr;
+	xfs_agblock_t		blocks;
+	int			error = 0;
+
+	if (!xfs_sb_version_hasinobtcounts(&sc->mp->m_sb))
+		return;
+
+	if (sc->sa.ino_cur) {
+		error = xfs_btree_count_blocks(sc->sa.ino_cur, &blocks);
+		if (!xchk_should_check_xref(sc, &error, &sc->sa.ino_cur))
+			return;
+		if (blocks != be32_to_cpu(agi->agi_iblocks))
+			xchk_block_xref_set_corrupt(sc, sc->sa.agi_bp);
+	}
+
+	if (sc->sa.fino_cur) {
+		error = xfs_btree_count_blocks(sc->sa.fino_cur, &blocks);
+		if (!xchk_should_check_xref(sc, &error, &sc->sa.fino_cur))
+			return;
+		if (blocks != be32_to_cpu(agi->agi_fblocks))
+			xchk_block_xref_set_corrupt(sc, sc->sa.agi_bp);
+	}
+}
+
 /* Cross-reference with the other btrees. */
 STATIC void
 xchk_agi_xref(
@@ -804,6 +833,7 @@ xchk_agi_xref(
 	xchk_agi_xref_icounts(sc);
 	xchk_xref_is_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_FS);
 	xchk_xref_is_not_shared(sc, agbno, 1);
+	xchk_agi_xref_fiblocks(sc);
 
 	/* scrub teardown will take care of sc->sa for us */
 }

fs/xfs/scrub/agheader_repair.c

@@ -810,10 +810,34 @@ xrep_agi_calc_from_btrees(
 	error = xfs_ialloc_count_inodes(cur, &count, &freecount);
 	if (error)
 		goto err;
+	if (xfs_sb_version_hasinobtcounts(&mp->m_sb)) {
+		xfs_agblock_t	blocks;
+
+		error = xfs_btree_count_blocks(cur, &blocks);
+		if (error)
+			goto err;
+		agi->agi_iblocks = cpu_to_be32(blocks);
+	}
 	xfs_btree_del_cursor(cur, error);
 
 	agi->agi_count = cpu_to_be32(count);
 	agi->agi_freecount = cpu_to_be32(freecount);
+
+	if (xfs_sb_version_hasfinobt(&mp->m_sb) &&
+	    xfs_sb_version_hasinobtcounts(&mp->m_sb)) {
+		xfs_agblock_t	blocks;
+
+		cur = xfs_inobt_init_cursor(mp, sc->tp, agi_bp, sc->sa.agno,
+				XFS_BTNUM_FINO);
+		if (error)
+			goto err;
+		error = xfs_btree_count_blocks(cur, &blocks);
+		if (error)
+			goto err;
+		xfs_btree_del_cursor(cur, error);
+		agi->agi_fblocks = cpu_to_be32(blocks);
+	}
+
 	return 0;
 err:
 	xfs_btree_del_cursor(cur, error);

fs/xfs/scrub/inode.c

@@ -190,11 +190,30 @@ xchk_inode_flags2(
 	if ((flags2 & XFS_DIFLAG2_DAX) && (flags2 & XFS_DIFLAG2_REFLINK))
 		goto bad;
 
+	/* no bigtime iflag without the bigtime feature */
+	if (xfs_dinode_has_bigtime(dip) &&
+	    !xfs_sb_version_hasbigtime(&mp->m_sb))
+		goto bad;
+
 	return;
 bad:
 	xchk_ino_set_corrupt(sc, ino);
 }
 
+static inline void
+xchk_dinode_nsec(
+	struct xfs_scrub	*sc,
+	xfs_ino_t		ino,
+	struct xfs_dinode	*dip,
+	const xfs_timestamp_t	ts)
+{
+	struct timespec64	tv;
+
+	tv = xfs_inode_from_disk_ts(dip, ts);
+	if (tv.tv_nsec < 0 || tv.tv_nsec >= NSEC_PER_SEC)
+		xchk_ino_set_corrupt(sc, ino);
+}
+
 /* Scrub all the ondisk inode fields. */
 STATIC void
 xchk_dinode(
@@ -293,12 +312,9 @@ xchk_dinode(
 	}
 
 	/* di_[amc]time.nsec */
-	if (be32_to_cpu(dip->di_atime.t_nsec) >= NSEC_PER_SEC)
+	xchk_dinode_nsec(sc, ino, dip, dip->di_atime);
-		xchk_ino_set_corrupt(sc, ino);
+	xchk_dinode_nsec(sc, ino, dip, dip->di_mtime);
-	if (be32_to_cpu(dip->di_mtime.t_nsec) >= NSEC_PER_SEC)
+	xchk_dinode_nsec(sc, ino, dip, dip->di_ctime);
-		xchk_ino_set_corrupt(sc, ino);
-	if (be32_to_cpu(dip->di_ctime.t_nsec) >= NSEC_PER_SEC)
-		xchk_ino_set_corrupt(sc, ino);
 
 	/*
 	 * di_size.  xfs_dinode_verify checks for things that screw up
@@ -403,8 +419,7 @@ xchk_dinode(
 	}
 
 	if (dip->di_version >= 3) {
-		if (be32_to_cpu(dip->di_crtime.t_nsec) >= NSEC_PER_SEC)
+		xchk_dinode_nsec(sc, ino, dip, dip->di_crtime);
-			xchk_ino_set_corrupt(sc, ino);
 		xchk_inode_flags2(sc, dip, ino, mode, flags, flags2);
 		xchk_inode_cowextsize(sc, dip, ino, mode, flags,
 				flags2);

fs/xfs/scrub/symlink.c

@@ -22,7 +22,7 @@ xchk_setup_symlink(
 	struct xfs_inode	*ip)
 {
 	/* Allocate the buffer without the inode lock held. */
-	sc->buf = kmem_zalloc_large(XFS_SYMLINK_MAXLEN + 1, 0);
+	sc->buf = kvzalloc(XFS_SYMLINK_MAXLEN + 1, GFP_KERNEL);
 	if (!sc->buf)
 		return -ENOMEM;
 

fs/xfs/xfs_acl.c

@@ -192,7 +192,7 @@ __xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 
 	if (acl) {
 		args.valuelen = XFS_ACL_SIZE(acl->a_count);
-		args.value = kmem_zalloc_large(args.valuelen, 0);
+		args.value = kvzalloc(args.valuelen, GFP_KERNEL);
 		if (!args.value)
 			return -ENOMEM;
 		xfs_acl_to_disk(args.value, acl);

fs/xfs/xfs_aops.c

@@ -544,7 +544,7 @@ xfs_discard_page(
 			page, ip->i_ino, offset);
 
 	error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
-			PAGE_SIZE / i_blocksize(inode));
+			i_blocks_per_page(inode, page));
 	if (error && !XFS_FORCED_SHUTDOWN(mp))
 		xfs_alert(mp, "page discard unable to remove delalloc mapping.");
 out_invalidate:

fs/xfs/xfs_attr_list.c

@@ -61,7 +61,7 @@ xfs_attr_shortform_list(
 	int				error = 0;
 
 	ASSERT(dp->i_afp != NULL);
-	sf = (xfs_attr_shortform_t *)dp->i_afp->if_u1.if_data;
+	sf = (struct xfs_attr_shortform *)dp->i_afp->if_u1.if_data;
 	ASSERT(sf != NULL);
 	if (!sf->hdr.count)
 		return 0;
@@ -96,7 +96,7 @@ xfs_attr_shortform_list(
 			 */
 			if (context->seen_enough)
 				break;
-			sfe = XFS_ATTR_SF_NEXTENTRY(sfe);
+			sfe = xfs_attr_sf_nextentry(sfe);
 		}
 		trace_xfs_attr_list_sf_all(context);
 		return 0;
@@ -136,7 +136,7 @@ xfs_attr_shortform_list(
 		/* These are bytes, and both on-disk, don't endian-flip */
 		sbp->valuelen = sfe->valuelen;
 		sbp->flags = sfe->flags;
-		sfe = XFS_ATTR_SF_NEXTENTRY(sfe);
+		sfe = xfs_attr_sf_nextentry(sfe);
 		sbp++;
 		nsbuf++;
 	}

fs/xfs/xfs_bmap_util.c

@@ -946,6 +946,14 @@ xfs_free_file_space(
 	startoffset_fsb = XFS_B_TO_FSB(mp, offset);
 	endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len);
 
+	/* We can only free complete realtime extents. */
+	if (XFS_IS_REALTIME_INODE(ip)) {
+		xfs_extlen_t	extsz = xfs_get_extsz_hint(ip);
+
+		if ((startoffset_fsb | endoffset_fsb) & (extsz - 1))
+			return -EINVAL;
+	}
+
 	/*
 	 * Need to zero the stuff we're not freeing, on disk.
 	 */
@@ -1139,6 +1147,14 @@ xfs_insert_file_space(
 
 	trace_xfs_insert_file_space(ip);
 
+	/* We can only insert complete realtime extents. */
+	if (XFS_IS_REALTIME_INODE(ip)) {
+		xfs_extlen_t	extsz = xfs_get_extsz_hint(ip);
+
+		if ((stop_fsb | shift_fsb) & (extsz - 1))
+			return -EINVAL;
+	}
+
 	error = xfs_bmap_can_insert_extents(ip, stop_fsb, shift_fsb);
 	if (error)
 		return error;

fs/xfs/xfs_buf.c

@@ -52,6 +52,15 @@ static kmem_zone_t *xfs_buf_zone;
  *	  b_lock (trylock due to inversion)
  */
 
+static int __xfs_buf_submit(struct xfs_buf *bp, bool wait);
+
+static inline int
+xfs_buf_submit(
+	struct xfs_buf		*bp)
+{
+	return __xfs_buf_submit(bp, !(bp->b_flags & XBF_ASYNC));
+}
+
 static inline int
 xfs_buf_is_vmapped(
 	struct xfs_buf	*bp)
@@ -751,7 +760,7 @@ found:
 	return 0;
 }
 
-STATIC int
+int
 _xfs_buf_read(
 	xfs_buf_t		*bp,
 	xfs_buf_flags_t		flags)
@@ -759,7 +768,7 @@ _xfs_buf_read(
 	ASSERT(!(flags & XBF_WRITE));
 	ASSERT(bp->b_maps[0].bm_bn != XFS_BUF_DADDR_NULL);
 
-	bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD);
+	bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD | XBF_DONE);
 	bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD);
 
 	return xfs_buf_submit(bp);
@@ -1170,20 +1179,145 @@ xfs_buf_wait_unpin(
 	set_current_state(TASK_RUNNING);
 }
 
-/*
+static void
- *	Buffer Utility Routines
+xfs_buf_ioerror_alert_ratelimited(
- */
+	struct xfs_buf		*bp)
+{
+	static unsigned long	lasttime;
+	static struct xfs_buftarg *lasttarg;
 
-void
+	if (bp->b_target != lasttarg ||
+	    time_after(jiffies, (lasttime + 5*HZ))) {
+		lasttime = jiffies;
+		xfs_buf_ioerror_alert(bp, __this_address);
+	}
+	lasttarg = bp->b_target;
+}
+
+/*
+ * Account for this latest trip around the retry handler, and decide if
+ * we've failed enough times to constitute a permanent failure.
+ */
+static bool
+xfs_buf_ioerror_permanent(
+	struct xfs_buf		*bp,
+	struct xfs_error_cfg	*cfg)
+{
+	struct xfs_mount	*mp = bp->b_mount;
+
+	if (cfg->max_retries != XFS_ERR_RETRY_FOREVER &&
+	    ++bp->b_retries > cfg->max_retries)
+		return true;
+	if (cfg->retry_timeout != XFS_ERR_RETRY_FOREVER &&
+	    time_after(jiffies, cfg->retry_timeout + bp->b_first_retry_time))
+		return true;
+
+	/* At unmount we may treat errors differently */
+	if ((mp->m_flags & XFS_MOUNT_UNMOUNTING) && mp->m_fail_unmount)
+		return true;
+
+	return false;
+}
+
+/*
+ * On a sync write or shutdown we just want to stale the buffer and let the
+ * caller handle the error in bp->b_error appropriately.
+ *
+ * If the write was asynchronous then no one will be looking for the error.  If
+ * this is the first failure of this type, clear the error state and write the
+ * buffer out again. This means we always retry an async write failure at least
+ * once, but we also need to set the buffer up to behave correctly now for
+ * repeated failures.
+ *
+ * If we get repeated async write failures, then we take action according to the
+ * error configuration we have been set up to use.
+ *
+ * Returns true if this function took care of error handling and the caller must
+ * not touch the buffer again.  Return false if the caller should proceed with
+ * normal I/O completion handling.
+ */
+static bool
+xfs_buf_ioend_handle_error(
+	struct xfs_buf		*bp)
+{
+	struct xfs_mount	*mp = bp->b_mount;
+	struct xfs_error_cfg	*cfg;
+
+	/*
+	 * If we've already decided to shutdown the filesystem because of I/O
+	 * errors, there's no point in giving this a retry.
+	 */
+	if (XFS_FORCED_SHUTDOWN(mp))
+		goto out_stale;
+
+	xfs_buf_ioerror_alert_ratelimited(bp);
+
+	/*
+	 * We're not going to bother about retrying this during recovery.
+	 * One strike!
+	 */
+	if (bp->b_flags & _XBF_LOGRECOVERY) {
+		xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
+		return false;
+	}
+
+	/*
+	 * Synchronous writes will have callers process the error.
+	 */
+	if (!(bp->b_flags & XBF_ASYNC))
+		goto out_stale;
+
+	trace_xfs_buf_iodone_async(bp, _RET_IP_);
+
+	cfg = xfs_error_get_cfg(mp, XFS_ERR_METADATA, bp->b_error);
+	if (bp->b_last_error != bp->b_error ||
+	    !(bp->b_flags & (XBF_STALE | XBF_WRITE_FAIL))) {
+		bp->b_last_error = bp->b_error;
+		if (cfg->retry_timeout != XFS_ERR_RETRY_FOREVER &&
+		    !bp->b_first_retry_time)
+			bp->b_first_retry_time = jiffies;
+		goto resubmit;
+	}
+
+	/*
+	 * Permanent error - we need to trigger a shutdown if we haven't already
+	 * to indicate that inconsistency will result from this action.
+	 */
+	if (xfs_buf_ioerror_permanent(bp, cfg)) {
+		xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
+		goto out_stale;
+	}
+
+	/* Still considered a transient error. Caller will schedule retries. */
+	if (bp->b_flags & _XBF_INODES)
+		xfs_buf_inode_io_fail(bp);
+	else if (bp->b_flags & _XBF_DQUOTS)
+		xfs_buf_dquot_io_fail(bp);
+	else
+		ASSERT(list_empty(&bp->b_li_list));
+	xfs_buf_ioerror(bp, 0);
+	xfs_buf_relse(bp);
+	return true;
+
+resubmit:
+	xfs_buf_ioerror(bp, 0);
+	bp->b_flags |= (XBF_DONE | XBF_WRITE_FAIL);
+	xfs_buf_submit(bp);
+	return true;
+out_stale:
+	xfs_buf_stale(bp);
+	bp->b_flags |= XBF_DONE;
+	bp->b_flags &= ~XBF_WRITE;
+	trace_xfs_buf_error_relse(bp, _RET_IP_);
+	return false;
+}
+
+static void
 xfs_buf_ioend(
 	struct xfs_buf	*bp)
 {
-	bool		read = bp->b_flags & XBF_READ;
-
 	trace_xfs_buf_iodone(bp, _RET_IP_);
 
-	bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD);
-
 	/*
 	 * Pull in IO completion errors now. We are guaranteed to be running
 	 * single threaded, so we don't need the lock to read b_io_error.
@@ -1191,39 +1325,47 @@ xfs_buf_ioend(
 	if (!bp->b_error && bp->b_io_error)
 		xfs_buf_ioerror(bp, bp->b_io_error);
 
-	if (read) {
+	if (bp->b_flags & XBF_READ) {
 		if (!bp->b_error && bp->b_ops)
 			bp->b_ops->verify_read(bp);
 		if (!bp->b_error)
 			bp->b_flags |= XBF_DONE;
-		xfs_buf_ioend_finish(bp);
+	} else {
-		return;
+		if (!bp->b_error) {
+			bp->b_flags &= ~XBF_WRITE_FAIL;
+			bp->b_flags |= XBF_DONE;
+		}
+
+		if (unlikely(bp->b_error) && xfs_buf_ioend_handle_error(bp))
+			return;
+
+		/* clear the retry state */
+		bp->b_last_error = 0;
+		bp->b_retries = 0;
+		bp->b_first_retry_time = 0;
+
+		/*
+		 * Note that for things like remote attribute buffers, there may
+		 * not be a buffer log item here, so processing the buffer log
+		 * item must remain optional.
+		 */
+		if (bp->b_log_item)
+			xfs_buf_item_done(bp);
+
+		if (bp->b_flags & _XBF_INODES)
+			xfs_buf_inode_iodone(bp);
+		else if (bp->b_flags & _XBF_DQUOTS)
+			xfs_buf_dquot_iodone(bp);
+
 	}
 
-	if (!bp->b_error) {
+	bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD |
-		bp->b_flags &= ~XBF_WRITE_FAIL;
+			 _XBF_LOGRECOVERY);
-		bp->b_flags |= XBF_DONE;
-	}
 
-	/*
+	if (bp->b_flags & XBF_ASYNC)
-	 * If this is a log recovery buffer, we aren't doing transactional IO
+		xfs_buf_relse(bp);
-	 * yet so we need to let it handle IO completions.
+	else
-	 */
+		complete(&bp->b_iowait);
-	if (bp->b_flags & _XBF_LOGRECOVERY) {
-		xlog_recover_iodone(bp);
-		return;
-	}
-
-	if (bp->b_flags & _XBF_INODES) {
-		xfs_buf_inode_iodone(bp);
-		return;
-	}
-
-	if (bp->b_flags & _XBF_DQUOTS) {
-		xfs_buf_dquot_iodone(bp);
-		return;
-	}
-	xfs_buf_iodone(bp);
 }
 
 static void
@@ -1506,7 +1648,7 @@ xfs_buf_iowait(
  * safe to reference the buffer after a call to this function unless the caller
  * holds an additional reference itself.
  */
-int
+static int
 __xfs_buf_submit(
 	struct xfs_buf	*bp,
 	bool		wait)

fs/xfs/xfs_buf.h

@@ -249,6 +249,7 @@ int xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks, int flags,
 int xfs_buf_read_uncached(struct xfs_buftarg *target, xfs_daddr_t daddr,
 			  size_t numblks, int flags, struct xfs_buf **bpp,
 			  const struct xfs_buf_ops *ops);
+int _xfs_buf_read(struct xfs_buf *bp, xfs_buf_flags_t flags);
 void xfs_buf_hold(struct xfs_buf *bp);
 
 /* Releasing Buffers */
@@ -269,28 +270,12 @@ static inline void xfs_buf_relse(xfs_buf_t *bp)
 
 /* Buffer Read and Write Routines */
 extern int xfs_bwrite(struct xfs_buf *bp);
-extern void xfs_buf_ioend(struct xfs_buf *bp);
-static inline void xfs_buf_ioend_finish(struct xfs_buf *bp)
-{
-	if (bp->b_flags & XBF_ASYNC)
-		xfs_buf_relse(bp);
-	else
-		complete(&bp->b_iowait);
-}
 
 extern void __xfs_buf_ioerror(struct xfs_buf *bp, int error,
 		xfs_failaddr_t failaddr);
 #define xfs_buf_ioerror(bp, err) __xfs_buf_ioerror((bp), (err), __this_address)
 extern void xfs_buf_ioerror_alert(struct xfs_buf *bp, xfs_failaddr_t fa);
 void xfs_buf_ioend_fail(struct xfs_buf *);
-
-extern int __xfs_buf_submit(struct xfs_buf *bp, bool);
-static inline int xfs_buf_submit(struct xfs_buf *bp)
-{
-	bool wait = bp->b_flags & XBF_ASYNC ? false : true;
-	return __xfs_buf_submit(bp, wait);
-}
-
 void xfs_buf_zero(struct xfs_buf *bp, size_t boff, size_t bsize);
 void __xfs_buf_mark_corrupt(struct xfs_buf *bp, xfs_failaddr_t fa);
 #define xfs_buf_mark_corrupt(bp) __xfs_buf_mark_corrupt((bp), __this_address)

fs/xfs/xfs_buf_item.c

@@ -30,8 +30,6 @@ static inline struct xfs_buf_log_item *BUF_ITEM(struct xfs_log_item *lip)
 	return container_of(lip, struct xfs_buf_log_item, bli_item);
 }
 
-static void xfs_buf_item_done(struct xfs_buf *bp);
-
 /* Is this log iovec plausibly large enough to contain the buffer log format? */
 bool
 xfs_buf_log_check_iovec(
@@ -463,7 +461,7 @@ xfs_buf_item_unpin(
 		 */
 		if (bip->bli_flags & XFS_BLI_STALE_INODE) {
 			xfs_buf_item_done(bp);
-			xfs_iflush_done(bp);
+			xfs_buf_inode_iodone(bp);
 			ASSERT(list_empty(&bp->b_li_list));
 		} else {
 			xfs_trans_ail_delete(lip, SHUTDOWN_LOG_IO_ERROR);
@@ -956,153 +954,10 @@ xfs_buf_item_relse(
 	xfs_buf_item_free(bip);
 }
 
-/*
+void
- * Decide if we're going to retry the write after a failure, and prepare
- * the buffer for retrying the write.
- */
-static bool
-xfs_buf_ioerror_fail_without_retry(
-	struct xfs_buf		*bp)
-{
-	struct xfs_mount	*mp = bp->b_mount;
-	static ulong		lasttime;
-	static xfs_buftarg_t	*lasttarg;
-
-	/*
-	 * If we've already decided to shutdown the filesystem because of
-	 * I/O errors, there's no point in giving this a retry.
-	 */
-	if (XFS_FORCED_SHUTDOWN(mp))
-		return true;
-
-	if (bp->b_target != lasttarg ||
-	    time_after(jiffies, (lasttime + 5*HZ))) {
-		lasttime = jiffies;
-		xfs_buf_ioerror_alert(bp, __this_address);
-	}
-	lasttarg = bp->b_target;
-
-	/* synchronous writes will have callers process the error */
-	if (!(bp->b_flags & XBF_ASYNC))
-		return true;
-	return false;
-}
-
-static bool
-xfs_buf_ioerror_retry(
-	struct xfs_buf		*bp,
-	struct xfs_error_cfg	*cfg)
-{
-	if ((bp->b_flags & (XBF_STALE | XBF_WRITE_FAIL)) &&
-	    bp->b_last_error == bp->b_error)
-		return false;
-
-	bp->b_flags |= (XBF_WRITE | XBF_DONE | XBF_WRITE_FAIL);
-	bp->b_last_error = bp->b_error;
-	if (cfg->retry_timeout != XFS_ERR_RETRY_FOREVER &&
-	    !bp->b_first_retry_time)
-		bp->b_first_retry_time = jiffies;
-	return true;
-}
-
-/*
- * Account for this latest trip around the retry handler, and decide if
- * we've failed enough times to constitute a permanent failure.
- */
-static bool
-xfs_buf_ioerror_permanent(
-	struct xfs_buf		*bp,
-	struct xfs_error_cfg	*cfg)
-{
-	struct xfs_mount	*mp = bp->b_mount;
-
-	if (cfg->max_retries != XFS_ERR_RETRY_FOREVER &&
-	    ++bp->b_retries > cfg->max_retries)
-		return true;
-	if (cfg->retry_timeout != XFS_ERR_RETRY_FOREVER &&
-	    time_after(jiffies, cfg->retry_timeout + bp->b_first_retry_time))
-		return true;
-
-	/* At unmount we may treat errors differently */
-	if ((mp->m_flags & XFS_MOUNT_UNMOUNTING) && mp->m_fail_unmount)
-		return true;
-
-	return false;
-}
-
-/*
- * On a sync write or shutdown we just want to stale the buffer and let the
- * caller handle the error in bp->b_error appropriately.
- *
- * If the write was asynchronous then no one will be looking for the error.  If
- * this is the first failure of this type, clear the error state and write the
- * buffer out again. This means we always retry an async write failure at least
- * once, but we also need to set the buffer up to behave correctly now for
- * repeated failures.
- *
- * If we get repeated async write failures, then we take action according to the
- * error configuration we have been set up to use.
- *
- * Multi-state return value:
- *
- * XBF_IOERROR_FINISH: clear IO error retry state and run callback completions
- * XBF_IOERROR_DONE: resubmitted immediately, do not run any completions
- * XBF_IOERROR_FAIL: transient error, run failure callback completions and then
- *    release the buffer
- */
-enum {
-	XBF_IOERROR_FINISH,
-	XBF_IOERROR_DONE,
-	XBF_IOERROR_FAIL,
-};
-
-static int
-xfs_buf_iodone_error(
-	struct xfs_buf		*bp)
-{
-	struct xfs_mount	*mp = bp->b_mount;
-	struct xfs_error_cfg	*cfg;
-
-	if (xfs_buf_ioerror_fail_without_retry(bp))
-		goto out_stale;
-
-	trace_xfs_buf_item_iodone_async(bp, _RET_IP_);
-
-	cfg = xfs_error_get_cfg(mp, XFS_ERR_METADATA, bp->b_error);
-	if (xfs_buf_ioerror_retry(bp, cfg)) {
-		xfs_buf_ioerror(bp, 0);
-		xfs_buf_submit(bp);
-		return XBF_IOERROR_DONE;
-	}
-
-	/*
-	 * Permanent error - we need to trigger a shutdown if we haven't already
-	 * to indicate that inconsistency will result from this action.
-	 */
-	if (xfs_buf_ioerror_permanent(bp, cfg)) {
-		xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
-		goto out_stale;
-	}
-
-	/* Still considered a transient error. Caller will schedule retries. */
-	return XBF_IOERROR_FAIL;
-
-out_stale:
-	xfs_buf_stale(bp);
-	bp->b_flags |= XBF_DONE;
-	trace_xfs_buf_error_relse(bp, _RET_IP_);
-	return XBF_IOERROR_FINISH;
-}
-
-static void
 xfs_buf_item_done(
 	struct xfs_buf		*bp)
 {
-	struct xfs_buf_log_item	*bip = bp->b_log_item;
-
-	if (!bip)
-		return;
-
 	/*
 	 * If we are forcibly shutting down, this may well be off the AIL
 	 * already. That's because we simulate the log-committed callbacks to
@@ -1111,113 +966,12 @@ xfs_buf_item_done(
 	 * xfs_trans_ail_delete() takes care of these.
 	 *
 	 * Either way, AIL is useless if we're forcing a shutdown.
+	 *
+	 * Note that log recovery writes might have buffer items that are not on
+	 * the AIL even when the file system is not shut down.
 	 */
-	xfs_trans_ail_delete(&bip->bli_item, SHUTDOWN_CORRUPT_INCORE);
+	xfs_trans_ail_delete(&bp->b_log_item->bli_item,
-	bp->b_log_item = NULL;
+			     (bp->b_flags & _XBF_LOGRECOVERY) ? 0 :
-	xfs_buf_item_free(bip);
+			     SHUTDOWN_CORRUPT_INCORE);
-	xfs_buf_rele(bp);
+	xfs_buf_item_relse(bp);
-}
-
-static inline void
-xfs_buf_clear_ioerror_retry_state(
-	struct xfs_buf		*bp)
-{
-	bp->b_last_error = 0;
-	bp->b_retries = 0;
-	bp->b_first_retry_time = 0;
-}
-
-/*
- * Inode buffer iodone callback function.
- */
-void
-xfs_buf_inode_iodone(
-	struct xfs_buf		*bp)
-{
-	if (bp->b_error) {
-		struct xfs_log_item *lip;
-		int ret = xfs_buf_iodone_error(bp);
-
-		if (ret == XBF_IOERROR_FINISH)
-			goto finish_iodone;
-		if (ret == XBF_IOERROR_DONE)
-			return;
-		ASSERT(ret == XBF_IOERROR_FAIL);
-		list_for_each_entry(lip, &bp->b_li_list, li_bio_list) {
-			set_bit(XFS_LI_FAILED, &lip->li_flags);
-		}
-		xfs_buf_ioerror(bp, 0);
-		xfs_buf_relse(bp);
-		return;
-	}
-
-finish_iodone:
-	xfs_buf_clear_ioerror_retry_state(bp);
-	xfs_buf_item_done(bp);
-	xfs_iflush_done(bp);
-	xfs_buf_ioend_finish(bp);
-}
-
-/*
- * Dquot buffer iodone callback function.
- */
-void
-xfs_buf_dquot_iodone(
-	struct xfs_buf		*bp)
-{
-	if (bp->b_error) {
-		struct xfs_log_item *lip;
-		int ret = xfs_buf_iodone_error(bp);
-
-		if (ret == XBF_IOERROR_FINISH)
-			goto finish_iodone;
-		if (ret == XBF_IOERROR_DONE)
-			return;
-		ASSERT(ret == XBF_IOERROR_FAIL);
-		spin_lock(&bp->b_mount->m_ail->ail_lock);
-		list_for_each_entry(lip, &bp->b_li_list, li_bio_list) {
-			xfs_set_li_failed(lip, bp);
-		}
-		spin_unlock(&bp->b_mount->m_ail->ail_lock);
-		xfs_buf_ioerror(bp, 0);
-		xfs_buf_relse(bp);
-		return;
-	}
-
-finish_iodone:
-	xfs_buf_clear_ioerror_retry_state(bp);
-	/* a newly allocated dquot buffer might have a log item attached */
-	xfs_buf_item_done(bp);
-	xfs_dquot_done(bp);
-	xfs_buf_ioend_finish(bp);
-}
-
-/*
- * Dirty buffer iodone callback function.
- *
- * Note that for things like remote attribute buffers, there may not be a buffer
- * log item here, so processing the buffer log item must remain be optional.
- */
-void
-xfs_buf_iodone(
-	struct xfs_buf		*bp)
-{
-	if (bp->b_error) {
-		int ret = xfs_buf_iodone_error(bp);
-
-		if (ret == XBF_IOERROR_FINISH)
-			goto finish_iodone;
-		if (ret == XBF_IOERROR_DONE)
-			return;
-		ASSERT(ret == XBF_IOERROR_FAIL);
-		ASSERT(list_empty(&bp->b_li_list));
-		xfs_buf_ioerror(bp, 0);
-		xfs_buf_relse(bp);
-		return;
-	}
-
-finish_iodone:
-	xfs_buf_clear_ioerror_retry_state(bp);
-	xfs_buf_item_done(bp);
-	xfs_buf_ioend_finish(bp);
 }

fs/xfs/xfs_buf_item.h

@@ -50,12 +50,24 @@ struct xfs_buf_log_item {
 };
 
 int	xfs_buf_item_init(struct xfs_buf *, struct xfs_mount *);
+void	xfs_buf_item_done(struct xfs_buf *bp);
 void	xfs_buf_item_relse(struct xfs_buf *);
 bool	xfs_buf_item_put(struct xfs_buf_log_item *);
 void	xfs_buf_item_log(struct xfs_buf_log_item *, uint, uint);
 bool	xfs_buf_item_dirty_format(struct xfs_buf_log_item *);
 void	xfs_buf_inode_iodone(struct xfs_buf *);
+void	xfs_buf_inode_io_fail(struct xfs_buf *bp);
+#ifdef CONFIG_XFS_QUOTA
 void	xfs_buf_dquot_iodone(struct xfs_buf *);
+void	xfs_buf_dquot_io_fail(struct xfs_buf *bp);
+#else
+static inline void xfs_buf_dquot_iodone(struct xfs_buf *bp)
+{
+}
+static inline void xfs_buf_dquot_io_fail(struct xfs_buf *bp)
+{
+}
+#endif /* CONFIG_XFS_QUOTA */
 void	xfs_buf_iodone(struct xfs_buf *);
 bool	xfs_buf_log_check_iovec(struct xfs_log_iovec *iovec);
 

fs/xfs/xfs_buf_item_recover.c

@@ -414,7 +414,7 @@ xlog_recover_validate_buf_type(
 	 *
 	 * Write verifiers update the metadata LSN from log items attached to
 	 * the buffer. Therefore, initialize a bli purely to carry the LSN to
-	 * the verifier. We'll clean it up in our ->iodone() callback.
+	 * the verifier.
 	 */
 	if (bp->b_ops) {
 		struct xfs_buf_log_item	*bip;

fs/xfs/xfs_dquot.c

@@ -98,12 +98,33 @@ xfs_qm_adjust_dqlimits(
 		xfs_dquot_set_prealloc_limits(dq);
 }
 
+/* Set the expiration time of a quota's grace period. */
+time64_t
+xfs_dquot_set_timeout(
+	struct xfs_mount	*mp,
+	time64_t		timeout)
+{
+	struct xfs_quotainfo	*qi = mp->m_quotainfo;
+
+	return clamp_t(time64_t, timeout, qi->qi_expiry_min,
+					  qi->qi_expiry_max);
+}
+
+/* Set the length of the default grace period. */
+time64_t
+xfs_dquot_set_grace_period(
+	time64_t		grace)
+{
+	return clamp_t(time64_t, grace, XFS_DQ_GRACE_MIN, XFS_DQ_GRACE_MAX);
+}
+
 /*
  * Determine if this quota counter is over either limit and set the quota
  * timers as appropriate.
  */
 static inline void
 xfs_qm_adjust_res_timer(
+	struct xfs_mount	*mp,
 	struct xfs_dquot_res	*res,
 	struct xfs_quota_limits	*qlim)
 {
@@ -112,7 +133,8 @@ xfs_qm_adjust_res_timer(
 	if ((res->softlimit && res->count > res->softlimit) ||
 	    (res->hardlimit && res->count > res->hardlimit)) {
 		if (res->timer == 0)
-			res->timer = ktime_get_real_seconds() + qlim->time;
+			res->timer = xfs_dquot_set_timeout(mp,
+					ktime_get_real_seconds() + qlim->time);
 	} else {
 		if (res->timer == 0)
 			res->warnings = 0;
@@ -145,9 +167,9 @@ xfs_qm_adjust_dqtimers(
 	ASSERT(dq->q_id);
 	defq = xfs_get_defquota(qi, xfs_dquot_type(dq));
 
-	xfs_qm_adjust_res_timer(&dq->q_blk, &defq->blk);
+	xfs_qm_adjust_res_timer(dq->q_mount, &dq->q_blk, &defq->blk);
-	xfs_qm_adjust_res_timer(&dq->q_ino, &defq->ino);
+	xfs_qm_adjust_res_timer(dq->q_mount, &dq->q_ino, &defq->ino);
-	xfs_qm_adjust_res_timer(&dq->q_rtb, &defq->rtb);
+	xfs_qm_adjust_res_timer(dq->q_mount, &dq->q_rtb, &defq->rtb);
 }
 
 /*
@@ -201,6 +223,8 @@ xfs_qm_init_dquot_blk(
 		d->dd_diskdq.d_version = XFS_DQUOT_VERSION;
 		d->dd_diskdq.d_id = cpu_to_be32(curid);
 		d->dd_diskdq.d_type = type;
+		if (curid > 0 && xfs_sb_version_hasbigtime(&mp->m_sb))
+			d->dd_diskdq.d_type |= XFS_DQTYPE_BIGTIME;
 		if (xfs_sb_version_hascrc(&mp->m_sb)) {
 			uuid_copy(&d->dd_uuid, &mp->m_sb.sb_meta_uuid);
 			xfs_update_cksum((char *)d, sizeof(struct xfs_dqblk),
@@ -514,9 +538,9 @@ xfs_dquot_from_disk(
 	dqp->q_ino.warnings = be16_to_cpu(ddqp->d_iwarns);
 	dqp->q_rtb.warnings = be16_to_cpu(ddqp->d_rtbwarns);
 
-	dqp->q_blk.timer = be32_to_cpu(ddqp->d_btimer);
+	dqp->q_blk.timer = xfs_dquot_from_disk_ts(ddqp, ddqp->d_btimer);
-	dqp->q_ino.timer = be32_to_cpu(ddqp->d_itimer);
+	dqp->q_ino.timer = xfs_dquot_from_disk_ts(ddqp, ddqp->d_itimer);
-	dqp->q_rtb.timer = be32_to_cpu(ddqp->d_rtbtimer);
+	dqp->q_rtb.timer = xfs_dquot_from_disk_ts(ddqp, ddqp->d_rtbtimer);
 
 	/*
 	 * Reservation counters are defined as reservation plus current usage
@@ -559,9 +583,9 @@ xfs_dquot_to_disk(
 	ddqp->d_iwarns = cpu_to_be16(dqp->q_ino.warnings);
 	ddqp->d_rtbwarns = cpu_to_be16(dqp->q_rtb.warnings);
 
-	ddqp->d_btimer = cpu_to_be32(dqp->q_blk.timer);
+	ddqp->d_btimer = xfs_dquot_to_disk_ts(dqp, dqp->q_blk.timer);
-	ddqp->d_itimer = cpu_to_be32(dqp->q_ino.timer);
+	ddqp->d_itimer = xfs_dquot_to_disk_ts(dqp, dqp->q_ino.timer);
-	ddqp->d_rtbtimer = cpu_to_be32(dqp->q_rtb.timer);
+	ddqp->d_rtbtimer = xfs_dquot_to_disk_ts(dqp, dqp->q_rtb.timer);
 }
 
 /* Allocate and initialize the dquot buffer for this in-core dquot. */
@@ -1107,7 +1131,7 @@ xfs_qm_dqflush_done(
 }
 
 void
-xfs_dquot_done(
+xfs_buf_dquot_iodone(
 	struct xfs_buf		*bp)
 {
 	struct xfs_log_item	*lip, *n;
@@ -1118,6 +1142,18 @@ xfs_dquot_done(
 	}
 }
 
+void
+xfs_buf_dquot_io_fail(
+	struct xfs_buf		*bp)
+{
+	struct xfs_log_item	*lip;
+
+	spin_lock(&bp->b_mount->m_ail->ail_lock);
+	list_for_each_entry(lip, &bp->b_li_list, li_bio_list)
+		xfs_set_li_failed(lip, bp);
+	spin_unlock(&bp->b_mount->m_ail->ail_lock);
+}
+
 /* Check incore dquot for errors before we flush. */
 static xfs_failaddr_t
 xfs_qm_dqflush_check(
@@ -1145,6 +1181,14 @@ xfs_qm_dqflush_check(
 	    !dqp->q_rtb.timer)
 		return __this_address;
 
+	/* bigtime flag should never be set on root dquots */
+	if (dqp->q_type & XFS_DQTYPE_BIGTIME) {
+		if (!xfs_sb_version_hasbigtime(&dqp->q_mount->m_sb))
+			return __this_address;
+		if (dqp->q_id == 0)
+			return __this_address;
+	}
+
 	return NULL;
 }
 

fs/xfs/xfs_dquot.h

@@ -237,4 +237,7 @@ typedef int (*xfs_qm_dqiterate_fn)(struct xfs_dquot *dq,
 int xfs_qm_dqiterate(struct xfs_mount *mp, xfs_dqtype_t type,
 		xfs_qm_dqiterate_fn iter_fn, void *priv);
 
+time64_t xfs_dquot_set_timeout(struct xfs_mount *mp, time64_t timeout);
+time64_t xfs_dquot_set_grace_period(time64_t grace);
+
 #endif /* __XFS_DQUOT_H__ */

fs/xfs/xfs_file.c

@@ -1008,6 +1008,21 @@ xfs_file_fadvise(
 	return ret;
 }
 
+/* Does this file, inode, or mount want synchronous writes? */
+static inline bool xfs_file_sync_writes(struct file *filp)
+{
+	struct xfs_inode	*ip = XFS_I(file_inode(filp));
+
+	if (ip->i_mount->m_flags & XFS_MOUNT_WSYNC)
+		return true;
+	if (filp->f_flags & (__O_SYNC | O_DSYNC))
+		return true;
+	if (IS_SYNC(file_inode(filp)))
+		return true;
+
+	return false;
+}
+
 STATIC loff_t
 xfs_file_remap_range(
 	struct file		*file_in,
@@ -1065,7 +1080,7 @@ xfs_file_remap_range(
 	if (ret)
 		goto out_unlock;
 
-	if (mp->m_flags & XFS_MOUNT_WSYNC)
+	if (xfs_file_sync_writes(file_in) || xfs_file_sync_writes(file_out))
 		xfs_log_force_inode(dest);
 out_unlock:
 	xfs_iunlock2_io_mmap(src, dest);

fs/xfs/xfs_icache.c

@@ -52,7 +52,6 @@ xfs_inode_alloc(
 
 	XFS_STATS_INC(mp, vn_active);
 	ASSERT(atomic_read(&ip->i_pincount) == 0);
-	ASSERT(!xfs_isiflocked(ip));
 	ASSERT(ip->i_ino == 0);
 
 	/* initialise the xfs inode */
@@ -123,7 +122,7 @@ void
 xfs_inode_free(
 	struct xfs_inode	*ip)
 {
-	ASSERT(!xfs_isiflocked(ip));
+	ASSERT(!xfs_iflags_test(ip, XFS_IFLUSHING));
 
 	/*
 	 * Because we use RCU freeing we need to ensure the inode always
@@ -1035,23 +1034,21 @@ xfs_reclaim_inode(
 
 	if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL))
 		goto out;
-	if (!xfs_iflock_nowait(ip))
+	if (xfs_iflags_test_and_set(ip, XFS_IFLUSHING))
 		goto out_iunlock;
 
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
 		xfs_iunpin_wait(ip);
-		/* xfs_iflush_abort() drops the flush lock */
 		xfs_iflush_abort(ip);
 		goto reclaim;
 	}
 	if (xfs_ipincount(ip))
-		goto out_ifunlock;
+		goto out_clear_flush;
 	if (!xfs_inode_clean(ip))
-		goto out_ifunlock;
+		goto out_clear_flush;
 
-	xfs_ifunlock(ip);
+	xfs_iflags_clear(ip, XFS_IFLUSHING);
 reclaim:
-	ASSERT(!xfs_isiflocked(ip));
 
 	/*
 	 * Because we use RCU freeing we need to ensure the inode always appears
@@ -1101,8 +1098,8 @@ reclaim:
 	__xfs_inode_free(ip);
 	return;
 
-out_ifunlock:
+out_clear_flush:
-	xfs_ifunlock(ip);
+	xfs_iflags_clear(ip, XFS_IFLUSHING);
 out_iunlock:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 out:
@@ -1211,7 +1208,7 @@ xfs_reclaim_inodes(
 	while (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_RECLAIM_TAG)) {
 		xfs_ail_push_all_sync(mp->m_ail);
 		xfs_reclaim_inodes_ag(mp, &nr_to_scan);
-	};
+	}
 }
 
 /*

fs/xfs/xfs_inode.c

@@ -598,22 +598,6 @@ xfs_lock_two_inodes(
 	}
 }
 
-void
-__xfs_iflock(
-	struct xfs_inode	*ip)
-{
-	wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_IFLOCK_BIT);
-	DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_IFLOCK_BIT);
-
-	do {
-		prepare_to_wait_exclusive(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
-		if (xfs_isiflocked(ip))
-			io_schedule();
-	} while (!xfs_iflock_nowait(ip));
-
-	finish_wait(wq, &wait.wq_entry);
-}
-
 STATIC uint
 _xfs_dic2xflags(
 	uint16_t		di_flags,
@@ -840,7 +824,7 @@ xfs_ialloc(
 
 	if (xfs_sb_version_has_v3inode(&mp->m_sb)) {
 		inode_set_iversion(inode, 1);
-		ip->i_d.di_flags2 = 0;
+		ip->i_d.di_flags2 = mp->m_ino_geo.new_diflags2;
 		ip->i_d.di_cowextsize = 0;
 		ip->i_d.di_crtime = tv;
 	}
@@ -2531,11 +2515,8 @@ retry:
 	 * valid, the wrong inode or stale.
 	 */
 	spin_lock(&ip->i_flags_lock);
-	if (ip->i_ino != inum || __xfs_iflags_test(ip, XFS_ISTALE)) {
+	if (ip->i_ino != inum || __xfs_iflags_test(ip, XFS_ISTALE))
-		spin_unlock(&ip->i_flags_lock);
+		goto out_iflags_unlock;
-		rcu_read_unlock();
-		return;
-	}
 
 	/*
 	 * Don't try to lock/unlock the current inode, but we _cannot_ skip the
@@ -2552,16 +2533,14 @@ retry:
 		}
 	}
 	ip->i_flags |= XFS_ISTALE;
-	spin_unlock(&ip->i_flags_lock);
-	rcu_read_unlock();
 
 	/*
-	 * If we can't get the flush lock, the inode is already attached.  All
+	 * If the inode is flushing, it is already attached to the buffer.  All
 	 * we needed to do here is mark the inode stale so buffer IO completion
 	 * will remove it from the AIL.
 	 */
 	iip = ip->i_itemp;
-	if (!xfs_iflock_nowait(ip)) {
+	if (__xfs_iflags_test(ip, XFS_IFLUSHING)) {
 		ASSERT(!list_empty(&iip->ili_item.li_bio_list));
 		ASSERT(iip->ili_last_fields);
 		goto out_iunlock;
@@ -2573,10 +2552,12 @@ retry:
 	 * commit as the flock synchronises removal of the inode from the
 	 * cluster buffer against inode reclaim.
 	 */
-	if (!iip || list_empty(&iip->ili_item.li_bio_list)) {
+	if (!iip || list_empty(&iip->ili_item.li_bio_list))
-		xfs_ifunlock(ip);
 		goto out_iunlock;
-	}
+
+	__xfs_iflags_set(ip, XFS_IFLUSHING);
+	spin_unlock(&ip->i_flags_lock);
+	rcu_read_unlock();
 
 	/* we have a dirty inode in memory that has not yet been flushed. */
 	spin_lock(&iip->ili_lock);
@@ -2586,9 +2567,16 @@ retry:
 	spin_unlock(&iip->ili_lock);
 	ASSERT(iip->ili_last_fields);
 
+	if (ip != free_ip)
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	return;
+
 out_iunlock:
 	if (ip != free_ip)
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+out_iflags_unlock:
+	spin_unlock(&ip->i_flags_lock);
+	rcu_read_unlock();
 }
 
 /*
@@ -2631,8 +2619,9 @@ xfs_ifree_cluster(
 
 		/*
 		 * We obtain and lock the backing buffer first in the process
-		 * here, as we have to ensure that any dirty inode that we
+		 * here to ensure dirty inodes attached to the buffer remain in
-		 * can't get the flush lock on is attached to the buffer.
+		 * the flushing state while we mark them stale.
+		 *
 		 * If we scan the in-memory inodes first, then buffer IO can
 		 * complete before we get a lock on it, and hence we may fail
 		 * to mark all the active inodes on the buffer stale.
@@ -2717,7 +2706,7 @@ xfs_ifree(
 
 	VFS_I(ip)->i_mode = 0;		/* mark incore inode as free */
 	ip->i_d.di_flags = 0;
-	ip->i_d.di_flags2 = 0;
+	ip->i_d.di_flags2 = ip->i_mount->m_ino_geo.new_diflags2;
 	ip->i_d.di_dmevmask = 0;
 	ip->i_d.di_forkoff = 0;		/* mark the attr fork not in use */
 	ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;
@@ -3443,7 +3432,7 @@ xfs_iflush(
 	int			error;
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
-	ASSERT(xfs_isiflocked(ip));
+	ASSERT(xfs_iflags_test(ip, XFS_IFLUSHING));
 	ASSERT(ip->i_df.if_format != XFS_DINODE_FMT_BTREE ||
 	       ip->i_df.if_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));
 	ASSERT(iip->ili_item.li_buf == bp);
@@ -3553,8 +3542,8 @@ xfs_iflush(
 	 *
 	 * What we do is move the bits to the ili_last_fields field.  When
 	 * logging the inode, these bits are moved back to the ili_fields field.
-	 * In the xfs_iflush_done() routine we clear ili_last_fields, since we
+	 * In the xfs_buf_inode_iodone() routine we clear ili_last_fields, since
-	 * know that the information those bits represent is permanently on
+	 * we know that the information those bits represent is permanently on
 	 * disk.  As long as the flush completes before the inode is logged
 	 * again, then both ili_fields and ili_last_fields will be cleared.
 	 */
@@ -3568,7 +3557,7 @@ flush_out:
 
 	/*
 	 * Store the current LSN of the inode so that we can tell whether the
-	 * item has moved in the AIL from xfs_iflush_done().
+	 * item has moved in the AIL from xfs_buf_inode_iodone().
 	 */
 	xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn,
 				&iip->ili_item.li_lsn);
@@ -3613,7 +3602,7 @@ xfs_iflush_cluster(
 		/*
 		 * Quick and dirty check to avoid locks if possible.
 		 */
-		if (__xfs_iflags_test(ip, XFS_IRECLAIM | XFS_IFLOCK))
+		if (__xfs_iflags_test(ip, XFS_IRECLAIM | XFS_IFLUSHING))
 			continue;
 		if (xfs_ipincount(ip))
 			continue;
@@ -3627,7 +3616,7 @@ xfs_iflush_cluster(
 		 */
 		spin_lock(&ip->i_flags_lock);
 		ASSERT(!__xfs_iflags_test(ip, XFS_ISTALE));
-		if (__xfs_iflags_test(ip, XFS_IRECLAIM | XFS_IFLOCK)) {
+		if (__xfs_iflags_test(ip, XFS_IRECLAIM | XFS_IFLUSHING)) {
 			spin_unlock(&ip->i_flags_lock);
 			continue;
 		}
@@ -3635,23 +3624,16 @@ xfs_iflush_cluster(
 		/*
 		 * ILOCK will pin the inode against reclaim and prevent
 		 * concurrent transactions modifying the inode while we are
-		 * flushing the inode.
+		 * flushing the inode. If we get the lock, set the flushing
+		 * state before we drop the i_flags_lock.
 		 */
 		if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) {
 			spin_unlock(&ip->i_flags_lock);
 			continue;
 		}
+		__xfs_iflags_set(ip, XFS_IFLUSHING);
 		spin_unlock(&ip->i_flags_lock);
 
-		/*
-		 * Skip inodes that are already flush locked as they have
-		 * already been written to the buffer.
-		 */
-		if (!xfs_iflock_nowait(ip)) {
-			xfs_iunlock(ip, XFS_ILOCK_SHARED);
-			continue;
-		}
-
 		/*
 		 * Abort flushing this inode if we are shut down because the
 		 * inode may not currently be in the AIL. This can occur when
@@ -3661,7 +3643,6 @@ xfs_iflush_cluster(
 		 */
 		if (XFS_FORCED_SHUTDOWN(mp)) {
 			xfs_iunpin_wait(ip);
-			/* xfs_iflush_abort() drops the flush lock */
 			xfs_iflush_abort(ip);
 			xfs_iunlock(ip, XFS_ILOCK_SHARED);
 			error = -EIO;
@@ -3670,7 +3651,7 @@ xfs_iflush_cluster(
 
 		/* don't block waiting on a log force to unpin dirty inodes */
 		if (xfs_ipincount(ip)) {
-			xfs_ifunlock(ip);
+			xfs_iflags_clear(ip, XFS_IFLUSHING);
 			xfs_iunlock(ip, XFS_ILOCK_SHARED);
 			continue;
 		}
@@ -3678,7 +3659,7 @@ xfs_iflush_cluster(
 		if (!xfs_inode_clean(ip))
 			error = xfs_iflush(ip, bp);
 		else
-			xfs_ifunlock(ip);
+			xfs_iflags_clear(ip, XFS_IFLUSHING);
 		xfs_iunlock(ip, XFS_ILOCK_SHARED);
 		if (error)
 			break;

fs/xfs/xfs_inode.h

@@ -194,6 +194,11 @@ static inline bool xfs_inode_has_cow_data(struct xfs_inode *ip)
 	return ip->i_cowfp && ip->i_cowfp->if_bytes;
 }
 
+static inline bool xfs_inode_has_bigtime(struct xfs_inode *ip)
+{
+	return ip->i_d.di_flags2 & XFS_DIFLAG2_BIGTIME;
+}
+
 /*
  * Return the buftarg used for data allocations on a given inode.
  */
@@ -211,8 +216,7 @@ static inline bool xfs_inode_has_cow_data(struct xfs_inode *ip)
 #define XFS_INEW		(1 << __XFS_INEW_BIT)
 #define XFS_ITRUNCATED		(1 << 5) /* truncated down so flush-on-close */
 #define XFS_IDIRTY_RELEASE	(1 << 6) /* dirty release already seen */
-#define __XFS_IFLOCK_BIT	7	 /* inode is being flushed right now */
+#define XFS_IFLUSHING		(1 << 7) /* inode is being flushed */
-#define XFS_IFLOCK		(1 << __XFS_IFLOCK_BIT)
 #define __XFS_IPINNED_BIT	8	 /* wakeup key for zero pin count */
 #define XFS_IPINNED		(1 << __XFS_IPINNED_BIT)
 #define XFS_IEOFBLOCKS		(1 << 9) /* has the preallocblocks tag set */
@@ -233,36 +237,6 @@ static inline bool xfs_inode_has_cow_data(struct xfs_inode *ip)
 	(XFS_IRECLAIMABLE | XFS_IRECLAIM | \
 	 XFS_IDIRTY_RELEASE | XFS_ITRUNCATED)
 
-/*
- * Synchronize processes attempting to flush the in-core inode back to disk.
- */
-
-static inline int xfs_isiflocked(struct xfs_inode *ip)
-{
-	return xfs_iflags_test(ip, XFS_IFLOCK);
-}
-
-extern void __xfs_iflock(struct xfs_inode *ip);
-
-static inline int xfs_iflock_nowait(struct xfs_inode *ip)
-{
-	return !xfs_iflags_test_and_set(ip, XFS_IFLOCK);
-}
-
-static inline void xfs_iflock(struct xfs_inode *ip)
-{
-	if (!xfs_iflock_nowait(ip))
-		__xfs_iflock(ip);
-}
-
-static inline void xfs_ifunlock(struct xfs_inode *ip)
-{
-	ASSERT(xfs_isiflocked(ip));
-	xfs_iflags_clear(ip, XFS_IFLOCK);
-	smp_mb();
-	wake_up_bit(&ip->i_flags, __XFS_IFLOCK_BIT);
-}
-
 /*
  * Flags for inode locking.
  * Bit ranges:	1<<1  - 1<<16-1 -- iolock/ilock modes (bitfield)

fs/xfs/xfs_inode_item.c

@@ -295,6 +295,28 @@ xfs_inode_item_format_attr_fork(
 	}
 }
 
+/*
+ * Convert an incore timestamp to a log timestamp.  Note that the log format
+ * specifies host endian format!
+ */
+static inline xfs_ictimestamp_t
+xfs_inode_to_log_dinode_ts(
+	struct xfs_inode		*ip,
+	const struct timespec64		tv)
+{
+	struct xfs_legacy_ictimestamp	*lits;
+	xfs_ictimestamp_t		its;
+
+	if (xfs_inode_has_bigtime(ip))
+		return xfs_inode_encode_bigtime(tv);
+
+	lits = (struct xfs_legacy_ictimestamp *)&its;
+	lits->t_sec = tv.tv_sec;
+	lits->t_nsec = tv.tv_nsec;
+
+	return its;
+}
+
 static void
 xfs_inode_to_log_dinode(
 	struct xfs_inode	*ip,
@@ -313,12 +335,9 @@ xfs_inode_to_log_dinode(
 
 	memset(to->di_pad, 0, sizeof(to->di_pad));
 	memset(to->di_pad3, 0, sizeof(to->di_pad3));
-	to->di_atime.t_sec = inode->i_atime.tv_sec;
+	to->di_atime = xfs_inode_to_log_dinode_ts(ip, inode->i_atime);
-	to->di_atime.t_nsec = inode->i_atime.tv_nsec;
+	to->di_mtime = xfs_inode_to_log_dinode_ts(ip, inode->i_mtime);
-	to->di_mtime.t_sec = inode->i_mtime.tv_sec;
+	to->di_ctime = xfs_inode_to_log_dinode_ts(ip, inode->i_ctime);
-	to->di_mtime.t_nsec = inode->i_mtime.tv_nsec;
-	to->di_ctime.t_sec = inode->i_ctime.tv_sec;
-	to->di_ctime.t_nsec = inode->i_ctime.tv_nsec;
 	to->di_nlink = inode->i_nlink;
 	to->di_gen = inode->i_generation;
 	to->di_mode = inode->i_mode;
@@ -340,8 +359,7 @@ xfs_inode_to_log_dinode(
 	if (xfs_sb_version_has_v3inode(&ip->i_mount->m_sb)) {
 		to->di_version = 3;
 		to->di_changecount = inode_peek_iversion(inode);
-		to->di_crtime.t_sec = from->di_crtime.tv_sec;
+		to->di_crtime = xfs_inode_to_log_dinode_ts(ip, from->di_crtime);
-		to->di_crtime.t_nsec = from->di_crtime.tv_nsec;
 		to->di_flags2 = from->di_flags2;
 		to->di_cowextsize = from->di_cowextsize;
 		to->di_ino = ip->i_ino;
@@ -491,8 +509,7 @@ xfs_inode_item_push(
 	    (ip->i_flags & XFS_ISTALE))
 		return XFS_ITEM_PINNED;
 
-	/* If the inode is already flush locked, we're already flushing. */
+	if (xfs_iflags_test(ip, XFS_IFLUSHING))
-	if (xfs_isiflocked(ip))
 		return XFS_ITEM_FLUSHING;
 
 	if (!xfs_buf_trylock(bp))
@@ -703,7 +720,7 @@ xfs_iflush_finish(
 		iip->ili_last_fields = 0;
 		iip->ili_flush_lsn = 0;
 		spin_unlock(&iip->ili_lock);
-		xfs_ifunlock(iip->ili_inode);
+		xfs_iflags_clear(iip->ili_inode, XFS_IFLUSHING);
 		if (drop_buffer)
 			xfs_buf_rele(bp);
 	}
@@ -711,11 +728,11 @@ xfs_iflush_finish(
 
 /*
  * Inode buffer IO completion routine.  It is responsible for removing inodes
- * attached to the buffer from the AIL if they have not been re-logged, as well
+ * attached to the buffer from the AIL if they have not been re-logged and
- * as completing the flush and unlocking the inode.
+ * completing the inode flush.
  */
 void
-xfs_iflush_done(
+xfs_buf_inode_iodone(
 	struct xfs_buf		*bp)
 {
 	struct xfs_log_item	*lip, *n;
@@ -754,11 +771,21 @@ xfs_iflush_done(
 		list_splice_tail(&flushed_inodes, &bp->b_li_list);
 }
 
+void
+xfs_buf_inode_io_fail(
+	struct xfs_buf		*bp)
+{
+	struct xfs_log_item	*lip;
+
+	list_for_each_entry(lip, &bp->b_li_list, li_bio_list)
+		set_bit(XFS_LI_FAILED, &lip->li_flags);
+}
+
 /*
- * This is the inode flushing abort routine.  It is called from xfs_iflush when
+ * This is the inode flushing abort routine.  It is called when
  * the filesystem is shutting down to clean up the inode state.  It is
  * responsible for removing the inode item from the AIL if it has not been
- * re-logged, and unlocking the inode's flush lock.
+ * re-logged and clearing the inode's flush state.
  */
 void
 xfs_iflush_abort(
@@ -790,7 +817,7 @@ xfs_iflush_abort(
 		list_del_init(&iip->ili_item.li_bio_list);
 		spin_unlock(&iip->ili_lock);
 	}
-	xfs_ifunlock(ip);
+	xfs_iflags_clear(ip, XFS_IFLUSHING);
 	if (bp)
 		xfs_buf_rele(bp);
 }

fs/xfs/xfs_inode_item.h

@@ -25,8 +25,8 @@ struct xfs_inode_log_item {
 	 *
 	 * We need atomic changes between inode dirtying, inode flushing and
 	 * inode completion, but these all hold different combinations of
-	 * ILOCK and iflock and hence we need some other method of serialising
+	 * ILOCK and IFLUSHING and hence we need some other method of
-	 * updates to the flush state.
+	 * serialising updates to the flush state.
 	 */
 	spinlock_t		ili_lock;	   /* flush state lock */
 	unsigned int		ili_last_fields;   /* fields when flushed */
@@ -43,7 +43,6 @@ static inline int xfs_inode_clean(struct xfs_inode *ip)
 
 extern void xfs_inode_item_init(struct xfs_inode *, struct xfs_mount *);
 extern void xfs_inode_item_destroy(struct xfs_inode *);
-extern void xfs_iflush_done(struct xfs_buf *);
 extern void xfs_iflush_abort(struct xfs_inode *);
 extern int xfs_inode_item_format_convert(xfs_log_iovec_t *,
 					 struct xfs_inode_log_format *);

fs/xfs/xfs_inode_item_recover.c

@@ -115,6 +115,82 @@ out_free_ip:
 	return error;
 }
 
+static inline bool xfs_log_dinode_has_bigtime(const struct xfs_log_dinode *ld)
+{
+	return ld->di_version >= 3 &&
+	       (ld->di_flags2 & XFS_DIFLAG2_BIGTIME);
+}
+
+/* Convert a log timestamp to an ondisk timestamp. */
+static inline xfs_timestamp_t
+xfs_log_dinode_to_disk_ts(
+	struct xfs_log_dinode		*from,
+	const xfs_ictimestamp_t		its)
+{
+	struct xfs_legacy_timestamp	*lts;
+	struct xfs_legacy_ictimestamp	*lits;
+	xfs_timestamp_t			ts;
+
+	if (xfs_log_dinode_has_bigtime(from))
+		return cpu_to_be64(its);
+
+	lts = (struct xfs_legacy_timestamp *)&ts;
+	lits = (struct xfs_legacy_ictimestamp *)&its;
+	lts->t_sec = cpu_to_be32(lits->t_sec);
+	lts->t_nsec = cpu_to_be32(lits->t_nsec);
+
+	return ts;
+}
+
+STATIC void
+xfs_log_dinode_to_disk(
+	struct xfs_log_dinode	*from,
+	struct xfs_dinode	*to)
+{
+	to->di_magic = cpu_to_be16(from->di_magic);
+	to->di_mode = cpu_to_be16(from->di_mode);
+	to->di_version = from->di_version;
+	to->di_format = from->di_format;
+	to->di_onlink = 0;
+	to->di_uid = cpu_to_be32(from->di_uid);
+	to->di_gid = cpu_to_be32(from->di_gid);
+	to->di_nlink = cpu_to_be32(from->di_nlink);
+	to->di_projid_lo = cpu_to_be16(from->di_projid_lo);
+	to->di_projid_hi = cpu_to_be16(from->di_projid_hi);
+	memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));
+
+	to->di_atime = xfs_log_dinode_to_disk_ts(from, from->di_atime);
+	to->di_mtime = xfs_log_dinode_to_disk_ts(from, from->di_mtime);
+	to->di_ctime = xfs_log_dinode_to_disk_ts(from, from->di_ctime);
+
+	to->di_size = cpu_to_be64(from->di_size);
+	to->di_nblocks = cpu_to_be64(from->di_nblocks);
+	to->di_extsize = cpu_to_be32(from->di_extsize);
+	to->di_nextents = cpu_to_be32(from->di_nextents);
+	to->di_anextents = cpu_to_be16(from->di_anextents);
+	to->di_forkoff = from->di_forkoff;
+	to->di_aformat = from->di_aformat;
+	to->di_dmevmask = cpu_to_be32(from->di_dmevmask);
+	to->di_dmstate = cpu_to_be16(from->di_dmstate);
+	to->di_flags = cpu_to_be16(from->di_flags);
+	to->di_gen = cpu_to_be32(from->di_gen);
+
+	if (from->di_version == 3) {
+		to->di_changecount = cpu_to_be64(from->di_changecount);
+		to->di_crtime = xfs_log_dinode_to_disk_ts(from,
+							  from->di_crtime);
+		to->di_flags2 = cpu_to_be64(from->di_flags2);
+		to->di_cowextsize = cpu_to_be32(from->di_cowextsize);
+		to->di_ino = cpu_to_be64(from->di_ino);
+		to->di_lsn = cpu_to_be64(from->di_lsn);
+		memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
+		uuid_copy(&to->di_uuid, &from->di_uuid);
+		to->di_flushiter = 0;
+	} else {
+		to->di_flushiter = cpu_to_be16(from->di_flushiter);
+	}
+}
+
 STATIC int
 xlog_recover_inode_commit_pass2(
 	struct xlog			*log,

fs/xfs/xfs_ioctl.c

@@ -404,7 +404,7 @@ xfs_ioc_attr_list(
 	     context.cursor.offset))
 		return -EINVAL;
 
-	buffer = kmem_zalloc_large(bufsize, 0);
+	buffer = kvzalloc(bufsize, GFP_KERNEL);
 	if (!buffer)
 		return -ENOMEM;
 
@@ -1190,7 +1190,8 @@ xfs_flags2diflags2(
 	unsigned int		xflags)
 {
 	uint64_t		di_flags2 =
-		(ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK);
+		(ip->i_d.di_flags2 & (XFS_DIFLAG2_REFLINK |
+				      XFS_DIFLAG2_BIGTIME));
 
 	if (xflags & FS_XFLAG_DAX)
 		di_flags2 |= XFS_DIFLAG2_DAX;
@@ -1690,7 +1691,7 @@ xfs_ioc_getbmap(
 	if (bmx.bmv_count > ULONG_MAX / recsize)
 		return -ENOMEM;
 
-	buf = kmem_zalloc_large(bmx.bmv_count * sizeof(*buf), 0);
+	buf = kvzalloc(bmx.bmv_count * sizeof(*buf), GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 

fs/xfs/xfs_log_recover.c

@@ -265,32 +265,6 @@ xlog_header_check_mount(
 	return 0;
 }
 
-void
-xlog_recover_iodone(
-	struct xfs_buf	*bp)
-{
-	if (bp->b_error) {
-		/*
-		 * We're not going to bother about retrying
-		 * this during recovery. One strike!
-		 */
-		if (!XFS_FORCED_SHUTDOWN(bp->b_mount)) {
-			xfs_buf_ioerror_alert(bp, __this_address);
-			xfs_force_shutdown(bp->b_mount, SHUTDOWN_META_IO_ERROR);
-		}
-	}
-
-	/*
-	 * On v5 supers, a bli could be attached to update the metadata LSN.
-	 * Clean it up.
-	 */
-	if (bp->b_log_item)
-		xfs_buf_item_relse(bp);
-	ASSERT(bp->b_log_item == NULL);
-	bp->b_flags &= ~_XBF_LOGRECOVERY;
-	xfs_buf_ioend_finish(bp);
-}
-
 /*
  * This routine finds (to an approximation) the first block in the physical
  * log which contains the given cycle.  It uses a binary search algorithm.
@@ -2097,7 +2071,7 @@ xlog_recover_add_to_cont_trans(
 	old_ptr = item->ri_buf[item->ri_cnt-1].i_addr;
 	old_len = item->ri_buf[item->ri_cnt-1].i_len;
 
-	ptr = kmem_realloc(old_ptr, len + old_len, 0);
+	ptr = krealloc(old_ptr, len + old_len, GFP_KERNEL | __GFP_NOFAIL);
 	memcpy(&ptr[old_len], dp, len);
 	item->ri_buf[item->ri_cnt-1].i_len += len;
 	item->ri_buf[item->ri_cnt-1].i_addr = ptr;
@@ -3294,14 +3268,14 @@ xlog_do_log_recovery(
  */
 STATIC int
 xlog_do_recover(
-	struct xlog	*log,
+	struct xlog		*log,
-	xfs_daddr_t	head_blk,
+	xfs_daddr_t		head_blk,
-	xfs_daddr_t	tail_blk)
+	xfs_daddr_t		tail_blk)
 {
-	struct xfs_mount *mp = log->l_mp;
+	struct xfs_mount	*mp = log->l_mp;
-	int		error;
+	struct xfs_buf		*bp = mp->m_sb_bp;
-	xfs_buf_t	*bp;
+	struct xfs_sb		*sbp = &mp->m_sb;
-	xfs_sb_t	*sbp;
+	int			error;
 
 	trace_xfs_log_recover(log, head_blk, tail_blk);
 
@@ -3315,9 +3289,8 @@ xlog_do_recover(
 	/*
 	 * If IO errors happened during recovery, bail out.
 	 */
-	if (XFS_FORCED_SHUTDOWN(mp)) {
+	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
-	}
 
 	/*
 	 * We now update the tail_lsn since much of the recovery has completed
@@ -3331,16 +3304,12 @@ xlog_do_recover(
 	xlog_assign_tail_lsn(mp);
 
 	/*
-	 * Now that we've finished replaying all buffer and inode
+	 * Now that we've finished replaying all buffer and inode updates,
-	 * updates, re-read in the superblock and reverify it.
+	 * re-read the superblock and reverify it.
 	 */
-	bp = xfs_getsb(mp);
+	xfs_buf_lock(bp);
-	bp->b_flags &= ~(XBF_DONE | XBF_ASYNC);
+	xfs_buf_hold(bp);
-	ASSERT(!(bp->b_flags & XBF_WRITE));
+	error = _xfs_buf_read(bp, XBF_READ);
-	bp->b_flags |= XBF_READ;
-	bp->b_ops = &xfs_sb_buf_ops;
-
-	error = xfs_buf_submit(bp);
 	if (error) {
 		if (!XFS_FORCED_SHUTDOWN(mp)) {
 			xfs_buf_ioerror_alert(bp, __this_address);
@@ -3351,7 +3320,6 @@ xlog_do_recover(
 	}
 
 	/* Convert superblock from on-disk format */
-	sbp = &mp->m_sb;
 	xfs_sb_from_disk(sbp, bp->b_addr);
 	xfs_buf_relse(bp);
 

fs/xfs/xfs_mount.c

@@ -80,9 +80,9 @@ xfs_uuid_mount(
 	}
 
 	if (hole < 0) {
-		xfs_uuid_table = kmem_realloc(xfs_uuid_table,
+		xfs_uuid_table = krealloc(xfs_uuid_table,
 			(xfs_uuid_table_size + 1) * sizeof(*xfs_uuid_table),
-			0);
+			GFP_KERNEL | __GFP_NOFAIL);
 		hole = xfs_uuid_table_size++;
 	}
 	xfs_uuid_table[hole] = *uuid;
@@ -1059,11 +1059,12 @@ xfs_unmountfs(
 	 * We can potentially deadlock here if we have an inode cluster
 	 * that has been freed has its buffer still pinned in memory because
 	 * the transaction is still sitting in a iclog. The stale inodes
-	 * on that buffer will have their flush locks held until the
+	 * on that buffer will be pinned to the buffer until the
-	 * transaction hits the disk and the callbacks run. the inode
+	 * transaction hits the disk and the callbacks run. Pushing the AIL will
-	 * flush takes the flush lock unconditionally and with nothing to
+	 * skip the stale inodes and may never see the pinned buffer, so
-	 * push out the iclog we will never get that unlocked. hence we
+	 * nothing will push out the iclog and unpin the buffer. Hence we
-	 * need to force the log first.
+	 * need to force the log here to ensure all items are flushed into the
+	 * AIL before we go any further.
 	 */
 	xfs_log_force(mp, XFS_LOG_SYNC);
 
@@ -1288,23 +1289,6 @@ xfs_mod_frextents(
 	return ret;
 }
 
-/*
- * xfs_getsb() is called to obtain the buffer for the superblock.
- * The buffer is returned locked and read in from disk.
- * The buffer should be released with a call to xfs_brelse().
- */
-struct xfs_buf *
-xfs_getsb(
-	struct xfs_mount	*mp)
-{
-	struct xfs_buf		*bp = mp->m_sb_bp;
-
-	xfs_buf_lock(bp);
-	xfs_buf_hold(bp);
-	ASSERT(bp->b_flags & XBF_DONE);
-	return bp;
-}
-
 /*
  * Used to free the superblock along various error paths.
  */

fs/xfs/xfs_mount.h

@@ -410,7 +410,6 @@ extern int	xfs_mod_fdblocks(struct xfs_mount *mp, int64_t delta,
 				 bool reserved);
 extern int	xfs_mod_frextents(struct xfs_mount *mp, int64_t delta);
 
-extern struct xfs_buf *xfs_getsb(xfs_mount_t *);
 extern int	xfs_readsb(xfs_mount_t *, int);
 extern void	xfs_freesb(xfs_mount_t *);
 extern bool	xfs_fs_writable(struct xfs_mount *mp, int level);

fs/xfs/xfs_ondisk.h

@@ -15,6 +15,10 @@
 		"XFS: offsetof(" #structname ", " #member ") is wrong, " \
 		"expected " #off)
 
+#define XFS_CHECK_VALUE(value, expected) \
+	BUILD_BUG_ON_MSG((value) != (expected), \
+		"XFS: value of " #value " is wrong, expected " #expected)
+
 static inline void __init
 xfs_check_ondisk_structs(void)
 {
@@ -23,7 +27,7 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(struct xfs_acl_entry,		12);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_agf,			224);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_agfl,			36);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_agi,			336);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_agi,			344);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_bmbt_key,		8);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_bmbt_rec,		16);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_bmdr_block,		4);
@@ -41,7 +45,8 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(struct xfs_refcount_rec,		12);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_rmap_key,		20);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_rmap_rec,		24);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_timestamp,		8);
+	XFS_CHECK_STRUCT_SIZE(xfs_timestamp_t,			8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_legacy_timestamp,	8);
 	XFS_CHECK_STRUCT_SIZE(xfs_alloc_key_t,			8);
 	XFS_CHECK_STRUCT_SIZE(xfs_alloc_ptr_t,			4);
 	XFS_CHECK_STRUCT_SIZE(xfs_alloc_rec_t,			8);
@@ -84,12 +89,12 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, namelen,	8);
 	XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, name,	9);
 	XFS_CHECK_STRUCT_SIZE(xfs_attr_leafblock_t,		40);
-	XFS_CHECK_OFFSET(xfs_attr_shortform_t, hdr.totsize,	0);
+	XFS_CHECK_OFFSET(struct xfs_attr_shortform, hdr.totsize, 0);
-	XFS_CHECK_OFFSET(xfs_attr_shortform_t, hdr.count,	2);
+	XFS_CHECK_OFFSET(struct xfs_attr_shortform, hdr.count,	 2);
-	XFS_CHECK_OFFSET(xfs_attr_shortform_t, list[0].namelen,	4);
+	XFS_CHECK_OFFSET(struct xfs_attr_shortform, list[0].namelen,	4);
-	XFS_CHECK_OFFSET(xfs_attr_shortform_t, list[0].valuelen, 5);
+	XFS_CHECK_OFFSET(struct xfs_attr_shortform, list[0].valuelen,	5);
-	XFS_CHECK_OFFSET(xfs_attr_shortform_t, list[0].flags,	6);
+	XFS_CHECK_OFFSET(struct xfs_attr_shortform, list[0].flags,	6);
-	XFS_CHECK_OFFSET(xfs_attr_shortform_t, list[0].nameval,	7);
+	XFS_CHECK_OFFSET(struct xfs_attr_shortform, list[0].nameval,	7);
 	XFS_CHECK_STRUCT_SIZE(xfs_da_blkinfo_t,			12);
 	XFS_CHECK_STRUCT_SIZE(xfs_da_intnode_t,			16);
 	XFS_CHECK_STRUCT_SIZE(xfs_da_node_entry_t,		8);
@@ -121,7 +126,8 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(struct xfs_extent_64,		16);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_log_dinode,		176);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_icreate_log,		28);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_ictimestamp,		8);
+	XFS_CHECK_STRUCT_SIZE(xfs_ictimestamp_t,		8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_legacy_ictimestamp,	8);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format_32,	52);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format,	56);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_qoff_logformat,	20);
@@ -152,6 +158,20 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(struct xfs_inumbers,		24);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_bulkstat_req,		64);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_inumbers_req,		64);
+
+	/*
+	 * Make sure the incore inode timestamp range corresponds to hand
+	 * converted values based on the ondisk format specification.
+	 */
+	XFS_CHECK_VALUE(XFS_BIGTIME_TIME_MIN - XFS_BIGTIME_EPOCH_OFFSET,
+			XFS_LEGACY_TIME_MIN);
+	XFS_CHECK_VALUE(XFS_BIGTIME_TIME_MAX - XFS_BIGTIME_EPOCH_OFFSET,
+			16299260424LL);
+
+	/* Do the same with the incore quota expiration range. */
+	XFS_CHECK_VALUE(XFS_DQ_BIGTIME_EXPIRY_MIN << XFS_DQ_BIGTIME_SHIFT, 4);
+	XFS_CHECK_VALUE(XFS_DQ_BIGTIME_EXPIRY_MAX << XFS_DQ_BIGTIME_SHIFT,
+			16299260424LL);
 }
 
 #endif /* __XFS_ONDISK_H */

fs/xfs/xfs_qm.c

@@ -661,6 +661,17 @@ xfs_qm_init_quotainfo(
 	/* Precalc some constants */
 	qinf->qi_dqchunklen = XFS_FSB_TO_BB(mp, XFS_DQUOT_CLUSTER_SIZE_FSB);
 	qinf->qi_dqperchunk = xfs_calc_dquots_per_chunk(qinf->qi_dqchunklen);
+	if (xfs_sb_version_hasbigtime(&mp->m_sb)) {
+		qinf->qi_expiry_min =
+			xfs_dq_bigtime_to_unix(XFS_DQ_BIGTIME_EXPIRY_MIN);
+		qinf->qi_expiry_max =
+			xfs_dq_bigtime_to_unix(XFS_DQ_BIGTIME_EXPIRY_MAX);
+	} else {
+		qinf->qi_expiry_min = XFS_DQ_LEGACY_EXPIRY_MIN;
+		qinf->qi_expiry_max = XFS_DQ_LEGACY_EXPIRY_MAX;
+	}
+	trace_xfs_quota_expiry_range(mp, qinf->qi_expiry_min,
+			qinf->qi_expiry_max);
 
 	mp->m_qflags |= (mp->m_sb.sb_qflags & XFS_ALL_QUOTA_CHKD);
 
@@ -879,6 +890,8 @@ xfs_qm_reset_dqcounts(
 			ddq->d_bwarns = 0;
 			ddq->d_iwarns = 0;
 			ddq->d_rtbwarns = 0;
+			if (xfs_sb_version_hasbigtime(&mp->m_sb))
+				ddq->d_type |= XFS_DQTYPE_BIGTIME;
 		}
 
 		if (xfs_sb_version_hascrc(&mp->m_sb)) {

fs/xfs/xfs_qm.h

@@ -65,6 +65,10 @@ struct xfs_quotainfo {
 	struct xfs_def_quota	qi_grp_default;
 	struct xfs_def_quota	qi_prj_default;
 	struct shrinker		qi_shrinker;
+
+	/* Minimum and maximum quota expiration timestamp values. */
+	time64_t		qi_expiry_min;
+	time64_t		qi_expiry_max;
 };
 
 static inline struct radix_tree_root *

fs/xfs/xfs_qm_syscalls.c

@@ -479,13 +479,19 @@ xfs_setqlim_warns(
 
 static inline void
 xfs_setqlim_timer(
+	struct xfs_mount	*mp,
 	struct xfs_dquot_res	*res,
 	struct xfs_quota_limits	*qlim,
 	s64			timer)
 {
-	res->timer = timer;
+	if (qlim) {
-	if (qlim)
+		/* Set the length of the default grace period. */
-		qlim->time = timer;
+		res->timer = xfs_dquot_set_grace_period(timer);
+		qlim->time = res->timer;
+	} else {
+		/* Set the grace period expiration on a quota. */
+		res->timer = xfs_dquot_set_timeout(mp, timer);
+	}
 }
 
 /*
@@ -574,7 +580,7 @@ xfs_qm_scall_setqlim(
 	if (newlim->d_fieldmask & QC_SPC_WARNS)
 		xfs_setqlim_warns(res, qlim, newlim->d_spc_warns);
 	if (newlim->d_fieldmask & QC_SPC_TIMER)
-		xfs_setqlim_timer(res, qlim, newlim->d_spc_timer);
+		xfs_setqlim_timer(mp, res, qlim, newlim->d_spc_timer);
 
 	/* Blocks on the realtime device. */
 	hard = (newlim->d_fieldmask & QC_RT_SPC_HARD) ?
@@ -590,7 +596,7 @@ xfs_qm_scall_setqlim(
 	if (newlim->d_fieldmask & QC_RT_SPC_WARNS)
 		xfs_setqlim_warns(res, qlim, newlim->d_rt_spc_warns);
 	if (newlim->d_fieldmask & QC_RT_SPC_TIMER)
-		xfs_setqlim_timer(res, qlim, newlim->d_rt_spc_timer);
+		xfs_setqlim_timer(mp, res, qlim, newlim->d_rt_spc_timer);
 
 	/* Inodes */
 	hard = (newlim->d_fieldmask & QC_INO_HARD) ?
@@ -606,7 +612,7 @@ xfs_qm_scall_setqlim(
 	if (newlim->d_fieldmask & QC_INO_WARNS)
 		xfs_setqlim_warns(res, qlim, newlim->d_ino_warns);
 	if (newlim->d_fieldmask & QC_INO_TIMER)
-		xfs_setqlim_timer(res, qlim, newlim->d_ino_timer);
+		xfs_setqlim_timer(mp, res, qlim, newlim->d_ino_timer);
 
 	if (id != 0) {
 		/*

fs/xfs/xfs_quota.h

@@ -108,8 +108,6 @@ extern void xfs_qm_mount_quotas(struct xfs_mount *);
 extern void xfs_qm_unmount(struct xfs_mount *);
 extern void xfs_qm_unmount_quotas(struct xfs_mount *);
 
-void		xfs_dquot_done(struct xfs_buf *);
-
 #else
 static inline int
 xfs_qm_vop_dqalloc(struct xfs_inode *ip, kuid_t kuid, kgid_t kgid,
@@ -151,12 +149,6 @@ static inline int xfs_trans_reserve_quota_bydquots(struct xfs_trans *tp,
 #define xfs_qm_mount_quotas(mp)
 #define xfs_qm_unmount(mp)
 #define xfs_qm_unmount_quotas(mp)
-
-static inline void xfs_dquot_done(struct xfs_buf *bp)
-{
-	return;
-}
-
 #endif /* CONFIG_XFS_QUOTA */
 
 #define xfs_trans_unreserve_quota_nblks(tp, ip, nblks, ninos, flags) \

fs/xfs/xfs_rtalloc.c

@@ -247,6 +247,9 @@ xfs_rtallocate_extent_block(
 		end = XFS_BLOCKTOBIT(mp, bbno + 1) - 1;
 	     i <= end;
 	     i++) {
+		/* Make sure we don't scan off the end of the rt volume. */
+		maxlen = min(mp->m_sb.sb_rextents, i + maxlen) - i;
+
 		/*
 		 * See if there's a free extent of maxlen starting at i.
 		 * If it's not so then next will contain the first non-free.
@@ -442,6 +445,14 @@ xfs_rtallocate_extent_near(
 	 */
 	if (bno >= mp->m_sb.sb_rextents)
 		bno = mp->m_sb.sb_rextents - 1;
+
+	/* Make sure we don't run off the end of the rt volume. */
+	maxlen = min(mp->m_sb.sb_rextents, bno + maxlen) - bno;
+	if (maxlen < minlen) {
+		*rtblock = NULLRTBLOCK;
+		return 0;
+	}
+
 	/*
 	 * Try the exact allocation first.
 	 */
@@ -862,7 +873,7 @@ xfs_alloc_rsum_cache(
 	 * lower bound on the minimum level with any free extents. We can
 	 * continue without the cache if it couldn't be allocated.
 	 */
-	mp->m_rsum_cache = kmem_zalloc_large(rbmblocks, 0);
+	mp->m_rsum_cache = kvzalloc(rbmblocks, GFP_KERNEL);
 	if (!mp->m_rsum_cache)
 		xfs_warn(mp, "could not allocate realtime summary cache");
 }

fs/xfs/xfs_super.c

@@ -654,11 +654,11 @@ xfs_fs_destroy_inode(
 	ASSERT_ALWAYS(!xfs_iflags_test(ip, XFS_IRECLAIM));
 
 	/*
-	 * We always use background reclaim here because even if the
+	 * We always use background reclaim here because even if the inode is
-	 * inode is clean, it still may be under IO and hence we have
+	 * clean, it still may be under IO and hence we have wait for IO
-	 * to take the flush lock. The background reclaim path handles
+	 * completion to occur before we can reclaim the inode. The background
-	 * this more efficiently than we can here, so simply let background
+	 * reclaim path handles this more efficiently than we can here, so
-	 * reclaim tear down all inodes.
+	 * simply let background reclaim tear down all inodes.
 	 */
 	xfs_inode_set_reclaim_tag(ip);
 }
@@ -1484,8 +1484,14 @@ xfs_fc_fill_super(
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
 	sb->s_max_links = XFS_MAXLINK;
 	sb->s_time_gran = 1;
-	sb->s_time_min = S32_MIN;
+	if (xfs_sb_version_hasbigtime(&mp->m_sb)) {
-	sb->s_time_max = S32_MAX;
+		sb->s_time_min = xfs_bigtime_to_unix(XFS_BIGTIME_TIME_MIN);
+		sb->s_time_max = xfs_bigtime_to_unix(XFS_BIGTIME_TIME_MAX);
+	} else {
+		sb->s_time_min = XFS_LEGACY_TIME_MIN;
+		sb->s_time_max = XFS_LEGACY_TIME_MAX;
+	}
+	trace_xfs_inode_timestamp_range(mp, sb->s_time_min, sb->s_time_max);
 	sb->s_iflags |= SB_I_CGROUPWB;
 
 	set_posix_acl_flag(sb);
@@ -1494,6 +1500,10 @@ xfs_fc_fill_super(
 	if (XFS_SB_VERSION_NUM(&mp->m_sb) == XFS_SB_VERSION_5)
 		sb->s_flags |= SB_I_VERSION;
 
+	if (xfs_sb_version_hasbigtime(&mp->m_sb))
+		xfs_warn(mp,
+ "EXPERIMENTAL big timestamp feature in use. Use at your own risk!");
+
 	if (mp->m_flags & XFS_MOUNT_DAX_ALWAYS) {
 		bool rtdev_is_dax = false, datadev_is_dax;
 
@@ -1549,6 +1559,10 @@ xfs_fc_fill_super(
 		goto out_filestream_unmount;
 	}
 
+	if (xfs_sb_version_hasinobtcounts(&mp->m_sb))
+		xfs_warn(mp,
+ "EXPERIMENTAL inode btree counters feature in use. Use at your own risk!");
+
 	error = xfs_mountfs(mp);
 	if (error)
 		goto out_filestream_unmount;

fs/xfs/xfs_trace.h

@@ -338,7 +338,7 @@ DEFINE_BUF_EVENT(xfs_buf_delwri_split);
 DEFINE_BUF_EVENT(xfs_buf_delwri_pushbuf);
 DEFINE_BUF_EVENT(xfs_buf_get_uncached);
 DEFINE_BUF_EVENT(xfs_buf_item_relse);
-DEFINE_BUF_EVENT(xfs_buf_item_iodone_async);
+DEFINE_BUF_EVENT(xfs_buf_iodone_async);
 DEFINE_BUF_EVENT(xfs_buf_error_relse);
 DEFINE_BUF_EVENT(xfs_buf_wait_buftarg);
 DEFINE_BUF_EVENT(xfs_trans_read_buf_shut);
@@ -3676,7 +3676,6 @@ DEFINE_EVENT(xfs_kmem_class, name, \
 DEFINE_KMEM_EVENT(kmem_alloc);
 DEFINE_KMEM_EVENT(kmem_alloc_io);
 DEFINE_KMEM_EVENT(kmem_alloc_large);
-DEFINE_KMEM_EVENT(kmem_realloc);
 
 TRACE_EVENT(xfs_check_new_dalign,
 	TP_PROTO(struct xfs_mount *mp, int new_dalign, xfs_ino_t calc_rootino),
@@ -3844,6 +3843,32 @@ TRACE_EVENT(xfs_btree_bload_block,
 		  __entry->nr_records)
 )
 
+DECLARE_EVENT_CLASS(xfs_timestamp_range_class,
+	TP_PROTO(struct xfs_mount *mp, time64_t min, time64_t max),
+	TP_ARGS(mp, min, max),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(long long, min)
+		__field(long long, max)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->min = min;
+		__entry->max = max;
+	),
+	TP_printk("dev %d:%d min %lld max %lld",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->min,
+		  __entry->max)
+)
+
+#define DEFINE_TIMESTAMP_RANGE_EVENT(name) \
+DEFINE_EVENT(xfs_timestamp_range_class, name, \
+	TP_PROTO(struct xfs_mount *mp, long long min, long long max), \
+	TP_ARGS(mp, min, max))
+DEFINE_TIMESTAMP_RANGE_EVENT(xfs_inode_timestamp_range);
+DEFINE_TIMESTAMP_RANGE_EVENT(xfs_quota_expiry_range);
+
 #endif /* _TRACE_XFS_H */
 
 #undef TRACE_INCLUDE_PATH

fs/xfs/xfs_trans.c

@@ -468,7 +468,7 @@ xfs_trans_apply_sb_deltas(
 	xfs_buf_t	*bp;
 	int		whole = 0;
 
-	bp = xfs_trans_getsb(tp, tp->t_mountp);
+	bp = xfs_trans_getsb(tp);
 	sbp = bp->b_addr;
 
 	/*

fs/xfs/xfs_trans.h

@@ -209,7 +209,7 @@ xfs_trans_read_buf(
 				      flags, bpp, ops);
 }
 
-struct xfs_buf	*xfs_trans_getsb(xfs_trans_t *, struct xfs_mount *);
+struct xfs_buf	*xfs_trans_getsb(struct xfs_trans *);
 
 void		xfs_trans_brelse(xfs_trans_t *, struct xfs_buf *);
 void		xfs_trans_bjoin(xfs_trans_t *, struct xfs_buf *);

fs/xfs/xfs_trans_buf.c

@@ -166,50 +166,34 @@ xfs_trans_get_buf_map(
 }
 
 /*
- * Get and lock the superblock buffer of this file system for the
+ * Get and lock the superblock buffer for the given transaction.
- * given transaction.
- *
- * We don't need to use incore_match() here, because the superblock
- * buffer is a private buffer which we keep a pointer to in the
- * mount structure.
  */
-xfs_buf_t *
+struct xfs_buf *
 xfs_trans_getsb(
-	xfs_trans_t		*tp,
+	struct xfs_trans	*tp)
-	struct xfs_mount	*mp)
 {
-	xfs_buf_t		*bp;
+	struct xfs_buf		*bp = tp->t_mountp->m_sb_bp;
-	struct xfs_buf_log_item	*bip;
 
 	/*
-	 * Default to just trying to lock the superblock buffer
+	 * Just increment the lock recursion count if the buffer is already
-	 * if tp is NULL.
+	 * attached to this transaction.
 	 */
-	if (tp == NULL)
-		return xfs_getsb(mp);
-
-	/*
-	 * If the superblock buffer already has this transaction
-	 * pointer in its b_fsprivate2 field, then we know we already
-	 * have it locked.  In this case we just increment the lock
-	 * recursion count and return the buffer to the caller.
-	 */
-	bp = mp->m_sb_bp;
 	if (bp->b_transp == tp) {
-		bip = bp->b_log_item;
+		struct xfs_buf_log_item	*bip = bp->b_log_item;
+
 		ASSERT(bip != NULL);
 		ASSERT(atomic_read(&bip->bli_refcount) > 0);
 		bip->bli_recur++;
+
 		trace_xfs_trans_getsb_recur(bip);
-		return bp;
+	} else {
+		xfs_buf_lock(bp);
+		xfs_buf_hold(bp);
+		_xfs_trans_bjoin(tp, bp, 1);
+
+		trace_xfs_trans_getsb(bp->b_log_item);
 	}
 
-	bp = xfs_getsb(mp);
-	if (bp == NULL)
-		return NULL;
-
-	_xfs_trans_bjoin(tp, bp, 1);
-	trace_xfs_trans_getsb(bp->b_log_item);
 	return bp;
 }
 

fs/xfs/xfs_trans_dquot.c

@@ -55,6 +55,12 @@ xfs_trans_log_dquot(
 {
 	ASSERT(XFS_DQ_IS_LOCKED(dqp));
 
+	/* Upgrade the dquot to bigtime format if possible. */
+	if (dqp->q_id != 0 &&
+	    xfs_sb_version_hasbigtime(&tp->t_mountp->m_sb) &&
+	    !(dqp->q_type & XFS_DQTYPE_BIGTIME))
+		dqp->q_type |= XFS_DQTYPE_BIGTIME;
+
 	tp->t_flags |= XFS_TRANS_DIRTY;
 	set_bit(XFS_LI_DIRTY, &dqp->q_logitem.qli_item.li_flags);
 }

include/linux/dax.h

@@ -231,8 +231,7 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
 int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 				      pgoff_t index);
-int dax_iomap_zero(loff_t pos, unsigned offset, unsigned size,
+s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap);
-			struct iomap *iomap);
 static inline bool dax_mapping(struct address_space *mapping)
 {
 	return mapping->host && IS_DAX(mapping->host);

include/linux/iomap.h

@@ -13,6 +13,7 @@
 struct address_space;
 struct fiemap_extent_info;
 struct inode;
+struct iomap_dio;
 struct iomap_writepage_ctx;
 struct iov_iter;
 struct kiocb;
@@ -258,6 +259,10 @@ struct iomap_dio_ops {
 ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
 		bool wait_for_completion);
+struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
+		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
+		bool wait_for_completion);
+ssize_t iomap_dio_complete(struct iomap_dio *dio);
 int iomap_dio_iopoll(struct kiocb *kiocb, bool spin);
 
 #ifdef CONFIG_SWAP

include/linux/ipmi.h

@@ -333,4 +333,6 @@ struct ipmi_smi_info {
 /* This is to get the private info of struct ipmi_smi */
 extern int ipmi_get_smi_info(int if_num, struct ipmi_smi_info *data);
 
+#define GET_DEVICE_ID_MAX_RETRY		5
+
 #endif /* __LINUX_IPMI_H */

include/linux/pagemap.h

@@ -927,4 +927,20 @@ static inline int page_mkwrite_check_truncate(struct page *page,
 	return offset;
 }
 
+/**
+ * i_blocks_per_page - How many blocks fit in this page.
+ * @inode: The inode which contains the blocks.
+ * @page: The page (head page if the page is a THP).
+ *
+ * If the block size is larger than the size of this page, return zero.
+ *
+ * Context: The caller should hold a refcount on the page to prevent it
+ * from being split.
+ * Return: The number of filesystem blocks covered by this page.
+ */
+static inline
+unsigned int i_blocks_per_page(struct inode *inode, struct page *page)
+{
+	return thp_size(page) >> inode->i_blkbits;
+}
 #endif /* _LINUX_PAGEMAP_H */

include/linux/sched/task.h

@@ -83,7 +83,7 @@ extern void do_group_exit(int);
 extern void exit_files(struct task_struct *);
 extern void exit_itimers(struct signal_struct *);
 
-extern long _do_fork(struct kernel_clone_args *kargs);
+extern pid_t kernel_clone(struct kernel_clone_args *kargs);
 struct task_struct *fork_idle(int);
 struct mm_struct *copy_init_mm(void);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);

include/uapi/linux/ipmi_msgdefs.h

@@ -69,6 +69,8 @@
 #define IPMI_ERR_MSG_TRUNCATED		0xc6
 #define IPMI_REQ_LEN_INVALID_ERR	0xc7
 #define IPMI_REQ_LEN_EXCEEDED_ERR	0xc8
+#define IPMI_DEVICE_IN_FW_UPDATE_ERR	0xd1
+#define IPMI_DEVICE_IN_INIT_ERR		0xd2
 #define IPMI_NOT_IN_MY_STATE_ERR	0xd5	/* IPMI 2.0 */
 #define IPMI_LOST_ARBITRATION_ERR	0x81
 #define IPMI_BUS_ERR			0x82

include/uapi/linux/pidfd.h

@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+#ifndef _UAPI_LINUX_PIDFD_H
+#define _UAPI_LINUX_PIDFD_H
+
+#include <linux/types.h>
+#include <linux/fcntl.h>
+
+/* Flags for pidfd_open().  */
+#define PIDFD_NONBLOCK O_NONBLOCK
+
+#endif /* _UAPI_LINUX_PIDFD_H */

kernel/cgroup/cgroup.c

@@ -2006,7 +2006,6 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 	BUG_ON(!list_empty(&root_cgrp->self.children));
 	BUG_ON(atomic_read(&root->nr_cgrps) != 1);
 
-	kernfs_activate(root_cgrp->kn);
 	ret = 0;
 	goto out;
 
@@ -3682,6 +3681,9 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 	struct cgroup_subsys_state *css;
 	int ret;
 
+	if (!nbytes)
+		return 0;
+
 	/*
 	 * If namespaces are delegation boundaries, disallow writes to
 	 * files in an non-init namespace root from inside the namespace

kernel/exit.c

@@ -1474,7 +1474,7 @@ end:
 	return retval;
 }
 
-static struct pid *pidfd_get_pid(unsigned int fd)
+static struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags)
 {
 	struct fd f;
 	struct pid *pid;
@@ -1484,8 +1484,10 @@ static struct pid *pidfd_get_pid(unsigned int fd)
 		return ERR_PTR(-EBADF);
 
 	pid = pidfd_pid(f.file);
-	if (!IS_ERR(pid))
+	if (!IS_ERR(pid)) {
 		get_pid(pid);
+		*flags = f.file->f_flags;
+	}
 
 	fdput(f);
 	return pid;
@@ -1498,6 +1500,7 @@ static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
 	struct pid *pid = NULL;
 	enum pid_type type;
 	long ret;
+	unsigned int f_flags = 0;
 
 	if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED|
 			__WNOTHREAD|__WCLONE|__WALL))
@@ -1531,9 +1534,10 @@ static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
 		if (upid < 0)
 			return -EINVAL;
 
-		pid = pidfd_get_pid(upid);
+		pid = pidfd_get_pid(upid, &f_flags);
 		if (IS_ERR(pid))
 			return PTR_ERR(pid);
+
 		break;
 	default:
 		return -EINVAL;
@@ -1544,7 +1548,12 @@ static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
 	wo.wo_flags	= options;
 	wo.wo_info	= infop;
 	wo.wo_rusage	= ru;
+	if (f_flags & O_NONBLOCK)
+		wo.wo_flags |= WNOHANG;
+
 	ret = do_wait(&wo);
+	if (!ret && !(options & WNOHANG) && (f_flags & O_NONBLOCK))
+		ret = -EAGAIN;
 
 	put_pid(pid);
 	return ret;

kernel/fork.c

@@ -2416,14 +2416,14 @@ struct mm_struct *copy_init_mm(void)
  *
  * args->exit_signal is expected to be checked for sanity by the caller.
  */
-long _do_fork(struct kernel_clone_args *args)
+pid_t kernel_clone(struct kernel_clone_args *args)
 {
 	u64 clone_flags = args->flags;
 	struct completion vfork;
 	struct pid *pid;
 	struct task_struct *p;
 	int trace = 0;
-	long nr;
+	pid_t nr;
 
 	/*
 	 * For legacy clone() calls, CLONE_PIDFD uses the parent_tid argument
@@ -2511,7 +2511,7 @@ pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
 		.stack_size	= (unsigned long)arg,
 	};
 
-	return _do_fork(&args);
+	return kernel_clone(&args);
 }
 
 #ifdef __ARCH_WANT_SYS_FORK
@@ -2522,7 +2522,7 @@ SYSCALL_DEFINE0(fork)
 		.exit_signal = SIGCHLD,
 	};
 
-	return _do_fork(&args);
+	return kernel_clone(&args);
 #else
 	/* can not support in nommu mode */
 	return -EINVAL;
@@ -2538,7 +2538,7 @@ SYSCALL_DEFINE0(vfork)
 		.exit_signal	= SIGCHLD,
 	};
 
-	return _do_fork(&args);
+	return kernel_clone(&args);
 }
 #endif
 
@@ -2576,7 +2576,7 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
 		.tls		= tls,
 	};
 
-	return _do_fork(&args);
+	return kernel_clone(&args);
 }
 #endif
 
@@ -2734,7 +2734,7 @@ SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size)
 	if (!clone3_args_valid(&kargs))
 		return -EINVAL;
 
-	return _do_fork(&kargs);
+	return kernel_clone(&kargs);
 }
 #endif
 
@@ -2897,7 +2897,7 @@ int unshare_fd(unsigned long unshare_flags, unsigned int max_fds,
 /*
  * unshare allows a process to 'unshare' part of the process
  * context which was originally shared using clone.  copy_*
- * functions used by _do_fork() cannot be used here directly
+ * functions used by kernel_clone() cannot be used here directly
  * because they modify an inactive task_struct that is being
  * constructed. Here we are modifying the current, active,
  * task_struct.

kernel/pid.c

@@ -43,6 +43,7 @@
 #include <linux/sched/task.h>
 #include <linux/idr.h>
 #include <net/sock.h>
+#include <uapi/linux/pidfd.h>
 
 struct pid init_struct_pid = {
 	.count		= REFCOUNT_INIT(1),
@@ -523,7 +524,8 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
 /**
  * pidfd_create() - Create a new pid file descriptor.
  *
- * @pid:  struct pid that the pidfd will reference
+ * @pid:   struct pid that the pidfd will reference
+ * @flags: flags to pass
  *
  * This creates a new pid file descriptor with the O_CLOEXEC flag set.
  *
@@ -533,12 +535,12 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
  * Return: On success, a cloexec pidfd is returned.
  *         On error, a negative errno number will be returned.
  */
-static int pidfd_create(struct pid *pid)
+static int pidfd_create(struct pid *pid, unsigned int flags)
 {
 	int fd;
 
 	fd = anon_inode_getfd("[pidfd]", &pidfd_fops, get_pid(pid),
-			      O_RDWR | O_CLOEXEC);
+			      flags | O_RDWR | O_CLOEXEC);
 	if (fd < 0)
 		put_pid(pid);
 
@@ -566,7 +568,7 @@ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags)
 	int fd;
 	struct pid *p;
 
-	if (flags)
+	if (flags & ~PIDFD_NONBLOCK)
 		return -EINVAL;
 
 	if (pid <= 0)
@@ -577,7 +579,7 @@ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags)
 		return -ESRCH;
 
 	if (pid_has_task(p, PIDTYPE_TGID))
-		fd = pidfd_create(p);
+		fd = pidfd_create(p, flags);
 	else
 		fd = -EINVAL;
 

samples/kprobes/kprobe_example.c

@@ -2,13 +2,13 @@
 /*
  * NOTE: This example is works on x86 and powerpc.
  * Here's a sample kernel module showing the use of kprobes to dump a
- * stack trace and selected registers when _do_fork() is called.
+ * stack trace and selected registers when kernel_clone() is called.
  *
  * For more information on theory of operation of kprobes, see
  * Documentation/trace/kprobes.rst
  *
  * You will see the trace data in /var/log/messages and on the console
- * whenever _do_fork() is invoked to create a new process.
+ * whenever kernel_clone() is invoked to create a new process.
  */
 
 #include <linux/kernel.h>
@@ -16,7 +16,7 @@
 #include <linux/kprobes.h>
 
 #define MAX_SYMBOL_LEN	64
-static char symbol[MAX_SYMBOL_LEN] = "_do_fork";
+static char symbol[MAX_SYMBOL_LEN] = "kernel_clone";
 module_param_string(symbol, symbol, sizeof(symbol), 0644);
 
 /* For each probe you need to allocate a kprobe structure */

samples/kprobes/kretprobe_example.c

@@ -8,7 +8,7 @@
  *
  * usage: insmod kretprobe_example.ko func=<func_name>
  *
- * If no func_name is specified, _do_fork is instrumented
+ * If no func_name is specified, kernel_clone is instrumented
  *
  * For more information on theory of operation of kretprobes, see
  * Documentation/trace/kprobes.rst
@@ -26,7 +26,7 @@
 #include <linux/limits.h>
 #include <linux/sched.h>
 
-static char func_name[NAME_MAX] = "_do_fork";
+static char func_name[NAME_MAX] = "kernel_clone";
 module_param_string(func, func_name, NAME_MAX, S_IRUGO);
 MODULE_PARM_DESC(func, "Function to kretprobe; this module will report the"
 			" function's execution time");

tools/lib/subcmd/help.c

@@ -65,12 +65,14 @@ void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes)
 	ci = cj = ei = 0;
 	while (ci < cmds->cnt && ei < excludes->cnt) {
 		cmp = strcmp(cmds->names[ci]->name, excludes->names[ei]->name);
-		if (cmp < 0)
+		if (cmp < 0) {
 			cmds->names[cj++] = cmds->names[ci++];
-		else if (cmp == 0)
+		} else if (cmp == 0) {
-			ci++, ei++;
+			ci++;
-		else if (cmp > 0)
 			ei++;
+		} else if (cmp > 0) {
+			ei++;
+		}
 	}
 
 	while (ci < cmds->cnt)

tools/power/cpupower/utils/cpufreq-set.c

@@ -99,13 +99,17 @@ static unsigned long string_to_frequency(const char *str)
 		continue;
 
 	if (str[cp] == '.') {
-		while (power > -1 && isdigit(str[cp+1]))
+		while (power > -1 && isdigit(str[cp+1])) {
-			cp++, power--;
+			cp++;
+			power--;
+		}
 	}
-	if (power >= -1)	/* not enough => pad */
+	if (power >= -1) {		/* not enough => pad */
 		pad = power + 1;
-	else			/* to much => strip */
+	} else {			/* too much => strip */
-		pad = 0, cp += power + 1;
+		pad = 0;
+		cp += power + 1;
+	}
 	/* check bounds */
 	if (cp <= 0 || cp + pad > NORM_FREQ_LEN - 1)
 		return 0;

tools/testing/selftests/ftrace/test.d/dynevent/add_remove_kprobe.tc

@@ -6,7 +6,7 @@
 echo 0 > events/enable
 echo > dynamic_events
 
-PLACE=_do_fork
+PLACE=kernel_clone
 
 echo "p:myevent1 $PLACE" >> dynamic_events
 echo "r:myevent2 $PLACE" >> dynamic_events

tools/testing/selftests/ftrace/test.d/dynevent/clear_select_events.tc

@@ -6,7 +6,7 @@
 echo 0 > events/enable
 echo > dynamic_events
 
-PLACE=_do_fork
+PLACE=kernel_clone
 
 setup_events() {
 echo "p:myevent1 $PLACE" >> dynamic_events

tools/testing/selftests/ftrace/test.d/dynevent/generic_clear_event.tc

@@ -6,7 +6,7 @@
 echo 0 > events/enable
 echo > dynamic_events
 
-PLACE=_do_fork
+PLACE=kernel_clone
 
 setup_events() {
 echo "p:myevent1 $PLACE" >> dynamic_events

tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc

@@ -4,9 +4,9 @@
 # requires: set_ftrace_filter
 # flags: instance
 
-echo _do_fork:stacktrace >> set_ftrace_filter
+echo kernel_clone:stacktrace >> set_ftrace_filter
 
-grep -q "_do_fork:stacktrace:unlimited" set_ftrace_filter
+grep -q "kernel_clone:stacktrace:unlimited" set_ftrace_filter
 
 (echo "forked"; sleep 1)
 

tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc

@@ -3,7 +3,7 @@
 # description: Kprobe dynamic event - adding and removing
 # requires: kprobe_events
 
-echo p:myevent _do_fork > kprobe_events
+echo p:myevent kernel_clone > kprobe_events
 grep myevent kprobe_events
 test -d events/kprobes/myevent
 echo > kprobe_events

tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc

@@ -3,7 +3,7 @@
 # description: Kprobe dynamic event - busy event check
 # requires: kprobe_events
 
-echo p:myevent _do_fork > kprobe_events
+echo p:myevent kernel_clone > kprobe_events
 test -d events/kprobes/myevent
 echo 1 > events/kprobes/myevent/enable
 echo > kprobe_events && exit_fail # this must fail

tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc

@@ -3,13 +3,13 @@
 # description: Kprobe dynamic event with arguments
 # requires: kprobe_events
 
-echo 'p:testprobe _do_fork $stack $stack0 +0($stack)' > kprobe_events
+echo 'p:testprobe kernel_clone $stack $stack0 +0($stack)' > kprobe_events
 grep testprobe kprobe_events | grep -q 'arg1=\$stack arg2=\$stack0 arg3=+0(\$stack)'
 test -d events/kprobes/testprobe
 
 echo 1 > events/kprobes/testprobe/enable
 ( echo "forked")
-grep testprobe trace | grep '_do_fork' | \
+grep testprobe trace | grep 'kernel_clone' | \
   grep -q 'arg1=0x[[:xdigit:]]* arg2=0x[[:xdigit:]]* arg3=0x[[:xdigit:]]*$'
 
 echo 0 > events/kprobes/testprobe/enable