Merge branch 'for-linus-4.21-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rw/uml

Pull UML updates from Richard Weinberger:

 - DISCARD support for our block device driver

 - Many TLB flush optimizations

 - Various smaller fixes

 - And most important, Anton agreed to help me maintaining UML

* 'for-linus-4.21-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rw/uml:
  um: Remove obsolete reenable_XX calls
  um: writev needs <sys/uio.h>
  Add Anton Ivanov to UML maintainers
  um: remove redundant generic-y
  um: Optimize Flush TLB for force/fork case
  um: Avoid marking pages with "changed protection"
  um: Skip TLB flushing where not needed
  um: Optimize TLB operations v2
  um: Remove unnecessary faulted check in uaccess.c
  um: Add support for DISCARD in the UBD Driver
  um: Remove unsafe printks from the io thread
  um: Clean-up command processing in UML UBD driver
  um: Switch to block-mq constants in the UML UBD driver
  um: Make GCOV depend on !KCOV
  um: Include sys/uio.h to have writev()
  um: Add HAVE_DEBUG_BUGVERBOSE
  um: Update maintainers file entry

MAINTAINERS

@@ -15951,15 +15951,16 @@ F:	drivers/media/usb/zr364xx/
 USER-MODE LINUX (UML)
 M:	Jeff Dike <jdike@addtoit.com>
 M:	Richard Weinberger <richard@nod.at>
+M:	Anton Ivanov <anton.ivanov@cambridgegreys.com>
 L:	linux-um@lists.infradead.org
 W:	http://user-mode-linux.sourceforge.net
+Q:	https://patchwork.ozlabs.org/project/linux-um/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rw/uml.git
 S:	Maintained
 F:	Documentation/virtual/uml/
 F:	arch/um/
 F:	arch/x86/um/
 F:	fs/hostfs/
-F:	fs/hppfs/
 
 USERSPACE COPYIN/COPYOUT (UIOVEC)
 M:	Alexander Viro <viro@zeniv.linux.org.uk>

arch/um/Kconfig

@@ -12,6 +12,7 @@ config UML
 	select HAVE_UID16
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_DEBUG_KMEMLEAK
+	select HAVE_DEBUG_BUGVERBOSE
 	select GENERIC_IRQ_SHOW
 	select GENERIC_CPU_DEVICES
 	select GENERIC_CLOCKEVENTS

arch/um/Kconfig.debug

@@ -16,6 +16,7 @@ config GPROF
 config GCOV
 	bool "Enable gcov support"
 	depends on DEBUG_INFO
+	depends on !KCOV
 	help
 	  This option allows developers to retrieve coverage data from a UML
 	  session.

arch/um/drivers/chan_kern.c

@@ -211,12 +211,6 @@ void deactivate_chan(struct chan *chan, int irq)
 		deactivate_fd(chan->fd, irq);
 }
 
-void reactivate_chan(struct chan *chan, int irq)
-{
-	if (chan && chan->enabled)
-		reactivate_fd(chan->fd, irq);
-}
-
 int write_chan(struct chan *chan, const char *buf, int len,
 	       int write_irq)
 {
@@ -228,8 +222,6 @@ int write_chan(struct chan *chan, const char *buf, int len,
 	n = chan->ops->write(chan->fd, buf, len, chan->data);
 	if (chan->primary) {
 		ret = n;
-		if ((ret == -EAGAIN) || ((ret >= 0) && (ret < len)))
-			reactivate_fd(chan->fd, write_irq);
 	}
 	return ret;
 }
@@ -527,8 +519,6 @@ void chan_interrupt(struct line *line, int irq)
 			tty_insert_flip_char(port, c, TTY_NORMAL);
 	} while (err > 0);
 
-	if (err == 0)
-		reactivate_fd(chan->fd, irq);
 	if (err == -EIO) {
 		if (chan->primary) {
 			tty_port_tty_hangup(&line->port, false);

arch/um/drivers/line.c

@@ -235,14 +235,6 @@ void line_unthrottle(struct tty_struct *tty)
 
 	line->throttled = 0;
 	chan_interrupt(line, line->driver->read_irq);
-
-	/*
-	 * Maybe there is enough stuff pending that calling the interrupt
-	 * throttles us again.  In this case, line->throttled will be 1
-	 * again and we shouldn't turn the interrupt back on.
-	 */
-	if (!line->throttled)
-		reactivate_chan(line->chan_in, line->driver->read_irq);
 }
 
 static irqreturn_t line_write_interrupt(int irq, void *data)
@@ -667,8 +659,6 @@ static irqreturn_t winch_interrupt(int irq, void *data)
 		tty_kref_put(tty);
 	}
  out:
-	if (winch->fd != -1)
-		reactivate_fd(winch->fd, WINCH_IRQ);
 	return IRQ_HANDLED;
 }
 

arch/um/drivers/mconsole_kern.c

@@ -96,7 +96,6 @@ static irqreturn_t mconsole_interrupt(int irq, void *dev_id)
 	}
 	if (!list_empty(&mc_requests))
 		schedule_work(&mconsole_work);
-	reactivate_fd(fd, MCONSOLE_IRQ);
 	return IRQ_HANDLED;
 }
 
@@ -240,7 +239,6 @@ void mconsole_stop(struct mc_request *req)
 		(*req->cmd->handler)(req);
 	}
 	os_set_fd_block(req->originating_fd, 0);
-	reactivate_fd(req->originating_fd, MCONSOLE_IRQ);
 	mconsole_reply(req, "", 0, 0);
 }
 

arch/um/drivers/net_kern.c

@@ -137,8 +137,6 @@ static irqreturn_t uml_net_interrupt(int irq, void *dev_id)
 		schedule_work(&lp->work);
 		goto out;
 	}
-	reactivate_fd(lp->fd, UM_ETH_IRQ);
-
 out:
 	spin_unlock(&lp->lock);
 	return IRQ_HANDLED;

arch/um/drivers/port_kern.c

@@ -137,7 +137,6 @@ static void port_work_proc(struct work_struct *unused)
 		if (!port->has_connection)
 			continue;
 
-		reactivate_fd(port->fd, ACCEPT_IRQ);
 		while (port_accept(port))
 			;
 		port->has_connection = 0;

arch/um/drivers/random.c

@@ -73,7 +73,6 @@ static ssize_t rng_dev_read (struct file *filp, char __user *buf, size_t size,
 				return ret ? : -EAGAIN;
 
 			atomic_inc(&host_sleep_count);
-			reactivate_fd(random_fd, RANDOM_IRQ);
 			add_sigio_fd(random_fd);
 
 			add_wait_queue(&host_read_wait, &wait);

arch/um/drivers/vector_user.c

@@ -25,11 +25,13 @@
 #include <linux/if_packet.h>
 #include <sys/socket.h>
 #include <sys/wait.h>
+#include <sys/uio.h>
 #include <linux/virtio_net.h>
 #include <netdb.h>
 #include <stdlib.h>
 #include <os.h>
 #include <um_malloc.h>
+#include <sys/uio.h>
 #include "vector_user.h"
 
 #define ID_GRE 0

arch/um/include/asm/Kbuild

@@ -10,9 +10,7 @@ generic-y += exec.h
 generic-y += extable.h
 generic-y += ftrace.h
 generic-y += futex.h
-generic-y += hardirq.h
 generic-y += hw_irq.h
-generic-y += io.h
 generic-y += irq_regs.h
 generic-y += irq_work.h
 generic-y += kdebug.h

arch/um/include/asm/pgtable.h

@@ -197,12 +197,17 @@ static inline pte_t pte_mkold(pte_t pte)
 
 static inline pte_t pte_wrprotect(pte_t pte)
 { 
-	pte_clear_bits(pte, _PAGE_RW);
+	if (likely(pte_get_bits(pte, _PAGE_RW)))
+		pte_clear_bits(pte, _PAGE_RW);
+	else
+		return pte;
 	return(pte_mknewprot(pte)); 
 }
 
 static inline pte_t pte_mkread(pte_t pte)
 { 
+	if (unlikely(pte_get_bits(pte, _PAGE_USER)))
+		return pte;
 	pte_set_bits(pte, _PAGE_USER);
 	return(pte_mknewprot(pte)); 
 }
@@ -221,6 +226,8 @@ static inline pte_t pte_mkyoung(pte_t pte)
 
 static inline pte_t pte_mkwrite(pte_t pte)	
 {
+	if (unlikely(pte_get_bits(pte,  _PAGE_RW)))
+		return pte;
 	pte_set_bits(pte, _PAGE_RW);
 	return(pte_mknewprot(pte)); 
 }

arch/um/include/shared/irq_user.h

@@ -31,7 +31,6 @@ struct irq_fd {
 struct siginfo;
 extern void sigio_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs);
 extern void free_irq_by_fd(int fd);
-extern void reactivate_fd(int fd, int irqnum);
 extern void deactivate_fd(int fd, int irqnum);
 extern int deactivate_all_fds(void);
 extern int activate_ipi(int fd, int pid);

arch/um/include/shared/os.h

@@ -175,6 +175,7 @@ extern int os_fchange_dir(int fd);
 extern unsigned os_major(unsigned long long dev);
 extern unsigned os_minor(unsigned long long dev);
 extern unsigned long long os_makedev(unsigned major, unsigned minor);
+extern int os_falloc_punch(int fd, unsigned long long offset, int count);
 
 /* start_up.c */
 extern void os_early_checks(void);

arch/um/kernel/irq.c

@@ -350,11 +350,6 @@ static void free_irq_by_irq_and_dev(unsigned int irq, void *dev)
 }
 
 
-void reactivate_fd(int fd, int irqnum)
-{
-	/** NOP - we do auto-EOI now **/
-}
-
 void deactivate_fd(int fd, int irqnum)
 {
 	struct irq_entry *to_free;
@@ -449,7 +444,6 @@ int um_request_irq(unsigned int irq, int fd, int type,
 }
 
 EXPORT_SYMBOL(um_request_irq);
-EXPORT_SYMBOL(reactivate_fd);
 
 /*
  * irq_chip must define at least enable/disable and ack when

arch/um/kernel/sigio.c

@@ -16,7 +16,6 @@ static irqreturn_t sigio_interrupt(int irq, void *data)
 	char c;
 
 	os_read_file(sigio_irq_fd, &c, sizeof(c));
-	reactivate_fd(sigio_irq_fd, SIGIO_WRITE_IRQ);
 	return IRQ_HANDLED;
 }
 

arch/um/kernel/skas/uaccess.c

@@ -62,27 +62,28 @@ static int do_op_one_page(unsigned long addr, int len, int is_write,
 	jmp_buf buf;
 	struct page *page;
 	pte_t *pte;
-	int n, faulted;
+	int n;
 
 	pte = maybe_map(addr, is_write);
 	if (pte == NULL)
 		return -1;
 
 	page = pte_page(*pte);
+#ifdef CONFIG_64BIT
+	pagefault_disable();
+	addr = (unsigned long) page_address(page) +
+		(addr & ~PAGE_MASK);
+#else
 	addr = (unsigned long) kmap_atomic(page) +
 		(addr & ~PAGE_MASK);
+#endif
+	n = (*op)(addr, len, arg);
 
-	current->thread.fault_catcher = &buf;
-
-	faulted = UML_SETJMP(&buf);
-	if (faulted == 0)
-		n = (*op)(addr, len, arg);
-	else
-		n = -1;
-
-	current->thread.fault_catcher = NULL;
-
+#ifdef CONFIG_64BIT
+	pagefault_enable();
+#else
 	kunmap_atomic((void *)addr);
+#endif
 
 	return n;
 }

arch/um/kernel/tlb.c

@@ -37,17 +37,19 @@ struct host_vm_change {
 			} mprotect;
 		} u;
 	} ops[1];
+	int userspace;
 	int index;
-	struct mm_id *id;
+	struct mm_struct *mm;
 	void *data;
 	int force;
 };
 
-#define INIT_HVC(mm, force) \
+#define INIT_HVC(mm, force, userspace) \
 	((struct host_vm_change) \
 	 { .ops		= { { .type = NONE } },	\
-	   .id		= &mm->context.id, \
+	   .mm		= mm, \
        	   .data	= NULL, \
+	   .userspace	= userspace, \
 	   .index	= 0, \
 	   .force	= force })
 
@@ -68,18 +70,40 @@ static int do_ops(struct host_vm_change *hvc, int end,
 		op = &hvc->ops[i];
 		switch (op->type) {
 		case MMAP:
-			ret = map(hvc->id, op->u.mmap.addr, op->u.mmap.len,
-				  op->u.mmap.prot, op->u.mmap.fd,
-				  op->u.mmap.offset, finished, &hvc->data);
+			if (hvc->userspace)
+				ret = map(&hvc->mm->context.id, op->u.mmap.addr,
+					  op->u.mmap.len, op->u.mmap.prot,
+					  op->u.mmap.fd,
+					  op->u.mmap.offset, finished,
+					  &hvc->data);
+			else
+				map_memory(op->u.mmap.addr, op->u.mmap.offset,
+					   op->u.mmap.len, 1, 1, 1);
 			break;
 		case MUNMAP:
-			ret = unmap(hvc->id, op->u.munmap.addr,
-				    op->u.munmap.len, finished, &hvc->data);
+			if (hvc->userspace)
+				ret = unmap(&hvc->mm->context.id,
+					    op->u.munmap.addr,
+					    op->u.munmap.len, finished,
+					    &hvc->data);
+			else
+				ret = os_unmap_memory(
+					(void *) op->u.munmap.addr,
+						      op->u.munmap.len);
+
 			break;
 		case MPROTECT:
-			ret = protect(hvc->id, op->u.mprotect.addr,
-				      op->u.mprotect.len, op->u.mprotect.prot,
-				      finished, &hvc->data);
+			if (hvc->userspace)
+				ret = protect(&hvc->mm->context.id,
+					      op->u.mprotect.addr,
+					      op->u.mprotect.len,
+					      op->u.mprotect.prot,
+					      finished, &hvc->data);
+			else
+				ret = os_protect_memory(
+					(void *) op->u.mprotect.addr,
+							op->u.mprotect.len,
+							1, 1, 1);
 			break;
 		default:
 			printk(KERN_ERR "Unknown op type %d in do_ops\n",
@@ -100,9 +124,12 @@ static int add_mmap(unsigned long virt, unsigned long phys, unsigned long len,
 {
 	__u64 offset;
 	struct host_vm_op *last;
-	int fd, ret = 0;
+	int fd = -1, ret = 0;
 
-	fd = phys_mapping(phys, &offset);
+	if (hvc->userspace)
+		fd = phys_mapping(phys, &offset);
+	else
+		offset = phys;
 	if (hvc->index != 0) {
 		last = &hvc->ops[hvc->index - 1];
 		if ((last->type == MMAP) &&
@@ -215,10 +242,11 @@ static inline int update_pte_range(pmd_t *pmd, unsigned long addr,
 		prot = ((r ? UM_PROT_READ : 0) | (w ? UM_PROT_WRITE : 0) |
 			(x ? UM_PROT_EXEC : 0));
 		if (hvc->force || pte_newpage(*pte)) {
-			if (pte_present(*pte))
-				ret = add_mmap(addr, pte_val(*pte) & PAGE_MASK,
-					       PAGE_SIZE, prot, hvc);
-			else
+			if (pte_present(*pte)) {
+				if (pte_newpage(*pte))
+					ret = add_mmap(addr, pte_val(*pte) & PAGE_MASK,
+						       PAGE_SIZE, prot, hvc);
+			} else
 				ret = add_munmap(addr, PAGE_SIZE, hvc);
 		} else if (pte_newprot(*pte))
 			ret = add_mprotect(addr, PAGE_SIZE, prot, hvc);
@@ -277,9 +305,9 @@ void fix_range_common(struct mm_struct *mm, unsigned long start_addr,
 	pgd_t *pgd;
 	struct host_vm_change hvc;
 	unsigned long addr = start_addr, next;
-	int ret = 0;
+	int ret = 0, userspace = 1;
 
-	hvc = INIT_HVC(mm, force);
+	hvc = INIT_HVC(mm, force, userspace);
 	pgd = pgd_offset(mm, addr);
 	do {
 		next = pgd_addr_end(addr, end_addr);
@@ -314,9 +342,11 @@ static int flush_tlb_kernel_range_common(unsigned long start, unsigned long end)
 	pmd_t *pmd;
 	pte_t *pte;
 	unsigned long addr, last;
-	int updated = 0, err;
+	int updated = 0, err = 0, force = 0, userspace = 0;
+	struct host_vm_change hvc;
 
 	mm = &init_mm;
+	hvc = INIT_HVC(mm, force, userspace);
 	for (addr = start; addr < end;) {
 		pgd = pgd_offset(mm, addr);
 		if (!pgd_present(*pgd)) {
@@ -325,8 +355,7 @@ static int flush_tlb_kernel_range_common(unsigned long start, unsigned long end)
 				last = end;
 			if (pgd_newpage(*pgd)) {
 				updated = 1;
-				err = os_unmap_memory((void *) addr,
-						      last - addr);
+				err = add_munmap(addr, last - addr, &hvc);
 				if (err < 0)
 					panic("munmap failed, errno = %d\n",
 					      -err);
@@ -342,8 +371,7 @@ static int flush_tlb_kernel_range_common(unsigned long start, unsigned long end)
 				last = end;
 			if (pud_newpage(*pud)) {
 				updated = 1;
-				err = os_unmap_memory((void *) addr,
-						      last - addr);
+				err = add_munmap(addr, last - addr, &hvc);
 				if (err < 0)
 					panic("munmap failed, errno = %d\n",
 					      -err);
@@ -359,8 +387,7 @@ static int flush_tlb_kernel_range_common(unsigned long start, unsigned long end)
 				last = end;
 			if (pmd_newpage(*pmd)) {
 				updated = 1;
-				err = os_unmap_memory((void *) addr,
-						      last - addr);
+				err = add_munmap(addr, last - addr, &hvc);
 				if (err < 0)
 					panic("munmap failed, errno = %d\n",
 					      -err);
@@ -372,22 +399,25 @@ static int flush_tlb_kernel_range_common(unsigned long start, unsigned long end)
 		pte = pte_offset_kernel(pmd, addr);
 		if (!pte_present(*pte) || pte_newpage(*pte)) {
 			updated = 1;
-			err = os_unmap_memory((void *) addr,
-					      PAGE_SIZE);
+			err = add_munmap(addr, PAGE_SIZE, &hvc);
 			if (err < 0)
 				panic("munmap failed, errno = %d\n",
 				      -err);
 			if (pte_present(*pte))
-				map_memory(addr,
-					   pte_val(*pte) & PAGE_MASK,
-					   PAGE_SIZE, 1, 1, 1);
+				err = add_mmap(addr, pte_val(*pte) & PAGE_MASK,
+					       PAGE_SIZE, 0, &hvc);
 		}
 		else if (pte_newprot(*pte)) {
 			updated = 1;
-			os_protect_memory((void *) addr, PAGE_SIZE, 1, 1, 1);
+			err = add_mprotect(addr, PAGE_SIZE, 0, &hvc);
 		}
 		addr += PAGE_SIZE;
 	}
+	if (!err)
+		err = do_ops(&hvc, hvc.index, 1);
+
+	if (err < 0)
+		panic("flush_tlb_kernel failed, errno = %d\n", err);
 	return updated;
 }
 
@@ -491,6 +521,13 @@ pte_t *addr_pte(struct task_struct *task, unsigned long addr)
 
 void flush_tlb_all(void)
 {
+	/*
+	 * Don't bother flushing if this address space is about to be
+	 * destroyed.
+	 */
+	if (atomic_read(&current->mm->mm_users) == 0)
+		return;
+
 	flush_tlb_mm(current->mm);
 }
 
@@ -512,6 +549,13 @@ void __flush_tlb_one(unsigned long addr)
 static void fix_range(struct mm_struct *mm, unsigned long start_addr,
 		      unsigned long end_addr, int force)
 {
+	/*
+	 * Don't bother flushing if this address space is about to be
+	 * destroyed.
+	 */
+	if (atomic_read(&mm->mm_users) == 0)
+		return;
+
 	fix_range_common(mm, start_addr, end_addr, force);
 }
 
@@ -527,13 +571,6 @@ EXPORT_SYMBOL(flush_tlb_range);
 void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 			unsigned long end)
 {
-	/*
-	 * Don't bother flushing if this address space is about to be
-	 * destroyed.
-	 */
-	if (atomic_read(&mm->mm_users) == 0)
-		return;
-
 	fix_range(mm, start, end, 0);
 }
 

arch/um/os-Linux/file.c

@@ -610,3 +610,13 @@ unsigned long long os_makedev(unsigned major, unsigned minor)
 {
 	return makedev(major, minor);
 }
+
+int os_falloc_punch(int fd, unsigned long long offset, int len)
+{
+	int n = fallocate(fd, FALLOC_FL_PUNCH_HOLE|FALLOC_FL_KEEP_SIZE, offset, len);
+
+	if (n < 0)
+		return -errno;
+	return n;
+}
+