Merge tag 'for-linus-5.14-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rw/uml

Pull UML updates from Richard Weinberger:

 - Support for optimized routines based on the host CPU

 - Support for PCI via virtio

 - Various fixes

* tag 'for-linus-5.14-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rw/uml:
  um: remove unneeded semicolon in um_arch.c
  um: Remove the repeated declaration
  um: fix error return code in winch_tramp()
  um: fix error return code in slip_open()
  um: Fix stack pointer alignment
  um: implement flush_cache_vmap/flush_cache_vunmap
  um: add a UML specific futex implementation
  um: enable the use of optimized xor routines in UML
  um: Add support for host CPU flags and alignment
  um: allow not setting extra rpaths in the linux binary
  um: virtio/pci: enable suspend/resume
  um: add PCI over virtio emulation driver
  um: irqs: allow invoking time-travel handler multiple times
  um: time-travel/signals: fix ndelay() in interrupt
  um: expose time-travel mode to userspace side
  um: export signals_enabled directly
  um: remove unused smp_sigio_handler() declaration
  lib: add iomem emulation (logic_iomem)
  um: allow disabling NO_IOMEM

8 files changed, 258 insertions, 44 deletions

diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile
index e698e0c7dbdc..1d18e4e46989 100644
--- a/arch/um/kernel/Makefile
+++ b/arch/um/kernel/Makefile
@@ -17,18 +17,19 @@ extra-y := vmlinux.lds
 obj-y = config.o exec.o exitcode.o irq.o ksyms.o mem.o \
 	physmem.o process.o ptrace.o reboot.o sigio.o \
 	signal.o syscall.o sysrq.o time.o tlb.o trap.o \
-	um_arch.o umid.o maccess.o kmsg_dump.o skas/
+	um_arch.o umid.o maccess.o kmsg_dump.o capflags.o skas/
 
 obj-$(CONFIG_BLK_DEV_INITRD) += initrd.o
 obj-$(CONFIG_GPROF)	+= gprof_syms.o
 obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
 obj-$(CONFIG_STACKTRACE) += stacktrace.o
+obj-$(CONFIG_GENERIC_PCI_IOMAP) += ioport.o
 
 USER_OBJS := config.o
 
 include arch/um/scripts/Makefile.rules
 
-targets := config.c config.tmp
+targets := config.c config.tmp capflags.c
 
 # Be careful with the below Sed code - sed is pitfall-rich!
 # We use sed to lower build requirements, for "embedded" builders for instance.
@@ -43,6 +44,15 @@ quiet_cmd_quote1 = QUOTE   $@
 $(obj)/config.c: $(src)/config.c.in $(obj)/config.tmp FORCE
 	$(call if_changed,quote2)
 
+quiet_cmd_mkcapflags = MKCAP   $@
+      cmd_mkcapflags = $(CONFIG_SHELL) $(srctree)/$(src)/../../x86/kernel/cpu/mkcapflags.sh $@ $^
+
+cpufeature = $(src)/../../x86/include/asm/cpufeatures.h
+vmxfeature = $(src)/../../x86/include/asm/vmxfeatures.h
+
+$(obj)/capflags.c: $(cpufeature) $(vmxfeature) $(src)/../../x86/kernel/cpu/mkcapflags.sh FORCE
+	$(call if_changed,mkcapflags)
+
 quiet_cmd_quote2 = QUOTE   $@
       cmd_quote2 = sed -e '/CONFIG/{'          \
 		  -e 's/"CONFIG"//'            \
diff --git a/arch/um/kernel/ioport.c b/arch/um/kernel/ioport.c
new file mode 100644
index 000000000000..7220615b3beb
--- /dev/null
+++ b/arch/um/kernel/ioport.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Intel Corporation
+ * Author: Johannes Berg <johannes@sipsolutions.net>
+ */
+#include <asm/iomap.h>
+#include <asm-generic/pci_iomap.h>
+
+void __iomem *__pci_ioport_map(struct pci_dev *dev, unsigned long port,
+			       unsigned int nr)
+{
+	return NULL;
+}
diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c
index 82af5191e73d..a8873d9bc28b 100644
--- a/arch/um/kernel/irq.c
+++ b/arch/um/kernel/irq.c
@@ -56,7 +56,7 @@ struct irq_entry {
 
 static DEFINE_SPINLOCK(irq_lock);
 static LIST_HEAD(active_fds);
-static DECLARE_BITMAP(irqs_allocated, NR_IRQS);
+static DECLARE_BITMAP(irqs_allocated, UM_LAST_SIGNAL_IRQ);
 static bool irqs_suspended;
 
 static void irq_io_loop(struct irq_reg *irq, struct uml_pt_regs *regs)
@@ -101,10 +101,12 @@ static bool irq_do_timetravel_handler(struct irq_entry *entry,
 	if (!reg->timetravel_handler)
 		return false;
 
-	/* prevent nesting - we'll get it again later when we SIGIO ourselves */
-	if (reg->pending_on_resume)
-		return true;
-
+	/*
+	 * Handle all messages - we might get multiple even while
+	 * interrupts are already suspended, due to suspend order
+	 * etc. Note that time_travel_add_irq_event() will not add
+	 * an event twice, if it's pending already "first wins".
+	 */
 	reg->timetravel_handler(reg->irq, entry->fd, reg->id, &reg->event);
 
 	if (!reg->event.pending)
@@ -123,7 +125,8 @@ static bool irq_do_timetravel_handler(struct irq_entry *entry,
 #endif
 
 static void sigio_reg_handler(int idx, struct irq_entry *entry, enum um_irq_type t,
-			      struct uml_pt_regs *regs)
+			      struct uml_pt_regs *regs,
+			      bool timetravel_handlers_only)
 {
 	struct irq_reg *reg = &entry->reg[t];
 
@@ -136,18 +139,29 @@ static void sigio_reg_handler(int idx, struct irq_entry *entry, enum um_irq_type
 	if (irq_do_timetravel_handler(entry, t))
 		return;
 
-	if (irqs_suspended)
+	/*
+	 * If we're called to only run time-travel handlers then don't
+	 * actually proceed but mark sigio as pending (if applicable).
+	 * For suspend/resume, timetravel_handlers_only may be true
+	 * despite time-travel not being configured and used.
+	 */
+	if (timetravel_handlers_only) {
+#ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT
+		mark_sigio_pending();
+#endif
 		return;
+	}
 
 	irq_io_loop(reg, regs);
 }
 
-void sigio_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
+static void _sigio_handler(struct uml_pt_regs *regs,
+			   bool timetravel_handlers_only)
 {
 	struct irq_entry *irq_entry;
 	int n, i;
 
-	if (irqs_suspended && !um_irq_timetravel_handler_used())
+	if (timetravel_handlers_only && !um_irq_timetravel_handler_used())
 		return;
 
 	while (1) {
@@ -172,14 +186,20 @@ void sigio_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
 			irq_entry = os_epoll_get_data_pointer(i);
 
 			for (t = 0; t < NUM_IRQ_TYPES; t++)
-				sigio_reg_handler(i, irq_entry, t, regs);
+				sigio_reg_handler(i, irq_entry, t, regs,
+						  timetravel_handlers_only);
 		}
 	}
 
-	if (!irqs_suspended)
+	if (!timetravel_handlers_only)
 		free_irqs();
 }
 
+void sigio_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
+{
+	_sigio_handler(regs, irqs_suspended);
+}
+
 static struct irq_entry *get_irq_entry_by_fd(int fd)
 {
 	struct irq_entry *walk;
@@ -399,7 +419,8 @@ unsigned int do_IRQ(int irq, struct uml_pt_regs *regs)
 
 void um_free_irq(int irq, void *dev)
 {
-	if (WARN(irq < 0 || irq > NR_IRQS, "freeing invalid irq %d", irq))
+	if (WARN(irq < 0 || irq > UM_LAST_SIGNAL_IRQ,
+		 "freeing invalid irq %d", irq))
 		return;
 
 	free_irq_by_irq_and_dev(irq, dev);
@@ -467,6 +488,11 @@ int um_request_irq_tt(int irq, int fd, enum um_irq_type type,
 			       devname, dev_id, timetravel_handler);
 }
 EXPORT_SYMBOL(um_request_irq_tt);
+
+void sigio_run_timetravel_handlers(void)
+{
+	_sigio_handler(NULL, true);
+}
 #endif
 
 #ifdef CONFIG_PM_SLEEP
@@ -623,7 +649,7 @@ void __init init_IRQ(void)
 
 	irq_set_chip_and_handler(TIMER_IRQ, &alarm_irq_type, handle_edge_irq);
 
-	for (i = 1; i < NR_IRQS; i++)
+	for (i = 1; i < UM_LAST_SIGNAL_IRQ; i++)
 		irq_set_chip_and_handler(i, &normal_irq_type, handle_edge_irq);
 	/* Initialize EPOLL Loop */
 	os_setup_epoll();
diff --git a/arch/um/kernel/ksyms.c b/arch/um/kernel/ksyms.c
index 8ade54a86a7e..b1e5634398d0 100644
--- a/arch/um/kernel/ksyms.c
+++ b/arch/um/kernel/ksyms.c
@@ -7,7 +7,7 @@
 #include <os.h>
 
 EXPORT_SYMBOL(set_signals);
-EXPORT_SYMBOL(get_signals);
+EXPORT_SYMBOL(signals_enabled);
 
 EXPORT_SYMBOL(os_stat_fd);
 EXPORT_SYMBOL(os_stat_file);
diff --git a/arch/um/kernel/skas/clone.c b/arch/um/kernel/skas/clone.c
index 592cdb138441..5afac0fef24e 100644
--- a/arch/um/kernel/skas/clone.c
+++ b/arch/um/kernel/skas/clone.c
@@ -29,7 +29,7 @@ stub_clone_handler(void)
 	long err;
 
 	err = stub_syscall2(__NR_clone, CLONE_PARENT | CLONE_FILES | SIGCHLD,
-			    (unsigned long)data + UM_KERN_PAGE_SIZE / 2 - sizeof(void *));
+			    (unsigned long)data + UM_KERN_PAGE_SIZE / 2);
 	if (err) {
 		data->parent_err = err;
 		goto done;
diff --git a/arch/um/kernel/skas/uaccess.c b/arch/um/kernel/skas/uaccess.c
index 2dec915abe6f..6c76df96e858 100644
--- a/arch/um/kernel/skas/uaccess.c
+++ b/arch/um/kernel/skas/uaccess.c
@@ -11,6 +11,7 @@
 #include <asm/current.h>
 #include <asm/page.h>
 #include <kern_util.h>
+#include <asm/futex.h>
 #include <os.h>
 
 pte_t *virt_to_pte(struct mm_struct *mm, unsigned long addr)
@@ -248,3 +249,138 @@ long __strnlen_user(const void __user *str, long len)
 	return 0;
 }
 EXPORT_SYMBOL(__strnlen_user);
+
+/**
+ * arch_futex_atomic_op_inuser() - Atomic arithmetic operation with constant
+ *			  argument and comparison of the previous
+ *			  futex value with another constant.
+ *
+ * @encoded_op:	encoded operation to execute
+ * @uaddr:	pointer to user space address
+ *
+ * Return:
+ * 0 - On success
+ * -EFAULT - User access resulted in a page fault
+ * -EAGAIN - Atomic operation was unable to complete due to contention
+ * -ENOSYS - Operation not supported
+ */
+
+int arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, u32 __user *uaddr)
+{
+	int oldval, ret;
+	struct page *page;
+	unsigned long addr = (unsigned long) uaddr;
+	pte_t *pte;
+
+	ret = -EFAULT;
+	if (!access_ok(uaddr, sizeof(*uaddr)))
+		return -EFAULT;
+	preempt_disable();
+	pte = maybe_map(addr, 1);
+	if (pte == NULL)
+		goto out_inuser;
+
+	page = pte_page(*pte);
+#ifdef CONFIG_64BIT
+	pagefault_disable();
+	addr = (unsigned long) page_address(page) +
+			(((unsigned long) addr) & ~PAGE_MASK);
+#else
+	addr = (unsigned long) kmap_atomic(page) +
+		((unsigned long) addr & ~PAGE_MASK);
+#endif
+	uaddr = (u32 *) addr;
+	oldval = *uaddr;
+
+	ret = 0;
+
+	switch (op) {
+	case FUTEX_OP_SET:
+		*uaddr = oparg;
+		break;
+	case FUTEX_OP_ADD:
+		*uaddr += oparg;
+		break;
+	case FUTEX_OP_OR:
+		*uaddr |= oparg;
+		break;
+	case FUTEX_OP_ANDN:
+		*uaddr &= ~oparg;
+		break;
+	case FUTEX_OP_XOR:
+		*uaddr ^= oparg;
+		break;
+	default:
+		ret = -ENOSYS;
+	}
+#ifdef CONFIG_64BIT
+	pagefault_enable();
+#else
+	kunmap_atomic((void *)addr);
+#endif
+
+out_inuser:
+	preempt_enable();
+
+	if (ret == 0)
+		*oval = oldval;
+
+	return ret;
+}
+EXPORT_SYMBOL(arch_futex_atomic_op_inuser);
+
+/**
+ * futex_atomic_cmpxchg_inatomic() - Compare and exchange the content of the
+ *				uaddr with newval if the current value is
+ *				oldval.
+ * @uval:	pointer to store content of @uaddr
+ * @uaddr:	pointer to user space address
+ * @oldval:	old value
+ * @newval:	new value to store to @uaddr
+ *
+ * Return:
+ * 0 - On success
+ * -EFAULT - User access resulted in a page fault
+ * -EAGAIN - Atomic operation was unable to complete due to contention
+ * -ENOSYS - Function not implemented (only if !HAVE_FUTEX_CMPXCHG)
+ */
+
+int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
+{
+	struct page *page;
+	pte_t *pte;
+	int ret = -EFAULT;
+
+	if (!access_ok(uaddr, sizeof(*uaddr)))
+		return -EFAULT;
+
+	preempt_disable();
+	pte = maybe_map((unsigned long) uaddr, 1);
+	if (pte == NULL)
+		goto out_inatomic;
+
+	page = pte_page(*pte);
+#ifdef CONFIG_64BIT
+	pagefault_disable();
+	uaddr = page_address(page) + (((unsigned long) uaddr) & ~PAGE_MASK);
+#else
+	uaddr = kmap_atomic(page) + ((unsigned long) uaddr & ~PAGE_MASK);
+#endif
+
+	*uval = *uaddr;
+
+	ret = cmpxchg(uaddr, oldval, newval);
+
+#ifdef CONFIG_64BIT
+	pagefault_enable();
+#else
+	kunmap_atomic(uaddr);
+#endif
+	ret = 0;
+
+out_inatomic:
+	preempt_enable();
+	return ret;
+}
+EXPORT_SYMBOL(futex_atomic_cmpxchg_inatomic);
diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c
index e0cdb9694fb8..fddd1dec27e6 100644
--- a/arch/um/kernel/time.c
+++ b/arch/um/kernel/time.c
@@ -68,23 +68,15 @@ static void time_travel_handle_message(struct um_timetravel_msg *msg,
 	int ret;
 
 	/*
-	 * Poll outside the locked section (if we're not called to only read
-	 * the response) so we can get interrupts for e.g. virtio while we're
-	 * here, but then we need to lock to not get interrupted between the
-	 * read of the message and write of the ACK.
+	 * We can't unlock here, but interrupt signals with a timetravel_handler
+	 * (see um_request_irq_tt) get to the timetravel_handler anyway.
 	 */
 	if (mode != TTMH_READ) {
-		bool disabled = irqs_disabled();
+		BUG_ON(mode == TTMH_IDLE && !irqs_disabled());
 
-		BUG_ON(mode == TTMH_IDLE && !disabled);
-
-		if (disabled)
-			local_irq_enable();
 		while (os_poll(1, &time_travel_ext_fd) != 0) {
 			/* nothing */
 		}
-		if (disabled)
-			local_irq_disable();
 	}
 
 	ret = os_read_file(time_travel_ext_fd, msg, sizeof(*msg));
@@ -123,15 +115,15 @@ static u64 time_travel_ext_req(u32 op, u64 time)
 		.time = time,
 		.seq = mseq,
 	};
-	unsigned long flags;
 
 	/*
-	 * We need to save interrupts here and only restore when we
-	 * got the ACK - otherwise we can get interrupted and send
-	 * another request while we're still waiting for an ACK, but
-	 * the peer doesn't know we got interrupted and will send
-	 * the ACKs in the same order as the message, but we'd need
-	 * to see them in the opposite order ...
+	 * We need to block even the timetravel handlers of SIGIO here and
+	 * only restore their use when we got the ACK - otherwise we may
+	 * (will) get interrupted by that, try to queue the IRQ for future
+	 * processing and thus send another request while we're still waiting
+	 * for an ACK, but the peer doesn't know we got interrupted and will
+	 * send the ACKs in the same order as the message, but we'd need to
+	 * see them in the opposite order ...
 	 *
 	 * This wouldn't matter *too* much, but some ACKs carry the
 	 * current time (for UM_TIMETRAVEL_GET) and getting another
@@ -140,7 +132,7 @@ static u64 time_travel_ext_req(u32 op, u64 time)
 	 * The sequence number assignment that happens here lets us
 	 * debug such message handling issues more easily.
 	 */
-	local_irq_save(flags);
+	block_signals_hard();
 	os_write_file(time_travel_ext_fd, &msg, sizeof(msg));
 
 	while (msg.op != UM_TIMETRAVEL_ACK)
@@ -152,7 +144,7 @@ static u64 time_travel_ext_req(u32 op, u64 time)
 
 	if (op == UM_TIMETRAVEL_GET)
 		time_travel_set_time(msg.time);
-	local_irq_restore(flags);
+	unblock_signals_hard();
 
 	return msg.time;
 }
@@ -352,9 +344,6 @@ void deliver_time_travel_irqs(void)
 	while ((e = list_first_entry_or_null(&time_travel_irqs,
 					     struct time_travel_event,
 					     list))) {
-		WARN(e->time != time_travel_time,
-		     "time moved from %lld to %lld before IRQ delivery\n",
-		     time_travel_time, e->time);
 		list_del(&e->list);
 		e->pending = false;
 		e->fn(e);
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index 9512253947d5..a149a5e9a16a 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -6,6 +6,7 @@
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/mm.h>
+#include <linux/ctype.h>
 #include <linux/module.h>
 #include <linux/panic_notifier.h>
 #include <linux/seq_file.h>
@@ -17,6 +18,7 @@
 #include <linux/suspend.h>
 
 #include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <as-layout.h>
@@ -51,9 +53,13 @@ static void __init add_arg(char *arg)
  */
 struct cpuinfo_um boot_cpu_data = {
 	.loops_per_jiffy	= 0,
-	.ipi_pipe		= { -1, -1 }
+	.ipi_pipe		= { -1, -1 },
+	.cache_alignment	= L1_CACHE_BYTES,
+	.x86_capability		= { 0 }
 };
 
+EXPORT_SYMBOL(boot_cpu_data);
+
 union thread_union cpu0_irqstack
 	__section(".data..init_irqstack") =
 		{ .thread_info = INIT_THREAD_INFO(init_task) };
@@ -63,17 +69,25 @@ static char host_info[(__NEW_UTS_LEN + 1) * 5];
 
 static int show_cpuinfo(struct seq_file *m, void *v)
 {
-	int index = 0;
+	int i = 0;
 
-	seq_printf(m, "processor\t: %d\n", index);
+	seq_printf(m, "processor\t: %d\n", i);
 	seq_printf(m, "vendor_id\t: User Mode Linux\n");
 	seq_printf(m, "model name\t: UML\n");
 	seq_printf(m, "mode\t\t: skas\n");
 	seq_printf(m, "host\t\t: %s\n", host_info);
-	seq_printf(m, "bogomips\t: %lu.%02lu\n\n",
+	seq_printf(m, "fpu\t\t: %s\n", cpu_has(&boot_cpu_data, X86_FEATURE_FPU) ? "yes" : "no");
+	seq_printf(m, "flags\t\t:");
+	for (i = 0; i < 32*NCAPINTS; i++)
+		if (cpu_has(&boot_cpu_data, i) && (x86_cap_flags[i] != NULL))
+			seq_printf(m, " %s", x86_cap_flags[i]);
+	seq_printf(m, "\n");
+	seq_printf(m, "cache_alignment\t: %d\n", boot_cpu_data.cache_alignment);
+	seq_printf(m, "bogomips\t: %lu.%02lu\n",
 		   loops_per_jiffy/(500000/HZ),
 		   (loops_per_jiffy/(5000/HZ)) % 100);
 
+
 	return 0;
 }
 
@@ -262,6 +276,30 @@ EXPORT_SYMBOL(end_iomem);
 
 #define MIN_VMALLOC (32 * 1024 * 1024)
 
+static void parse_host_cpu_flags(char *line)
+{
+	int i;
+	for (i = 0; i < 32*NCAPINTS; i++) {
+		if ((x86_cap_flags[i] != NULL) && strstr(line, x86_cap_flags[i]))
+			set_cpu_cap(&boot_cpu_data, i);
+	}
+}
+static void parse_cache_line(char *line)
+{
+	long res;
+	char *to_parse = strstr(line, ":");
+	if (to_parse) {
+		to_parse++;
+		while (*to_parse != 0 && isspace(*to_parse)) {
+			to_parse++;
+		}
+		if (kstrtoul(to_parse, 10, &res) == 0 && is_power_of_2(res))
+			boot_cpu_data.cache_alignment = res;
+		else
+			boot_cpu_data.cache_alignment = L1_CACHE_BYTES;
+	}
+}
+
 int __init linux_main(int argc, char **argv)
 {
 	unsigned long avail, diff;
@@ -298,6 +336,8 @@ int __init linux_main(int argc, char **argv)
 	/* OS sanity checks that need to happen before the kernel runs */
 	os_early_checks();
 
+	get_host_cpu_features(parse_host_cpu_flags, parse_cache_line);
+
 	brk_start = (unsigned long) sbrk(0);
 
 	/*