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

arch/um/Kconfig

@@ -15,7 +15,7 @@ config UML
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DEBUG_BUGVERBOSE
-	select NO_DMA
+	select NO_DMA if !UML_DMA_EMULATION
 	select GENERIC_IRQ_SHOW
 	select GENERIC_CPU_DEVICES
 	select HAVE_GCC_PLUGINS
@@ -26,7 +26,22 @@ config MMU
 	bool
 	default y
 
+config UML_DMA_EMULATION
+	bool
+
 config NO_IOMEM
+	bool "disable IOMEM" if EXPERT
+	depends on !INDIRECT_IOMEM
+	default y
+
+config UML_IOMEM_EMULATION
+	bool
+	select INDIRECT_IOMEM
+	select GENERIC_PCI_IOMAP
+	select GENERIC_IOMAP
+	select NO_GENERIC_PCI_IOPORT_MAP
+
+config NO_IOPORT_MAP
 	def_bool y
 
 config ISA
@@ -61,6 +76,9 @@ config NR_CPUS
 	range 1 1
 	default 1
 
+config ARCH_HAS_CACHE_LINE_SIZE
+	def_bool y
+
 source "arch/$(HEADER_ARCH)/um/Kconfig"
 
 config MAY_HAVE_RUNTIME_DEPS
@@ -91,6 +109,19 @@ config LD_SCRIPT_DYN
 	depends on !LD_SCRIPT_STATIC
 	select MODULE_REL_CRCS if MODVERSIONS
 
+config LD_SCRIPT_DYN_RPATH
+	bool "set rpath in the binary" if EXPERT
+	default y
+	depends on LD_SCRIPT_DYN
+	help
+	  Add /lib (and /lib64 for 64-bit) to the linux binary's rpath
+	  explicitly.
+
+	  You may need to turn this off if compiling for nix systems
+	  that have their libraries in random /nix directories and
+	  might otherwise unexpected use libraries from /lib or /lib64
+	  instead of the desired ones.
+
 config HOSTFS
 	tristate "Host filesystem"
 	help

arch/um/Makefile

@@ -118,7 +118,8 @@ archprepare:
 	$(Q)$(MAKE) $(build)=$(HOST_DIR)/um include/generated/user_constants.h
 
 LINK-$(CONFIG_LD_SCRIPT_STATIC) += -static
-LINK-$(CONFIG_LD_SCRIPT_DYN) += -Wl,-rpath,/lib $(call cc-option, -no-pie)
+LINK-$(CONFIG_LD_SCRIPT_DYN) += $(call cc-option, -no-pie)
+LINK-$(CONFIG_LD_SCRIPT_DYN_RPATH) += -Wl,-rpath,/lib
 
 CFLAGS_NO_HARDENING := $(call cc-option, -fno-PIC,) $(call cc-option, -fno-pic,) \
 	-fno-stack-protector $(call cc-option, -fno-stack-protector-all)

arch/um/drivers/Kconfig

@@ -357,3 +357,23 @@ config UML_RTC
 	  rtcwake, especially in time-travel mode. This driver enables that
 	  by providing a fake RTC clock that causes a wakeup at the right
 	  time.
+
+config UML_PCI_OVER_VIRTIO
+	bool "Enable PCI over VIRTIO device simulation"
+	# in theory, just VIRTIO is enough, but that causes recursion
+	depends on VIRTIO_UML
+	select FORCE_PCI
+	select UML_IOMEM_EMULATION
+	select UML_DMA_EMULATION
+	select PCI_MSI
+	select PCI_MSI_IRQ_DOMAIN
+	select PCI_LOCKLESS_CONFIG
+
+config UML_PCI_OVER_VIRTIO_DEVICE_ID
+	int "set the virtio device ID for PCI emulation"
+	default -1
+	depends on UML_PCI_OVER_VIRTIO
+	help
+	  There's no official device ID assigned (yet), set the one you
+	  wish to use for experimentation here. The default of -1 is
+	  not valid and will cause the driver to fail at probe.

arch/um/drivers/Makefile

@@ -64,6 +64,7 @@ obj-$(CONFIG_BLK_DEV_COW_COMMON) += cow_user.o
 obj-$(CONFIG_UML_RANDOM) += random.o
 obj-$(CONFIG_VIRTIO_UML) += virtio_uml.o
 obj-$(CONFIG_UML_RTC) += rtc.o
+obj-$(CONFIG_UML_PCI_OVER_VIRTIO) += virt-pci.o
 
 # pcap_user.o must be added explicitly.
 USER_OBJS := fd.o null.o pty.o tty.o xterm.o slip_common.o pcap_user.o vde_user.o vector_user.o

arch/um/drivers/chan_user.c

@@ -256,7 +256,8 @@ static int winch_tramp(int fd, struct tty_port *port, int *fd_out,
 		goto out_close;
 	}
 
-	if (os_set_fd_block(*fd_out, 0)) {
+	err = os_set_fd_block(*fd_out, 0);
+	if (err) {
 		printk(UM_KERN_ERR "winch_tramp: failed to set thread_fd "
 		       "non-blocking.\n");
 		goto out_close;

arch/um/drivers/slip_user.c

@@ -145,7 +145,8 @@ static int slip_open(void *data)
 	}
 	sfd = err;
 
-	if (set_up_tty(sfd))
+	err = set_up_tty(sfd);
+	if (err)
 		goto out_close2;
 
 	pri->slave = sfd;

arch/um/drivers/ubd_kern.c

@@ -1242,8 +1242,7 @@ static int __init ubd_driver_init(void){
 		 * enough. So use anyway the io thread. */
 	}
 	stack = alloc_stack(0, 0);
-	io_pid = start_io_thread(stack + PAGE_SIZE - sizeof(void *),
-				 &thread_fd);
+	io_pid = start_io_thread(stack + PAGE_SIZE, &thread_fd);
 	if(io_pid < 0){
 		printk(KERN_ERR
 		       "ubd : Failed to start I/O thread (errno = %d) - "

arch/um/drivers/virtio_uml.c

@@ -56,6 +56,7 @@ struct virtio_uml_device {
 	u8 status;
 	u8 registered:1;
 	u8 suspended:1;
+	u8 no_vq_suspend:1;
 
 	u8 config_changed_irq:1;
 	uint64_t vq_irq_vq_map;
@@ -1098,6 +1099,19 @@ static void virtio_uml_release_dev(struct device *d)
 	kfree(vu_dev);
 }
 
+void virtio_uml_set_no_vq_suspend(struct virtio_device *vdev,
+				  bool no_vq_suspend)
+{
+	struct virtio_uml_device *vu_dev = to_virtio_uml_device(vdev);
+
+	if (WARN_ON(vdev->config != &virtio_uml_config_ops))
+		return;
+
+	vu_dev->no_vq_suspend = no_vq_suspend;
+	dev_info(&vdev->dev, "%sabled VQ suspend\n",
+		 no_vq_suspend ? "dis" : "en");
+}
+
 /* Platform device */
 
 static int virtio_uml_probe(struct platform_device *pdev)
@@ -1302,13 +1316,16 @@ MODULE_DEVICE_TABLE(of, virtio_uml_match);
 static int virtio_uml_suspend(struct platform_device *pdev, pm_message_t state)
 {
 	struct virtio_uml_device *vu_dev = platform_get_drvdata(pdev);
-	struct virtqueue *vq;
 
-	virtio_device_for_each_vq((&vu_dev->vdev), vq) {
-		struct virtio_uml_vq_info *info = vq->priv;
+	if (!vu_dev->no_vq_suspend) {
+		struct virtqueue *vq;
 
-		info->suspended = true;
-		vhost_user_set_vring_enable(vu_dev, vq->index, false);
+		virtio_device_for_each_vq((&vu_dev->vdev), vq) {
+			struct virtio_uml_vq_info *info = vq->priv;
+
+			info->suspended = true;
+			vhost_user_set_vring_enable(vu_dev, vq->index, false);
+		}
 	}
 
 	if (!device_may_wakeup(&vu_dev->vdev.dev)) {
@@ -1322,13 +1339,16 @@ static int virtio_uml_suspend(struct platform_device *pdev, pm_message_t state)
 static int virtio_uml_resume(struct platform_device *pdev)
 {
 	struct virtio_uml_device *vu_dev = platform_get_drvdata(pdev);
-	struct virtqueue *vq;
 
-	virtio_device_for_each_vq((&vu_dev->vdev), vq) {
-		struct virtio_uml_vq_info *info = vq->priv;
+	if (!vu_dev->no_vq_suspend) {
+		struct virtqueue *vq;
 
-		info->suspended = false;
-		vhost_user_set_vring_enable(vu_dev, vq->index, true);
+		virtio_device_for_each_vq((&vu_dev->vdev), vq) {
+			struct virtio_uml_vq_info *info = vq->priv;
+
+			info->suspended = false;
+			vhost_user_set_vring_enable(vu_dev, vq->index, true);
+		}
 	}
 
 	vu_dev->suspended = false;

arch/um/include/asm/Kbuild

@@ -7,8 +7,8 @@ generic-y += device.h
 generic-y += emergency-restart.h
 generic-y += exec.h
 generic-y += extable.h
+generic-y += fb.h
 generic-y += ftrace.h
-generic-y += futex.h
 generic-y += hw_irq.h
 generic-y += irq_regs.h
 generic-y += irq_work.h
@@ -17,7 +17,6 @@ generic-y += mcs_spinlock.h
 generic-y += mmiowb.h
 generic-y += module.lds.h
 generic-y += param.h
-generic-y += pci.h
 generic-y += percpu.h
 generic-y += preempt.h
 generic-y += softirq_stack.h
@@ -27,3 +26,4 @@ generic-y += trace_clock.h
 generic-y += word-at-a-time.h
 generic-y += kprobes.h
 generic-y += mm_hooks.h
+generic-y += vga.h

arch/um/include/asm/cacheflush.h

@@ -0,0 +1,9 @@
+#ifndef __UM_ASM_CACHEFLUSH_H
+#define __UM_ASM_CACHEFLUSH_H
+
+#include <asm/tlbflush.h>
+#define flush_cache_vmap flush_tlb_kernel_range
+#define flush_cache_vunmap flush_tlb_kernel_range
+
+#include <asm-generic/cacheflush.h>
+#endif /* __UM_ASM_CACHEFLUSH_H */

arch/um/include/asm/cpufeature.h

@@ -0,0 +1,157 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_UM_CPUFEATURE_H
+#define _ASM_UM_CPUFEATURE_H
+
+#include <asm/processor.h>
+
+#if defined(__KERNEL__) && !defined(__ASSEMBLY__)
+
+#include <asm/asm.h>
+#include <linux/bitops.h>
+
+extern const char * const x86_cap_flags[NCAPINTS*32];
+extern const char * const x86_power_flags[32];
+#define X86_CAP_FMT "%s"
+#define x86_cap_flag(flag) x86_cap_flags[flag]
+
+/*
+ * In order to save room, we index into this array by doing
+ * X86_BUG_<name> - NCAPINTS*32.
+ */
+extern const char * const x86_bug_flags[NBUGINTS*32];
+
+#define test_cpu_cap(c, bit)						\
+	 test_bit(bit, (unsigned long *)((c)->x86_capability))
+
+/*
+ * There are 32 bits/features in each mask word.  The high bits
+ * (selected with (bit>>5) give us the word number and the low 5
+ * bits give us the bit/feature number inside the word.
+ * (1UL<<((bit)&31) gives us a mask for the feature_bit so we can
+ * see if it is set in the mask word.
+ */
+#define CHECK_BIT_IN_MASK_WORD(maskname, word, bit)	\
+	(((bit)>>5)==(word) && (1UL<<((bit)&31) & maskname##word ))
+
+#define cpu_has(c, bit)							\
+	 test_cpu_cap(c, bit)
+
+#define this_cpu_has(bit)						\
+	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
+	 x86_this_cpu_test_bit(bit,					\
+		(unsigned long __percpu *)&cpu_info.x86_capability))
+
+/*
+ * This macro is for detection of features which need kernel
+ * infrastructure to be used.  It may *not* directly test the CPU
+ * itself.  Use the cpu_has() family if you want true runtime
+ * testing of CPU features, like in hypervisor code where you are
+ * supporting a possible guest feature where host support for it
+ * is not relevant.
+ */
+#define cpu_feature_enabled(bit)	\
+	(__builtin_constant_p(bit) && DISABLED_MASK_BIT_SET(bit) ? 0 : static_cpu_has(bit))
+
+#define boot_cpu_has(bit)	cpu_has(&boot_cpu_data, bit)
+
+#define set_cpu_cap(c, bit)	set_bit(bit, (unsigned long *)((c)->x86_capability))
+
+extern void setup_clear_cpu_cap(unsigned int bit);
+
+#define setup_force_cpu_cap(bit) do { \
+	set_cpu_cap(&boot_cpu_data, bit);	\
+	set_bit(bit, (unsigned long *)cpu_caps_set);	\
+} while (0)
+
+#define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit)
+
+#if defined(__clang__) && !defined(CONFIG_CC_HAS_ASM_GOTO)
+
+/*
+ * Workaround for the sake of BPF compilation which utilizes kernel
+ * headers, but clang does not support ASM GOTO and fails the build.
+ */
+#ifndef __BPF_TRACING__
+#warning "Compiler lacks ASM_GOTO support. Add -D __BPF_TRACING__ to your compiler arguments"
+#endif
+
+#define static_cpu_has(bit)            boot_cpu_has(bit)
+
+#else
+
+/*
+ * Static testing of CPU features. Used the same as boot_cpu_has(). It
+ * statically patches the target code for additional performance. Use
+ * static_cpu_has() only in fast paths, where every cycle counts. Which
+ * means that the boot_cpu_has() variant is already fast enough for the
+ * majority of cases and you should stick to using it as it is generally
+ * only two instructions: a RIP-relative MOV and a TEST.
+ */
+static __always_inline bool _static_cpu_has(u16 bit)
+{
+	asm_volatile_goto("1: jmp 6f\n"
+		 "2:\n"
+		 ".skip -(((5f-4f) - (2b-1b)) > 0) * "
+			 "((5f-4f) - (2b-1b)),0x90\n"
+		 "3:\n"
+		 ".section .altinstructions,\"a\"\n"
+		 " .long 1b - .\n"		/* src offset */
+		 " .long 4f - .\n"		/* repl offset */
+		 " .word %P[always]\n"		/* always replace */
+		 " .byte 3b - 1b\n"		/* src len */
+		 " .byte 5f - 4f\n"		/* repl len */
+		 " .byte 3b - 2b\n"		/* pad len */
+		 ".previous\n"
+		 ".section .altinstr_replacement,\"ax\"\n"
+		 "4: jmp %l[t_no]\n"
+		 "5:\n"
+		 ".previous\n"
+		 ".section .altinstructions,\"a\"\n"
+		 " .long 1b - .\n"		/* src offset */
+		 " .long 0\n"			/* no replacement */
+		 " .word %P[feature]\n"		/* feature bit */
+		 " .byte 3b - 1b\n"		/* src len */
+		 " .byte 0\n"			/* repl len */
+		 " .byte 0\n"			/* pad len */
+		 ".previous\n"
+		 ".section .altinstr_aux,\"ax\"\n"
+		 "6:\n"
+		 " testb %[bitnum],%[cap_byte]\n"
+		 " jnz %l[t_yes]\n"
+		 " jmp %l[t_no]\n"
+		 ".previous\n"
+		 : : [feature]  "i" (bit),
+		     [always]   "i" (X86_FEATURE_ALWAYS),
+		     [bitnum]   "i" (1 << (bit & 7)),
+		     [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3])
+		 : : t_yes, t_no);
+t_yes:
+	return true;
+t_no:
+	return false;
+}
+
+#define static_cpu_has(bit)					\
+(								\
+	__builtin_constant_p(boot_cpu_has(bit)) ?		\
+		boot_cpu_has(bit) :				\
+		_static_cpu_has(bit)				\
+)
+#endif
+
+#define cpu_has_bug(c, bit)		cpu_has(c, (bit))
+#define set_cpu_bug(c, bit)		set_cpu_cap(c, (bit))
+
+#define static_cpu_has_bug(bit)		static_cpu_has((bit))
+#define boot_cpu_has_bug(bit)		cpu_has_bug(&boot_cpu_data, (bit))
+#define boot_cpu_set_bug(bit)		set_cpu_cap(&boot_cpu_data, (bit))
+
+#define MAX_CPU_FEATURES		(NCAPINTS * 32)
+#define cpu_have_feature		boot_cpu_has
+
+#define CPU_FEATURE_TYPEFMT		"x86,ven%04Xfam%04Xmod%04X"
+#define CPU_FEATURE_TYPEVAL		boot_cpu_data.x86_vendor, boot_cpu_data.x86, \
+					boot_cpu_data.x86_model
+
+#endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */
+#endif /* _ASM_UM_CPUFEATURE_H */

arch/um/include/asm/fpu/api.h

@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _ASM_UM_FPU_API_H
+#define _ASM_UM_FPU_API_H
+
+/* Copyright (c) 2020 Cambridge Greys Ltd
+ * Copyright (c) 2020 Red Hat Inc.
+ * A set of "dummy" defines to allow the direct inclusion
+ * of x86 optimized copy, xor, etc routines into the
+ * UML code tree. */
+
+#define kernel_fpu_begin() (void)0
+#define kernel_fpu_end() (void)0
+
+static inline bool irq_fpu_usable(void)
+{
+	return true;
+}
+
+
+#endif

arch/um/include/asm/futex.h

@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_UM_FUTEX_H
+#define _ASM_UM_FUTEX_H
+
+#include <linux/futex.h>
+#include <linux/uaccess.h>
+#include <asm/errno.h>
+
+
+int arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, u32 __user *uaddr);
+int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval);
+
+#endif

arch/um/include/asm/io.h

@@ -3,16 +3,23 @@
 #define _ASM_UM_IO_H
 #include <linux/types.h>
 
+/* get emulated iomem (if desired) */
+#include <asm-generic/logic_io.h>
+
+#ifndef ioremap
 #define ioremap ioremap
 static inline void __iomem *ioremap(phys_addr_t offset, size_t size)
 {
 	return NULL;
 }
+#endif /* ioremap */
 
+#ifndef iounmap
 #define iounmap iounmap
 static inline void iounmap(void __iomem *addr)
 {
 }
+#endif /* iounmap */
 
 #include <asm-generic/io.h>
 

arch/um/include/asm/irq.h

@@ -31,7 +31,13 @@
 
 #endif
 
-#define NR_IRQS			64
+#define UM_LAST_SIGNAL_IRQ	64
+/* If we have (simulated) PCI MSI, allow 64 more interrupt numbers for it */
+#ifdef CONFIG_PCI_MSI
+#define NR_IRQS			(UM_LAST_SIGNAL_IRQ + 64)
+#else
+#define NR_IRQS			UM_LAST_SIGNAL_IRQ
+#endif /* CONFIG_PCI_MSI */
 
 #include <asm-generic/irq.h>
 #endif

arch/um/include/asm/irqflags.h

@@ -2,15 +2,15 @@
 #ifndef __UM_IRQFLAGS_H
 #define __UM_IRQFLAGS_H
 
-extern int get_signals(void);
-extern int set_signals(int enable);
-extern void block_signals(void);
-extern void unblock_signals(void);
+extern int signals_enabled;
+int set_signals(int enable);
+void block_signals(void);
+void unblock_signals(void);
 
 #define arch_local_save_flags arch_local_save_flags
 static inline unsigned long arch_local_save_flags(void)
 {
-	return get_signals();
+	return signals_enabled;
 }
 
 #define arch_local_irq_restore arch_local_irq_restore

arch/um/include/asm/msi.h

@@ -0,0 +1 @@
+#include <asm-generic/msi.h>

arch/um/include/asm/pci.h

@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ASM_UM_PCI_H
+#define __ASM_UM_PCI_H
+#include <linux/types.h>
+#include <asm/io.h>
+
+#define PCIBIOS_MIN_IO		0
+#define PCIBIOS_MIN_MEM		0
+
+#define pcibios_assign_all_busses() 1
+
+extern int isa_dma_bridge_buggy;
+
+#ifdef CONFIG_PCI
+static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
+{
+	/* no legacy IRQs */
+	return -ENODEV;
+}
+#endif
+
+#ifdef CONFIG_PCI_DOMAINS
+static inline int pci_proc_domain(struct pci_bus *bus)
+{
+	/* always show the domain in /proc */
+	return 1;
+}
+#endif  /* CONFIG_PCI */
+
+#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
+/*
+ * This is a bit of an annoying hack, and it assumes we only have
+ * the virt-pci (if anything). Which is true, but still.
+ */
+void *pci_root_bus_fwnode(struct pci_bus *bus);
+#define pci_root_bus_fwnode	pci_root_bus_fwnode
+#endif
+
+#endif  /* __ASM_UM_PCI_H */

arch/um/include/asm/processor-generic.h

@@ -16,6 +16,8 @@ struct task_struct;
 
 #include <linux/prefetch.h>
 
+#include <asm/cpufeatures.h>
+
 struct mm_struct;
 
 struct thread_struct {
@@ -90,12 +92,18 @@ extern void start_thread(struct pt_regs *regs, unsigned long entry,
 struct cpuinfo_um {
 	unsigned long loops_per_jiffy;
 	int ipi_pipe[2];
+	int cache_alignment;
+	union {
+		__u32		x86_capability[NCAPINTS + NBUGINTS];
+		unsigned long	x86_capability_alignment;
+	};
 };
 
 extern struct cpuinfo_um boot_cpu_data;
 
 #define cpu_data (&boot_cpu_data)
 #define current_cpu_data boot_cpu_data
+#define cache_line_size()	(boot_cpu_data.cache_alignment)
 
 #define KSTK_REG(tsk, reg) get_thread_reg(reg, &tsk->thread.switch_buf)
 extern unsigned long get_wchan(struct task_struct *p);