diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2024-07-25 12:33:08 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2024-07-25 12:33:08 -0700 |
| commit | f9bcc61ad1fbe7dbc6bdd71d31254e429100a009 (patch) | |
| tree | 3b35885ba936318985bf6a21339173750e9fdeb7 /arch | |
| parent | c2a96b7f187fb6a455836d4a6e113947ff11de97 (diff) | |
| parent | 98ff534ec2cd02496c166614e6c1391d8e092e51 (diff) | |
Merge tag 'uml-for-linus-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/uml/linux
Pull UML updates from Richard Weinberger:
- Support for preemption
- i386 Rust support
- Huge cleanup by Benjamin Berg
- UBSAN support
- Removal of dead code
* tag 'uml-for-linus-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/uml/linux: (41 commits)
um: vector: always reset vp->opened
um: vector: remove vp->lock
um: register power-off handler
um: line: always fill *error_out in setup_one_line()
um: remove pcap driver from documentation
um: Enable preemption in UML
um: refactor TLB update handling
um: simplify and consolidate TLB updates
um: remove force_flush_all from fork_handler
um: Do not flush MM in flush_thread
um: Delay flushing syscalls until the thread is restarted
um: remove copy_context_skas0
um: remove LDT support
um: compress memory related stub syscalls while adding them
um: Rework syscall handling
um: Add generic stub_syscall6 function
um: Create signal stack memory assignment in stub_data
um: Remove stub-data.h include from common-offsets.h
um: time-travel: fix signal blocking race/hang
um: time-travel: remove time_exit()
...
Diffstat (limited to 'arch')
60 files changed, 1086 insertions, 1927 deletions
diff --git a/arch/um/Kconfig b/arch/um/Kconfig index 93a5a8999b07..dca84fd6d00a 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -11,7 +11,7 @@ config UML select ARCH_HAS_KCOV select ARCH_HAS_STRNCPY_FROM_USER select ARCH_HAS_STRNLEN_USER - select ARCH_NO_PREEMPT + select ARCH_NO_PREEMPT_DYNAMIC select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_KASAN if X86_64 select HAVE_ARCH_KASAN_VMALLOC if HAVE_ARCH_KASAN @@ -31,7 +31,8 @@ config UML select TRACE_IRQFLAGS_SUPPORT select TTY # Needed for line.c select HAVE_ARCH_VMAP_STACK - select HAVE_RUST if X86_64 + select HAVE_RUST + select ARCH_HAS_UBSAN config MMU bool @@ -48,12 +49,13 @@ config NO_IOMEM config UML_IOMEM_EMULATION bool select INDIRECT_IOMEM + select HAS_IOPORT select GENERIC_PCI_IOMAP select GENERIC_IOMAP select NO_GENERIC_PCI_IOPORT_MAP config NO_IOPORT_MAP - def_bool y + def_bool !UML_IOMEM_EMULATION config ISA bool diff --git a/arch/um/drivers/Kconfig b/arch/um/drivers/Kconfig index b94b2618e7d8..ede40a160c5e 100644 --- a/arch/um/drivers/Kconfig +++ b/arch/um/drivers/Kconfig @@ -297,26 +297,6 @@ config UML_NET_MCAST If unsure, say N. -config UML_NET_PCAP - bool "pcap transport (obsolete)" - depends on UML_NET - depends on !MODVERSIONS - select MAY_HAVE_RUNTIME_DEPS - help - The pcap transport makes a pcap packet stream on the host look - like an ethernet device inside UML. This is useful for making - UML act as a network monitor for the host. You must have libcap - installed in order to build the pcap transport into UML. - - For more information, see - <http://user-mode-linux.sourceforge.net/old/networking.html> That site - has examples of the UML command line to use to enable this option. - - NOTE: THIS TRANSPORT IS DEPRECATED AND WILL BE REMOVED SOON!!! Please - migrate to UML_NET_VECTOR. - - If unsure, say N. - config UML_NET_SLIRP bool "SLiRP transport (obsolete)" depends on UML_NET diff --git a/arch/um/drivers/Makefile b/arch/um/drivers/Makefile index 0e6af81096fd..57882e6bc215 100644 --- a/arch/um/drivers/Makefile +++ b/arch/um/drivers/Makefile @@ -20,14 +20,9 @@ harddog-objs := harddog_kern.o harddog-builtin-$(CONFIG_UML_WATCHDOG) := harddog_user.o harddog_user_exp.o rtc-objs := rtc_kern.o rtc_user.o -LDFLAGS_pcap.o = $(shell $(CC) $(KBUILD_CFLAGS) -print-file-name=libpcap.a) - LDFLAGS_vde.o = $(shell $(CC) $(CFLAGS) -print-file-name=libvdeplug.a) -targets := pcap_kern.o pcap_user.o vde_kern.o vde_user.o - -$(obj)/pcap.o: $(obj)/pcap_kern.o $(obj)/pcap_user.o - $(LD) -r -dp -o $@ $^ $(ld_flags) +targets := vde_kern.o vde_user.o $(obj)/vde.o: $(obj)/vde_kern.o $(obj)/vde_user.o $(LD) -r -dp -o $@ $^ $(ld_flags) @@ -49,7 +44,6 @@ obj-$(CONFIG_UML_NET_DAEMON) += daemon.o obj-$(CONFIG_UML_NET_VECTOR) += vector.o obj-$(CONFIG_UML_NET_VDE) += vde.o obj-$(CONFIG_UML_NET_MCAST) += umcast.o -obj-$(CONFIG_UML_NET_PCAP) += pcap.o obj-$(CONFIG_UML_NET) += net.o obj-$(CONFIG_MCONSOLE) += mconsole.o obj-$(CONFIG_MMAPPER) += mmapper_kern.o @@ -69,7 +63,7 @@ obj-$(CONFIG_UML_RTC) += rtc.o obj-$(CONFIG_UML_PCI_OVER_VIRTIO) += virt-pci.o # pcap_user.o must be added explicitly. -USER_OBJS := fd.o null.o pty.o tty.o xterm.o slip_common.o pcap_user.o vde_user.o vector_user.o +USER_OBJS := fd.o null.o pty.o tty.o xterm.o slip_common.o vde_user.o vector_user.o CFLAGS_null.o = -DDEV_NULL=$(DEV_NULL_PATH) CFLAGS_xterm.o += '-DCONFIG_XTERM_CHAN_DEFAULT_EMULATOR="$(CONFIG_XTERM_CHAN_DEFAULT_EMULATOR)"' diff --git a/arch/um/drivers/chan.h b/arch/um/drivers/chan.h index e14b9cdf7a33..5a61db512ffb 100644 --- a/arch/um/drivers/chan.h +++ b/arch/um/drivers/chan.h @@ -22,7 +22,8 @@ struct chan { unsigned int output:1; unsigned int opened:1; unsigned int enabled:1; - int fd; + int fd_in; + int fd_out; /* only different to fd_in if blocking output is needed */ const struct chan_ops *ops; void *data; }; diff --git a/arch/um/drivers/chan_kern.c b/arch/um/drivers/chan_kern.c index 37538b4168da..e78a99816c86 100644 --- a/arch/um/drivers/chan_kern.c +++ b/arch/um/drivers/chan_kern.c @@ -81,6 +81,12 @@ static const struct chan_ops not_configged_ops = { }; #endif /* CONFIG_NOCONFIG_CHAN */ +static inline bool need_output_blocking(void) +{ + return time_travel_mode == TT_MODE_INFCPU || + time_travel_mode == TT_MODE_EXTERNAL; +} + static int open_one_chan(struct chan *chan) { int fd, err; @@ -96,15 +102,43 @@ static int open_one_chan(struct chan *chan) return fd; err = os_set_fd_block(fd, 0); - if (err) { - (*chan->ops->close)(fd, chan->data); - return err; - } + if (err) + goto out_close; + + chan->fd_in = fd; + chan->fd_out = fd; + + /* + * In time-travel modes infinite-CPU and external we need to guarantee + * that any writes to the output succeed immdiately from the point of + * the VM. The best way to do this is to put the FD in blocking mode + * and simply wait/retry until everything is written. + * As every write is guaranteed to complete, we also do not need to + * request an IRQ for the output. + * + * Note that input cannot happen in a time synchronized way. We permit + * it, but time passes very quickly if anything waits for a read. + */ + if (chan->output && need_output_blocking()) { + err = os_dup_file(chan->fd_out); + if (err < 0) + goto out_close; - chan->fd = fd; + chan->fd_out = err; + + err = os_set_fd_block(chan->fd_out, 1); + if (err) { + os_close_file(chan->fd_out); + goto out_close; + } + } chan->opened = 1; return 0; + +out_close: + (*chan->ops->close)(fd, chan->data); + return err; } static int open_chan(struct list_head *chans) @@ -125,7 +159,7 @@ static int open_chan(struct list_head *chans) void chan_enable_winch(struct chan *chan, struct tty_port *port) { if (chan && chan->primary && chan->ops->winch) - register_winch(chan->fd, port); + register_winch(chan->fd_in, port); } static void line_timer_cb(struct work_struct *work) @@ -156,8 +190,9 @@ int enable_chan(struct line *line) if (chan->enabled) continue; - err = line_setup_irq(chan->fd, chan->input, chan->output, line, - chan); + err = line_setup_irq(chan->fd_in, chan->input, + chan->output && !need_output_blocking(), + line, chan); if (err) goto out_close; @@ -196,7 +231,8 @@ void free_irqs(void) if (chan->input && chan->enabled) um_free_irq(chan->line->read_irq, chan); - if (chan->output && chan->enabled) + if (chan->output && chan->enabled && + !need_output_blocking()) um_free_irq(chan->line->write_irq, chan); chan->enabled = 0; } @@ -216,15 +252,19 @@ static void close_one_chan(struct chan *chan, int delay_free_irq) } else { if (chan->input && chan->enabled) um_free_irq(chan->line->read_irq, chan); - if (chan->output && chan->enabled) + if (chan->output && chan->enabled && + !need_output_blocking()) um_free_irq(chan->line->write_irq, chan); chan->enabled = 0; } + if (chan->fd_out != chan->fd_in) + os_close_file(chan->fd_out); if (chan->ops->close != NULL) - (*chan->ops->close)(chan->fd, chan->data); + (*chan->ops->close)(chan->fd_in, chan->data); chan->opened = 0; - chan->fd = -1; + chan->fd_in = -1; + chan->fd_out = -1; } void close_chan(struct line *line) @@ -244,7 +284,7 @@ void close_chan(struct line *line) void deactivate_chan(struct chan *chan, int irq) { if (chan && chan->enabled) - deactivate_fd(chan->fd, irq); + deactivate_fd(chan->fd_in, irq); } int write_chan(struct chan *chan, const u8 *buf, size_t len, int write_irq) @@ -254,7 +294,7 @@ int write_chan(struct chan *chan, const u8 *buf, size_t len, int write_irq) if (len == 0 || !chan || !chan->ops->write) return 0; - n = chan->ops->write(chan->fd, buf, len, chan->data); + n = chan->ops->write(chan->fd_out, buf, len, chan->data); if (chan->primary) { ret = n; } @@ -268,7 +308,7 @@ int console_write_chan(struct chan *chan, const char *buf, int len) if (!chan || !chan->ops->console_write) return 0; - n = chan->ops->console_write(chan->fd, buf, len); + n = chan->ops->console_write(chan->fd_out, buf, len); if (chan->primary) ret = n; return ret; @@ -296,14 +336,14 @@ int chan_window_size(struct line *line, unsigned short *rows_out, if (chan && chan->primary) { if (chan->ops->window_size == NULL) return 0; - return chan->ops->window_size(chan->fd, chan->data, + return chan->ops->window_size(chan->fd_in, chan->data, rows_out, cols_out); } chan = line->chan_out; if (chan && chan->primary) { if (chan->ops->window_size == NULL) return 0; - return chan->ops->window_size(chan->fd, chan->data, + return chan->ops->window_size(chan->fd_in, chan->data, rows_out, cols_out); } return 0; @@ -319,7 +359,7 @@ static void free_one_chan(struct chan *chan) (*chan->ops->free)(chan->data); if (chan->primary && chan->output) - ignore_sigio_fd(chan->fd); + ignore_sigio_fd(chan->fd_in); kfree(chan); } @@ -478,7 +518,8 @@ static struct chan *parse_chan(struct line *line, char *str, int device, .output = 0, .opened = 0, .enabled = 0, - .fd = -1, + .fd_in = -1, + .fd_out = -1, .ops = ops, .data = data }); return chan; @@ -549,7 +590,7 @@ void chan_interrupt(struct line *line, int irq) schedule_delayed_work(&line->task, 1); goto out; } - err = chan->ops->read(chan->fd, &c, chan->data); + err = chan->ops->read(chan->fd_in, &c, chan->data); if (err > 0) tty_insert_flip_char(port, c, TTY_NORMAL); } while (err > 0); diff --git a/arch/um/drivers/chan_user.c b/arch/um/drivers/chan_user.c index ec04e47b9d79..a66e556012c4 100644 --- a/arch/um/drivers/chan_user.c +++ b/arch/um/drivers/chan_user.c @@ -23,7 +23,7 @@ int generic_read(int fd, __u8 *c_out, void *unused) { int n; - n = read(fd, c_out, sizeof(*c_out)); + CATCH_EINTR(n = read(fd, c_out, sizeof(*c_out))); if (n > 0) return n; else if (n == 0) @@ -37,11 +37,23 @@ int generic_read(int fd, __u8 *c_out, void *unused) int generic_write(int fd, const __u8 *buf, size_t n, void *unused) { + int written = 0; int err; - err = write(fd, buf, n); - if (err > 0) - return err; + /* The FD may be in blocking mode, as such, need to retry short writes, + * they may have been interrupted by a signal. + */ + do { + errno = 0; + err = write(fd, buf + written, n - written); + if (err > 0) { + written += err; + continue; + } + } while (err < 0 && errno == EINTR); + + if (written > 0) + return written; else if (errno == EAGAIN) return 0; else if (err == 0) diff --git a/arch/um/drivers/harddog_kern.c b/arch/um/drivers/harddog_kern.c index 60d1c6cab8a9..99a7144b229f 100644 --- a/arch/um/drivers/harddog_kern.c +++ b/arch/um/drivers/harddog_kern.c @@ -49,6 +49,7 @@ #include "mconsole.h" #include "harddog.h" +MODULE_DESCRIPTION("UML hardware watchdog"); MODULE_LICENSE("GPL"); static DEFINE_MUTEX(harddog_mutex); diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c index d82bc3fdb86e..43d8959cc746 100644 --- a/arch/um/drivers/line.c +++ b/arch/um/drivers/line.c @@ -383,6 +383,7 @@ int setup_one_line(struct line *lines, int n, char *init, parse_chan_pair(NULL, line, n, opts, error_out); err = 0; } + *error_out = "configured as 'none'"; } else { char *new = kstrdup(init, GFP_KERNEL); if (!new) { @@ -406,6 +407,7 @@ int setup_one_line(struct line *lines, int n, char *init, } } if (err) { + *error_out = "failed to parse channel pair"; line->init_str = NULL; line->valid = 0; kfree(new); diff --git a/arch/um/drivers/pcap_kern.c b/arch/um/drivers/pcap_kern.c deleted file mode 100644 index d9bf95d7867b..000000000000 --- a/arch/um/drivers/pcap_kern.c +++ /dev/null @@ -1,113 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) - */ - -#include <linux/init.h> -#include <linux/netdevice.h> -#include <net_kern.h> -#include "pcap_user.h" - -struct pcap_init { - char *host_if; - int promisc; - int optimize; - char *filter; -}; - -static void pcap_init_kern(struct net_device *dev, void *data) -{ - struct uml_net_private *pri; - struct pcap_data *ppri; - struct pcap_init *init = data; - - pri = netdev_priv(dev); - ppri = (struct pcap_data *) pri->user; - ppri->host_if = init->host_if; - ppri->promisc = init->promisc; - ppri->optimize = init->optimize; - ppri->filter = init->filter; - - printk("pcap backend, host interface %s\n", ppri->host_if); -} - -static int pcap_read(int fd, struct sk_buff *skb, struct uml_net_private *lp) -{ - return pcap_user_read(fd, skb_mac_header(skb), - skb->dev->mtu + ETH_HEADER_OTHER, - (struct pcap_data *) &lp->user); -} - -static int pcap_write(int fd, struct sk_buff *skb, struct uml_net_private *lp) -{ - return -EPERM; -} - -static const struct net_kern_info pcap_kern_info = { - .init = pcap_init_kern, - .protocol = eth_protocol, - .read = pcap_read, - .write = pcap_write, -}; - -static int pcap_setup(char *str, char **mac_out, void *data) -{ - struct pcap_init *init = data; - char *remain, *host_if = NULL, *options[2] = { NULL, NULL }; - int i; - - *init = ((struct pcap_init) - { .host_if = "eth0", - .promisc = 1, - .optimize = 0, - .filter = NULL }); - - remain = split_if_spec(str, &host_if, &init->filter, - &options[0], &options[1], mac_out, NULL); - if (remain != NULL) { - printk(KERN_ERR "pcap_setup - Extra garbage on " - "specification : '%s'\n", remain); - return 0; - } - - if (host_if != NULL) - init->host_if = host_if; - - for (i = 0; i < ARRAY_SIZE(options); i++) { - if (options[i] == NULL) - continue; - if (!strcmp(options[i], "promisc")) - init->promisc = 1; - else if (!strcmp(options[i], "nopromisc")) - init->promisc = 0; - else if (!strcmp(options[i], "optimize")) - init->optimize = 1; - else if (!strcmp(options[i], "nooptimize")) - init->optimize = 0; - else { - printk(KERN_ERR "pcap_setup : bad option - '%s'\n", - options[i]); - return 0; - } - } - - return 1; -} - -static struct transport pcap_transport = { - .list = LIST_HEAD_INIT(pcap_transport.list), - .name = "pcap", - .setup = pcap_setup, - .user = &pcap_user_info, - .kern = &pcap_kern_info, - .private_size = sizeof(struct pcap_data), - .setup_size = sizeof(struct pcap_init), -}; - -static int register_pcap(void) -{ - register_transport(&pcap_transport); - return 0; -} - -late_initcall(register_pcap); diff --git a/arch/um/drivers/pcap_user.c b/arch/um/drivers/pcap_user.c deleted file mode 100644 index 52ddda3e3b10..000000000000 --- a/arch/um/drivers/pcap_user.c +++ /dev/null @@ -1,137 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) - */ - -#include <errno.h> -#include <pcap.h> -#include <string.h> -#include <asm/types.h> -#include <net_user.h> -#include "pcap_user.h" -#include <um_malloc.h> - -#define PCAP_FD(p) (*(int *)(p)) - -static int pcap_user_init(void *data, void *dev) -{ - struct pcap_data *pri = data; - pcap_t *p; - char errors[PCAP_ERRBUF_SIZE]; - - p = pcap_open_live(pri->host_if, ETH_MAX_PACKET + ETH_HEADER_OTHER, - pri->promisc, 0, errors); - if (p == NULL) { - printk(UM_KERN_ERR "pcap_user_init : pcap_open_live failed - " - "'%s'\n", errors); - return -EINVAL; - } - - pri->dev = dev; - pri->pcap = p; - return 0; -} - -static int pcap_user_open(void *data) -{ - struct pcap_data *pri = data; - __u32 netmask; - int err; - - if (pri->pcap == NULL) - return -ENODEV; - - if (pri->filter != NULL) { - err = dev_netmask(pri->dev, &netmask); - if (err < 0) { - printk(UM_KERN_ERR "pcap_user_open : dev_netmask failed\n"); - return -EIO; - } - - pri->compiled = uml_kmalloc(sizeof(struct bpf_program), - UM_GFP_KERNEL); - if (pri->compiled == NULL) { - printk(UM_KERN_ERR "pcap_user_open : kmalloc failed\n"); - return -ENOMEM; - } - - err = pcap_compile(pri->pcap, - (struct bpf_program *) pri->compiled, - pri->filter, pri->optimize, netmask); - if (err < 0) { - printk(UM_KERN_ERR "pcap_user_open : pcap_compile failed - " - "'%s'\n", pcap_geterr(pri->pcap)); - goto out; - } - - err = pcap_setfilter(pri->pcap, pri->compiled); - if (err < 0) { - printk(UM_KERN_ERR "pcap_user_open : pcap_setfilter " - "failed - '%s'\n", pcap_geterr(pri->pcap)); - goto out; - } - } - - return PCAP_FD(pri->pcap); - - out: - kfree(pri->compiled); - return -EIO; -} - -static void pcap_remove(void *data) -{ - struct pcap_data *pri = data; - - if (pri->compiled != NULL) - pcap_freecode(pri->compiled); - - if (pri->pcap != NULL) - pcap_close(pri->pcap); -} - -struct pcap_handler_data { - char *buffer; - int len; -}; - -static void handler(u_char *data, const struct pcap_pkthdr *header, - const u_char *packet) -{ - int len; - - struct pcap_handler_data *hdata = (struct pcap_handler_data *) data; - - len = hdata->len < header->caplen ? hdata->len : header->caplen; - memcpy(hdata->buffer, packet, len); - hdata->len = len; -} - -int pcap_user_read(int fd, void *buffer, int len, struct pcap_data *pri) -{ - struct pcap_handler_data hdata = ((struct pcap_handler_data) - { .buffer = buffer, - .len = len }); - int n; - - n = pcap_dispatch(pri->pcap, 1, handler, (u_char *) &hdata); - if (n < 0) { - printk(UM_KERN_ERR "pcap_dispatch failed - %s\n", - pcap_geterr(pri->pcap)); - return -EIO; - } - else if (n == 0) - return 0; - return hdata.len; -} - -const struct net_user_info pcap_user_info = { - .init = pcap_user_init, - .open = pcap_user_open, - .close = NULL, - .remove = pcap_remove, - .add_address = NULL, - .delete_address = NULL, - .mtu = ETH_MAX_PACKET, - .max_packet = ETH_MAX_PACKET + ETH_HEADER_OTHER, -}; diff --git a/arch/um/drivers/pcap_user.h b/arch/um/drivers/pcap_user.h deleted file mode 100644 index 216246f5f09b..000000000000 --- a/arch/um/drivers/pcap_user.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2002 Jeff Dike (jdike@karaya.com) - */ - -#include <net_user.h> - -struct pcap_data { - char *host_if; - int promisc; - int optimize; - char *filter; - void *compiled; - void *pcap; - void *dev; -}; - -extern const struct net_user_info pcap_user_info; - -extern int pcap_user_read(int fd, void *buf, int len, struct pcap_data *pri); - diff --git a/arch/um/drivers/port_kern.c b/arch/um/drivers/port_kern.c index c52b3ff3c092..a4508470df78 100644 --- a/arch/um/drivers/port_kern.c +++ b/arch/um/drivers/port_kern.c @@ -45,15 +45,17 @@ struct connection { static irqreturn_t pipe_interrupt(int irq, void *data) { struct connection *conn = data; - int fd; + int n_fds = 1, fd = -1; + ssize_t ret; - fd = os_rcv_fd(conn->socket[0], &conn->helper_pid); - if (fd < 0) { - if (fd == -EAGAIN) + ret = os_rcv_fd_msg(conn->socket[0], &fd, n_fds, &conn->helper_pid, + sizeof(conn->helper_pid)); + if (ret != sizeof(conn->helper_pid)) { + if (ret == -EAGAIN) return IRQ_NONE; - printk(KERN_ERR "pipe_interrupt : os_rcv_fd returned %d\n", - -fd); + printk(KERN_ERR "pipe_interrupt : os_rcv_fd_msg returned %zd\n", + ret); os_close_file(conn->fd); } diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 9f1e76ddda5a..7f28ec1929dc 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -36,7 +36,6 @@ #include <linux/vmalloc.h> #include <linux/platform_device.h> #include <linux/scatterlist.h> -#include <asm/tlbflush.h> #include <kern_util.h> #include "mconsole_kern.h" #include <init.h> @@ -106,7 +105,6 @@ static inline void ubd_set_bit(__u64 bit, unsigned char *data) #define DRIVER_NAME "uml-blkdev" static DEFINE_MUTEX(ubd_lock); -static DEFINE_MUTEX(ubd_mutex); /* replaces BKL, might not be needed */ static int ubd_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg); @@ -759,7 +757,6 @@ static int ubd_open_dev(struct ubd *ubd_dev) printk(KERN_ERR "Failed to vmalloc COW bitmap\n"); goto error; } - flush_tlb_kernel_vm(); err = read_cow_bitmap(ubd_dev->fd, ubd_dev->cow.bitmap, ubd_dev->cow.bitmap_offset, diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index 4279793b11b7..2d473282ab51 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -1115,11 +1115,12 @@ static int irq_rr; static int vector_net_close(struct net_device *dev) { struct vector_private *vp = netdev_priv(dev); - unsigned long flags; netif_stop_queue(dev); del_timer(&vp->tl); + vp->opened = false; + if (vp->fds == NULL) return 0; @@ -1158,10 +1159,7 @@ static int vector_net_close(struct net_device *dev) destroy_queue(vp->tx_queue); kfree(vp->fds); vp->fds = NULL; - spin_lock_irqsave(&vp->lock, flags); - vp->opened = false; vp->in_error = false; - spin_unlock_irqrestore(&vp->lock, flags); return 0; } @@ -1203,17 +1201,12 @@ static void vector_reset_tx(struct work_struct *work) static int vector_net_open(struct net_device *dev) { struct vector_private *vp = netdev_priv(dev); - unsigned long flags; int err = -EINVAL; struct vector_device *vdevice; - spin_lock_irqsave(&vp->lock, flags); - if (vp->opened) { - spin_unlock_irqrestore(&vp->lock, flags); + if (vp->opened) return -ENXIO; - } vp->opened = true; - spin_unlock_irqrestore(&vp->lock, flags); vp->bpf = uml_vector_user_bpf(get_bpf_file(vp->parsed)); @@ -1387,8 +1380,6 @@ static int vector_net_load_bpf_flash(struct net_device *dev, return -1; } - spin_lock(&vp->lock); - if (vp->bpf != NULL) { if (vp->opened) uml_vector_detach_bpf(vp->fds->rx_fd, vp->bpf); @@ -1417,15 +1408,12 @@ static int vector_net_load_bpf_flash(struct net_device *dev, if (vp->opened) result = uml_vector_attach_bpf(vp->fds->rx_fd, vp->bpf); - spin_unlock(&vp->lock); - return result; free_buffer: release_firmware(fw); flash_fail: - spin_unlock(&vp->lock); if (vp->bpf != NULL) kfree(vp->bpf->filter); kfree(vp->bpf); @@ -1631,7 +1619,6 @@ static void vector_eth_configure( INIT_WORK(&vp->reset_tx, vector_reset_tx); timer_setup(&vp->tl, vector_timer_expire, 0); - spin_lock_init(&vp->lock); /* FIXME */ dev->netdev_ops = &vector_netdev_ops; diff --git a/arch/um/drivers/vector_kern.h b/arch/um/drivers/vector_kern.h index 2a1fa8e0f3e1..806df551be0b 100644 --- a/arch/um/drivers/vector_kern.h +++ b/arch/um/drivers/vector_kern.h @@ -71,7 +71,6 @@ struct vector_estats { struct vector_private { struct list_head list; - spinlock_t lock; struct net_device *dev; struct napi_struct napi ____cacheline_aligned; diff --git a/arch/um/drivers/xterm.c b/arch/um/drivers/xterm.c index 6918de5e2956..e4316c7981e8 100644 --- a/arch/um/drivers/xterm.c +++ b/arch/um/drivers/xterm.c @@ -156,7 +156,7 @@ static int xterm_open(int input, int output, int primary, void *d, new = xterm_fd(fd, &data->helper_pid); if (new < 0) { err = new; - printk(UM_KERN_ERR "xterm_open : os_rcv_fd failed, err = %d\n", + printk(UM_KERN_ERR "xterm_open : xterm_fd failed, err = %d\n", -err); goto out_kill; } diff --git a/arch/um/drivers/xterm_kern.c b/arch/um/drivers/xterm_kern.c index 8011e51993d5..3971252cb1a6 100644 --- a/arch/um/drivers/xterm_kern.c +++ b/arch/um/drivers/xterm_kern.c @@ -21,12 +21,19 @@ struct xterm_wait { static irqreturn_t xterm_interrupt(int irq, void *data) { struct xterm_wait *xterm = data; - int fd; + int fd = -1, n_fds = 1; + ssize_t ret; - fd = os_rcv_fd(xterm->fd, &xterm->pid); - if (fd == -EAGAIN) + ret = os_rcv_fd_msg(xterm->fd, &fd, n_fds, + &xterm->pid, sizeof(xterm->pid)); + if (ret == -EAGAIN) return IRQ_NONE; + if (ret < 0) + fd = ret; + else if (ret != sizeof(xterm->pid)) + fd = -EMSGSIZE; + xterm->new_fd = fd; complete(&xterm->ready); diff --git a/arch/um/include/asm/mmu.h b/arch/um/include/asm/mmu.h index f2923c767bb9..a3eaca41ff61 100644 --- a/arch/um/include/asm/mmu.h +++ b/arch/um/include/asm/mmu.h @@ -7,15 +7,13 @@ #define __ARCH_UM_MMU_H #include <mm_id.h> -#include <asm/mm_context.h> typedef struct mm_context { struct mm_id id; - struct uml_arch_mm_context arch; -} mm_context_t; -/* Avoid tangled inclusion with asm/ldt.h */ -extern long init_new_ldt(struct mm_context *to_mm, struct mm_context *from_mm); -extern void free_ldt(struct mm_context *mm); + /* Address range in need of a TLB sync */ + unsigned long sync_tlb_range_from; + unsigned long sync_tlb_range_to; +} mm_context_t; #endif diff --git a/arch/um/include/asm/mmu_context.h b/arch/um/include/asm/mmu_context.h index 68e2eb9cfb47..23dcc914d44e 100644 --- a/arch/um/include/asm/mmu_context.h +++ b/arch/um/include/asm/mmu_context.h @@ -13,8 +13,6 @@ #include <asm/mm_hooks.h> #include <asm/mmu.h> -extern void force_flush_all(void); - #define activate_mm activate_mm static inline void activate_mm(struct mm_struct *old, struct mm_struct *new) { diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h index e1ece21dbe3f..5bb397b65efb 100644 --- a/arch/um/include/asm/pgtable.h +++ b/arch/um/include/asm/pgtable.h @@ -244,6 +244,38 @@ static inline void set_pte(pte_t *pteptr, pte_t pteval) #define PFN_PTE_SHIFT PAGE_SHIFT +static inline void um_tlb_mark_sync(struct mm_struct *mm, unsigned long start, + unsigned long end) +{ + if (!mm->context.sync_tlb_range_to) { + mm->context.sync_tlb_range_from = start; + mm->context.sync_tlb_range_to = end; + } else { + if (start < mm->context.sync_tlb_range_from) + mm->context.sync_tlb_range_from = start; + if (end > mm->context.sync_tlb_range_to) + mm->context.sync_tlb_range_to = end; + } +} + +#define set_ptes set_ptes +static inline void set_ptes(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, int nr) +{ + /* Basically the default implementation */ + size_t length = nr * PAGE_SIZE; + + for (;;) { + set_pte(ptep, pte); + if (--nr == 0) + break; + ptep++; + pte = __pte(pte_val(pte) + (nr << PFN_PTE_SHIFT)); + } + + um_tlb_mark_sync(mm, addr, addr + length); +} + #define __HAVE_ARCH_PTE_SAME static inline int pte_same(pte_t pte_a, pte_t pte_b) { diff --git a/arch/um/include/asm/tlbflush.h b/arch/um/include/asm/tlbflush.h index a5bda890390d..db997976b6ea 100644 --- a/arch/um/include/asm/tlbflush.h +++ b/arch/um/include/asm/tlbflush.h @@ -9,23 +9,51 @@ #include <linux/mm.h> /* - * TLB flushing: + * In UML, we need to sync the TLB over by using mmap/munmap/mprotect syscalls + * from the process handling the MM (which can be the kernel itself). + * + * To track updates, we can hook into set_ptes and flush_tlb_*. With set_ptes + * we catch all PTE transitions where memory that was unusable becomes usable. + * While with flush_tlb_* we can track any memory that becomes unusable and + * even if a higher layer of the page table was modified. + * + * So, we simply track updates using both methods and mark the memory area to + * be synced later on. The only special case is that flush_tlb_kern_* needs to + * be executed immediately as there is no good synchronization point in that + * case. In contrast, in the set_ptes case we can wait for the next kernel + * segfault before we do the synchornization. * - * - flush_tlb() flushes the current mm struct TLBs * - flush_tlb_all() flushes all processes TLBs * - flush_tlb_mm(mm) flushes the specified mm context TLB's * - flush_tlb_page(vma, vmaddr) flushes one page - * - flush_tlb_kernel_vm() flushes the kernel vm area * - flush_tlb_range(vma, start, end) flushes a range of pages + * - flush_tlb_kernel_range(start, end) flushes a range of kernel pages */ +extern int um_tlb_sync(struct mm_struct *mm); + extern void flush_tlb_all(void); extern void flush_tlb_mm(struct mm_struct *mm); -extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end); -extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long address); -extern void flush_tlb_kernel_vm(void); -extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); -extern void __flush_tlb_one(unsigned long addr); + +static inline void flush_tlb_page(struct vm_area_struct *vma, + unsigned long address) +{ + um_tlb_mark_sync(vma->vm_mm, address, address + PAGE_SIZE); +} + +static inline void flush_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + um_tlb_mark_sync(vma->vm_mm, start, end); +} + +static inline void flush_tlb_kernel_range(unsigned long start, + unsigned long end) +{ + um_tlb_mark_sync(&init_mm, start, end); + + /* Kernel needs to be synced immediately */ + um_tlb_sync(&init_mm); +} #endif diff --git a/arch/um/include/shared/as-layout.h b/arch/um/include/shared/as-layout.h index c22f46a757dc..06292fca5a4d 100644 --- a/arch/um/include/shared/as-layout.h +++ b/arch/um/include/shared/as-layout.h @@ -23,7 +23,7 @@ #define STUB_START stub_start #define STUB_CODE STUB_START #define STUB_DATA (STUB_CODE + UM_KERN_PAGE_SIZE) -#define STUB_DATA_PAGES 1 /* must be a power of two */ +#define STUB_DATA_PAGES 2 /* must be a power of two */ #define STUB_END (STUB_DATA + STUB_DATA_PAGES * UM_KERN_PAGE_SIZE) #ifndef __ASSEMBLY__ diff --git a/arch/um/include/shared/common-offsets.h b/arch/um/include/shared/common-offsets.h index 96195483fbd0..579ed946a3a9 100644 --- a/arch/um/include/shared/common-offsets.h +++ b/arch/um/include/shared/common-offsets.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* for use by sys-$SUBARCH/kernel-offsets.c */ -#include <stub-data.h> DEFINE(KERNEL_MADV_REMOVE, MADV_REMOVE); @@ -30,7 +29,3 @@ DEFINE(UML_CONFIG_64BIT, CONFIG_64BIT); DEFINE(UML_CONFIG_UML_TIME_TRAVEL_SUPPORT, CONFIG_UML_TIME_TRAVEL_SUPPORT); #endif -/* for stub */ -DEFINE(UML_STUB_FIELD_OFFSET, offsetof(struct stub_data, offset)); -DEFINE(UML_STUB_FIELD_CHILD_ERR, offsetof(struct stub_data, child_err)); -DEFINE(UML_STUB_FIELD_FD, offsetof(struct stub_data, fd)); diff --git a/arch/um/include/shared/kern_util.h b/arch/um/include/shared/kern_util.h index 95521b1f5b20..d8ffd2db168e 100644 --- a/arch/um/include/shared/kern_util.h +++ b/arch/um/include/shared/kern_util.h @@ -13,7 +13,6 @@ struct siginfo; extern int uml_exitcode; -extern int ncpus; extern int kmalloc_ok; #define UML_ROUND_UP(addr) \ diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h index aff8906304ea..9a039d6f1f74 100644 --- a/arch/um/include/shared/os.h +++ b/arch/um/include/shared/os.h @@ -163,8 +163,10 @@ extern int os_set_fd_block(int fd, int blocking); extern int os_accept_connection(int fd); extern int os_create_unix_socket(const char *file, int len, int close_on_exec); extern int os_shutdown_socket(int fd, int r, int w); +extern int os_dup_file(int fd); extern void os_close_file(int fd); -extern int os_rcv_fd(int fd, int *helper_pid_out); +ssize_t os_rcv_fd_msg(int fd, int *fds, unsigned int n_fds, + void *data, size_t data_len); extern int os_connect_socket(const char *name); extern int os_file_type(char *file); extern int os_file_mode(const char *file, struct openflags *mode_out); @@ -179,6 +181,8 @@ extern int os_eventfd(unsigned int initval, int flags); extern int os_sendmsg_fds(int fd, const void *buf, unsigned int len, const int *fds, unsigned int fds_num); int os_poll(unsigned int n, const int *fds); +void *os_mmap_rw_shared(int fd, size_t size); +void *os_mremap_rw_shared(void *old_addr, size_t old_size, size_t new_size); /* start_up.c */ extern void os_early_checks(void); @@ -191,6 +195,9 @@ extern void get_host_cpu_features( /* mem.c */ extern int create_mem_file(unsigned long long len); +/* tlb.c */ +extern void report_enomem(void); + /* process.c */ extern unsigned long os_process_pc(int pid); extern int os_process_parent(int pid); @@ -268,24 +275,20 @@ extern long long os_persistent_clock_emulation(void); extern long long os_nsecs(void); /* skas/mem.c */ -extern long run_syscall_stub(struct mm_id * mm_idp, - int syscall, unsigned long *args, long expected, - void **addr, int done); -extern long syscall_stub_data(struct mm_id * mm_idp, - unsigned long *data, int data_count, - void **addr, void **stub_addr); -extern int map(struct mm_id * mm_idp, unsigned long virt, - unsigned long len, int prot, int phys_fd, - unsigned long long offset, int done, void **data); -extern int unmap(struct mm_id * mm_idp, unsigned long addr, unsigned long len, - int done, void **data); -extern int protect(struct mm_id * mm_idp, unsigned long addr, - unsigned long len, unsigned int prot, int done, void **data); +int syscall_stub_flush(struct mm_id *mm_idp); +struct stub_syscall *syscall_stub_alloc(struct mm_id *mm_idp); +void syscall_stub_dump_error(struct mm_id *mm_idp); + +int map(struct mm_id *mm_idp, unsigned long virt, + unsigned long len, int prot, int phys_fd, + unsigned long long offset); +int unmap(struct mm_id *mm_idp, unsigned long addr, unsigned long len); +int protect(struct mm_id *mm_idp, unsigned long addr, + unsigned long len, unsigned int prot); /* skas/process.c */ extern int is_skas_winch(int pid, int fd, void *data); extern int start_userspace(unsigned long stub_stack); -extern int copy_context_skas0(unsigned long stack, int pid); extern void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs); extern void new_thread(void *stack, jmp_buf *buf, void (*handler)(void)); extern void switch_threads(jmp_buf *me, jmp_buf *you); diff --git a/arch/um/include/shared/skas/mm_id.h b/arch/um/include/shared/skas/mm_id.h index 92dbf727e384..1e76ba40feba 100644 --- a/arch/um/include/shared/skas/mm_id.h +++ b/arch/um/include/shared/skas/mm_id.h @@ -12,7 +12,7 @@ struct mm_id { int pid; } u; unsigned long stack; - int kill; + int syscall_data_len; }; void __switch_mm(struct mm_id *mm_idp); diff --git a/arch/um/include/shared/skas/skas.h b/arch/um/include/shared/skas/skas.h index c93d2cbc8f32..ebaa116de30b 100644 --- a/arch/um/include/shared/skas/skas.h +++ b/arch/um/include/shared/skas/skas.h @@ -15,5 +15,7 @@ extern void new_thread_handler(void); extern void handle_syscall(struct uml_pt_regs *regs); extern long execute_syscall_skas(void *r); extern unsigned long current_stub_stack(void); +extern struct mm_id *current_mm_id(void); +extern void current_mm_sync(void); #endif diff --git a/arch/um/include/shared/skas/stub-data.h b/arch/um/include/shared/skas/stub-data.h index 5e3ade3fb38b..2b6b44759dfa 100644 --- a/arch/um/include/shared/skas/stub-data.h +++ b/arch/um/include/shared/skas/stub-data.h @@ -8,10 +8,42 @@ #ifndef __STUB_DATA_H #define __STUB_DATA_H +#include <linux/compiler_types.h> +#include <as-layout.h> +#include <sysdep/tls.h> + +#define STUB_NEXT_SYSCALL(s) \ + ((struct stub_syscall *) (((unsigned long) s) + (s)->cmd_len)) + +enum stub_syscall_type { + STUB_SYSCALL_UNSET = 0, + STUB_SYSCALL_MMAP, + STUB_SYSCALL_MUNMAP, + STUB_SYSCALL_MPROTECT, +}; + +struct stub_syscall { + struct { + unsigned long addr; + unsigned long length; + unsigned long offset; + int fd; + int prot; + } mem; + + enum stub_syscall_type syscall; +}; + struct stub_data { unsigned long offset; - int fd; - long parent_err, child_err; + long err, child_err; + + int syscall_data_len; + /* 128 leaves enough room for additional fields in the struct */ + struct stub_syscall syscall_data[(UM_KERN_PAGE_SIZE - 128) / sizeof(struct stub_syscall)] __aligned(16); + + /* Stack for our signal handlers and for calling into . */ + unsigned char sigstack[UM_KERN_PAGE_SIZE] __aligned(UM_KERN_PAGE_SIZE); }; #endif diff --git a/arch/um/include/shared/timetravel.h b/arch/um/include/shared/timetravel.h index e5c3d69f1b69..c8db2f213dba 100644 --- a/arch/um/include/shared/timetravel.h +++ b/arch/um/include/shared/timetravel.h @@ -15,8 +15,17 @@ enum time_travel_mode { #if defined(UML_CONFIG_UML_TIME_TRAVEL_SUPPORT) || \ defined(CONFIG_UML_TIME_TRAVEL_SUPPORT) extern enum time_travel_mode time_travel_mode; +extern int time_travel_should_print_bc_msg; #else #define time_travel_mode TT_MODE_OFF +#define time_travel_should_print_bc_msg 0 #endif /* (UML_)CONFIG_UML_TIME_TRAVEL_SUPPORT */ +void _time_travel_print_bc_msg(void); +static inline void time_travel_print_bc_msg(void) +{ + if (time_travel_should_print_bc_msg) + _time_travel_print_bc_msg(); +} + #endif /* _UM_TIME_TRAVEL_H_ */ diff --git a/arch/um/include/shared/user.h b/arch/um/include/shared/user.h index 326e52450e41..bbab79c0c074 100644 --- a/arch/um/include/shared/user.h +++ b/arch/um/include/shared/user.h @@ -42,11 +42,19 @@ extern void panic(const char *fmt, ...) #define printk(...) _printk(__VA_ARGS__) extern int _printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 2))); +extern void print_hex_dump(const char *level, const char *prefix_str, + int prefix_type, int rowsize, int groupsize, + const void *buf, size_t len, _Bool ascii); #else static inline int printk(const char *fmt, ...) { return 0; } +static inline void print_hex_dump(const char *level, const char *prefix_str, + int prefix_type, int rowsize, int groupsize, + const void *buf, size_t len, _Bool ascii) +{ +} #endif extern int in_aton(char *str); diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c index 827a0d3fa589..2c15bb2c104c 100644 --- a/arch/um/kernel/exec.c +++ b/arch/um/kernel/exec.c @@ -22,17 +22,8 @@ void flush_thread(void) { - void *data = NULL; - int ret; - arch_flush_thread(¤t->thread.arch); - ret = unmap(¤t->mm->context.id, 0, TASK_SIZE, 1, &data); - if (ret) { - printk(KERN_ERR "%s - clearing address space failed, err = %d\n", - __func__, ret); - force_sig(SIGKILL); - } get_safe_registers(current_pt_regs()->regs.gp, current_pt_regs()->regs.fp); diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c index 635d44606bfe..534e91797f89 100644 --- a/arch/um/kernel/irq.c +++ b/arch/um/kernel/irq.c @@ -37,7 +37,7 @@ struct irq_reg { bool pending; bool wakeup; #ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT - bool pending_on_resume; + bool pending_event; void (*timetravel_handler)(int, int, void *, struct time_travel_event *); struct time_travel_event event; @@ -56,6 +56,9 @@ static DEFINE_SPINLOCK(irq_lock); static LIST_HEAD(active_fds); static DECLARE_BITMAP(irqs_allocated, UM_LAST_SIGNAL_IRQ); static bool irqs_suspended; +#ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT +static bool irqs_pending; +#endif static void irq_io_loop(struct irq_reg *irq, struct uml_pt_regs *regs) { @@ -84,9 +87,12 @@ static void irq_event_handler(struct time_travel_event *ev) { struct irq_reg *reg = container_of(ev, struct irq_reg, event); - /* do nothing if suspended - just to cause a wakeup */ - if (irqs_suspended) + /* do nothing if suspended; just cause a wakeup and mark as pending */ + if (irqs_suspended) { + irqs_pending = true; + reg->pending_event = true; return; + } generic_handle_irq(reg->irq); } @@ -110,16 +116,47 @@ static bool irq_do_timetravel_handler(struct irq_entry *entry, if (!reg->event.pending) return false; - if (irqs_suspended) - reg->pending_on_resume = true; return true; } + +static void irq_do_pending_events(bool timetravel_handlers_only) +{ + struct irq_entry *entry; + + if (!irqs_pending || timetravel_handlers_only) + return; + + irqs_pending = false; + + list_for_each_entry(entry, &active_fds, list) { + enum um_irq_type t; + + for (t = 0; t < NUM_IRQ_TYPES; t++) { + struct irq_reg *reg = &entry->reg[t]; + + /* + * Any timetravel_handler was invoked already, just + * directly run the IRQ. + */ + if (reg->pending_event) { + irq_enter(); + generic_handle_irq(reg->irq); + irq_exit(); + reg->pending_event = false; + } + } + } +} #else static bool irq_do_timetravel_handler(struct irq_entry *entry, enum um_irq_type t) { return false; } + +static void irq_do_pending_events(bool timetravel_handlers_only) +{ +} #endif static void sigio_reg_handler(int idx, struct irq_entry *entry, enum um_irq_type t, @@ -145,6 +182,8 @@ static void sigio_reg_handler(int idx, struct irq_entry *entry, enum um_irq_type */ if (timetravel_handlers_only) { #ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT + reg->pending_event = true; + irqs_pending = true; mark_sigio_pending(); #endif return; @@ -162,6 +201,10 @@ static void _sigio_handler(struct uml_pt_regs *regs, if (timetravel_handlers_only && !um_irq_timetravel_handler_used()) return; + /* Flush out pending events that were ignored due to time-travel. */ + if (!irqs_suspended) + irq_do_pending_events(timetravel_handlers_only); + while (1) { /* This is now lockless - epoll keeps back-referencesto the irqs * which have trigger it so there is no need to walk the irq @@ -195,7 +238,9 @@ static void _sigio_handler(struct uml_pt_regs *regs, void sigio_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs) { + preempt_disable(); _sigio_handler(regs, irqs_suspended); + preempt_enable(); } static struct irq_entry *get_irq_entry_by_fd(int fd) @@ -543,30 +588,7 @@ void um_irqs_resume(void) unsigned long flags; - local_irq_save(flags); -#ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT - /* - * We don't need to lock anything here since we're in resume - * and nothing else is running, but have disabled IRQs so we - * don't try anything else with the interrupt list from there. - */ - list_for_each_entry(entry, &active_fds, list) { - enum um_irq_type t; - - for (t = 0; t < NUM_IRQ_TYPES; t++) { - struct irq_reg *reg = &entry->reg[t]; - - if (reg->pending_on_resume) { - irq_enter(); - generic_handle_irq(reg->irq); - irq_exit(); - reg->pending_on_resume = false; - } - } - } -#endif - - spin_lock(&irq_lock); + spin_lock_irqsave(&irq_lock, flags); list_for_each_entry(entry, &active_fds, list) { if (entry->suspended) { int err = os_set_fd_async(entry->fd); diff --git a/arch/um/kernel/ksyms.c b/arch/um/kernel/ksyms.c index 3a85bde3e173..f2fb77da08cf 100644 --- a/arch/um/kernel/ksyms.c +++ b/arch/um/kernel/ksyms.c @@ -33,7 +33,7 @@ EXPORT_SYMBOL(os_shutdown_socket); EXPORT_SYMBOL(os_create_unix_socket); EXPORT_SYMBOL(os_connect_socket); EXPORT_SYMBOL(os_accept_connection); -EXPORT_SYMBOL(os_rcv_fd); +EXPORT_SYMBOL(os_rcv_fd_msg); EXPORT_SYMBOL(run_helper); EXPORT_SYMBOL(os_major); EXPORT_SYMBOL(os_minor); diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index ca91accd64fc..a5b4fe2ad931 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -73,7 +73,6 @@ void __init mem_init(void) /* this will put all low memory onto the freelists */ memblock_free_all(); - max_low_pfn = totalram_pages(); max_pfn = max_low_pfn; kmalloc_ok = 1; } diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index d2134802f6a8..f36b63f53bab 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -122,8 +122,6 @@ void new_thread_handler(void) /* Called magically, see new_thread_handler above */ static void fork_handler(void) { - force_flush_all(); - schedule_tail(current->thread.prev_sched); /* @@ -237,73 +235,6 @@ int copy_from_user_proc(void *to, void __user *from, int size) return copy_from_user(to, from, size); } -static atomic_t using_sysemu = ATOMIC_INIT(0); -int sysemu_supported; - -static void set_using_sysemu(int value) -{ - if (value > sysemu_supported) - return; - atomic_set(&using_sysemu, value); -} - -static int get_using_sysemu(void) -{ - return atomic_read(&using_sysemu); -} - -static int sysemu_proc_show(struct seq_file *m, void *v) -{ - seq_printf(m, "%d\n", get_using_sysemu()); - return 0; -} - -static int sysemu_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, sysemu_proc_show, NULL); -} - -static ssize_t sysemu_proc_write(struct file *file, const char __user *buf, - size_t count, loff_t *pos) -{ - char tmp[2]; - - if (copy_from_user(tmp, buf, 1)) - return -EFAULT; - - if (tmp[0] >= '0' && tmp[0] <= '2') - set_using_sysemu(tmp[0] - '0'); - /* We use the first char, but pretend to write everything */ - return count; -} - -static const struct proc_ops sysemu_proc_ops = { - .proc_open = sysemu_proc_open, - .proc_read = seq_read, - .proc_lseek = seq_lseek, - .proc_release = single_release, - .proc_write = sysemu_proc_write, -}; - -static int __init make_proc_sysemu(void) -{ - struct proc_dir_entry *ent; - if (!sysemu_supported) - return 0; - - ent = proc_create("sysemu", 0600, NULL, &sysemu_proc_ops); - - if (ent == NULL) - { - printk(KERN_WARNING "Failed to register /proc/sysemu\n"); - return 0; - } - - return 0; -} - -late_initcall(make_proc_sysemu); - int singlestepping(void) { return test_thread_flag(TIF_SINGLESTEP); diff --git a/arch/um/kernel/reboot.c b/arch/um/kernel/reboot.c index 25840eee1068..3736bca626ba 100644 --- a/arch/um/kernel/reboot.c +++ b/arch/um/kernel/reboot.c @@ -59,3 +59,18 @@ void machine_halt(void) { machine_power_off(); } + +static int sys_power_off_handler(struct sys_off_data *data) +{ + machine_power_off(); + return 0; +} + +static int register_power_off(void) +{ + register_sys_off_handler(SYS_OFF_MODE_POWER_OFF, + SYS_OFF_PRIO_DEFAULT, + sys_power_off_handler, NULL); + return 0; +} +__initcall(register_power_off); diff --git a/arch/um/kernel/skas/Makefile b/arch/um/kernel/skas/Makefile index f93972a25765..6f86d53e3d69 100644 --- a/arch/um/kernel/skas/Makefile +++ b/arch/um/kernel/skas/Makefile @@ -3,15 +3,14 @@ # Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) # -obj-y := clone.o mmu.o process.o syscall.o uaccess.o +obj-y := stub.o mmu.o process.o syscall.o uaccess.o -# clone.o is in the stub, so it can't be built with profiling +# stub.o is in the stub, so it can't be built with profiling # GCC hardened also auto-enables -fpic, but we need %ebx so it can't work -> # disable it -CFLAGS_clone.o := $(CFLAGS_NO_HARDENING) -UNPROFILE_OBJS := clone.o - +CFLAGS_stub.o := $(CFLAGS_NO_HARDENING) +UNPROFILE_OBJS := stub.o KCOV_INSTRUMENT := n include $(srctree)/arch/um/scripts/Makefile.rules diff --git a/arch/um/kernel/skas/clone.c b/arch/um/kernel/skas/clone.c deleted file mode 100644 index 62435187dda4..000000000000 --- a/arch/um/kernel/skas/clone.c +++ /dev/null @@ -1,48 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2015 Thomas Meyer (thomas@m3y3r.de) - * Copyright (C) 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) - */ - -#include <signal.h> -#include <sched.h> -#include <asm/unistd.h> -#include <sys/time.h> -#include <as-layout.h> -#include <ptrace_user.h> -#include <stub-data.h> -#include <sysdep/stub.h> - -/* - * This is in a separate file because it needs to be compiled with any - * extraneous gcc flags (-pg, -fprofile-arcs, -ftest-coverage) disabled - * - * Use UM_KERN_PAGE_SIZE instead of PAGE_SIZE because that calls getpagesize - * on some systems. - */ - -void __attribute__ ((__section__ (".__syscall_stub"))) -stub_clone_handler(void) -{ - struct stub_data *data = get_stub_data(); - long err; - - err = stub_syscall2(__NR_clone, CLONE_PARENT | CLONE_FILES | SIGCHLD, - (unsigned long)data + - STUB_DATA_PAGES * UM_KERN_PAGE_SIZE / 2); - if (err) { - data->parent_err = err; - goto done; - } - - err = stub_syscall4(__NR_ptrace, PTRACE_TRACEME, 0, 0, 0); - if (err) { - data->child_err = err; - goto done; - } - - remap_stack_and_trap(); - - done: - trap_myself(); -} diff --git a/arch/um/kernel/skas/mmu.c b/arch/um/kernel/skas/mmu.c index aeed1c2aaf3c..47f98d87ea3c 100644 --- a/arch/um/kernel/skas/mmu.c +++ b/arch/um/kernel/skas/mmu.c @@ -14,11 +14,14 @@ #include <as-layout.h> #include <os.h> #include <skas.h> +#include <stub-data.h> + +/* Ensure the stub_data struct covers the allocated area */ +static_assert(sizeof(struct stub_data) == STUB_DATA_PAGES * UM_KERN_PAGE_SIZE); int init_new_context(struct task_struct *task, struct mm_struct *mm) { - struct mm_context *from_mm = NULL; - struct mm_context *to_mm = &mm->context; + struct mm_id *new_id = &mm->context.id; unsigned long stack = 0; int ret = -ENOMEM; @@ -26,34 +29,46 @@ int init_new_context(struct task_struct *task, struct mm_struct *mm) if (stack == 0) goto out; - to_mm->id.stack = stack; - if (current->mm != NULL && current->mm != &init_mm) - from_mm = ¤t->mm->context; + new_id->stack = stack; block_signals_trace(); - if (from_mm) - to_mm->id.u.pid = copy_context_skas0(stack, - from_mm->id.u.pid); - else to_mm->id.u.pid = start_userspace(stack); + new_id->u.pid = start_userspace(stack); unblock_signals_trace(); - if (to_mm->id.u.pid < 0) { - ret = to_mm->id.u.pid; + if (new_id->u.pid < 0) { + ret = new_id->u.pid; goto out_free; } - ret = init_new_ldt(to_mm, from_mm); - if (ret < 0) { - printk(KERN_ERR "init_new_context_skas - init_ldt" - " failed, errno = %d\n", ret); - goto out_free; - } + /* + * Ensure the new MM is clean and nothing unwanted is mapped. + * + * TODO: We should clear the memory up to STUB_START to ensure there is + * nothing mapped there, i.e. we (currently) have: + * + * |- user memory -|- unused -|- stub -|- unused -| + * ^ TASK_SIZE ^ STUB_START + * + * Meaning we have two unused areas where we may still have valid + * mappings from our internal clone(). That isn't really a problem as + * userspace is not going to access them, but it is definitely not + * correct. + * + * However, we are "lucky" and if rseq is configured, then on 32 bit + * it will fall into the first empty range while on 64 bit it is going + * to use an anonymous mapping in the second range. As such, things + * continue to work for now as long as we don't start unmapping these + * areas. + * + * Change this to STUB_START once we have a clean userspace. + */ + unmap(new_id, 0, TASK_SIZE); return 0; out_free: - if (to_mm->id.stack != 0) - free_pages(to_mm->id.stack, ilog2(STUB_DATA_PAGES)); + if (new_id->stack != 0) + free_pages(new_id->stack, ilog2(STUB_DATA_PAGES)); out: return ret; } @@ -76,5 +91,4 @@ void destroy_context(struct mm_struct *mm) os_kill_ptraced_process(mmu->id.u.pid, 1); free_pages(mmu->id.stack, ilog2(STUB_DATA_PAGES)); - free_ldt(mmu); } diff --git a/arch/um/kernel/skas/process.c b/arch/um/kernel/skas/process.c index 99a5cbb36083..5f9c1c5f36e2 100644 --- a/arch/um/kernel/skas/process.c +++ b/arch/um/kernel/skas/process.c @@ -8,6 +8,8 @@ #include <linux/sched/task_stack.h> #include <linux/sched/task.h> +#include <asm/tlbflush.h> + #include <as-layout.h> #include <kern.h> #include <os.h> @@ -50,3 +52,19 @@ unsigned long current_stub_stack(void) return current->mm->context.id.stack; } + +struct mm_id *current_mm_id(void) +{ + if (current->mm == NULL) + return NULL; + + return ¤t->mm->context.id; +} + +void current_mm_sync(void) +{ + if (current->mm == NULL) + return; + + um_tlb_sync(current->mm); +} diff --git a/arch/um/kernel/skas/stub.c b/arch/um/kernel/skas/stub.c new file mode 100644 index 000000000000..5d52ffa682dc --- /dev/null +++ b/arch/um/kernel/skas/stub.c @@ -0,0 +1,69 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 Benjamin Berg <benjamin@sipsolutions.net> + */ + +#include <sysdep/stub.h> + +static __always_inline int syscall_handler(struct stub_data *d) +{ + int i; + unsigned long res; + + for (i = 0; i < d->syscall_data_len; i++) { + struct stub_syscall *sc = &d->syscall_data[i]; + + switch (sc->syscall) { + case STUB_SYSCALL_MMAP: + res = stub_syscall6(STUB_MMAP_NR, + sc->mem.addr, sc->mem.length, + sc->mem.prot, + MAP_SHARED | MAP_FIXED, + sc->mem.fd, sc->mem.offset); + if (res != sc->mem.addr) { + d->err = res; + d->syscall_data_len = i; + return -1; + } + break; + case STUB_SYSCALL_MUNMAP: + res = stub_syscall2(__NR_munmap, + sc->mem.addr, sc->mem.length); + if (res) { + d->err = res; + d->syscall_data_len = i; + return -1; + } + break; + case STUB_SYSCALL_MPROTECT: + res = stub_syscall3(__NR_mprotect, + sc->mem.addr, sc->mem.length, + sc->mem.prot); + if (res) { + d->err = res; + d->syscall_data_len = i; + return -1; + } + break; + default: + d->err = -95; /* EOPNOTSUPP */ + d->syscall_data_len = i; + return -1; + } + } + + d->err = 0; + d->syscall_data_len = 0; + + return 0; +} + +void __section(".__syscall_stub") +stub_syscall_handler(void) +{ + struct stub_data *d = get_stub_data(); + + syscall_handler(d); + + trap_myself(); +} diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c index a8bfe8be1526..47b9f5e63566 100644 --- a/arch/um/kernel/time.c +++ b/arch/um/kernel/time.c @@ -31,6 +31,7 @@ EXPORT_SYMBOL_GPL(time_travel_mode); static bool time_travel_start_set; static unsigned long long time_travel_start; static unsigned long long time_travel_time; +static unsigned long long time_travel_shm_offset; static LIST_HEAD(time_travel_events); static LIST_HEAD(time_travel_irqs); static unsigned long long time_travel_timer_interval; @@ -40,8 +41,11 @@ static int time_travel_ext_fd = -1; static unsigned int time_travel_ext_waiting; static bool time_travel_ext_prev_request_valid; static unsigned long long time_travel_ext_prev_request; -static bool time_travel_ext_free_until_valid; -static unsigned long long time_travel_ext_free_until; +static unsigned long long *time_travel_ext_free_until; +static unsigned long long _time_travel_ext_free_until; +static u16 time_travel_shm_id; +static struct um_timetravel_schedshm *time_travel_shm; +static union um_timetravel_schedshm_client *time_travel_shm_client; static void time_travel_set_time(unsigned long long ns) { @@ -58,8 +62,52 @@ enum time_travel_message_handling { TTMH_IDLE, TTMH_POLL, TTMH_READ, + TTMH_READ_START_ACK, }; +static u64 bc_message; +int time_travel_should_print_bc_msg; + +void _time_travel_print_bc_msg(void) +{ + time_travel_should_print_bc_msg = 0; + printk(KERN_INFO "time-travel: received broadcast 0x%llx\n", bc_message); +} + +static void time_travel_setup_shm(int fd, u16 id) +{ + u32 len; + + time_travel_shm = os_mmap_rw_shared(fd, sizeof(*time_travel_shm)); + + if (!time_travel_shm) + goto out; + + len = time_travel_shm->len; + + if (time_travel_shm->version != UM_TIMETRAVEL_SCHEDSHM_VERSION || + len < struct_size(time_travel_shm, clients, id + 1)) { + os_unmap_memory(time_travel_shm, sizeof(*time_travel_shm)); + time_travel_shm = NULL; + goto out; + } + + time_travel_shm = os_mremap_rw_shared(time_travel_shm, + sizeof(*time_travel_shm), + len); + if (!time_travel_shm) + goto out; + + time_travel_shm_offset = time_travel_shm->current_time; + time_travel_shm_client = &time_travel_shm->clients[id]; + time_travel_shm_client->capa |= UM_TIMETRAVEL_SCHEDSHM_CAP_TIME_SHARE; + time_travel_shm_id = id; + /* always look at that free_until from now on */ + time_travel_ext_free_until = &time_travel_shm->free_until; +out: + os_close_file(fd); +} + static void time_travel_handle_message(struct um_timetravel_msg *msg, enum time_travel_message_handling mode) { @@ -80,7 +128,20 @@ static void time_travel_handle_message(struct um_timetravel_msg *msg, } } - ret = os_read_file(time_travel_ext_fd, msg, sizeof(*msg)); + if (unlikely(mode == TTMH_READ_START_ACK)) { + int fd[UM_TIMETRAVEL_SHARED_MAX_FDS]; + + ret = os_rcv_fd_msg(time_travel_ext_fd, fd, + ARRAY_SIZE(fd), msg, sizeof(*msg)); + if (ret == sizeof(*msg)) { + time_travel_setup_shm(fd[UM_TIMETRAVEL_SHARED_MEMFD], + msg->time & UM_TIMETRAVEL_START_ACK_ID); + /* we don't use the logging for now */ + os_close_file(fd[UM_TIMETRAVEL_SHARED_LOGFD]); + } + } else { + ret = os_read_file(time_travel_ext_fd, msg, sizeof(*msg)); + } if (ret == 0) panic("time-travel external link is broken\n"); @@ -96,10 +157,24 @@ static void time_travel_handle_message(struct um_timetravel_msg *msg, return; case UM_TIMETRAVEL_RUN: time_travel_set_time(msg->time); + if (time_travel_shm) { + /* no request right now since we're running */ + time_travel_shm_client->flags &= + ~UM_TIMETRAVEL_SCHEDSHM_FLAGS_REQ_RUN; + /* no ack for shared memory RUN */ + return; + } break; case UM_TIMETRAVEL_FREE_UNTIL: - time_travel_ext_free_until_valid = true; - time_travel_ext_free_until = msg->time; + /* not supposed to get this with shm, but ignore it */ + if (time_travel_shm) + break; + time_travel_ext_free_until = &_time_travel_ext_free_until; + _time_travel_ext_free_until = msg->time; + break; + case UM_TIMETRAVEL_BROADCAST: + bc_message = msg->time; + time_travel_should_print_bc_msg = 1; break; } @@ -136,8 +211,15 @@ static u64 time_travel_ext_req(u32 op, u64 time) block_signals_hard(); os_write_file(time_travel_ext_fd, &msg, sizeof(msg)); + /* no ACK expected for WAIT in shared memory mode */ + if (msg.op == UM_TIMETRAVEL_WAIT && time_travel_shm) + goto done; + while (msg.op != UM_TIMETRAVEL_ACK) - time_travel_handle_message(&msg, TTMH_READ); + time_travel_handle_message(&msg, + op == UM_TIMETRAVEL_START ? + TTMH_READ_START_ACK : + TTMH_READ); if (msg.seq != mseq) panic("time-travel: ACK message has different seqno! op=%d, seq=%d != %d time=%lld\n", @@ -145,6 +227,7 @@ static u64 time_travel_ext_req(u32 op, u64 time) if (op == UM_TIMETRAVEL_GET) time_travel_set_time(msg.time); +done: unblock_signals_hard(); return msg.time; @@ -180,13 +263,33 @@ static void time_travel_ext_update_request(unsigned long long time) /* * if we're running and are allowed to run past the request * then we don't need to update it either + * + * Note for shm we ignore FREE_UNTIL messages and leave the pointer + * to shared memory, and for non-shm the offset is 0. */ - if (!time_travel_ext_waiting && time_travel_ext_free_until_valid && - time < time_travel_ext_free_until) + if (!time_travel_ext_waiting && time_travel_ext_free_until && + time < (*time_travel_ext_free_until - time_travel_shm_offset)) return; time_travel_ext_prev_request = time; time_travel_ext_prev_request_valid = true; + + if (time_travel_shm) { + union um_timetravel_schedshm_client *running; + + running = &time_travel_shm->clients[time_travel_shm->running_id]; + + if (running->capa & UM_TIMETRAVEL_SCHEDSHM_CAP_TIME_SHARE) { + time_travel_shm_client->flags |= + UM_TIMETRAVEL_SCHEDSHM_FLAGS_REQ_RUN; + time += time_travel_shm_offset; + time_travel_shm_client->req_time = time; + if (time < time_travel_shm->free_until) + time_travel_shm->free_until = time; + return; + } + } + time_travel_ext_req(UM_TIMETRAVEL_REQUEST, time); } @@ -194,6 +297,14 @@ void __time_travel_propagate_time(void) { static unsigned long long last_propagated; + if (time_travel_shm) { + if (time_travel_shm->running_id != time_travel_shm_id) + panic("time-travel: setting time while not running\n"); + time_travel_shm->current_time = time_travel_time + + time_travel_shm_offset; + return; + } + if (last_propagated == time_travel_time) return; @@ -209,9 +320,12 @@ static bool time_travel_ext_request(unsigned long long time) * If we received an external sync point ("free until") then we * don't have to request/wait for anything until then, unless * we're already waiting. + * + * Note for shm we ignore FREE_UNTIL messages and leave the pointer + * to shared memory, and for non-shm the offset is 0. */ - if (!time_travel_ext_waiting && time_travel_ext_free_until_valid && - time < time_travel_ext_free_until) + if (!time_travel_ext_waiting && time_travel_ext_free_until && + time < (*time_travel_ext_free_until - time_travel_shm_offset)) return false; time_travel_ext_update_request(time); @@ -225,7 +339,8 @@ static void time_travel_ext_wait(bool idle) }; time_travel_ext_prev_request_valid = false; - time_travel_ext_free_until_valid = false; + if (!time_travel_shm) + time_travel_ext_free_until = NULL; time_travel_ext_waiting++; time_travel_ext_req(UM_TIMETRAVEL_WAIT, -1); @@ -248,7 +363,11 @@ static void time_travel_ext_wait(bool idle) static void time_travel_ext_get_time(void) { - time_travel_ext_req(UM_TIMETRAVEL_GET, -1); + if (time_travel_shm) + time_travel_set_time(time_travel_shm->current_time - + time_travel_shm_offset); + else + time_travel_ext_req(UM_TIMETRAVEL_GET, -1); } static void __time_travel_update_time(unsigned long long ns, bool idle) @@ -875,9 +994,49 @@ static int setup_time_travel_start(char *str) return 1; } -__setup("time-travel-start", setup_time_travel_start); +__setup("time-travel-start=", setup_time_travel_start); __uml_help(setup_time_travel_start, -"time-travel-start=<seconds>\n" +"time-travel-start=<nanoseconds>\n" "Configure the UML instance's wall clock to start at this value rather than\n" "the host's wall clock at the time of UML boot.\n"); +static struct kobject *bc_time_kobject; + +static ssize_t bc_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "0x%llx", bc_message); +} + +static ssize_t bc_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) +{ + int ret; + u64 user_bc_message; + + ret = kstrtou64(buf, 0, &user_bc_message); + if (ret) + return ret; + + bc_message = user_bc_message; + + time_travel_ext_req(UM_TIMETRAVEL_BROADCAST, bc_message); + pr_info("um: time: sent broadcast message: 0x%llx\n", bc_message); + return count; +} + +static struct kobj_attribute bc_attribute = __ATTR(bc-message, 0660, bc_show, bc_store); + +static int __init um_bc_start(void) +{ + if (time_travel_mode != TT_MODE_EXTERNAL) + return 0; + + bc_time_kobject = kobject_create_and_add("um-ext-time", kernel_kobj); + if (!bc_time_kobject) + return 0; + + if (sysfs_create_file(bc_time_kobject, &bc_attribute.attr)) + pr_debug("failed to create the bc file in /sys/kernel/um_time"); + + return 0; +} +late_initcall(um_bc_start); #endif diff --git a/arch/um/kernel/tlb.c b/arch/um/kernel/tlb.c index 8784f03fa4a6..44c6fc697f3a 100644 --- a/arch/um/kernel/tlb.c +++ b/arch/um/kernel/tlb.c @@ -15,209 +15,54 @@ #include <skas.h> #include <kern_util.h> -struct host_vm_change { - struct host_vm_op { - enum { NONE, MMAP, MUNMAP, MPROTECT } type; - union { - struct { - unsigned long addr; - unsigned long len; - unsigned int prot; - int fd; - __u64 offset; - } mmap; - struct { - unsigned long addr; - unsigned long len; - } munmap; - struct { - unsigned long addr; - unsigned long len; - unsigned int prot; - } mprotect; - } u; - } ops[1]; - int userspace; - int index; - struct mm_struct *mm; - void *data; - int force; +struct vm_ops { + struct mm_id *mm_idp; + + int (*mmap)(struct mm_id *mm_idp, + unsigned long virt, unsigned long len, int prot, + int phys_fd, unsigned long long offset); + int (*unmap)(struct mm_id *mm_idp, + unsigned long virt, unsigned long len); + int (*mprotect)(struct mm_id *mm_idp, + unsigned long virt, unsigned long len, + unsigned int prot); }; -#define INIT_HVC(mm, force, userspace) \ - ((struct host_vm_change) \ - { .ops = { { .type = NONE } }, \ - .mm = mm, \ - .data = NULL, \ - .userspace = userspace, \ - .index = 0, \ - .force = force }) - -static void report_enomem(void) +static int kern_map(struct mm_id *mm_idp, + unsigned long virt, unsigned long len, int prot, + int phys_fd, unsigned long long offset) { - printk(KERN_ERR "UML ran out of memory on the host side! " - "This can happen due to a memory limitation or " - "vm.max_map_count has been reached.\n"); -} - -static int do_ops(struct host_vm_change *hvc, int end, - int finished) -{ - struct host_vm_op *op; - int i, ret = 0; - - for (i = 0; i < end && !ret; i++) { - op = &hvc->ops[i]; - switch (op->type) { - case MMAP: - 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: - 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: - 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", - op->type); - BUG(); - break; - } - } - - if (ret == -ENOMEM) - report_enomem(); - - return ret; + /* TODO: Why is executable needed to be always set in the kernel? */ + return os_map_memory((void *)virt, phys_fd, offset, len, + prot & UM_PROT_READ, prot & UM_PROT_WRITE, + 1); } -static int add_mmap(unsigned long virt, unsigned long phys, unsigned long len, - unsigned int prot, struct host_vm_change *hvc) +static int kern_unmap(struct mm_id *mm_idp, + unsigned long virt, unsigned long len) { - __u64 offset; - struct host_vm_op *last; - int fd = -1, ret = 0; - - 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) && - (last->u.mmap.addr + last->u.mmap.len == virt) && - (last->u.mmap.prot == prot) && (last->u.mmap.fd == fd) && - (last->u.mmap.offset + last->u.mmap.len == offset)) { - last->u.mmap.len += len; - return 0; - } - } - - if (hvc->index == ARRAY_SIZE(hvc->ops)) { - ret = do_ops(hvc, ARRAY_SIZE(hvc->ops), 0); - hvc->index = 0; - } - - hvc->ops[hvc->index++] = ((struct host_vm_op) - { .type = MMAP, - .u = { .mmap = { .addr = virt, - .len = len, - .prot = prot, - .fd = fd, - .offset = offset } - } }); - return ret; + return os_unmap_memory((void *)virt, len); } -static int add_munmap(unsigned long addr, unsigned long len, - struct host_vm_change *hvc) +static int kern_mprotect(struct mm_id *mm_idp, + unsigned long virt, unsigned long len, + unsigned int prot) { - struct host_vm_op *last; - int ret = 0; - - if (hvc->index != 0) { - last = &hvc->ops[hvc->index - 1]; - if ((last->type == MUNMAP) && - (last->u.munmap.addr + last->u.mmap.len == addr)) { - last->u.munmap.len += len; - return 0; - } - } - - if (hvc->index == ARRAY_SIZE(hvc->ops)) { - ret = do_ops(hvc, ARRAY_SIZE(hvc->ops), 0); - hvc->index = 0; - } - - hvc->ops[hvc->index++] = ((struct host_vm_op) - { .type = MUNMAP, - .u = { .munmap = { .addr = addr, - .len = len } } }); - return ret; + return os_protect_memory((void *)virt, len, + prot & UM_PROT_READ, prot & UM_PROT_WRITE, + 1); } -static int add_mprotect(unsigned long addr, unsigned long len, - unsigned int prot, struct host_vm_change *hvc) +void report_enomem(void) { - struct host_vm_op *last; - int ret = 0; - - if (hvc->index != 0) { - last = &hvc->ops[hvc->index - 1]; - if ((last->type == MPROTECT) && - (last->u.mprotect.addr + last->u.mprotect.len == addr) && - (last->u.mprotect.prot == prot)) { - last->u.mprotect.len += len; - return 0; - } - } - - if (hvc->index == ARRAY_SIZE(hvc->ops)) { - ret = do_ops(hvc, ARRAY_SIZE(hvc->ops), 0); - hvc->index = 0; - } - - hvc->ops[hvc->index++] = ((struct host_vm_op) - { .type = MPROTECT, - .u = { .mprotect = { .addr = addr, - .len = len, - .prot = prot } } }); - return ret; + printk(KERN_ERR "UML ran out of memory on the host side! " + "This can happen due to a memory limitation or " + "vm.max_map_count has been reached.\n"); } -#define ADD_ROUND(n, inc) (((n) + (inc)) & ~((inc) - 1)) - static inline int update_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, - struct host_vm_change *hvc) + struct vm_ops *ops) { pte_t *pte; int r, w, x, prot, ret = 0; @@ -235,15 +80,22 @@ 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_newpage(*pte)) { if (pte_present(*pte)) { - if (pte_newpage(*pte)) - ret = add_mmap(addr, pte_val(*pte) & PAGE_MASK, - PAGE_SIZE, prot, hvc); + if (pte_newpage(*pte)) { + __u64 offset; + unsigned long phys = + pte_val(*pte) & PAGE_MASK; + int fd = phys_mapping(phys, &offset); + + ret = ops->mmap(ops->mm_idp, addr, + PAGE_SIZE, prot, fd, + offset); + } } else - ret = add_munmap(addr, PAGE_SIZE, hvc); + ret = ops->unmap(ops->mm_idp, addr, PAGE_SIZE); } else if (pte_newprot(*pte)) - ret = add_mprotect(addr, PAGE_SIZE, prot, hvc); + ret = ops->mprotect(ops->mm_idp, addr, PAGE_SIZE, prot); *pte = pte_mkuptodate(*pte); } while (pte++, addr += PAGE_SIZE, ((addr < end) && !ret)); return ret; @@ -251,7 +103,7 @@ static inline int update_pte_range(pmd_t *pmd, unsigned long addr, static inline int update_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, - struct host_vm_change *hvc) + struct vm_ops *ops) { pmd_t *pmd; unsigned long next; @@ -261,19 +113,20 @@ static inline int update_pmd_range(pud_t *pud, unsigned long addr, do { next = pmd_addr_end(addr, end); if (!pmd_present(*pmd)) { - if (hvc->force || pmd_newpage(*pmd)) { - ret = add_munmap(addr, next - addr, hvc); + if (pmd_newpage(*pmd)) { + ret = ops->unmap(ops->mm_idp, addr, + next - addr); pmd_mkuptodate(*pmd); } } - else ret = update_pte_range(pmd, addr, next, hvc); + else ret = update_pte_range(pmd, addr, next, ops); } while (pmd++, addr = next, ((addr < end) && !ret)); return ret; } static inline int update_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, - struct host_vm_change *hvc) + struct vm_ops *ops) { pud_t *pud; unsigned long next; @@ -283,19 +136,20 @@ static inline int update_pud_range(p4d_t *p4d, unsigned long addr, do { next = pud_addr_end(addr, end); if (!pud_present(*pud)) { - if (hvc->force || pud_newpage(*pud)) { - ret = add_munmap(addr, next - addr, hvc); + if (pud_newpage(*pud)) { + ret = ops->unmap(ops->mm_idp, addr, + next - addr); pud_mkuptodate(*pud); } } - else ret = update_pmd_range(pud, addr, next, hvc); + else ret = update_pmd_range(pud, addr, next, ops); } while (pud++, addr = next, ((addr < end) && !ret)); return ret; } static inline int update_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, - struct host_vm_change *hvc) + struct vm_ops *ops) { p4d_t *p4d; unsigned long next; @@ -305,227 +159,59 @@ static inline int update_p4d_range(pgd_t *pgd, unsigned long addr, do { next = p4d_addr_end(addr, end); if (!p4d_present(*p4d)) { - if (hvc->force || p4d_newpage(*p4d)) { - ret = add_munmap(addr, next - addr, hvc); + if (p4d_newpage(*p4d)) { + ret = ops->unmap(ops->mm_idp, addr, + next - addr); p4d_mkuptodate(*p4d); } } else - ret = update_pud_range(p4d, addr, next, hvc); + ret = update_pud_range(p4d, addr, next, ops); } while (p4d++, addr = next, ((addr < end) && !ret)); return ret; } -static void fix_range_common(struct mm_struct *mm, unsigned long start_addr, - unsigned long end_addr, int force) +int um_tlb_sync(struct mm_struct *mm) { pgd_t *pgd; - struct host_vm_change hvc; - unsigned long addr = start_addr, next; - int ret = 0, userspace = 1; + struct vm_ops ops; + unsigned long addr = mm->context.sync_tlb_range_from, next; + int ret = 0; + + if (mm->context.sync_tlb_range_to == 0) + return 0; + + ops.mm_idp = &mm->context.id; + if (mm == &init_mm) { + ops.mmap = kern_map; + ops.unmap = kern_unmap; + ops.mprotect = kern_mprotect; + } else { + ops.mmap = map; + ops.unmap = unmap; + ops.mprotect = protect; + } - hvc = INIT_HVC(mm, force, userspace); pgd = pgd_offset(mm, addr); do { - next = pgd_addr_end(addr, end_addr); + next = pgd_addr_end(addr, mm->context.sync_tlb_range_to); if (!pgd_present(*pgd)) { - if (force || pgd_newpage(*pgd)) { - ret = add_munmap(addr, next - addr, &hvc); + if (pgd_newpage(*pgd)) { + ret = ops.unmap(ops.mm_idp, addr, + next - addr); pgd_mkuptodate(*pgd); } } else - ret = update_p4d_range(pgd, addr, next, &hvc); - } while (pgd++, addr = next, ((addr < end_addr) && !ret)); + ret = update_p4d_range(pgd, addr, next, &ops); + } while (pgd++, addr = next, + ((addr < mm->context.sync_tlb_range_to) && !ret)); - if (!ret) - ret = do_ops(&hvc, hvc.index, 1); - - /* This is not an else because ret is modified above */ - if (ret) { - struct mm_id *mm_idp = ¤t->mm->context.id; - - printk(KERN_ERR "fix_range_common: failed, killing current " - "process: %d\n", task_tgid_vnr(current)); - mm_idp->kill = 1; - } -} - -static int flush_tlb_kernel_range_common(unsigned long start, unsigned long end) -{ - struct mm_struct *mm; - pgd_t *pgd; - p4d_t *p4d; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - unsigned long addr, last; - 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)) { - last = ADD_ROUND(addr, PGDIR_SIZE); - if (last > end) - last = end; - if (pgd_newpage(*pgd)) { - updated = 1; - err = add_munmap(addr, last - addr, &hvc); - if (err < 0) - panic("munmap failed, errno = %d\n", - -err); - } - addr = last; - continue; - } - - p4d = p4d_offset(pgd, addr); - if (!p4d_present(*p4d)) { - last = ADD_ROUND(addr, P4D_SIZE); - if (last > end) - last = end; - if (p4d_newpage(*p4d)) { - updated = 1; - err = add_munmap(addr, last - addr, &hvc); - if (err < 0) - panic("munmap failed, errno = %d\n", - -err); - } - addr = last; - continue; - } - - pud = pud_offset(p4d, addr); - if (!pud_present(*pud)) { - last = ADD_ROUND(addr, PUD_SIZE); - if (last > end) - last = end; - if (pud_newpage(*pud)) { - updated = 1; - err = add_munmap(addr, last - addr, &hvc); - if (err < 0) - panic("munmap failed, errno = %d\n", - -err); - } - addr = last; - continue; - } - - pmd = pmd_offset(pud, addr); - if (!pmd_present(*pmd)) { - last = ADD_ROUND(addr, PMD_SIZE); - if (last > end) - last = end; - if (pmd_newpage(*pmd)) { - updated = 1; - err = add_munmap(addr, last - addr, &hvc); - if (err < 0) - panic("munmap failed, errno = %d\n", - -err); - } - addr = last; - continue; - } - - pte = pte_offset_kernel(pmd, addr); - if (!pte_present(*pte) || pte_newpage(*pte)) { - updated = 1; - err = add_munmap(addr, PAGE_SIZE, &hvc); - if (err < 0) - panic("munmap failed, errno = %d\n", - -err); - if (pte_present(*pte)) - err = add_mmap(addr, pte_val(*pte) & PAGE_MASK, - PAGE_SIZE, 0, &hvc); - } - else if (pte_newprot(*pte)) { - updated = 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; -} - -void flush_tlb_page(struct vm_area_struct *vma, unsigned long address) -{ - pgd_t *pgd; - p4d_t *p4d; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - struct mm_struct *mm = vma->vm_mm; - void *flush = NULL; - int r, w, x, prot, err = 0; - struct mm_id *mm_id; - - address &= PAGE_MASK; - - pgd = pgd_offset(mm, address); - if (!pgd_present(*pgd)) - goto kill; - - p4d = p4d_offset(pgd, address); - if (!p4d_present(*p4d)) - goto kill; - - pud = pud_offset(p4d, address); - if (!pud_present(*pud)) - goto kill; - - pmd = pmd_offset(pud, address); - if (!pmd_present(*pmd)) - goto kill; - - pte = pte_offset_kernel(pmd, address); - - r = pte_read(*pte); - w = pte_write(*pte); - x = pte_exec(*pte); - if (!pte_young(*pte)) { - r = 0; - w = 0; - } else if (!pte_dirty(*pte)) { - w = 0; - } - - mm_id = &mm->context.id; - prot = ((r ? UM_PROT_READ : 0) | (w ? UM_PROT_WRITE : 0) | - (x ? UM_PROT_EXEC : 0)); - if (pte_newpage(*pte)) { - if (pte_present(*pte)) { - unsigned long long offset; - int fd; - - fd = phys_mapping(pte_val(*pte) & PAGE_MASK, &offset); - err = map(mm_id, address, PAGE_SIZE, prot, fd, offset, - 1, &flush); - } - else err = unmap(mm_id, address, PAGE_SIZE, 1, &flush); - } - else if (pte_newprot(*pte)) - err = protect(mm_id, address, PAGE_SIZE, prot, 1, &flush); - - if (err) { - if (err == -ENOMEM) - report_enomem(); - - goto kill; - } - - *pte = pte_mkuptodate(*pte); + if (ret == -ENOMEM) + report_enomem(); - return; + mm->context.sync_tlb_range_from = 0; + mm->context.sync_tlb_range_to = 0; -kill: - printk(KERN_ERR "Failed to flush page for address 0x%lx\n", address); - force_sig(SIGKILL); + return ret; } void flush_tlb_all(void) @@ -540,60 +226,11 @@ void flush_tlb_all(void) flush_tlb_mm(current->mm); } -void flush_tlb_kernel_range(unsigned long start, unsigned long end) -{ - flush_tlb_kernel_range_common(start, end); -} - -void flush_tlb_kernel_vm(void) -{ - flush_tlb_kernel_range_common(start_vm, end_vm); -} - -void __flush_tlb_one(unsigned long addr) -{ - flush_tlb_kernel_range_common(addr, addr + PAGE_SIZE); -} - -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); -} - -void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end) -{ - if (vma->vm_mm == NULL) - flush_tlb_kernel_range_common(start, end); - else fix_range(vma->vm_mm, start, end, 0); -} -EXPORT_SYMBOL(flush_tlb_range); - void flush_tlb_mm(struct mm_struct *mm) { struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, 0); for_each_vma(vmi, vma) - fix_range(mm, vma->vm_start, vma->vm_end, 0); -} - -void force_flush_all(void) -{ - struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; - VMA_ITERATOR(vmi, mm, 0); - - mmap_read_lock(mm); - for_each_vma(vmi, vma) - fix_range(mm, vma->vm_start, vma->vm_end, 1); - mmap_read_unlock(mm); + um_tlb_mark_sync(mm, vma->vm_start, vma->vm_end); } diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 6d8ae86ae978..97c8df9c4401 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -113,7 +113,7 @@ good_area: #if 0 WARN_ON(!pte_young(*pte) || (is_write && !pte_dirty(*pte))); #endif - flush_tlb_page(vma, address); + out: mmap_read_unlock(mm); out_nosemaphore: @@ -210,8 +210,17 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user, if (!is_user && regs) current->thread.segv_regs = container_of(regs, struct pt_regs, regs); - if (!is_user && (address >= start_vm) && (address < end_vm)) { - flush_tlb_kernel_vm(); + if (!is_user && init_mm.context.sync_tlb_range_to) { + /* + * Kernel has pending updates from set_ptes that were not + * flushed yet. Syncing them should fix the pagefault (if not + * we'll get here again and panic). + */ + err = um_tlb_sync(&init_mm); + if (err == -ENOMEM) + report_enomem(); + if (err) + panic("Failed to sync kernel TLBs: %d", err); goto out; } else if (current->mm == NULL) { diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index e95f805e5004..8e594cda6d77 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -126,9 +126,6 @@ unsigned long uml_reserved; /* Also modified in mem_init */ unsigned long start_vm; unsigned long end_vm; -/* Set in uml_ncpus_setup */ -int ncpus = 1; - /* Set in early boot */ static int have_root __initdata; static int have_console __initdata; diff --git a/arch/um/os-Linux/file.c b/arch/um/os-Linux/file.c index fc4450db59bd..5adf8f630049 100644 --- a/arch/um/os-Linux/file.c +++ b/arch/um/os-Linux/file.c @@ -17,6 +17,7 @@ #include <sys/stat.h> #include <sys/sysmacros.h> #include <sys/un.h> +#include <sys/mman.h> #include <sys/types.h> #include <sys/eventfd.h> #include <poll.h> @@ -240,6 +241,16 @@ out: return err; } +int os_dup_file(int fd) +{ + int new_fd = dup(fd); + + if (new_fd < 0) + return -errno; + + return new_fd; +} + void os_close_file(int fd) { close(fd); @@ -502,44 +513,47 @@ int os_shutdown_socket(int fd, int r, int w) return 0; } -int os_rcv_fd(int fd, int *helper_pid_out) +/** + * os_rcv_fd_msg - receive message with (optional) FDs + * @fd: the FD to receive from + * @fds: the array for FDs to write to + * @n_fds: number of FDs to receive (@fds array size) + * @data: the message buffer + * @data_len: the size of the message to receive + * + * Receive a message with FDs. + * + * Returns: the size of the received message, or an error code + */ +ssize_t os_rcv_fd_msg(int fd, int *fds, unsigned int n_fds, + void *data, size_t data_len) { - int new, n; - char buf[CMSG_SPACE(sizeof(new))]; - struct msghdr msg; + char buf[CMSG_SPACE(sizeof(*fds) * n_fds)]; struct cmsghdr *cmsg; - struct iovec iov; - - msg.msg_name = NULL; - msg.msg_namelen = 0; - iov = ((struct iovec) { .iov_base = helper_pid_out, - .iov_len = sizeof(*helper_pid_out) }); - msg.msg_iov = &iov; - msg.msg_iovlen = 1; - msg.msg_control = buf; - msg.msg_controllen = sizeof(buf); - msg.msg_flags = 0; + struct iovec iov = { + .iov_base = data, + .iov_len = data_len, + }; + struct msghdr msg = { + .msg_iov = &iov, + .msg_iovlen = 1, + .msg_control = buf, + .msg_controllen = sizeof(buf), + }; + int n; n = recvmsg(fd, &msg, 0); if (n < 0) return -errno; - else if (n != iov.iov_len) - *helper_pid_out = -1; cmsg = CMSG_FIRSTHDR(&msg); - if (cmsg == NULL) { - printk(UM_KERN_ERR "rcv_fd didn't receive anything, " - "error = %d\n", errno); - return -1; - } - if ((cmsg->cmsg_level != SOL_SOCKET) || - (cmsg->cmsg_type != SCM_RIGHTS)) { - printk(UM_KERN_ERR "rcv_fd didn't receive a descriptor\n"); - return -1; - } + if (!cmsg || + cmsg->cmsg_level != SOL_SOCKET || + cmsg->cmsg_type != SCM_RIGHTS) + return n; - new = ((int *) CMSG_DATA(cmsg))[0]; - return new; + memcpy(fds, CMSG_DATA(cmsg), cmsg->cmsg_len); + return n; } int os_create_unix_socket(const char *file, int len, int close_on_exec) @@ -705,3 +719,25 @@ int os_poll(unsigned int n, const int *fds) return -EIO; } + +void *os_mmap_rw_shared(int fd, size_t size) +{ + void *res = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + + if (res == MAP_FAILED) + return NULL; + + return res; +} + +void *os_mremap_rw_shared(void *old_addr, size_t old_size, size_t new_size) +{ + void *res; + + res = mremap(old_addr, old_size, new_size, MREMAP_MAYMOVE, NULL); + + if (res == MAP_FAILED) + return NULL; + + return res; +} diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c index 787cfb9a0308..b11ed66c8bb0 100644 --- a/arch/um/os-Linux/signal.c +++ b/arch/um/os-Linux/signal.c @@ -8,6 +8,7 @@ #include <stdlib.h> #include <stdarg.h> +#include <stdbool.h> #include <errno.h> #include <signal.h> #include <string.h> @@ -65,9 +66,7 @@ static void sig_handler_common(int sig, struct siginfo *si, mcontext_t *mc) int signals_enabled; #ifdef UML_CONFIG_UML_TIME_TRAVEL_SUPPORT -static int signals_blocked; -#else -#define signals_blocked 0 +static int signals_blocked, signals_blocked_pending; #endif static unsigned int signals_pending; static unsigned int signals_active = 0; @@ -76,14 +75,27 @@ static void sig_handler(int sig, struct siginfo *si, mcontext_t *mc) { int enabled = signals_enabled; - if ((signals_blocked || !enabled) && (sig == SIGIO)) { +#ifdef UML_CONFIG_UML_TIME_TRAVEL_SUPPORT + if ((signals_blocked || + __atomic_load_n(&signals_blocked_pending, __ATOMIC_SEQ_CST)) && + (sig == SIGIO)) { + /* increment so unblock will do another round */ + __atomic_add_fetch(&signals_blocked_pending, 1, + __ATOMIC_SEQ_CST); + return; + } +#endif + + if (!enabled && (sig == SIGIO)) { /* * In TT_MODE_EXTERNAL, need to still call time-travel - * handlers unless signals are also blocked for the - * external time message processing. This will mark - * signals_pending by itself (only if necessary.) + * handlers. This will mark signals_pending by itself + * (only if necessary.) + * Note we won't get here if signals are hard-blocked + * (which is handled above), in that case the hard- + * unblock will handle things. */ - if (!signals_blocked && time_travel_mode == TT_MODE_EXTERNAL) + if (time_travel_mode == TT_MODE_EXTERNAL) sigio_run_timetravel_handlers(); else signals_pending |= SIGIO_MASK; @@ -380,33 +392,99 @@ int um_set_signals_trace(int enable) #ifdef UML_CONFIG_UML_TIME_TRAVEL_SUPPORT void mark_sigio_pending(void) { + /* + * It would seem that this should be atomic so + * it isn't a read-modify-write with a signal + * that could happen in the middle, losing the + * value set by the signal. + * + * However, this function is only called when in + * time-travel=ext simulation mode, in which case + * the only signal ever pending is SIGIO, which + * is blocked while this can be called, and the + * timer signal (SIGALRM) cannot happen. + */ signals_pending |= SIGIO_MASK; } void block_signals_hard(void) { - if (signals_blocked) - return; - signals_blocked = 1; + signals_blocked++; barrier(); } void unblock_signals_hard(void) { + static bool unblocking; + if (!signals_blocked) + panic("unblocking signals while not blocked"); + + if (--signals_blocked) return; - /* Must be set to 0 before we check the pending bits etc. */ - signals_blocked = 0; + /* + * Must be set to 0 before we check pending so the + * SIGIO handler will run as normal unless we're still + * going to process signals_blocked_pending. + */ barrier(); - if (signals_pending && signals_enabled) { - /* this is a bit inefficient, but that's not really important */ - block_signals(); - unblock_signals(); - } else if (signals_pending & SIGIO_MASK) { - /* we need to run time-travel handlers even if not enabled */ - sigio_run_timetravel_handlers(); + /* + * Note that block_signals_hard()/unblock_signals_hard() can be called + * within the unblock_signals()/sigio_run_timetravel_handlers() below. + * This would still be prone to race conditions since it's actually a + * call _within_ e.g. vu_req_read_message(), where we observed this + * issue, which loops. Thus, if the inner call handles the recorded + * pending signals, we can get out of the inner call with the real + * signal hander no longer blocked, and still have a race. Thus don't + * handle unblocking in the inner call, if it happens, but only in + * the outermost call - 'unblocking' serves as an ownership for the + * signals_blocked_pending decrement. + */ + if (unblocking) + return; + unblocking = true; + + while (__atomic_load_n(&signals_blocked_pending, __ATOMIC_SEQ_CST)) { + if (signals_enabled) { + /* signals are enabled so we can touch this */ + signals_pending |= SIGIO_MASK; + /* + * this is a bit inefficient, but that's + * not really important + */ + block_signals(); + unblock_signals(); + } else { + /* + * we need to run time-travel handlers even + * if not enabled + */ + sigio_run_timetravel_handlers(); + } + + /* + * The decrement of signals_blocked_pending must be atomic so + * that the signal handler will either happen before or after + * the decrement, not during a read-modify-write: + * - If it happens before, it can increment it and we'll + * decrement it and do another round in the loop. + * - If it happens after it'll see 0 for both signals_blocked + * and signals_blocked_pending and thus run the handler as + * usual (subject to signals_enabled, but that's unrelated.) + * + * Note that a call to unblock_signals_hard() within the calls + * to unblock_signals() or sigio_run_timetravel_handlers() above + * will do nothing due to the 'unblocking' state, so this cannot + * underflow as the only one decrementing will be the outermost + * one. + */ + if (__atomic_sub_fetch(&signals_blocked_pending, 1, + __ATOMIC_SEQ_CST) < 0) + panic("signals_blocked_pending underflow"); } + + unblocking = false; } #endif diff --git a/arch/um/os-Linux/skas/mem.c b/arch/um/os-Linux/skas/mem.c index 1f9c1bffc3a6..c55430775efd 100644 --- a/arch/um/os-Linux/skas/mem.c +++ b/arch/um/os-Linux/skas/mem.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* + * Copyright (C) 2021 Benjamin Berg <benjamin@sipsolutions.net> * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) */ @@ -19,7 +20,30 @@ #include <sysdep/stub.h> #include "../internal.h" -extern char batch_syscall_stub[], __syscall_stub_start[]; +extern char __syscall_stub_start[]; + +void syscall_stub_dump_error(struct mm_id *mm_idp) +{ + struct stub_data *proc_data = (void *)mm_idp->stack; + struct stub_syscall *sc; + + if (proc_data->syscall_data_len < 0 || + proc_data->syscall_data_len >= ARRAY_SIZE(proc_data->syscall_data)) + panic("Syscall data was corrupted by stub (len is: %d, expected maximum: %d)!", + proc_data->syscall_data_len, + mm_idp->syscall_data_len); + + sc = &proc_data->syscall_data[proc_data->syscall_data_len]; + + printk(UM_KERN_ERR "%s : length = %d, last offset = %d", + __func__, mm_idp->syscall_data_len, + proc_data->syscall_data_len); + printk(UM_KERN_ERR "%s : stub syscall type %d failed, return value = 0x%lx\n", + __func__, sc->syscall, proc_data->err); + + print_hex_dump(UM_KERN_ERR, " syscall data: ", 0, + 16, 4, sc, sizeof(*sc), 0); +} static inline unsigned long *check_init_stack(struct mm_id * mm_idp, unsigned long *stack) @@ -36,22 +60,24 @@ static unsigned long syscall_regs[MAX_REG_NR]; static int __init init_syscall_regs(void) { get_safe_registers(syscall_regs, NULL); + syscall_regs[REGS_IP_INDEX] = STUB_CODE + - ((unsigned long) batch_syscall_stub - + ((unsigned long) stub_syscall_handler - (unsigned long) __syscall_stub_start); - syscall_regs[REGS_SP_INDEX] = STUB_DATA; + syscall_regs[REGS_SP_INDEX] = STUB_DATA + + offsetof(struct stub_data, sigstack) + + sizeof(((struct stub_data *) 0)->sigstack) - + sizeof(void *); return 0; } __initcall(init_syscall_regs); -static inline long do_syscall_stub(struct mm_id * mm_idp, void **addr) +static inline long do_syscall_stub(struct mm_id *mm_idp) { + struct stub_data *proc_data = (void *)mm_idp->stack; int n, i; - long ret, offset; - unsigned long * data; - unsigned long * syscall; int err, pid = mm_idp->u.pid; n = ptrace_setregs(pid, syscall_regs); @@ -63,6 +89,9 @@ static inline long do_syscall_stub(struct mm_id * mm_idp, void **addr) __func__, -n); } + /* Inform process how much we have filled in. */ + proc_data->syscall_data_len = mm_idp->syscall_data_len; + err = ptrace(PTRACE_CONT, pid, 0, 0); if (err) panic("Failed to continue stub, pid = %d, errno = %d\n", pid, @@ -71,135 +100,141 @@ static inline long do_syscall_stub(struct mm_id * mm_idp, void **addr) wait_stub_done(pid); /* - * When the stub stops, we find the following values on the - * beginning of the stack: - * (long )return_value - * (long )offset to failed sycall-data (0, if no error) + * proc_data->err will be non-zero if there was an (unexpected) error. + * In that case, syscall_data_len points to the last executed syscall, + * otherwise it will be zero (but we do not need to rely on that). */ - ret = *((unsigned long *) mm_idp->stack); - offset = *((unsigned long *) mm_idp->stack + 1); - if (offset) { - data = (unsigned long *)(mm_idp->stack + offset - STUB_DATA); - printk(UM_KERN_ERR "%s : ret = %ld, offset = %ld, data = %p\n", - __func__, ret, offset, data); - syscall = (unsigned long *)((unsigned long)data + data[0]); - printk(UM_KERN_ERR "%s: syscall %ld failed, return value = 0x%lx, expected return value = 0x%lx\n", - __func__, syscall[0], ret, syscall[7]); - printk(UM_KERN_ERR " syscall parameters: 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx\n", - syscall[1], syscall[2], syscall[3], - syscall[4], syscall[5], syscall[6]); - for (n = 1; n < data[0]/sizeof(long); n++) { - if (n == 1) - printk(UM_KERN_ERR " additional syscall data:"); - if (n % 4 == 1) - printk("\n" UM_KERN_ERR " "); - printk(" 0x%lx", data[n]); - } - if (n > 1) - printk("\n"); - } - else ret = 0; + if (proc_data->err < 0) { + syscall_stub_dump_error(mm_idp); - *addr = check_init_stack(mm_idp, NULL); + /* Store error code in case someone tries to add more syscalls */ + mm_idp->syscall_data_len = proc_data->err; + } else { + mm_idp->syscall_data_len = 0; + } - return ret; + return mm_idp->syscall_data_len; } -long run_syscall_stub(struct mm_id * mm_idp, int syscall, - unsigned long *args, long expected, void **addr, - int done) +int syscall_stub_flush(struct mm_id *mm_idp) { - unsigned long *stack = check_init_stack(mm_idp, *addr); - - *stack += sizeof(long); - stack += *stack / sizeof(long); - - *stack++ = syscall; - *stack++ = args[0]; - *stack++ = args[1]; - *stack++ = args[2]; - *stack++ = args[3]; - *stack++ = args[4]; - *stack++ = args[5]; - *stack++ = expected; - *stack = 0; - - if (!done && ((((unsigned long) stack) & ~UM_KERN_PAGE_MASK) < - UM_KERN_PAGE_SIZE - 10 * sizeof(long))) { - *addr = stack; + int res; + + if (mm_idp->syscall_data_len == 0) return 0; + + /* If an error happened already, report it and reset the state. */ + if (mm_idp->syscall_data_len < 0) { + res = mm_idp->syscall_data_len; + mm_idp->syscall_data_len = 0; + return res; } - return do_syscall_stub(mm_idp, addr); + res = do_syscall_stub(mm_idp); + mm_idp->syscall_data_len = 0; + + return res; } -long syscall_stub_data(struct mm_id * mm_idp, - unsigned long *data, int data_count, - void **addr, void **stub_addr) +struct stub_syscall *syscall_stub_alloc(struct mm_id *mm_idp) { - unsigned long *stack; - int ret = 0; - - /* - * If *addr still is uninitialized, it *must* contain NULL. - * Thus in this case do_syscall_stub correctly won't be called. - */ - if ((((unsigned long) *addr) & ~UM_KERN_PAGE_MASK) >= - UM_KERN_PAGE_SIZE - (10 + data_count) * sizeof(long)) { - ret = do_syscall_stub(mm_idp, addr); - /* in case of error, don't overwrite data on stack */ - if (ret) - return ret; + struct stub_syscall *sc; + struct stub_data *proc_data = (struct stub_data *) mm_idp->stack; + + if (mm_idp->syscall_data_len > 0 && + mm_idp->syscall_data_len == ARRAY_SIZE(proc_data->syscall_data)) + do_syscall_stub(mm_idp); + + if (mm_idp->syscall_data_len < 0) { + /* Return dummy to retain error state. */ + sc = &proc_data->syscall_data[0]; + } else { + sc = &proc_data->syscall_data[mm_idp->syscall_data_len]; + mm_idp->syscall_data_len += 1; } + memset(sc, 0, sizeof(*sc)); - stack = check_init_stack(mm_idp, *addr); - *addr = stack; + return sc; +} - *stack = data_count * sizeof(long); +static struct stub_syscall *syscall_stub_get_previous(struct mm_id *mm_idp, + int syscall_type, + unsigned long virt) +{ + if (mm_idp->syscall_data_len > 0) { + struct stub_data *proc_data = (void *) mm_idp->stack; + struct stub_syscall *sc; - memcpy(stack + 1, data, data_count * sizeof(long)); + sc = &proc_data->syscall_data[mm_idp->syscall_data_len - 1]; - *stub_addr = (void *)(((unsigned long)(stack + 1) & - ~UM_KERN_PAGE_MASK) + STUB_DATA); + if (sc->syscall == syscall_type && + sc->mem.addr + sc->mem.length == virt) + return sc; + } - return 0; + return NULL; } -int map(struct mm_id * mm_idp, unsigned long virt, unsigned long len, int prot, - int phys_fd, unsigned long long offset, int done, void **data) +int map(struct mm_id *mm_idp, unsigned long virt, unsigned long len, int prot, + int phys_fd, unsigned long long offset) { - int ret; - unsigned long args[] = { virt, len, prot, - MAP_SHARED | MAP_FIXED, phys_fd, - MMAP_OFFSET(offset) }; + struct stub_syscall *sc; - ret = run_syscall_stub(mm_idp, STUB_MMAP_NR, args, virt, - data, done); + /* Compress with previous syscall if that is possible */ + sc = syscall_stub_get_previous(mm_idp, STUB_SYSCALL_MMAP, virt); + if (sc && sc->mem.prot == prot && sc->mem.fd == phys_fd && + sc->mem.offset == MMAP_OFFSET(offset - sc->mem.length)) { + sc->mem.length += len; + return 0; + } - return ret; + sc = syscall_stub_alloc(mm_idp); + sc->syscall = STUB_SYSCALL_MMAP; + sc->mem.addr = virt; + sc->mem.length = len; + sc->mem.prot = prot; + sc->mem.fd = phys_fd; + sc->mem.offset = MMAP_OFFSET(offset); + + return 0; } -int unmap(struct mm_id * mm_idp, unsigned long addr, unsigned long len, - int done, void **data) +int unmap(struct mm_id *mm_idp, unsigned long addr, unsigned long len) { - int ret; - unsigned long args[] = { (unsigned long) addr, len, 0, 0, 0, - 0 }; + struct stub_syscall *sc; - ret = run_syscall_stub(mm_idp, __NR_munmap, args, 0, - data, done); + /* Compress with previous syscall if that is possible */ + sc = syscall_stub_get_previous(mm_idp, STUB_SYSCALL_MUNMAP, addr); + if (sc) { + sc->mem.length += len; + return 0; + } - return ret; + sc = syscall_stub_alloc(mm_idp); + sc->syscall = STUB_SYSCALL_MUNMAP; + sc->mem.addr = addr; + sc->mem.length = len; + + return 0; } -int protect(struct mm_id * mm_idp, unsigned long addr, unsigned long len, - unsigned int prot, int done, void **data) +int protect(struct mm_id *mm_idp, unsigned long addr, unsigned long len, + unsigned int prot) { - int ret; - unsigned long args[] = { addr, len, prot, 0, 0, 0 }; + struct stub_syscall *sc; - ret = run_syscall_stub(mm_idp, __NR_mprotect, args, 0, - data, done); + /* Compress with previous syscall if that is possible */ + sc = syscall_stub_get_previous(mm_idp, STUB_SYSCALL_MPROTECT, addr); + if (sc && sc->mem.prot == prot) { + sc->mem.length += len; + return 0; + } - return ret; + sc = syscall_stub_alloc(mm_idp); + sc->syscall = STUB_SYSCALL_MPROTECT; + sc->mem.addr = addr; + sc->mem.length = len; + sc->mem.prot = prot; + + return 0; } diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c index 41a288dcfc34..f7088345b3fc 100644 --- a/arch/um/os-Linux/skas/process.c +++ b/arch/um/os-Linux/skas/process.c @@ -23,6 +23,7 @@ #include <skas.h> #include <sysdep/stub.h> #include <linux/threads.h> +#include <timetravel.h> #include "../internal.h" int is_skas_winch(int pid, int fd, void *data) @@ -253,7 +254,6 @@ static int userspace_tramp(void *stack) } int userspace_pid[NR_CPUS]; -int kill_userspace_mm[NR_CPUS]; /** * start_userspace() - prepare a new userspace process @@ -345,8 +345,20 @@ void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs) interrupt_end(); while (1) { - if (kill_userspace_mm[0]) + time_travel_print_bc_msg(); + + current_mm_sync(); + + /* Flush out any pending syscalls */ + err = syscall_stub_flush(current_mm_id()); + if (err) { + if (err == -ENOMEM) + report_enomem(); + + printk(UM_KERN_ERR "%s - Error flushing stub syscalls: %d", + __func__, -err); fatal_sigsegv(); + } /* * This can legitimately fail if the process loads a @@ -461,113 +473,6 @@ void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs) } } -static unsigned long thread_regs[MAX_REG_NR]; -static unsigned long thread_fp_regs[FP_SIZE]; - -static int __init init_thread_regs(void) -{ - get_safe_registers(thread_regs, thread_fp_regs); - /* Set parent's instruction pointer to start of clone-stub */ - thread_regs[REGS_IP_INDEX] = STUB_CODE + - (unsigned long) stub_clone_handler - - (unsigned long) __syscall_stub_start; - thread_regs[REGS_SP_INDEX] = STUB_DATA + STUB_DATA_PAGES * UM_KERN_PAGE_SIZE - - sizeof(void *); -#ifdef __SIGNAL_FRAMESIZE - thread_regs[REGS_SP_INDEX] -= __SIGNAL_FRAMESIZE; -#endif - return 0; -} - -__initcall(init_thread_regs); - -int copy_context_skas0(unsigned long new_stack, int pid) -{ - int err; - unsigned long current_stack = current_stub_stack(); - struct stub_data *data = (struct stub_data *) current_stack; - struct stub_data *child_data = (struct stub_data *) new_stack; - unsigned long long new_offset; - int new_fd = phys_mapping(uml_to_phys((void *)new_stack), &new_offset); - - /* - * prepare offset and fd of child's stack as argument for parent's - * and child's mmap2 calls - */ - *data = ((struct stub_data) { - .offset = MMAP_OFFSET(new_offset), - .fd = new_fd, - .parent_err = -ESRCH, - .child_err = 0, - }); - - *child_data = ((struct stub_data) { - .child_err = -ESRCH, - }); - - err = ptrace_setregs(pid, thread_regs); - if (err < 0) { - err = -errno; - printk(UM_KERN_ERR "%s : PTRACE_SETREGS failed, pid = %d, errno = %d\n", - __func__, pid, -err); - return err; - } - - err = put_fp_registers(pid, thread_fp_regs); - if (err < 0) { - printk(UM_KERN_ERR "%s : put_fp_registers failed, pid = %d, err = %d\n", - __func__, pid, err); - return err; - } - - /* - * Wait, until parent has finished its work: read child's pid from - * parent's stack, and check, if bad result. - */ - err = ptrace(PTRACE_CONT, pid, 0, 0); - if (err) { - err = -errno; - printk(UM_KERN_ERR "Failed to continue new process, pid = %d, errno = %d\n", - pid, errno); - return err; - } - - wait_stub_done(pid); - - pid = data->parent_err; - if (pid < 0) { - printk(UM_KERN_ERR "%s - stub-parent reports error %d\n", - __func__, -pid); - return pid; - } - - /* - * Wait, until child has finished too: read child's result from - * child's stack and check it. - */ - wait_stub_done(pid); - if (child_data->child_err != STUB_DATA) { - printk(UM_KERN_ERR "%s - stub-child %d reports error %ld\n", - __func__, pid, data->child_err); - err = data->child_err; - goto out_kill; - } - - if (ptrace(PTRACE_SETOPTIONS, pid, NULL, - (void *)PTRACE_O_TRACESYSGOOD) < 0) { - err = -errno; - printk(UM_KERN_ERR "%s : PTRACE_SETOPTIONS failed, errno = %d\n", - __func__, errno); - goto out_kill; - } - - return pid; - - out_kill: - os_kill_ptraced_process(pid, 1); - return err; -} - void new_thread(void *stack, jmp_buf *buf, void (*handler)(void)) { (*buf)[0].JB_IP = (unsigned long) handler; @@ -684,5 +589,4 @@ void reboot_skas(void) void __switch_mm(struct mm_id *mm_idp) { userspace_pid[0] = mm_idp->u.pid; - kill_userspace_mm[0] = mm_idp->kill; } diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c index 89ad9f4f865c..93fc82c01aba 100644 --- a/arch/um/os-Linux/start_up.c +++ b/arch/um/os-Linux/start_up.c @@ -17,6 +17,7 @@ #include <sys/wait.h> #include <sys/time.h> #include <sys/resource.h> +#include <asm/ldt.h> #include <asm/unistd.h> #include <init.h> #include <os.h> diff --git a/arch/x86/Makefile.um b/arch/x86/Makefile.um index 2106a2bd152b..a46b1397ad01 100644 --- a/arch/x86/Makefile.um +++ b/arch/x86/Makefile.um @@ -9,6 +9,7 @@ core-y += arch/x86/crypto/ # ifeq ($(CONFIG_CC_IS_CLANG),y) KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx +KBUILD_RUSTFLAGS += --target=$(objtree)/scripts/target.json KBUILD_RUSTFLAGS += -Ctarget-feature=-sse,-sse2,-sse3,-ssse3,-sse4.1,-sse4.2,-avx,-avx2 endif diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile index 8bc72a51b257..36e67fc97c22 100644 --- a/arch/x86/um/Makefile +++ b/arch/x86/um/Makefile @@ -9,9 +9,9 @@ else BITS := 64 endif -obj-y = bugs_$(BITS).o delay.o fault.o ldt.o \ +obj-y = bugs_$(BITS).o delay.o fault.o \ ptrace_$(BITS).o ptrace_user.o setjmp_$(BITS).o signal.o \ - stub_$(BITS).o stub_segv.o \ + stub_segv.o \ sys_call_table_$(BITS).o sysrq_$(BITS).o tls_$(BITS).o \ mem_$(BITS).o subarch.o os-Linux/ @@ -31,7 +31,6 @@ obj-y += syscalls_64.o vdso/ subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o \ ../lib/memmove_64.o ../lib/memset_64.o -subarch-$(CONFIG_PREEMPTION) += ../entry/thunk_64.o endif diff --git a/arch/x86/um/asm/mm_context.h b/arch/x86/um/asm/mm_context.h deleted file mode 100644 index dc32dc023c2f..000000000000 --- a/arch/x86/um/asm/mm_context.h +++ /dev/null @@ -1,70 +0,0 @@ -/* - * Copyright (C) 2004 Fujitsu Siemens Computers GmbH - * Licensed under the GPL - * - * Author: Bodo Stroesser <bstroesser@fujitsu-siemens.com> - */ - -#ifndef __ASM_LDT_H -#define __ASM_LDT_H - -#include <linux/mutex.h> -#include <asm/ldt.h> - -#define LDT_PAGES_MAX \ - ((LDT_ENTRIES * LDT_ENTRY_SIZE)/PAGE_SIZE) -#define LDT_ENTRIES_PER_PAGE \ - (PAGE_SIZE/LDT_ENTRY_SIZE) -#define LDT_DIRECT_ENTRIES \ - ((LDT_PAGES_MAX*sizeof(void *))/LDT_ENTRY_SIZE) - -struct ldt_entry { - __u32 a; - __u32 b; -}; - -typedef struct uml_ldt { - int entry_count; - struct mutex lock; - union { - struct ldt_entry * pages[LDT_PAGES_MAX]; - struct ldt_entry entries[LDT_DIRECT_ENTRIES]; - } u; -} uml_ldt_t; - -#define LDT_entry_a(info) \ - ((((info)->base_addr & 0x0000ffff) << 16) | ((info)->limit & 0x0ffff)) - -#define LDT_entry_b(info) \ - (((info)->base_addr & 0xff000000) | \ - (((info)->base_addr & 0x00ff0000) >> 16) | \ - ((info)->limit & 0xf0000) | \ - (((info)->read_exec_only ^ 1) << 9) | \ - ((info)->contents << 10) | \ - (((info)->seg_not_present ^ 1) << 15) | \ - ((info)->seg_32bit << 22) | \ - ((info)->limit_in_pages << 23) | \ - ((info)->useable << 20) | \ - 0x7000) - -#define _LDT_empty(info) (\ - (info)->base_addr == 0 && \ - (info)->limit == 0 && \ - (info)->contents == 0 && \ - (info)->read_exec_only == 1 && \ - (info)->seg_32bit == 0 && \ - (info)->limit_in_pages == 0 && \ - (info)->seg_not_present == 1 && \ - (info)->useable == 0 ) - -#ifdef CONFIG_X86_64 -#define LDT_empty(info) (_LDT_empty(info) && ((info)->lm == 0)) -#else -#define LDT_empty(info) (_LDT_empty(info)) -#endif - -struct uml_arch_mm_context { - uml_ldt_t ldt; -}; - -#endif diff --git a/arch/x86/um/ldt.c b/arch/x86/um/ldt.c deleted file mode 100644 index 255a44dd415a..000000000000 --- a/arch/x86/um/ldt.c +++ /dev/null @@ -1,380 +0,0 @@ -/* - * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) - * Licensed under the GPL - */ - -#include <linux/mm.h> -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/syscalls.h> -#include <linux/uaccess.h> -#include <asm/unistd.h> -#include <os.h> -#include <skas.h> -#include <sysdep/tls.h> - -static inline int modify_ldt (int func, void *ptr, unsigned long bytecount) -{ - return syscall(__NR_modify_ldt, func, ptr, bytecount); -} - -static long write_ldt_entry(struct mm_id *mm_idp, int func, - struct user_desc *desc, void **addr, int done) -{ - long res; - void *stub_addr; - - BUILD_BUG_ON(sizeof(*desc) % sizeof(long)); - - res = syscall_stub_data(mm_idp, (unsigned long *)desc, - sizeof(*desc) / sizeof(long), - addr, &stub_addr); - if (!res) { - unsigned long args[] = { func, - (unsigned long)stub_addr, - sizeof(*desc), - 0, 0, 0 }; - res = run_syscall_stub(mm_idp, __NR_modify_ldt, args, - 0, addr, done); - } - - return res; -} - -/* - * In skas mode, we hold our own ldt data in UML. - * Thus, the code implementing sys_modify_ldt_skas - * is very similar to (and mostly stolen from) sys_modify_ldt - * for arch/i386/kernel/ldt.c - * The routines copied and modified in part are: - * - read_ldt - * - read_default_ldt - * - write_ldt - * - sys_modify_ldt_skas - */ - -static int read_ldt(void __user * ptr, unsigned long bytecount) -{ - int i, err = 0; - unsigned long size; - uml_ldt_t *ldt = ¤t->mm->context.arch.ldt; - - if (!ldt->entry_count) - goto out; - if (bytecount > LDT_ENTRY_SIZE*LDT_ENTRIES) - bytecount = LDT_ENTRY_SIZE*LDT_ENTRIES; - err = bytecount; - - mutex_lock(&ldt->lock); - if (ldt->entry_count <= LDT_DIRECT_ENTRIES) { - size = LDT_ENTRY_SIZE*LDT_DIRECT_ENTRIES; - if (size > bytecount) - size = bytecount; - if (copy_to_user(ptr, ldt->u.entries, size)) - err = -EFAULT; - bytecount -= size; - ptr += size; - } - else { - for (i=0; i<ldt->entry_count/LDT_ENTRIES_PER_PAGE && bytecount; - i++) { - size = PAGE_SIZE; - if (size > bytecount) - size = bytecount; - if (copy_to_user(ptr, ldt->u.pages[i], size)) { - err = -EFAULT; - break; - } - bytecount -= size; - ptr += size; - } - } - mutex_unlock(&ldt->lock); - - if (bytecount == 0 || err == -EFAULT) - goto out; - - if (clear_user(ptr, bytecount)) - err = -EFAULT; - -out: - return err; -} - -static int read_default_ldt(void __user * ptr, unsigned long bytecount) -{ - int err; - - if (bytecount > 5*LDT_ENTRY_SIZE) - bytecount = 5*LDT_ENTRY_SIZE; - - err = bytecount; - /* - * UML doesn't support lcall7 and lcall27. - * So, we don't really have a default ldt, but emulate - * an empty ldt of common host default ldt size. - */ - if (clear_user(ptr, bytecount)) - err = -EFAULT; - - return err; -} - -static int write_ldt(void __user * ptr, unsigned long bytecount, int func) -{ - uml_ldt_t *ldt = ¤t->mm->context.arch.ldt; - struct mm_id * mm_idp = ¤t->mm->context.id; - int i, err; - struct user_desc ldt_info; - struct ldt_entry entry0, *ldt_p; - void *addr = NULL; - - err = -EINVAL; - if (bytecount != sizeof(ldt_info)) - goto out; - err = -EFAULT; - if (copy_from_user(&ldt_info, ptr, sizeof(ldt_info))) - goto out; - - err = -EINVAL; - if (ldt_info.entry_number >= LDT_ENTRIES) - goto out; - if (ldt_info.contents == 3) { - if (func == 1) - goto out; - if (ldt_info.seg_not_present == 0) - goto out; - } - - mutex_lock(&ldt->lock); - - err = write_ldt_entry(mm_idp, func, &ldt_info, &addr, 1); - if (err) - goto out_unlock; - - if (ldt_info.entry_number >= ldt->entry_count && - ldt_info.entry_number >= LDT_DIRECT_ENTRIES) { - for (i=ldt->entry_count/LDT_ENTRIES_PER_PAGE; - i*LDT_ENTRIES_PER_PAGE <= ldt_info.entry_number; - i++) { - if (i == 0) - memcpy(&entry0, ldt->u.entries, - sizeof(entry0)); - ldt->u.pages[i] = (struct ldt_entry *) - __get_free_page(GFP_KERNEL|__GFP_ZERO); - if (!ldt->u.pages[i]) { - err = -ENOMEM; - /* Undo the change in host */ - memset(&ldt_info, 0, sizeof(ldt_info)); - write_ldt_entry(mm_idp, 1, &ldt_info, &addr, 1); - goto out_unlock; - } - if (i == 0) { - memcpy(ldt->u.pages[0], &entry0, - sizeof(entry0)); - memcpy(ldt->u.pages[0]+1, ldt->u.entries+1, - sizeof(entry0)*(LDT_DIRECT_ENTRIES-1)); - } - ldt->entry_count = (i + 1) * LDT_ENTRIES_PER_PAGE; - } - } - if (ldt->entry_count <= ldt_info.entry_number) - ldt->entry_count = ldt_info.entry_number + 1; - - if (ldt->entry_count <= LDT_DIRECT_ENTRIES) - ldt_p = ldt->u.entries + ldt_info.entry_number; - else - ldt_p = ldt->u.pages[ldt_info.entry_number/LDT_ENTRIES_PER_PAGE] + - ldt_info.entry_number%LDT_ENTRIES_PER_PAGE; - - if (ldt_info.base_addr == 0 && ldt_info.limit == 0 && - (func == 1 || LDT_empty(&ldt_info))) { - ldt_p->a = 0; - ldt_p->b = 0; - } - else{ - if (func == 1) - ldt_info.useable = 0; - ldt_p->a = LDT_entry_a(&ldt_info); - ldt_p->b = LDT_entry_b(&ldt_info); - } - err = 0; - -out_unlock: - mutex_unlock(&ldt->lock); -out: - return err; -} - -static long do_modify_ldt_skas(int func, void __user *ptr, - unsigned long bytecount) -{ - int ret = -ENOSYS; - - switch (func) { - case 0: - ret = read_ldt(ptr, bytecount); - break; - case 1: - case 0x11: - ret = write_ldt(ptr, bytecount, func); - break; - case 2: - ret = read_default_ldt(ptr, bytecount); - break; - } - return ret; -} - -static DEFINE_SPINLOCK(host_ldt_lock); -static short dummy_list[9] = {0, -1}; -static short * host_ldt_entries = NULL; - -static void ldt_get_host_info(void) -{ - long ret; - struct ldt_entry * ldt; - short *tmp; - int i, size, k, order; - - spin_lock(&host_ldt_lock); - - if (host_ldt_entries != NULL) { - spin_unlock(&host_ldt_lock); - return; - } - host_ldt_entries = dummy_list+1; - - spin_unlock(&host_ldt_lock); - - for (i = LDT_PAGES_MAX-1, order=0; i; i>>=1, order++) - ; - - ldt = (struct ldt_entry *) - __get_free_pages(GFP_KERNEL|__GFP_ZERO, order); - if (ldt == NULL) { - printk(KERN_ERR "ldt_get_host_info: couldn't allocate buffer " - "for host ldt\n"); - return; - } - - ret = modify_ldt(0, ldt, (1<<order)*PAGE_SIZE); - if (ret < 0) { - printk(KERN_ERR "ldt_get_host_info: couldn't read host ldt\n"); - goto out_free; - } - if (ret == 0) { - /* default_ldt is active, simply write an empty entry 0 */ - host_ldt_entries = dummy_list; - goto out_free; - } - - for (i=0, size=0; i<ret/LDT_ENTRY_SIZE; i++) { - if (ldt[i].a != 0 || ldt[i].b != 0) - size++; - } - - if (size < ARRAY_SIZE(dummy_list)) - host_ldt_entries = dummy_list; - else { - size = (size + 1) * sizeof(dummy_list[0]); - tmp = kmalloc(size, GFP_KERNEL); - if (tmp == NULL) { - printk(KERN_ERR "ldt_get_host_info: couldn't allocate " - "host ldt list\n"); - goto out_free; - } - host_ldt_entries = tmp; - } - - for (i=0, k=0; i<ret/LDT_ENTRY_SIZE; i++) { - if (ldt[i].a != 0 || ldt[i].b != 0) - host_ldt_entries[k++] = i; - } - host_ldt_entries[k] = -1; - -out_free: - free_pages((unsigned long)ldt, order); -} - -long init_new_ldt(struct mm_context *new_mm, struct mm_context *from_mm) -{ - struct user_desc desc; - short * num_p; - int i; - long page, err=0; - void *addr = NULL; - - - mutex_init(&new_mm->arch.ldt.lock); - - if (!from_mm) { - memset(&desc, 0, sizeof(desc)); - /* - * Now we try to retrieve info about the ldt, we - * inherited from the host. All ldt-entries found - * will be reset in the following loop - */ - ldt_get_host_info(); - for (num_p=host_ldt_entries; *num_p != -1; num_p++) { - desc.entry_number = *num_p; - err = write_ldt_entry(&new_mm->id, 1, &desc, - &addr, *(num_p + 1) == -1); - if (err) - break; - } - new_mm->arch.ldt.entry_count = 0; - - goto out; - } - - /* - * Our local LDT is used to supply the data for - * modify_ldt(READLDT), if PTRACE_LDT isn't available, - * i.e., we have to use the stub for modify_ldt, which - * can't handle the big read buffer of up to 64kB. - */ - mutex_lock(&from_mm->arch.ldt.lock); - if (from_mm->arch.ldt.entry_count <= LDT_DIRECT_ENTRIES) - memcpy(new_mm->arch.ldt.u.entries, from_mm->arch.ldt.u.entries, - sizeof(new_mm->arch.ldt.u.entries)); - else { - i = from_mm->arch.ldt.entry_count / LDT_ENTRIES_PER_PAGE; - while (i-->0) { - page = __get_free_page(GFP_KERNEL|__GFP_ZERO); - if (!page) { - err = -ENOMEM; - break; - } - new_mm->arch.ldt.u.pages[i] = - (struct ldt_entry *) page; - memcpy(new_mm->arch.ldt.u.pages[i], - from_mm->arch.ldt.u.pages[i], PAGE_SIZE); - } - } - new_mm->arch.ldt.entry_count = from_mm->arch.ldt.entry_count; - mutex_unlock(&from_mm->arch.ldt.lock); - - out: - return err; -} - - -void free_ldt(struct mm_context *mm) -{ - int i; - - if (mm->arch.ldt.entry_count > LDT_DIRECT_ENTRIES) { - i = mm->arch.ldt.entry_count / LDT_ENTRIES_PER_PAGE; - while (i-- > 0) - free_page((long) mm->arch.ldt.u.pages[i]); - } - mm->arch.ldt.entry_count = 0; -} - -SYSCALL_DEFINE3(modify_ldt, int , func , void __user * , ptr , - unsigned long , bytecount) -{ - /* See non-um modify_ldt() for why we do this cast */ - return (unsigned int)do_modify_ldt_skas(func, ptr, bytecount); -} diff --git a/arch/x86/um/shared/sysdep/stub.h b/arch/x86/um/shared/sysdep/stub.h index ce0ca46ad383..dc89f4423454 100644 --- a/arch/x86/um/shared/sysdep/stub.h +++ b/arch/x86/um/shared/sysdep/stub.h @@ -12,4 +12,4 @@ #endif extern void stub_segv_handler(int, siginfo_t *, void *); -extern void stub_clone_handler(void); +extern void stub_syscall_handler(void); diff --git a/arch/x86/um/shared/sysdep/stub_32.h b/arch/x86/um/shared/sysdep/stub_32.h index ea8b5a2d67af..0b44a86dd346 100644 --- a/arch/x86/um/shared/sysdep/stub_32.h +++ b/arch/x86/um/shared/sysdep/stub_32.h @@ -6,6 +6,7 @@ #ifndef __SYSDEP_STUB_H #define __SYSDEP_STUB_H +#include <stddef.h> #include <asm/ptrace.h> #include <generated/asm-offsets.h> @@ -79,33 +80,31 @@ static __always_inline long stub_syscall5(long syscall, long arg1, long arg2, return ret; } -static __always_inline void trap_myself(void) +static __always_inline long stub_syscall6(long syscall, long arg1, long arg2, + long arg3, long arg4, long arg5, + long arg6) { - __asm("int3"); + struct syscall_args { + int ebx, ebp; + } args = { arg1, arg6 }; + long ret; + + __asm__ volatile ("pushl %%ebp;" + "movl 0x4(%%ebx),%%ebp;" + "movl (%%ebx),%%ebx;" + "int $0x80;" + "popl %%ebp" + : "=a" (ret) + : "0" (syscall), "b" (&args), + "c" (arg2), "d" (arg3), "S" (arg4), "D" (arg5) + : "memory"); + + return ret; } -static __always_inline void remap_stack_and_trap(void) +static __always_inline void trap_myself(void) { - __asm__ volatile ( - "movl %%esp,%%ebx ;" - "andl %0,%%ebx ;" - "movl %1,%%eax ;" - "movl %%ebx,%%edi ; addl %2,%%edi ; movl (%%edi),%%edi ;" - "movl %%ebx,%%ebp ; addl %3,%%ebp ; movl (%%ebp),%%ebp ;" - "int $0x80 ;" - "addl %4,%%ebx ; movl %%eax, (%%ebx) ;" - "int $3" - : : - "g" (~(STUB_DATA_PAGES * UM_KERN_PAGE_SIZE - 1)), - "g" (STUB_MMAP_NR), - "g" (UML_STUB_FIELD_FD), - "g" (UML_STUB_FIELD_OFFSET), - "g" (UML_STUB_FIELD_CHILD_ERR), - "c" (STUB_DATA_PAGES * UM_KERN_PAGE_SIZE), - "d" (PROT_READ | PROT_WRITE), - "S" (MAP_FIXED | MAP_SHARED) - : - "memory"); + __asm("int3"); } static __always_inline void *get_stub_data(void) diff --git a/arch/x86/um/shared/sysdep/stub_64.h b/arch/x86/um/shared/sysdep/stub_64.h index b24168ef0ac4..67f44284f1aa 100644 --- a/arch/x86/um/shared/sysdep/stub_64.h +++ b/arch/x86/um/shared/sysdep/stub_64.h @@ -6,6 +6,7 @@ #ifndef __SYSDEP_STUB_H #define __SYSDEP_STUB_H +#include <stddef.h> #include <sysdep/ptrace_user.h> #include <generated/asm-offsets.h> #include <linux/stddef.h> @@ -79,35 +80,25 @@ static __always_inline long stub_syscall5(long syscall, long arg1, long arg2, return ret; } -static __always_inline void trap_myself(void) +static __always_inline long stub_syscall6(long syscall, long arg1, long arg2, + long arg3, long arg4, long arg5, + long arg6) { - __asm("int3"); + long ret; + + __asm__ volatile ("movq %5,%%r10 ; movq %6,%%r8 ; movq %7,%%r9 ; " + __syscall + : "=a" (ret) + : "0" (syscall), "D" (arg1), "S" (arg2), "d" (arg3), + "g" (arg4), "g" (arg5), "g" (arg6) + : __syscall_clobber, "r10", "r8", "r9"); + + return ret; } -static __always_inline void remap_stack_and_trap(void) +static __always_inline void trap_myself(void) { - __asm__ volatile ( - "movq %0,%%rax ;" - "movq %%rsp,%%rdi ;" - "andq %1,%%rdi ;" - "movq %2,%%r10 ;" - "movq %%rdi,%%r8 ; addq %3,%%r8 ; movq (%%r8),%%r8 ;" - "movq %%rdi,%%r9 ; addq %4,%%r9 ; movq (%%r9),%%r9 ;" - __syscall ";" - "movq %%rsp,%%rdi ; andq %1,%%rdi ;" - "addq %5,%%rdi ; movq %%rax, (%%rdi) ;" - "int3" - : : - "g" (STUB_MMAP_NR), - "g" (~(STUB_DATA_PAGES * UM_KERN_PAGE_SIZE - 1)), - "g" (MAP_FIXED | MAP_SHARED), - "g" (UML_STUB_FIELD_FD), - "g" (UML_STUB_FIELD_OFFSET), - "g" (UML_STUB_FIELD_CHILD_ERR), - "S" (STUB_DATA_PAGES * UM_KERN_PAGE_SIZE), - "d" (PROT_READ | PROT_WRITE) - : - __syscall_clobber, "r10", "r8", "r9"); + __asm("int3"); } static __always_inline void *get_stub_data(void) diff --git a/arch/x86/um/stub_32.S b/arch/x86/um/stub_32.S deleted file mode 100644 index 8291899e6aaf..000000000000 --- a/arch/x86/um/stub_32.S +++ /dev/null @@ -1,56 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include <as-layout.h> - -.section .__syscall_stub, "ax" - - .globl batch_syscall_stub -batch_syscall_stub: - /* %esp comes in as "top of page" */ - mov %esp, %ecx - /* %esp has pointer to first operation */ - add $8, %esp -again: - /* load length of additional data */ - mov 0x0(%esp), %eax - - /* if(length == 0) : end of list */ - /* write possible 0 to header */ - mov %eax, 0x4(%ecx) - cmpl $0, %eax - jz done - - /* save current pointer */ - mov %esp, 0x4(%ecx) - - /* skip additional data */ - add %eax, %esp - - /* load syscall-# */ - pop %eax - - /* load syscall params */ - pop %ebx - pop %ecx - pop %edx - pop %esi - pop %edi - pop %ebp - - /* execute syscall */ - int $0x80 - - /* restore top of page pointer in %ecx */ - mov %esp, %ecx - andl $(~UM_KERN_PAGE_SIZE) + 1, %ecx - - /* check return value */ - pop %ebx - cmp %ebx, %eax - je again - -done: - /* save return value */ - mov %eax, (%ecx) - - /* stop */ - int3 diff --git a/arch/x86/um/stub_64.S b/arch/x86/um/stub_64.S deleted file mode 100644 index f3404640197a..000000000000 --- a/arch/x86/um/stub_64.S +++ /dev/null @@ -1,50 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include <as-layout.h> - -.section .__syscall_stub, "ax" - .globl batch_syscall_stub -batch_syscall_stub: - /* %rsp has the pointer to first operation */ - mov %rsp, %rbx - add $0x10, %rsp -again: - /* load length of additional data */ - mov 0x0(%rsp), %rax - - /* if(length == 0) : end of list */ - /* write possible 0 to header */ - mov %rax, 8(%rbx) - cmp $0, %rax - jz done - - /* save current pointer */ - mov %rsp, 8(%rbx) - - /* skip additional data */ - add %rax, %rsp - - /* load syscall-# */ - pop %rax - - /* load syscall params */ - pop %rdi - pop %rsi - pop %rdx - pop %r10 - pop %r8 - pop %r9 - - /* execute syscall */ - syscall - - /* check return value */ - pop %rcx - cmp %rcx, %rax - je again - -done: - /* save return value */ - mov %rax, (%rbx) - - /* stop */ - int3 diff --git a/arch/x86/um/tls_32.c b/arch/x86/um/tls_32.c index d301deee041f..fbb129023080 100644 --- a/arch/x86/um/tls_32.c +++ b/arch/x86/um/tls_32.c @@ -11,6 +11,7 @@ #include <os.h> #include <skas.h> #include <sysdep/tls.h> +#include <asm/desc.h> /* * If needed we can detect when it's uninitialized. |