um: Add SMP support

index 0bbb24868557..c727e56ba116 100644
@@ -13,20 +13,9 @@
 #include <asm/mm_hooks.h>
 #include <asm/mmu.h>
 
-#define activate_mm activate_mm
-static inline void activate_mm(struct mm_struct *old, struct mm_struct *new)
-{
-}
-
 static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, 
 			     struct task_struct *tsk)
 {
-	unsigned cpu = smp_processor_id();
-
-	if (prev != next) {
-		cpumask_clear_cpu(cpu, mm_cpumask(prev));
-		cpumask_set_cpu(cpu, mm_cpumask(next));
-	}
 }
 
 #define init_new_context init_new_context

index 8a789c17acd8..236fdfd7cdbe 100644
@@ -81,8 +81,6 @@ struct cpuinfo_um {
 
 extern struct cpuinfo_um boot_cpu_data;
 
-#define cpu_data(cpu)    boot_cpu_data
-#define current_cpu_data boot_cpu_data
 #define cache_line_size()	(boot_cpu_data.cache_alignment)
 
 #define KSTK_REG(tsk, reg) get_thread_reg(reg, &tsk->thread.switch_buf)

index cbae2584124f..ee40ac446c1c 100644
@@ -17,7 +17,7 @@
 int __vdso_clock_gettime(clockid_t clock, struct __kernel_old_timespec *ts);
 int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
 __kernel_old_time_t __vdso_time(__kernel_old_time_t *t);
-long __vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *unused);
+long __vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *tcache);
 
 int __vdso_clock_gettime(clockid_t clock, struct __kernel_old_timespec *ts)
 {

@@ -60,18 +60,16 @@ __kernel_old_time_t __vdso_time(__kernel_old_time_t *t)
 __kernel_old_time_t time(__kernel_old_time_t *t) __attribute__((weak, alias("__vdso_time")));
 
 long
-__vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *unused)
+__vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *tcache)
 {
-	/*
-	 * UML does not support SMP, we can cheat here. :)
-	 */
+	long ret;
 
-	if (cpu)
-		*cpu = 0;
-	if (node)
-		*node = 0;
+	asm volatile("syscall"
+		: "=a" (ret)
+		: "0" (__NR_getcpu), "D" (cpu), "S" (node), "d" (tcache)
+		: "rcx", "r11", "memory");
 
-	return 0;
+	return ret;
 }
 
 long getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *tcache)

index 11f07f498270..217a71244b69 100644
@@ -201,8 +201,11 @@ static void hard_handler(int sig, siginfo_t *si, void *p)
 {
 	ucontext_t *uc = p;
 	mcontext_t *mc = &uc->uc_mcontext;
+	int errno_saved = errno;
 
 	(*handlers[sig])(sig, (struct siginfo *)si, mc);
+
+	errno = errno_saved;
 }
 
 void set_handler(int sig)

index 1e69ef5bc35e..31e49e0894c5 100644
@@ -2,7 +2,7 @@
 #ifndef __UM_IRQFLAGS_H
 #define __UM_IRQFLAGS_H
 
-extern int signals_enabled;
+int um_get_signals(void);
 int um_set_signals(int enable);
 void block_signals(void);
 void unblock_signals(void);

@@ -10,7 +10,7 @@ void unblock_signals(void);
 #define arch_local_save_flags arch_local_save_flags
 static inline unsigned long arch_local_save_flags(void)
 {
-	return signals_enabled;
+	return um_get_signals();
 }
 
 #define arch_local_irq_restore arch_local_irq_restore

index 8863319039f3..c53e43d980c8 100644
@@ -5,7 +5,6 @@
 #include <sysdep/archsetjmp.h>
 #include <os.h>
 
-extern int signals_enabled;
 extern int setjmp(jmp_buf);
 extern void longjmp(jmp_buf, int);
 

@@ -15,7 +14,7 @@ extern void longjmp(jmp_buf, int);
 
 #define UML_SETJMP(buf) ({				\
 	int n, enable;					\
-	enable = *(volatile int *)&signals_enabled;	\
+	enable = um_get_signals();			\
 	n = setjmp(*buf);				\
 	if(n != 0)					\
 		um_set_signals_trace(enable);		\

index b35cc8ce333b..324d4eed3385 100644
@@ -243,6 +243,7 @@ extern void send_sigio_to_self(void);
 extern int change_sig(int signal, int on);
 extern void block_signals(void);
 extern void unblock_signals(void);
+extern int um_get_signals(void);
 extern int um_set_signals(int enable);
 extern int um_set_signals_trace(int enable);
 extern void deliver_alarm(void);

index f2fb77da08cf..96314c31e61c 100644
@@ -6,8 +6,8 @@
 #include <linux/module.h>
 #include <os.h>
 
+EXPORT_SYMBOL(um_get_signals);
 EXPORT_SYMBOL(um_set_signals);
-EXPORT_SYMBOL(signals_enabled);
 
 EXPORT_SYMBOL(os_stat_fd);
 EXPORT_SYMBOL(os_stat_file);

index 217a71244b69..4f8c6b2b4888 100644
@@ -68,12 +68,12 @@ static void sig_handler_common(int sig, struct siginfo *si, mcontext_t *mc)
 #define SIGCHLD_BIT 2
 #define SIGCHLD_MASK (1 << SIGCHLD_BIT)
 
-int signals_enabled;
+static __thread int signals_enabled;
 #if IS_ENABLED(CONFIG_UML_TIME_TRAVEL_SUPPORT)
 static int signals_blocked, signals_blocked_pending;
 #endif
-static unsigned int signals_pending;
-static unsigned int signals_active = 0;
+static __thread unsigned int signals_pending;
+static __thread unsigned int signals_active;
 
 static void sig_handler(int sig, struct siginfo *si, mcontext_t *mc)
 {

@@ -345,6 +345,11 @@ void unblock_signals(void)
 	}
 }
 
+int um_get_signals(void)
+{
+	return signals_enabled;
+}
+
 int um_set_signals(int enable)
 {
 	int ret;

index 00ca3e12fd9a..3daaa5c4b35d 100644
@@ -55,6 +55,7 @@ extern int __uml_cant_sleep(void);
 extern int get_current_pid(void);
 extern int copy_from_user_proc(void *to, void *from, int size);
 extern char *uml_strdup(const char *string);
+int uml_need_resched(void);
 
 extern unsigned long to_irq_stack(unsigned long *mask_out);
 extern unsigned long from_irq_stack(int nested);

index 1be644de9e41..01b935c00454 100644
@@ -209,10 +209,13 @@ int arch_dup_task_struct(struct task_struct *dst,
 
 void um_idle_sleep(void)
 {
-	if (time_travel_mode != TT_MODE_OFF)
+	if (time_travel_mode != TT_MODE_OFF) {
 		time_travel_sleep();
-	else
+	} else {
+		raw_local_irq_enable();
 		os_idle_sleep();
+		raw_local_irq_disable();
+	}
 }
 
 void arch_cpu_idle(void)

@@ -225,6 +228,11 @@ int __uml_cant_sleep(void) {
 	/* Is in_interrupt() really needed? */
 }
 
+int uml_need_resched(void)
+{
+	return need_resched();
+}
+
 extern exitcall_t __uml_exitcall_begin, __uml_exitcall_end;
 
 void do_uml_exitcalls(void)

index 4d5591d96d8c..f25a4196bab7 100644
@@ -98,18 +98,17 @@ long long os_nsecs(void)
  */
 void os_idle_sleep(void)
 {
-	struct itimerspec its;
 	sigset_t set, old;
 
-	/* block SIGALRM while we analyze the timer state */
+	/* Block SIGALRM while performing the need_resched check. */
 	sigemptyset(&set);
 	sigaddset(&set, SIGALRM);
 	sigprocmask(SIG_BLOCK, &set, &old);
 
-	/* check the timer, and if it'll fire then wait for it */
-	timer_gettime(event_high_res_timer, &its);
-	if (its.it_value.tv_sec || its.it_value.tv_nsec)
+	/* Sleep if no resched is pending. */
+	if (!uml_need_resched())
 		sigsuspend(&old);
-	/* either way, restore the signal mask */
+
+	/* Restore the signal mask. */
 	sigprocmask(SIG_UNBLOCK, &set, NULL);
 }

index 138908b999d7..c274eb5ad55e 100644
@@ -90,4 +90,7 @@ extern unsigned long tt_extra_sched_jiffies;
  * which is intentional since we really shouldn't link it in that case.
  */
 void time_travel_ndelay(unsigned long nsec);
+
+int um_setup_timer(void);
+
 #endif /* __TIMER_INTERNAL_H__ */

index 324d4eed3385..0ca6e4548671 100644
@@ -269,9 +269,9 @@ extern void os_warn(const char *fmt, ...)
 /* time.c */
 extern void os_idle_sleep(void);
 extern int os_timer_create(void);
-extern int os_timer_set_interval(unsigned long long nsecs);
-extern int os_timer_one_shot(unsigned long long nsecs);
-extern void os_timer_disable(void);
+extern int os_timer_set_interval(int cpu, unsigned long long nsecs);
+extern int os_timer_one_shot(int cpu, unsigned long long nsecs);
+extern void os_timer_disable(int cpu);
 extern long long os_persistent_clock_emulation(void);
 extern long long os_nsecs(void);
 

index 0dfaf96bb7da..5ed8014e43e4 100644
@@ -683,7 +683,7 @@ void __init init_IRQ(void)
 {
 	int i;
 
-	irq_set_chip_and_handler(TIMER_IRQ, &alarm_irq_type, handle_edge_irq);
+	irq_set_chip_and_handler(TIMER_IRQ, &alarm_irq_type, handle_percpu_irq);
 
 	for (i = 1; i < UM_LAST_SIGNAL_IRQ; i++)
 		irq_set_chip_and_handler(i, &normal_irq_type, handle_edge_irq);

160 lines not on this page · raw message

index 3c63ce19e3bf..730723106228 100644
@@ -171,7 +171,7 @@ int __init main(int argc, char **argv, char **envp)
 	 */
 
 	/* stop timers and set timer signal to be ignored */
-	os_timer_disable();
+	os_timer_disable(0);
 
 	/* disable SIGIO for the fds and set SIGIO to be ignored */
 	err = deactivate_all_fds();

index f25a4196bab7..e38b6f84287b 100644
@@ -16,7 +16,7 @@
 #include <os.h>
 #include <string.h>
 
-static timer_t event_high_res_timer = 0;
+static timer_t event_high_res_timer[CONFIG_NR_CPUS] = { 0 };
 
 static inline long long timespec_to_ns(const struct timespec *ts)
 {

@@ -31,20 +31,30 @@ long long os_persistent_clock_emulation(void)
 	return timespec_to_ns(&realtime_tp);
 }
 
+#ifndef sigev_notify_thread_id
+#define sigev_notify_thread_id _sigev_un._tid
+#endif
+
 /**
  * os_timer_create() - create an new posix (interval) timer
  */
 int os_timer_create(void)
 {
-	timer_t *t = &event_high_res_timer;
+	timer_t *t = &event_high_res_timer[0];
+	struct sigevent sev = {
+		.sigev_notify = SIGEV_THREAD_ID,
+		.sigev_signo = SIGALRM,
+		.sigev_value.sival_ptr = t,
+		.sigev_notify_thread_id = gettid(),
+	};
 
-	if (timer_create(CLOCK_MONOTONIC, NULL, t) == -1)
+	if (timer_create(CLOCK_MONOTONIC, &sev, t) == -1)
 		return -1;
 
 	return 0;
 }
 
-int os_timer_set_interval(unsigned long long nsecs)
+int os_timer_set_interval(int cpu, unsigned long long nsecs)
 {
 	struct itimerspec its;
 

@@ -54,13 +64,13 @@ int os_timer_set_interval(unsigned long long nsecs)
 	its.it_interval.tv_sec = nsecs / UM_NSEC_PER_SEC;
 	its.it_interval.tv_nsec = nsecs % UM_NSEC_PER_SEC;
 
-	if (timer_settime(event_high_res_timer, 0, &its, NULL) == -1)
+	if (timer_settime(event_high_res_timer[cpu], 0, &its, NULL) == -1)
 		return -errno;
 
 	return 0;
 }
 
-int os_timer_one_shot(unsigned long long nsecs)
+int os_timer_one_shot(int cpu, unsigned long long nsecs)
 {
 	struct itimerspec its = {
 		.it_value.tv_sec = nsecs / UM_NSEC_PER_SEC,

@@ -70,19 +80,19 @@ int os_timer_one_shot(unsigned long long nsecs)
 		.it_interval.tv_nsec = 0, // we cheat here
 	};
 
-	timer_settime(event_high_res_timer, 0, &its, NULL);
+	timer_settime(event_high_res_timer[cpu], 0, &its, NULL);
 	return 0;
 }
 
 /**
  * os_timer_disable() - disable the posix (interval) timer
  */
-void os_timer_disable(void)
+void os_timer_disable(int cpu)
 {
 	struct itimerspec its;
 
 	memset(&its, 0, sizeof(struct itimerspec));
-	timer_settime(event_high_res_timer, 0, &its, NULL);
+	timer_settime(event_high_res_timer[cpu], 0, &its, NULL);
 }
 
 long long os_nsecs(void)

index 0ca6e4548671..ca377421181d 100644
@@ -155,7 +155,7 @@ extern int os_pread_file(int fd, void *buf, int len, unsigned long long offset);
 extern int os_pwrite_file(int fd, const void *buf, int count, unsigned long long offset);
 extern int os_file_modtime(const char *file, long long *modtime);
 extern int os_pipe(int *fd, int stream, int close_on_exec);
-extern int os_set_fd_async(int fd);
+extern int os_set_fd_async(int fd, int self);
 extern int os_clear_fd_async(int fd);
 extern int os_set_fd_block(int fd, int blocking);
 extern int os_accept_connection(int fd);

index 5ed8014e43e4..193b6374d890 100644
@@ -302,7 +302,7 @@ static int activate_fd(int irq, int fd, enum um_irq_type type, void *dev_id,
 	int err, events = os_event_mask(type);
 	unsigned long flags;
 
-	err = os_set_fd_async(fd);
+	err = os_set_fd_async(fd, 0);
 	if (err < 0)
 		goto out;
 

@@ -607,7 +607,7 @@ void um_irqs_resume(void)
 	raw_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);
+			int err = os_set_fd_async(entry->fd, 0);
 
 			WARN(err < 0, "os_set_fd_async returned %d\n", err);
 			entry->suspended = false;

index 617886d1fb1e..2544a0fc9fbb 100644
@@ -391,8 +391,12 @@ int os_pipe(int *fds, int stream, int close_on_exec)
 	return err;
 }
 
-int os_set_fd_async(int fd)
+int os_set_fd_async(int fd, int self)
 {
+	struct f_owner_ex owner = {
+		.type = F_OWNER_TID,
+		.pid = self ? gettid() : os_getpid(),
+	};
 	int err, flags;
 
 	flags = fcntl(fd, F_GETFL);

@@ -408,9 +412,9 @@ int os_set_fd_async(int fd)
 	}
 
 	if ((fcntl(fd, F_SETSIG, SIGIO) < 0) ||
-	    (fcntl(fd, F_SETOWN, os_getpid()) < 0)) {
+	    (fcntl(fd, F_SETOWN_EX, &owner) < 0)) {
 		err = -errno;
-		printk(UM_KERN_ERR "os_set_fd_async : Failed to fcntl F_SETOWN "
+		printk(UM_KERN_ERR "os_set_fd_async : Failed to fcntl F_SETOWN_EX "
 		       "(or F_SETSIG) fd %d, errno = %d\n", fd, errno);
 		return err;
 	}

index 8accc6d6f502..c563af70dcf2 100644
@@ -7,15 +7,16 @@
 
 #ifndef __ASSEMBLER__
 
+#include <asm/smp.h>
+
 struct task_struct;
 extern struct task_struct *cpu_tasks[NR_CPUS];
 
 static __always_inline struct task_struct *get_current(void)
 {
-	return cpu_tasks[0];
+	return cpu_tasks[raw_smp_processor_id()];
 }
 
-
 #define current get_current()
 
 #endif /* __ASSEMBLER__ */

index 52e2c36267a9..8de71752a9b8 100644
@@ -2,8 +2,30 @@
 #ifndef __ASM_UM_HARDIRQ_H
 #define __ASM_UM_HARDIRQ_H
 
-#include <asm-generic/hardirq.h>
+#include <linux/cache.h>
+#include <linux/threads.h>
 
 #define __ARCH_IRQ_EXIT_IRQS_DISABLED 1
 
+typedef struct {
+	unsigned int __softirq_pending;
+#if IS_ENABLED(CONFIG_SMP)
+	unsigned int irq_resched_count;
+	unsigned int irq_call_count;
+#endif
+} ____cacheline_aligned irq_cpustat_t;
+
+DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
+
+#define __ARCH_IRQ_STAT
+
+#define inc_irq_stat(member)	this_cpu_inc(irq_stat.member)
+
+#include <linux/irq.h>
+
+static inline void ack_bad_irq(unsigned int irq)
+{
+	pr_crit("unexpected IRQ trap at vector %02x\n", irq);
+}
+
 #endif /* __ASM_UM_HARDIRQ_H */

index 4d0e4239f3cc..07d48738b402 100644
@@ -7,16 +7,26 @@
 #define __ARCH_UM_MMU_H
 
 #include "linux/types.h"
+#include <linux/mutex.h>
+#include <linux/spinlock.h>
 #include <mm_id.h>
 
 typedef struct mm_context {
 	struct mm_id id;
+	struct mutex turnstile;
 
 	struct list_head list;
 
 	/* Address range in need of a TLB sync */
+	spinlock_t sync_tlb_lock;
 	unsigned long sync_tlb_range_from;
 	unsigned long sync_tlb_range_to;
 } mm_context_t;
 
+#define INIT_MM_CONTEXT(mm)						\
+	.context = {							\
+		.turnstile = __MUTEX_INITIALIZER(mm.context.turnstile),	\
+		.sync_tlb_lock = __SPIN_LOCK_INITIALIZER(mm.context.sync_tlb_lock), \
+	}
+
 #endif

new file mode 100644
index 000000000000..77e13a38f220
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_UM_PERCPU_H
+#define __ASM_UM_PERCPU_H
+
+#include <linux/threads.h>
+
+#if IS_ENABLED(CONFIG_SMP)
+
+#define __per_cpu_offset __per_cpu_offset
+#ifndef __ASSEMBLER__
+extern unsigned long __per_cpu_offset[NR_CPUS];
+#endif
+
+#define per_cpu_offset(x) (__per_cpu_offset[x])
+
+#endif /* CONFIG_SMP */
+
+#include <asm-generic/percpu.h>
+
+#endif /* __ASM_UM_PERCPU_H */

index 24fdea6f88c3..91aec3698475 100644
@@ -225,6 +225,8 @@ static inline void set_pte(pte_t *pteptr, pte_t pteval)
 static inline void um_tlb_mark_sync(struct mm_struct *mm, unsigned long start,
 				    unsigned long end)
 {
+	guard(spinlock_irqsave)(&mm->context.sync_tlb_lock);
+
 	if (!mm->context.sync_tlb_range_to) {
 		mm->context.sync_tlb_range_from = start;
 		mm->context.sync_tlb_range_to = end;

index 236fdfd7cdbe..0c4dd680f8bb 100644
@@ -81,6 +81,12 @@ struct cpuinfo_um {
 
 extern struct cpuinfo_um boot_cpu_data;
 
+#if IS_ENABLED(CONFIG_SMP)
+extern struct cpuinfo_um uml_cpu_data[];
+#else
+#define uml_cpu_data     (&boot_cpu_data)
+#endif
+
 #define cache_line_size()	(boot_cpu_data.cache_alignment)
 
 #define KSTK_REG(tsk, reg) get_thread_reg(reg, &tsk->thread.switch_buf)

index a8cc1d46ddcb..242ad4da5723 100644
@@ -2,6 +2,27 @@
 #ifndef __UM_SMP_H
 #define __UM_SMP_H
 
-#define hard_smp_processor_id()		0
+#if IS_ENABLED(CONFIG_SMP)
+
+#include <linux/bitops.h>
+#include <asm/current.h>
+#include <linux/cpumask.h>
+#include <shared/smp.h>
+
+#define raw_smp_processor_id() uml_curr_cpu()
+
+void arch_smp_send_reschedule(int cpu);
+
+void arch_send_call_function_single_ipi(int cpu);
+
+void arch_send_call_function_ipi_mask(const struct cpumask *mask);
+
+static inline void smp_cpus_done(unsigned int maxcpus) { }
+
+#else /* !CONFIG_SMP */
+
+#define raw_smp_processor_id() 0
+
+#endif /* CONFIG_SMP */
 
 #endif

new file mode 100644
index 000000000000..f2258443c316
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_UM_SPINLOCK_H
+#define __ASM_UM_SPINLOCK_H
+
+#include <asm/processor.h>
+#include <asm-generic/spinlock.h>
+
+#endif /* __ASM_UM_SPINLOCK_H */

new file mode 100644
index 000000000000..e7ad2b879cbb
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __UM_SMP_INTERNAL_H
+#define __UM_SMP_INTERNAL_H
+
+#if IS_ENABLED(CONFIG_SMP)
+
+int smp_sigio_handler(struct uml_pt_regs *regs);
+void prefill_possible_map(void);
+
+#else /* !CONFIG_SMP */
+
+static inline int smp_sigio_handler(struct uml_pt_regs *regs)
+{
+	return 0;
+}
+
+static inline void prefill_possible_map(void) { }
+
+#endif /* CONFIG_SMP */
+
+#endif /* __UM_SMP_INTERNAL_H */

index 3daaa5c4b35d..52db56400a06 100644
@@ -14,6 +14,7 @@ struct siginfo;
 extern int uml_exitcode;
 
 extern int kmalloc_ok;
+extern int disable_kmalloc[];
 
 #define UML_ROUND_UP(addr) \
 	((((unsigned long) addr) + PAGE_SIZE - 1) & PAGE_MASK)

index ca377421181d..e26655a7763e 100644
@@ -216,6 +216,8 @@ extern int can_drop_memory(void);
 
 void os_set_pdeathsig(void);
 
+int os_futex_wake(void *uaddr, unsigned int val);
+
 /* execvp.c */
 extern int execvp_noalloc(char *buf, const char *file, char *const argv[]);
 /* helper.c */

@@ -339,4 +341,8 @@ extern void um_trace_signals_off(void);
 /* time-travel */
 extern void deliver_time_travel_irqs(void);
 
+/* smp.c */
+int start_cpu_thread(int cpu);
+void start_idle_thread_secondary(void *arg, jmp_buf *switch_buf);
+
 #endif

index 4f977ef5dda5..bb9f8bd32ccb 100644
@@ -19,6 +19,9 @@ struct mm_id {
 	int syscall_fd_map[STUB_MAX_FDS];
 };
 
+void enter_turnstile(struct mm_id *mm_id);
+void exit_turnstile(struct mm_id *mm_id);
+
 void notify_mm_kill(int pid);
 
 #endif

new file mode 100644
index 000000000000..c1049835bd1d
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __UM_SHARED_SMP_H
+#define __UM_SHARED_SMP_H
+
+#if IS_ENABLED(CONFIG_SMP)
+
+extern int uml_ncpus;
+
+int uml_curr_cpu(void);
+void uml_start_idle(void *opaque);
+
+#else /* !CONFIG_SMP */
+
+#define uml_ncpus 1
+#define uml_curr_cpu() 0
+
+#endif /* CONFIG_SMP */
+
+#endif /* __UM_SHARED_SMP_H */

index 193b6374d890..c57cfbef6f2b 100644
@@ -20,8 +20,12 @@
 #include <os.h>
 #include <irq_user.h>
 #include <irq_kern.h>
+#include <linux/smp-internal.h>
 #include <linux/time-internal.h>
 
+DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
+
+#define irq_stats(x)		(&per_cpu(irq_stat, x))
 
 /* When epoll triggers we do not know why it did so
  * we can also have different IRQs for read and write.

@@ -205,6 +209,9 @@ static void _sigio_handler(struct uml_pt_regs *regs,
 	if (!irqs_suspended)
 		irq_do_pending_events(timetravel_handlers_only);
 
+	if (smp_sigio_handler(regs))
+		return;
+
 	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

@@ -696,3 +703,25 @@ void sigchld_handler(int sig, struct siginfo *unused_si,
 {
 	do_IRQ(SIGCHLD_IRQ, regs);
 }
+
+/*
+ * /proc/interrupts printing for arch specific interrupts
+ */
+int arch_show_interrupts(struct seq_file *p, int prec)
+{
+#if IS_ENABLED(CONFIG_SMP)
+	int cpu;
+
+	seq_printf(p, "%*s: ", prec, "RES");
+	for_each_online_cpu(cpu)
+		seq_printf(p, "%10u ", irq_stats(cpu)->irq_resched_count);
+	seq_puts(p, "  Rescheduling interrupts\n");
+
+	seq_printf(p, "%*s: ", prec, "CAL");
+	for_each_online_cpu(cpu)
+		seq_printf(p, "%10u ", irq_stats(cpu)->irq_call_count);
+	seq_puts(p, "  Function call interrupts\n");
+#endif
+
+	return 0;
+}

index 76bec7de81b5..8e7742140e93 100644
@@ -53,6 +53,8 @@ pgd_t swapper_pg_dir[PTRS_PER_PGD];
 /* Initialized at boot time, and readonly after that */
 int kmalloc_ok = 0;
 
+int disable_kmalloc[NR_CPUS] = { 0 };
+
 /* Used during early boot */
 static unsigned long brk_end;
 

index 01b935c00454..ec390f334853 100644
@@ -35,6 +35,7 @@
 #include <os.h>
 #include <skas.h>
 #include <registers.h>
+#include <linux/smp-internal.h>
 #include <linux/time-internal.h>
 #include <linux/elfcore.h>
 

@@ -185,11 +186,12 @@ int copy_thread(struct task_struct * p, const struct kernel_clone_args *args)
 
 void initial_thread_cb(void (*proc)(void *), void *arg)
 {
-	int save_kmalloc_ok = kmalloc_ok;
+	int cpu = raw_smp_processor_id();
+	int save_kmalloc = disable_kmalloc[cpu];
 
-	kmalloc_ok = 0;
+	disable_kmalloc[cpu] = 1;
 	initial_thread_cb_skas(proc, arg);
-	kmalloc_ok = save_kmalloc_ok;
+	disable_kmalloc[cpu] = save_kmalloc;
 }
 
 int arch_dup_task_struct(struct task_struct *dst,

index afe9a2f251ef..d3a71008f43e 100644
@@ -23,12 +23,30 @@ static_assert(sizeof(struct stub_data) == STUB_DATA_PAGES * UM_KERN_PAGE_SIZE);
 static spinlock_t mm_list_lock;
 static struct list_head mm_list;
 
+void enter_turnstile(struct mm_id *mm_id)
+{
+	struct mm_context *ctx = container_of(mm_id, struct mm_context, id);
+
+	mutex_lock(&ctx->turnstile);
+}
+
+void exit_turnstile(struct mm_id *mm_id)
+{
+	struct mm_context *ctx = container_of(mm_id, struct mm_context, id);
+
+	mutex_unlock(&ctx->turnstile);
+}
+
 int init_new_context(struct task_struct *task, struct mm_struct *mm)
 {
 	struct mm_id *new_id = &mm->context.id;
 	unsigned long stack = 0;
 	int ret = -ENOMEM;
 
+	mutex_init(&mm->context.turnstile);
+
+	spin_lock_init(&mm->context.sync_tlb_lock);
+
 	stack = __get_free_pages(GFP_KERNEL | __GFP_ZERO, ilog2(STUB_DATA_PAGES));
 	if (stack == 0)
 		goto out;

@@ -73,6 +91,9 @@ void destroy_context(struct mm_struct *mm)
 		return;
 	}
 
+	scoped_guard(spinlock_irqsave, &mm_list_lock)
+		list_del(&mm->context.list);
+
 	if (mmu->id.pid > 0) {
 		os_kill_ptraced_process(mmu->id.pid, 1);
 		mmu->id.pid = -1;

@@ -82,10 +103,6 @@ void destroy_context(struct mm_struct *mm)
 		os_close_file(mmu->id.sock);
 
 	free_pages(mmu->id.stack, ilog2(STUB_DATA_PAGES));
-
-	guard(spinlock_irqsave)(&mm_list_lock);
-
-	list_del(&mm->context.list);
 }
 
 static irqreturn_t mm_sigchld_irq(int irq, void* dev)

@@ -110,12 +127,11 @@ static irqreturn_t mm_sigchld_irq(int irq, void* dev)
 				/* Marks the MM as dead */
 				mm_context->id.pid = -1;
 
-				/*
-				 * NOTE: If SMP is implemented, a futex_wake
-				 * needs to be added here.
-				 */
 				stub_data = (void *)mm_context->id.stack;
 				stub_data->futex = FUTEX_IN_KERN;
+#if IS_ENABLED(CONFIG_SMP)
+				os_futex_wake(&stub_data->futex, 1);
+#endif
 
 				/*
 				 * NOTE: Currently executing syscalls by

266 lines not on this page · raw message

index cf7e0d4407f2..39608cccf2c6 100644
@@ -162,9 +162,11 @@ int um_tlb_sync(struct mm_struct *mm)
 {
 	pgd_t *pgd;
 	struct vm_ops ops;
-	unsigned long addr = mm->context.sync_tlb_range_from, next;
+	unsigned long addr, next;
 	int ret = 0;
 
+	guard(spinlock_irqsave)(&mm->context.sync_tlb_lock);
+
 	if (mm->context.sync_tlb_range_to == 0)
 		return 0;
 

@@ -177,6 +179,7 @@ int um_tlb_sync(struct mm_struct *mm)
 		ops.unmap = unmap;
 	}
 
+	addr = mm->context.sync_tlb_range_from;
 	pgd = pgd_offset(mm, addr);
 	do {
 		next = pgd_addr_end(addr, mm->context.sync_tlb_range_to);

index 5b80a3a89c20..177615820a4c 100644
@@ -316,7 +316,7 @@ 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 && init_mm.context.sync_tlb_range_to) {
+	if (!is_user && address >= start_vm && address < end_vm) {
 		/*
 		 * Kernel has pending updates from set_ptes that were not
 		 * flushed yet. Syncing them should fix the pagefault (if not

index 2f5ee045bc7a..a84fba9992f2 100644
@@ -19,6 +19,7 @@
 #include <linux/kmsg_dump.h>
 #include <linux/suspend.h>
 #include <linux/random.h>
+#include <linux/smp-internal.h>
 
 #include <asm/processor.h>
 #include <asm/cpufeature.h>

@@ -32,6 +33,7 @@
 #include <kern_util.h>
 #include <mem_user.h>
 #include <os.h>
+#include <smp.h>
 
 #include "um_arch.h"
 

@@ -74,6 +76,12 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 {
 	int i = 0;
 
+#if IS_ENABLED(CONFIG_SMP)
+	i = (struct cpuinfo_um *) v - uml_cpu_data;
+	if (!cpu_online(i))
+		return 0;
+#endif
+
 	seq_printf(m, "processor\t: %d\n", i);
 	seq_printf(m, "vendor_id\t: User Mode Linux\n");
 	seq_printf(m, "model name\t: UML\n");

@@ -90,13 +98,12 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		   loops_per_jiffy/(500000/HZ),
 		   (loops_per_jiffy/(5000/HZ)) % 100);
 
-
 	return 0;
 }
 
 static void *c_start(struct seq_file *m, loff_t *pos)
 {
-	return *pos < nr_cpu_ids ? &boot_cpu_data + *pos : NULL;
+	return *pos < nr_cpu_ids ? uml_cpu_data + *pos : NULL;
 }
 
 static void *c_next(struct seq_file *m, void *v, loff_t *pos)

@@ -426,6 +433,7 @@ void __init setup_arch(char **cmdline_p)
 	strscpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
 	*cmdline_p = command_line;
 	setup_hostinfo(host_info, sizeof host_info);
+	prefill_possible_map();
 
 	if (os_getrandom(rng_seed, sizeof(rng_seed), 0) == sizeof(rng_seed)) {
 		add_bootloader_randomness(rng_seed, sizeof(rng_seed));

@@ -460,6 +468,18 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
 {
 }
 
+#if IS_ENABLED(CONFIG_SMP)
+void alternatives_smp_module_add(struct module *mod, char *name,
+				 void *locks, void *locks_end,
+				 void *text,  void *text_end)
+{
+}
+
+void alternatives_smp_module_del(struct module *mod)
+{
+}
+#endif
+
 void *text_poke(void *addr, const void *opcode, size_t len)
 {
 	/*

index 730723106228..92028c14d2a3 100644
@@ -16,6 +16,7 @@
 #include <init.h>
 #include <kern_util.h>
 #include <os.h>
+#include <smp.h>
 #include <um_malloc.h>
 #include "internal.h"
 

@@ -207,7 +208,7 @@ void *__wrap_malloc(int size)
 {
 	void *ret;
 
-	if (!kmalloc_ok)
+	if (!kmalloc_ok || disable_kmalloc[uml_curr_cpu()])
 		return __real_malloc(size);
 	else if (size <= UM_KERN_PAGE_SIZE)
 		/* finding contiguous pages can be hard*/

index 00b49e90d05f..87aec6b5beeb 100644
@@ -10,6 +10,7 @@
 #include <errno.h>
 #include <signal.h>
 #include <fcntl.h>
+#include <linux/futex.h>
 #include <sys/mman.h>
 #include <sys/ptrace.h>
 #include <sys/prctl.h>

@@ -189,3 +190,12 @@ void os_set_pdeathsig(void)
 {
 	prctl(PR_SET_PDEATHSIG, SIGKILL);
 }
+
+int os_futex_wake(void *uaddr, unsigned int val)
+{
+	int r;
+
+	CATCH_EINTR(r = syscall(__NR_futex, uaddr, FUTEX_WAKE, val,
+				NULL, NULL, 0));
+	return r < 0 ? -errno : r;
+}

index 78f48fa9db8b..d3440a6c6616 100644
@@ -563,6 +563,13 @@ void userspace(struct uml_pt_regs *regs)
 	while (1) {
 		struct mm_id *mm_id = current_mm_id();
 
+		/*
+		 * At any given time, only one CPU thread can enter the
+		 * turnstile to operate on the same stub process, including
+		 * executing stub system calls (mmap and munmap).
+		 */
+		enter_turnstile(mm_id);
+
 		/*
 		 * When we are in time-travel mode, userspace can theoretically
 		 * do a *lot* of work without being scheduled. The problem with

@@ -740,6 +747,8 @@ void userspace(struct uml_pt_regs *regs)
 			}
 		}
 
+		exit_turnstile(mm_id);
+
 		UPT_SYSCALL_NR(regs) = -1; /* Assume: It's not a syscall */
 
 		if (sig) {

86 lines not on this page · raw message

index a827c2e01aa5..61c61e9c246c 100644
@@ -22,6 +22,7 @@
 #include <asm/unistd.h>
 #include <init.h>
 #include <os.h>
+#include <smp.h>
 #include <kern_util.h>
 #include <mem_user.h>
 #include <ptrace_user.h>

@@ -481,6 +482,9 @@ void __init os_early_checks(void)
 			fatal("SECCOMP userspace requested but not functional!\n");
 	}
 
+	if (uml_ncpus > 1)
+		fatal("SMP is not supported with PTRACE userspace.\n");
+
 	using_seccomp = 0;
 	check_ptrace();
 

index e38b6f84287b..ecf2fde01889 100644
@@ -14,6 +14,7 @@
 #include <sys/time.h>
 #include <kern_util.h>
 #include <os.h>
+#include <smp.h>
 #include <string.h>
 
 static timer_t event_high_res_timer[CONFIG_NR_CPUS] = { 0 };

@@ -40,7 +41,8 @@ long long os_persistent_clock_emulation(void)
  */
 int os_timer_create(void)
 {
-	timer_t *t = &event_high_res_timer[0];
+	int cpu = uml_curr_cpu();
+	timer_t *t = &event_high_res_timer[cpu];
 	struct sigevent sev = {
 		.sigev_notify = SIGEV_THREAD_ID,
 		.sigev_signo = SIGALRM,

@@ -110,9 +112,10 @@ void os_idle_sleep(void)
 {
 	sigset_t set, old;
 
-	/* Block SIGALRM while performing the need_resched check. */
+	/* Block SIGALRM and SIGIO while performing the need_resched check. */
 	sigemptyset(&set);
 	sigaddset(&set, SIGALRM);
+	sigaddset(&set, SIGIO);
 	sigprocmask(SIG_BLOCK, &set, &old);
 
 	/* Sleep if no resched is pending. */