um: Delay flushing syscalls until the thread is restarted

As running the syscalls is expensive due to context switches, we should
do so as late as possible in case more syscalls need to be queued later
on. This will also benefit a later move to a SECCOMP enabled userspace
as in that case the need for extra context switches is removed entirely.

Signed-off-by: Benjamin Berg <benjamin@sipsolutions.net>
Link: https://patch.msgid.link/20240703134536.1161108-9-benjamin@sipsolutions.net
Signed-off-by: Johannes Berg <johannes.berg@intel.com>

arch/um/include/shared/os.h

@@ -195,6 +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);
@@ -274,6 +277,7 @@ extern long long os_nsecs(void);
 /* skas/mem.c */
 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);
 
 void map(struct mm_id *mm_idp, unsigned long virt,
 	 unsigned long len, int prot, int phys_fd,

arch/um/include/shared/skas/mm_id.h

@@ -12,7 +12,6 @@ struct mm_id {
 		int pid;
 	} u;
 	unsigned long stack;
-	int kill;
 	int syscall_data_len;
 };
 

arch/um/include/shared/skas/skas.h

@@ -15,5 +15,6 @@ 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);
 
 #endif

arch/um/kernel/skas/process.c

@@ -50,3 +50,11 @@ 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 &current->mm->context.id;
+}

arch/um/kernel/tlb.c

@@ -53,7 +53,7 @@ struct host_vm_change {
 	   .index	= 0, \
 	   .force	= force })
 
-static void report_enomem(void)
+void report_enomem(void)
 {
 	printk(KERN_ERR "UML ran out of memory on the host side! "
 			"This can happen due to a memory limitation or "
@@ -338,15 +338,6 @@ static void fix_range_common(struct mm_struct *mm, unsigned long start_addr,
 
 	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 = &current->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)
@@ -461,7 +452,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long address)
 	pmd_t *pmd;
 	pte_t *pte;
 	struct mm_struct *mm = vma->vm_mm;
-	int r, w, x, prot, err = 0;
+	int r, w, x, prot;
 	struct mm_id *mm_id;
 
 	address &= PAGE_MASK;
@@ -509,14 +500,6 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long address)
 	} else if (pte_newprot(*pte))
 		protect(mm_id, address, PAGE_SIZE, prot);
 
-	err = syscall_stub_flush(mm_id);
-	if (err) {
-		if (err == -ENOMEM)
-			report_enomem();
-
-		goto kill;
-	}
-
 	*pte = pte_mkuptodate(*pte);
 
 	return;

arch/um/os-Linux/skas/mem.c

@@ -22,6 +22,29 @@
 
 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)
 {
@@ -82,26 +105,9 @@ static inline long do_syscall_stub(struct mm_id *mm_idp)
 	 * otherwise it will be zero (but we do not need to rely on that).
 	 */
 	if (proc_data->err < 0) {
-		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);
+		syscall_stub_dump_error(mm_idp);
 
+		/* 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;

arch/um/os-Linux/skas/process.c

@@ -254,7 +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
@@ -348,8 +347,16 @@ void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs)
 	while (1) {
 		time_travel_print_bc_msg();
 
-		if (kill_userspace_mm[0])
+		/* 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
@@ -580,5 +587,4 @@ 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;
 }