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()
  ...

13 files changed, 146 insertions, 42 deletions

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);