* [PATCH v7 1/7] um: Add generic stub_syscall1 function
2024-07-04 16:27 [PATCH v7 0/7] Increased address space for 64 bit Benjamin Berg
@ 2024-07-04 16:27 ` Benjamin Berg
2024-07-04 16:27 ` [PATCH v7 2/7] um: use execveat to create userspace MMs Benjamin Berg
` (5 subsequent siblings)
6 siblings, 0 replies; 11+ messages in thread
From: Benjamin Berg @ 2024-07-04 16:27 UTC (permalink / raw)
To: linux-um; +Cc: Benjamin Berg
From: Benjamin Berg <benjamin.berg@intel.com>
The 64bit version did not have a stub_syscall1 function yet. Add it as
it will be useful to implement a static binary for stub loading.
Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
---
arch/x86/um/shared/sysdep/stub_64.h | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/arch/x86/um/shared/sysdep/stub_64.h b/arch/x86/um/shared/sysdep/stub_64.h
index 67f44284f1aa..8e4ff39dcade 100644
--- a/arch/x86/um/shared/sysdep/stub_64.h
+++ b/arch/x86/um/shared/sysdep/stub_64.h
@@ -28,6 +28,17 @@ static __always_inline long stub_syscall0(long syscall)
return ret;
}
+static __always_inline long stub_syscall1(long syscall, long arg1)
+{
+ long ret;
+
+ __asm__ volatile (__syscall
+ : "=a" (ret)
+ : "0" (syscall), "D" (arg1) : __syscall_clobber );
+
+ return ret;
+}
+
static __always_inline long stub_syscall2(long syscall, long arg1, long arg2)
{
long ret;
--
2.45.2
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH v7 2/7] um: use execveat to create userspace MMs
2024-07-04 16:27 [PATCH v7 0/7] Increased address space for 64 bit Benjamin Berg
2024-07-04 16:27 ` [PATCH v7 1/7] um: Add generic stub_syscall1 function Benjamin Berg
@ 2024-07-04 16:27 ` Benjamin Berg
2024-07-04 16:49 ` Johannes Berg
2024-07-04 16:27 ` [PATCH v7 3/7] um: Fix stub_start address calculation Benjamin Berg
` (4 subsequent siblings)
6 siblings, 1 reply; 11+ messages in thread
From: Benjamin Berg @ 2024-07-04 16:27 UTC (permalink / raw)
To: linux-um; +Cc: Benjamin Berg
From: Benjamin Berg <benjamin.berg@intel.com>
Using clone will not undo features that have been enabled by libc. An
example of this already happening is rseq, which could cause the kernel
to read/write memory of the userspace process. In the future the
standard library might also use mseal by default to protect itself,
which would also thwart our attempts at unmapping everything.
Solve all this by taking a step back and doing an execve into a tiny
static binary that sets up the minimal environment required for the
stub without using any standard library. That way we have a clean
execution environment that is fully under the control of UML.
Note that this changes things a bit as the FDs are not anymore shared
with the kernel. Instead, we explicitly share the FDs for the physical
memory and all existing iomem regions. Doing this is fine, as iomem
regions cannot be added at runtime.
Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
---
v7:
- Rename stub_elf to stub_exe
- Move into architecture independent directory
- Fix 32 bit issues
- Improve tempfile logic
- Other cleanups
v6:
- Apply fixes pointed out by Tiwei Bie
- Add temporary file fallback as memfd is not always supported
---
arch/um/include/shared/skas/stub-data.h | 11 ++
arch/um/kernel/skas/.gitignore | 2 +
arch/um/kernel/skas/Makefile | 33 ++++-
arch/um/kernel/skas/stub_exe.c | 86 +++++++++++
arch/um/kernel/skas/stub_exe_embed.S | 11 ++
arch/um/os-Linux/mem.c | 2 +-
arch/um/os-Linux/skas/process.c | 183 ++++++++++++++++--------
7 files changed, 269 insertions(+), 59 deletions(-)
create mode 100644 arch/um/kernel/skas/.gitignore
create mode 100644 arch/um/kernel/skas/stub_exe.c
create mode 100644 arch/um/kernel/skas/stub_exe_embed.S
diff --git a/arch/um/include/shared/skas/stub-data.h b/arch/um/include/shared/skas/stub-data.h
index 2b6b44759dfa..3fbdda727373 100644
--- a/arch/um/include/shared/skas/stub-data.h
+++ b/arch/um/include/shared/skas/stub-data.h
@@ -12,6 +12,17 @@
#include <as-layout.h>
#include <sysdep/tls.h>
+struct stub_init_data {
+ unsigned long stub_start;
+
+ int stub_code_fd;
+ unsigned long stub_code_offset;
+ int stub_data_fd;
+ unsigned long stub_data_offset;
+
+ unsigned long segv_handler;
+};
+
#define STUB_NEXT_SYSCALL(s) \
((struct stub_syscall *) (((unsigned long) s) + (s)->cmd_len))
diff --git a/arch/um/kernel/skas/.gitignore b/arch/um/kernel/skas/.gitignore
new file mode 100644
index 000000000000..c3409ced0f38
--- /dev/null
+++ b/arch/um/kernel/skas/.gitignore
@@ -0,0 +1,2 @@
+stub_exe
+stub_exe.dbg
diff --git a/arch/um/kernel/skas/Makefile b/arch/um/kernel/skas/Makefile
index 6f86d53e3d69..fbb61968055f 100644
--- a/arch/um/kernel/skas/Makefile
+++ b/arch/um/kernel/skas/Makefile
@@ -3,14 +3,43 @@
# Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
#
-obj-y := stub.o mmu.o process.o syscall.o uaccess.o
+obj-y := stub.o mmu.o process.o syscall.o uaccess.o \
+ stub_exe_embed.o
+
+# Stub executable
+
+stub_exe_objs-y := stub_exe.o
+
+stub_exe_objs := $(foreach F,$(stub_exe_objs-y),$(obj)/$F)
+
+# Object file containing the ELF executable
+$(obj)/stub_exe_embed.o: $(src)/stub_exe_embed.S $(obj)/stub_exe
+
+$(obj)/stub_exe.dbg: $(stub_exe_objs) FORCE
+ $(call if_changed,stub_exe)
+
+$(obj)/stub_exe: OBJCOPYFLAGS := -S
+$(obj)/stub_exe: $(obj)/stub_exe.dbg FORCE
+ $(call if_changed,objcopy)
+
+quiet_cmd_stub_exe = STUB_EXE $@
+ cmd_stub_exe = $(CC) -nostdlib -o $@ \
+ $(KBUILD_CFLAGS) $(STUB_EXE_LDFLAGS) \
+ $(filter %.o,$^)
+
+STUB_EXE_LDFLAGS = -n -static
+
+targets += stub_exe.dbg stub_exe $(stub_exe_objs-y)
+
+# end
# 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_stub.o := $(CFLAGS_NO_HARDENING)
-UNPROFILE_OBJS := stub.o
+CFLAGS_stub_exe.o := $(CFLAGS_NO_HARDENING)
+UNPROFILE_OBJS := stub.o stub_exe.o
KCOV_INSTRUMENT := n
include $(srctree)/arch/um/scripts/Makefile.rules
diff --git a/arch/um/kernel/skas/stub_exe.c b/arch/um/kernel/skas/stub_exe.c
new file mode 100644
index 000000000000..bec471aeda30
--- /dev/null
+++ b/arch/um/kernel/skas/stub_exe.c
@@ -0,0 +1,86 @@
+#include <sys/ptrace.h>
+#include <sys/prctl.h>
+#include <asm/unistd.h>
+#include <sysdep/stub.h>
+#include <stub-data.h>
+
+void _start(void);
+
+noinline static void real_init(void)
+{
+ struct stub_init_data init_data;
+ unsigned long res;
+ struct {
+ void *ss_sp;
+ int ss_flags;
+ size_t ss_size;
+ } stack;
+ struct {
+ void *sa_handler_;
+ unsigned long sa_flags;
+ void *sa_restorer;
+ unsigned long long sa_mask;
+ } sa = {};
+
+ /* set a nice name */
+ stub_syscall2(__NR_prctl, PR_SET_NAME, (unsigned long)"uml-userspace");
+
+ /* read information from STDIN and close it */
+ res = stub_syscall3(__NR_read, 0,
+ (unsigned long)&init_data, sizeof(init_data));
+ if (res != sizeof(init_data))
+ stub_syscall1(__NR_exit, 10);
+
+ stub_syscall1(__NR_close, 0);
+
+ /* map stub code + data */
+ res = stub_syscall6(STUB_MMAP_NR,
+ init_data.stub_start, UM_KERN_PAGE_SIZE,
+ PROT_READ | PROT_EXEC, MAP_FIXED | MAP_SHARED,
+ init_data.stub_code_fd, init_data.stub_code_offset);
+ if (res != init_data.stub_start)
+ stub_syscall1(__NR_exit, 11);
+
+ res = stub_syscall6(STUB_MMAP_NR,
+ init_data.stub_start + UM_KERN_PAGE_SIZE,
+ STUB_DATA_PAGES * UM_KERN_PAGE_SIZE,
+ PROT_READ | PROT_WRITE, MAP_FIXED | MAP_SHARED,
+ init_data.stub_data_fd, init_data.stub_data_offset);
+ if (res != init_data.stub_start + UM_KERN_PAGE_SIZE)
+ stub_syscall1(__NR_exit, 12);
+
+ /* setup signal stack inside stub data */
+ stack.ss_flags = 0;
+ stack.ss_size = STUB_DATA_PAGES * UM_KERN_PAGE_SIZE;
+ stack.ss_sp = (void *)init_data.stub_start + UM_KERN_PAGE_SIZE;
+ stub_syscall2(__NR_sigaltstack, (unsigned long)&stack, 0);
+
+ /* register SIGSEGV handler (SA_RESTORER, the handler never returns) */
+ sa.sa_flags = SA_ONSTACK | SA_NODEFER | SA_SIGINFO | 0x04000000;
+ sa.sa_handler_ = (void *) init_data.segv_handler;
+ sa.sa_restorer = NULL;
+ sa.sa_mask = 0L; /* No need to mask anything */
+ res = stub_syscall4(__NR_rt_sigaction, SIGSEGV, (unsigned long)&sa, 0,
+ sizeof(sa.sa_mask));
+ if (res != 0)
+ stub_syscall1(__NR_exit, 13);
+
+ stub_syscall4(__NR_ptrace, PTRACE_TRACEME, 0, 0, 0);
+
+ stub_syscall2(__NR_kill, stub_syscall0(__NR_getpid), SIGSTOP);
+
+ stub_syscall1(__NR_exit, 14);
+
+ __builtin_unreachable();
+}
+
+void _start(void)
+{
+ char *alloc;
+
+ /* Make enough space for the stub (including space for alignment) */
+ alloc = __builtin_alloca((1 + 2 * STUB_DATA_PAGES - 1) * UM_KERN_PAGE_SIZE);
+ asm volatile("" : "+r,m"(alloc) : : "memory");
+
+ real_init();
+}
diff --git a/arch/um/kernel/skas/stub_exe_embed.S b/arch/um/kernel/skas/stub_exe_embed.S
new file mode 100644
index 000000000000..6d8914fbe8f1
--- /dev/null
+++ b/arch/um/kernel/skas/stub_exe_embed.S
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/init.h>
+#include <linux/linkage.h>
+
+__INITDATA
+
+SYM_DATA_START(stub_exe_start)
+ .incbin "arch/um/kernel/skas/stub_exe"
+SYM_DATA_END_LABEL(stub_exe_start, SYM_L_GLOBAL, stub_exe_end)
+
+__FINIT
diff --git a/arch/um/os-Linux/mem.c b/arch/um/os-Linux/mem.c
index cf44d386f23c..857e3deab293 100644
--- a/arch/um/os-Linux/mem.c
+++ b/arch/um/os-Linux/mem.c
@@ -42,7 +42,7 @@ void kasan_map_memory(void *start, size_t len)
}
/* Set by make_tempfile() during early boot. */
-static char *tempdir = NULL;
+char *tempdir = NULL;
/* Check if dir is on tmpfs. Return 0 if yes, -1 if no or error. */
static int __init check_tmpfs(const char *dir)
diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c
index f7088345b3fc..aea1dbe48a92 100644
--- a/arch/um/os-Linux/skas/process.c
+++ b/arch/um/os-Linux/skas/process.c
@@ -10,8 +10,11 @@
#include <sched.h>
#include <errno.h>
#include <string.h>
+#include <fcntl.h>
+#include <mem_user.h>
#include <sys/mman.h>
#include <sys/wait.h>
+#include <sys/stat.h>
#include <asm/unistd.h>
#include <as-layout.h>
#include <init.h>
@@ -189,69 +192,137 @@ static void handle_trap(int pid, struct uml_pt_regs *regs)
extern char __syscall_stub_start[];
-/**
- * userspace_tramp() - userspace trampoline
- * @stack: pointer to the new userspace stack page
- *
- * The userspace trampoline is used to setup a new userspace process in start_userspace() after it was clone()'ed.
- * This function will run on a temporary stack page.
- * It ptrace()'es itself, then
- * Two pages are mapped into the userspace address space:
- * - STUB_CODE (with EXEC), which contains the skas stub code
- * - STUB_DATA (with R/W), which contains a data page that is used to transfer certain data between the UML userspace process and the UML kernel.
- * Also for the userspace process a SIGSEGV handler is installed to catch pagefaults in the userspace process.
- * And last the process stops itself to give control to the UML kernel for this userspace process.
- *
- * Return: Always zero, otherwise the current userspace process is ended with non null exit() call
- */
+static int stub_exe_fd;
+
static int userspace_tramp(void *stack)
{
- struct sigaction sa;
- void *addr;
- int fd;
+ char *const argv[] = { "uml-userspace", NULL };
+ int pipe_fds[2];
unsigned long long offset;
- unsigned long segv_handler = STUB_CODE +
- (unsigned long) stub_segv_handler -
- (unsigned long) __syscall_stub_start;
-
- ptrace(PTRACE_TRACEME, 0, 0, 0);
-
- signal(SIGTERM, SIG_DFL);
- signal(SIGWINCH, SIG_IGN);
-
- fd = phys_mapping(uml_to_phys(__syscall_stub_start), &offset);
- addr = mmap64((void *) STUB_CODE, UM_KERN_PAGE_SIZE,
- PROT_EXEC, MAP_FIXED | MAP_PRIVATE, fd, offset);
- if (addr == MAP_FAILED) {
- os_info("mapping mmap stub at 0x%lx failed, errno = %d\n",
- STUB_CODE, errno);
- exit(1);
+ struct stub_init_data init_data = {
+ .stub_start = STUB_START,
+ .segv_handler = STUB_CODE +
+ (unsigned long) stub_segv_handler -
+ (unsigned long) __syscall_stub_start,
+ };
+ struct iomem_region *iomem;
+ int ret;
+
+ init_data.stub_code_fd = phys_mapping(uml_to_phys(__syscall_stub_start),
+ &offset);
+ init_data.stub_code_offset = MMAP_OFFSET(offset);
+
+ init_data.stub_data_fd = phys_mapping(uml_to_phys(stack), &offset);
+ init_data.stub_data_offset = MMAP_OFFSET(offset);
+
+ /* Set CLOEXEC on all FDs and then unset on all memory related FDs */
+ close_range(0, ~0U, CLOSE_RANGE_CLOEXEC);
+
+ fcntl(init_data.stub_data_fd, F_SETFD, 0);
+ for (iomem = iomem_regions; iomem; iomem = iomem->next)
+ fcntl(iomem->fd, F_SETFD, 0);
+
+ /* Create a pipe for init_data (no CLOEXEC) and dup2 to STDIN */
+ if (pipe2(pipe_fds, 0))
+ exit(2);
+
+ close(0);
+ if (dup2(pipe_fds[0], 0) < 0) {
+ close(pipe_fds[0]);
+ close(pipe_fds[1]);
+ exit(3);
}
+ close(pipe_fds[0]);
+
+ /* Write init_data and close write side */
+ ret = write(pipe_fds[1], &init_data, sizeof(init_data));
+ close(pipe_fds[1]);
+
+ if (ret != sizeof(init_data))
+ exit(4);
+
+ execveat(stub_exe_fd, "", argv, NULL, AT_EMPTY_PATH);
- fd = phys_mapping(uml_to_phys(stack), &offset);
- addr = mmap((void *) STUB_DATA,
- STUB_DATA_PAGES * UM_KERN_PAGE_SIZE, PROT_READ | PROT_WRITE,
- MAP_FIXED | MAP_SHARED, fd, offset);
- if (addr == MAP_FAILED) {
- os_info("mapping segfault stack at 0x%lx failed, errno = %d\n",
- STUB_DATA, errno);
- exit(1);
+ exit(5);
+}
+
+extern char stub_exe_start[];
+extern char stub_exe_end[];
+
+extern char *tempdir;
+
+#define STUB_EXE_NAME_TEMPLATE "/uml-userspace-XXXXXX"
+
+#ifndef MFD_EXEC
+#define MFD_EXEC 0x0010U
+#endif
+
+static int __init init_stub_exe_fd(void)
+{
+ size_t len = 0;
+ char *tmpfile = NULL;
+ int res;
+
+ stub_exe_fd = memfd_create("uml-userspace",
+ MFD_EXEC | MFD_CLOEXEC | MFD_ALLOW_SEALING);
+
+ if (stub_exe_fd < 0) {
+ printk(UM_KERN_INFO "Could not create executable memfd, using temporary file!");
+
+ tmpfile = malloc(strlen(tempdir) +
+ strlen(STUB_EXE_NAME_TEMPLATE) + 1);
+ if (tmpfile == NULL)
+ panic("Failed to allocate memory for stub executable name");
+
+ strcpy(tmpfile, tempdir);
+ strcat(tmpfile, STUB_EXE_NAME_TEMPLATE);
+
+ stub_exe_fd = mkstemp(tmpfile);
+ if (stub_exe_fd < 0)
+ panic("Could not create temporary file for stub binary: %d",
+ errno);
}
- set_sigstack((void *) STUB_DATA, STUB_DATA_PAGES * UM_KERN_PAGE_SIZE);
- sigemptyset(&sa.sa_mask);
- sa.sa_flags = SA_ONSTACK | SA_NODEFER | SA_SIGINFO;
- sa.sa_sigaction = (void *) segv_handler;
- sa.sa_restorer = NULL;
- if (sigaction(SIGSEGV, &sa, NULL) < 0) {
- os_info("%s - setting SIGSEGV handler failed - errno = %d\n",
- __func__, errno);
- exit(1);
+ while (len < stub_exe_end - stub_exe_start) {
+ res = write(stub_exe_fd, stub_exe_start + len,
+ stub_exe_end - stub_exe_start - len);
+ if (res < 0) {
+ if (errno == EINTR)
+ continue;
+
+ if (tmpfile)
+ unlink(tmpfile);
+ panic("%s: Failed write to memfd: %d", __func__, errno);
+ }
+
+ len += res;
+ }
+
+ if (!tmpfile) {
+ fcntl(stub_exe_fd, F_ADD_SEALS,
+ F_SEAL_WRITE | F_SEAL_SHRINK | F_SEAL_GROW | F_SEAL_SEAL);
+ } else {
+ /* Only executable by us */
+ if (fchmod(stub_exe_fd, 00500) < 0) {
+ unlink(tmpfile);
+ panic("Could not make stub binary excutable: %d",
+ errno);
+ }
+
+ close(stub_exe_fd);
+ stub_exe_fd = open(tmpfile, O_RDONLY | O_CLOEXEC | O_NOFOLLOW);
+ if (stub_exe_fd < 0) {
+ unlink(tmpfile);
+ panic("Could not reopen stub binary: %d", errno);
+ }
+
+ unlink(tmpfile);
+ free(tmpfile);
}
- kill(os_getpid(), SIGSTOP);
return 0;
}
+__initcall(init_stub_exe_fd);
int userspace_pid[NR_CPUS];
@@ -270,7 +341,7 @@ int start_userspace(unsigned long stub_stack)
{
void *stack;
unsigned long sp;
- int pid, status, n, flags, err;
+ int pid, status, n, err;
/* setup a temporary stack page */
stack = mmap(NULL, UM_KERN_PAGE_SIZE,
@@ -286,10 +357,10 @@ int start_userspace(unsigned long stub_stack)
/* set stack pointer to the end of the stack page, so it can grow downwards */
sp = (unsigned long)stack + UM_KERN_PAGE_SIZE;
- flags = CLONE_FILES | SIGCHLD;
-
/* clone into new userspace process */
- pid = clone(userspace_tramp, (void *) sp, flags, (void *) stub_stack);
+ pid = clone(userspace_tramp, (void *) sp,
+ CLONE_VFORK | CLONE_VM | SIGCHLD,
+ (void *)stub_stack);
if (pid < 0) {
err = -errno;
printk(UM_KERN_ERR "%s : clone failed, errno = %d\n",
--
2.45.2
^ permalink raw reply related [flat|nested] 11+ messages in thread* Re: [PATCH v7 2/7] um: use execveat to create userspace MMs
2024-07-04 16:27 ` [PATCH v7 2/7] um: use execveat to create userspace MMs Benjamin Berg
@ 2024-07-04 16:49 ` Johannes Berg
2024-07-04 17:39 ` Benjamin Berg
0 siblings, 1 reply; 11+ messages in thread
From: Johannes Berg @ 2024-07-04 16:49 UTC (permalink / raw)
To: Benjamin Berg, linux-um; +Cc: Benjamin Berg
On Thu, 2024-07-04 at 18:27 +0200, Benjamin Berg wrote:
>
> + /* set a nice name */
> + stub_syscall2(__NR_prctl, PR_SET_NAME, (unsigned long)"uml-userspace");
Is that even needed when you're passing it as argv[0] in execve()? But
whatever, it's fine, just wondering.
> + /* setup signal stack inside stub data */
> + stack.ss_flags = 0;
> + stack.ss_size = STUB_DATA_PAGES * UM_KERN_PAGE_SIZE;
> + stack.ss_sp = (void *)init_data.stub_start + UM_KERN_PAGE_SIZE;
> + stub_syscall2(__NR_sigaltstack, (unsigned long)&stack, 0);
> +
> + /* register SIGSEGV handler (SA_RESTORER, the handler never returns) */
> + sa.sa_flags = SA_ONSTACK | SA_NODEFER | SA_SIGINFO | 0x04000000;
> + sa.sa_handler_ = (void *) init_data.segv_handler;
> + sa.sa_restorer = NULL;
> + sa.sa_mask = 0L; /* No need to mask anything */
most of that init could be in the initializer, except the dynamic ones
of course; the NULL/0 is also unnecessary I guess (though might want the
sa_mask for the comment)
> + struct stub_init_data init_data = {
> + .stub_start = STUB_START,
> + .segv_handler = STUB_CODE +
> + (unsigned long) stub_segv_handler -
> + (unsigned long) __syscall_stub_start,
> + };
> + struct iomem_region *iomem;
> + int ret;
> +
> + init_data.stub_code_fd = phys_mapping(uml_to_phys(__syscall_stub_start),
> + &offset);
> + init_data.stub_code_offset = MMAP_OFFSET(offset);
> +
> + init_data.stub_data_fd = phys_mapping(uml_to_phys(stack), &offset);
> + init_data.stub_data_offset = MMAP_OFFSET(offset);
also could move more here into the initializer
> +static int __init init_stub_exe_fd(void)
> +{
> + size_t len = 0;
maybe that should be called 'written'?
> + int res;
and I technically that should be ssize_t for the write() return value,
not that it'll be big enough to matter
> + while (len < stub_exe_end - stub_exe_start) {
> + res = write(stub_exe_fd, stub_exe_start + len,
> + stub_exe_end - stub_exe_start - len);
> + if (res < 0) {
> + if (errno == EINTR)
> + continue;
> +
> + if (tmpfile)
> + unlink(tmpfile);
> + panic("%s: Failed write to memfd: %d", __func__, errno);
nit: not always memfd now
> + if (!tmpfile) {
> + fcntl(stub_exe_fd, F_ADD_SEALS,
> + F_SEAL_WRITE | F_SEAL_SHRINK | F_SEAL_GROW | F_SEAL_SEAL);
> + } else {
> + /* Only executable by us */
> + if (fchmod(stub_exe_fd, 00500) < 0) {
now it's also readable, so comment doesn't seem right? maybe just remove
it?
> + unlink(tmpfile);
> + panic("Could not make stub binary excutable: %d",
> + errno);
perhaps print -errno?
> + }
> +
> + close(stub_exe_fd);
> + stub_exe_fd = open(tmpfile, O_RDONLY | O_CLOEXEC | O_NOFOLLOW);
> + if (stub_exe_fd < 0) {
> + unlink(tmpfile);
> + panic("Could not reopen stub binary: %d", errno);
same here
johannes
^ permalink raw reply [flat|nested] 11+ messages in thread* Re: [PATCH v7 2/7] um: use execveat to create userspace MMs
2024-07-04 16:49 ` Johannes Berg
@ 2024-07-04 17:39 ` Benjamin Berg
0 siblings, 0 replies; 11+ messages in thread
From: Benjamin Berg @ 2024-07-04 17:39 UTC (permalink / raw)
To: Johannes Berg, linux-um
On Thu, 2024-07-04 at 18:49 +0200, Johannes Berg wrote:
> On Thu, 2024-07-04 at 18:27 +0200, Benjamin Berg wrote:
> >
> > + /* set a nice name */
> > + stub_syscall2(__NR_prctl, PR_SET_NAME, (unsigned long)"uml-userspace");
>
> Is that even needed when you're passing it as argv[0] in execve()? But
> whatever, it's fine, just wondering.
It is needed. I added it because the argv[0] was not being used and I
ended up with a number as the process name.
Benjamin
> > + /* setup signal stack inside stub data */
> > + stack.ss_flags = 0;
> > + stack.ss_size = STUB_DATA_PAGES * UM_KERN_PAGE_SIZE;
> > + stack.ss_sp = (void *)init_data.stub_start + UM_KERN_PAGE_SIZE;
> > + stub_syscall2(__NR_sigaltstack, (unsigned long)&stack, 0);
> > +
> > + /* register SIGSEGV handler (SA_RESTORER, the handler never returns) */
> > + sa.sa_flags = SA_ONSTACK | SA_NODEFER | SA_SIGINFO | 0x04000000;
> > + sa.sa_handler_ = (void *) init_data.segv_handler;
> > + sa.sa_restorer = NULL;
> > + sa.sa_mask = 0L; /* No need to mask anything */
>
> most of that init could be in the initializer, except the dynamic ones
> of course; the NULL/0 is also unnecessary I guess (though might want the
> sa_mask for the comment)
>
> > + struct stub_init_data init_data = {
> > + .stub_start = STUB_START,
> > + .segv_handler = STUB_CODE +
> > + (unsigned long) stub_segv_handler -
> > + (unsigned long) __syscall_stub_start,
> > + };
> > + struct iomem_region *iomem;
> > + int ret;
> > +
> > + init_data.stub_code_fd = phys_mapping(uml_to_phys(__syscall_stub_start),
> > + &offset);
> > + init_data.stub_code_offset = MMAP_OFFSET(offset);
> > +
> > + init_data.stub_data_fd = phys_mapping(uml_to_phys(stack), &offset);
> > + init_data.stub_data_offset = MMAP_OFFSET(offset);
>
> also could move more here into the initializer
>
> > +static int __init init_stub_exe_fd(void)
> > +{
> > + size_t len = 0;
>
> maybe that should be called 'written'?
>
> > + int res;
>
> and I technically that should be ssize_t for the write() return value,
> not that it'll be big enough to matter
>
> > + while (len < stub_exe_end - stub_exe_start) {
> > + res = write(stub_exe_fd, stub_exe_start + len,
> > + stub_exe_end - stub_exe_start - len);
> > + if (res < 0) {
> > + if (errno == EINTR)
> > + continue;
> > +
> > + if (tmpfile)
> > + unlink(tmpfile);
> > + panic("%s: Failed write to memfd: %d", __func__, errno);
>
> nit: not always memfd now
>
> > + if (!tmpfile) {
> > + fcntl(stub_exe_fd, F_ADD_SEALS,
> > + F_SEAL_WRITE | F_SEAL_SHRINK | F_SEAL_GROW | F_SEAL_SEAL);
> > + } else {
> > + /* Only executable by us */
> > + if (fchmod(stub_exe_fd, 00500) < 0) {
>
> now it's also readable, so comment doesn't seem right? maybe just remove
> it?
>
> > + unlink(tmpfile);
> > + panic("Could not make stub binary excutable: %d",
> > + errno);
>
> perhaps print -errno?
>
> > + }
> > +
> > + close(stub_exe_fd);
> > + stub_exe_fd = open(tmpfile, O_RDONLY | O_CLOEXEC | O_NOFOLLOW);
> > + if (stub_exe_fd < 0) {
> > + unlink(tmpfile);
> > + panic("Could not reopen stub binary: %d", errno);
>
> same here
>
> johannes
>
^ permalink raw reply [flat|nested] 11+ messages in thread
* [PATCH v7 3/7] um: Fix stub_start address calculation
2024-07-04 16:27 [PATCH v7 0/7] Increased address space for 64 bit Benjamin Berg
2024-07-04 16:27 ` [PATCH v7 1/7] um: Add generic stub_syscall1 function Benjamin Berg
2024-07-04 16:27 ` [PATCH v7 2/7] um: use execveat to create userspace MMs Benjamin Berg
@ 2024-07-04 16:27 ` Benjamin Berg
2024-07-04 16:27 ` [PATCH v7 4/7] um: Limit TASK_SIZE to the addressable range Benjamin Berg
` (3 subsequent siblings)
6 siblings, 0 replies; 11+ messages in thread
From: Benjamin Berg @ 2024-07-04 16:27 UTC (permalink / raw)
To: linux-um; +Cc: Benjamin Berg
From: Benjamin Berg <benjamin.berg@intel.com>
The calculation was wrong as it only subtracted one and then rounded
down for alignment. However, this is incorrect if host_task_size is not
already aligned.
This probably worked fine because on 64 bit the host_task_size is bigger
than returned by os_get_top_address.
Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
---
arch/um/kernel/um_arch.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index 8e594cda6d77..25cd2c6d7e95 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -328,7 +328,8 @@ int __init linux_main(int argc, char **argv)
/* reserve a few pages for the stubs (taking care of data alignment) */
/* align the data portion */
BUILD_BUG_ON(!is_power_of_2(STUB_DATA_PAGES));
- stub_start = (host_task_size - 1) & ~(STUB_DATA_PAGES * PAGE_SIZE - 1);
+ stub_start = (host_task_size - STUB_DATA_PAGES * PAGE_SIZE) &
+ ~(STUB_DATA_PAGES * PAGE_SIZE - 1);
/* another page for the code portion */
stub_start -= PAGE_SIZE;
host_task_size = stub_start;
--
2.45.2
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH v7 4/7] um: Limit TASK_SIZE to the addressable range
2024-07-04 16:27 [PATCH v7 0/7] Increased address space for 64 bit Benjamin Berg
` (2 preceding siblings ...)
2024-07-04 16:27 ` [PATCH v7 3/7] um: Fix stub_start address calculation Benjamin Berg
@ 2024-07-04 16:27 ` Benjamin Berg
2024-07-04 16:27 ` [PATCH v7 5/7] um: Discover host_task_size from envp Benjamin Berg
` (2 subsequent siblings)
6 siblings, 0 replies; 11+ messages in thread
From: Benjamin Berg @ 2024-07-04 16:27 UTC (permalink / raw)
To: linux-um; +Cc: Benjamin Berg
From: Benjamin Berg <benjamin.berg@intel.com>
We may have a TASK_SIZE from the host that is bigger than UML is able to
address with a three-level pagetable. Guard against that by clipping the
maximum TASK_SIZE to the maximum addressable area.
Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
---
v7: Fix integer overflow on 32 bit with 3-level page tables
---
arch/um/kernel/um_arch.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index 25cd2c6d7e95..f82dd4e854f3 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -334,11 +334,16 @@ int __init linux_main(int argc, char **argv)
stub_start -= PAGE_SIZE;
host_task_size = stub_start;
+ /* Limit TASK_SIZE to what is addressable by the page table */
+ task_size = host_task_size;
+ if (task_size > (unsigned long long) PTRS_PER_PGD * PGDIR_SIZE)
+ task_size = PTRS_PER_PGD * PGDIR_SIZE;
+
/*
* TASK_SIZE needs to be PGDIR_SIZE aligned or else exit_mmap craps
* out
*/
- task_size = host_task_size & PGDIR_MASK;
+ task_size = task_size & PGDIR_MASK;
/* OS sanity checks that need to happen before the kernel runs */
os_early_checks();
--
2.45.2
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH v7 5/7] um: Discover host_task_size from envp
2024-07-04 16:27 [PATCH v7 0/7] Increased address space for 64 bit Benjamin Berg
` (3 preceding siblings ...)
2024-07-04 16:27 ` [PATCH v7 4/7] um: Limit TASK_SIZE to the addressable range Benjamin Berg
@ 2024-07-04 16:27 ` Benjamin Berg
2024-07-04 16:27 ` [PATCH v7 6/7] um: clear all memory in new userspace processes Benjamin Berg
2024-07-04 16:27 ` [PATCH v7 7/7] um: Add 4 level page table support Benjamin Berg
6 siblings, 0 replies; 11+ messages in thread
From: Benjamin Berg @ 2024-07-04 16:27 UTC (permalink / raw)
To: linux-um; +Cc: Benjamin Berg
From: Benjamin Berg <benjamin.berg@intel.com>
When loading the UML binary, the host kernel will place the stack at the
highest possible address. It will then map the program name and
environment variables onto the start of the stack.
As such, an easy way to figure out the host_task_size is to use the
highest pointer to an environment variable as a reference.
Ensure that this works by disabling address layout randomization and
re-executing UML in case it was enabled.
This increases the available TASK_SIZE for 64 bit UML considerably.
Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
---
v7: Also use the same logic on 32bit
---
arch/um/include/shared/as-layout.h | 2 +-
arch/um/include/shared/os.h | 2 +-
arch/um/kernel/um_arch.c | 4 +-
arch/um/os-Linux/main.c | 9 +-
arch/x86/um/os-Linux/task_size.c | 152 ++---------------------------
5 files changed, 22 insertions(+), 147 deletions(-)
diff --git a/arch/um/include/shared/as-layout.h b/arch/um/include/shared/as-layout.h
index 06292fca5a4d..b69cb8dcfeed 100644
--- a/arch/um/include/shared/as-layout.h
+++ b/arch/um/include/shared/as-layout.h
@@ -48,7 +48,7 @@ extern unsigned long brk_start;
extern unsigned long host_task_size;
extern unsigned long stub_start;
-extern int linux_main(int argc, char **argv);
+extern int linux_main(int argc, char **argv, char **envp);
extern void uml_finishsetup(void);
struct siginfo;
diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h
index 9a039d6f1f74..10c83fcde7b0 100644
--- a/arch/um/include/shared/os.h
+++ b/arch/um/include/shared/os.h
@@ -330,7 +330,7 @@ extern int __ignore_sigio_fd(int fd);
extern int get_pty(void);
/* sys-$ARCH/task_size.c */
-extern unsigned long os_get_top_address(void);
+extern unsigned long os_get_top_address(char **envp);
long syscall(long number, ...);
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index f82dd4e854f3..8ac2f9e39b3b 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -302,7 +302,7 @@ static void parse_cache_line(char *line)
}
}
-int __init linux_main(int argc, char **argv)
+int __init linux_main(int argc, char **argv, char **envp)
{
unsigned long avail, diff;
unsigned long virtmem_size, max_physmem;
@@ -324,7 +324,7 @@ int __init linux_main(int argc, char **argv)
if (have_console == 0)
add_arg(DEFAULT_COMMAND_LINE_CONSOLE);
- host_task_size = os_get_top_address();
+ host_task_size = os_get_top_address(envp);
/* reserve a few pages for the stubs (taking care of data alignment) */
/* align the data portion */
BUILD_BUG_ON(!is_power_of_2(STUB_DATA_PAGES));
diff --git a/arch/um/os-Linux/main.c b/arch/um/os-Linux/main.c
index f98ff79cdbf7..9a61b1767795 100644
--- a/arch/um/os-Linux/main.c
+++ b/arch/um/os-Linux/main.c
@@ -11,6 +11,7 @@
#include <signal.h>
#include <string.h>
#include <sys/resource.h>
+#include <sys/personality.h>
#include <as-layout.h>
#include <init.h>
#include <kern_util.h>
@@ -108,6 +109,12 @@ int __init main(int argc, char **argv, char **envp)
char **new_argv;
int ret, i, err;
+ /* Disable randomization and re-exec if it was changed successfully */
+ ret = personality(PER_LINUX | ADDR_NO_RANDOMIZE);
+ if (ret >= 0 && (ret & (PER_LINUX | ADDR_NO_RANDOMIZE)) !=
+ (PER_LINUX | ADDR_NO_RANDOMIZE))
+ execve("/proc/self/exe", argv, envp);
+
set_stklim();
setup_env_path();
@@ -140,7 +147,7 @@ int __init main(int argc, char **argv, char **envp)
#endif
change_sig(SIGPIPE, 0);
- ret = linux_main(argc, argv);
+ ret = linux_main(argc, argv, envp);
/*
* Disable SIGPROF - I have no idea why libc doesn't do this or turn
diff --git a/arch/x86/um/os-Linux/task_size.c b/arch/x86/um/os-Linux/task_size.c
index 1dc9adc20b1c..a91599799b1a 100644
--- a/arch/x86/um/os-Linux/task_size.c
+++ b/arch/x86/um/os-Linux/task_size.c
@@ -1,151 +1,19 @@
// SPDX-License-Identifier: GPL-2.0
-#include <stdio.h>
-#include <stdlib.h>
-#include <signal.h>
-#include <sys/mman.h>
-#include <longjmp.h>
-#ifdef __i386__
-
-static jmp_buf buf;
-
-static void segfault(int sig)
-{
- longjmp(buf, 1);
-}
-
-static int page_ok(unsigned long page)
-{
- unsigned long *address = (unsigned long *) (page << UM_KERN_PAGE_SHIFT);
- unsigned long n = ~0UL;
- void *mapped = NULL;
- int ok = 0;
-
- /*
- * First see if the page is readable. If it is, it may still
- * be a VDSO, so we go on to see if it's writable. If not
- * then try mapping memory there. If that fails, then we're
- * still in the kernel area. As a sanity check, we'll fail if
- * the mmap succeeds, but gives us an address different from
- * what we wanted.
- */
- if (setjmp(buf) == 0)
- n = *address;
- else {
- mapped = mmap(address, UM_KERN_PAGE_SIZE,
- PROT_READ | PROT_WRITE,
- MAP_FIXED | MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
- if (mapped == MAP_FAILED)
- return 0;
- if (mapped != address)
- goto out;
- }
-
- /*
- * Now, is it writeable? If so, then we're in user address
- * space. If not, then try mprotecting it and try the write
- * again.
- */
- if (setjmp(buf) == 0) {
- *address = n;
- ok = 1;
- goto out;
- } else if (mprotect(address, UM_KERN_PAGE_SIZE,
- PROT_READ | PROT_WRITE) != 0)
- goto out;
-
- if (setjmp(buf) == 0) {
- *address = n;
- ok = 1;
- }
-
- out:
- if (mapped != NULL)
- munmap(mapped, UM_KERN_PAGE_SIZE);
- return ok;
-}
-
-unsigned long os_get_top_address(void)
+unsigned long os_get_top_address(char **envp)
{
- struct sigaction sa, old;
- unsigned long bottom = 0;
- /*
- * A 32-bit UML on a 64-bit host gets confused about the VDSO at
- * 0xffffe000. It is mapped, is readable, can be reprotected writeable
- * and written. However, exec discovers later that it can't be
- * unmapped. So, just set the highest address to be checked to just
- * below it. This might waste some address space on 4G/4G 32-bit
- * hosts, but shouldn't hurt otherwise.
- */
- unsigned long top = 0xffffd000 >> UM_KERN_PAGE_SHIFT;
- unsigned long test, original;
+ unsigned long top_addr = (unsigned long) &top_addr;
+ int i;
- printf("Locating the bottom of the address space ... ");
- fflush(stdout);
-
- /*
- * We're going to be longjmping out of the signal handler, so
- * SA_DEFER needs to be set.
- */
- sa.sa_handler = segfault;
- sigemptyset(&sa.sa_mask);
- sa.sa_flags = SA_NODEFER;
- if (sigaction(SIGSEGV, &sa, &old)) {
- perror("os_get_top_address");
- exit(1);
- }
-
- /* Manually scan the address space, bottom-up, until we find
- * the first valid page (or run out of them).
- */
- for (bottom = 0; bottom < top; bottom++) {
- if (page_ok(bottom))
- break;
- }
-
- /* If we've got this far, we ran out of pages. */
- if (bottom == top) {
- fprintf(stderr, "Unable to determine bottom of address "
- "space.\n");
- exit(1);
- }
-
- printf("0x%lx\n", bottom << UM_KERN_PAGE_SHIFT);
- printf("Locating the top of the address space ... ");
- fflush(stdout);
-
- original = bottom;
-
- /* This could happen with a 4G/4G split */
- if (page_ok(top))
- goto out;
-
- do {
- test = bottom + (top - bottom) / 2;
- if (page_ok(test))
- bottom = test;
- else
- top = test;
- } while (top - bottom > 1);
-
-out:
- /* Restore the old SIGSEGV handling */
- if (sigaction(SIGSEGV, &old, NULL)) {
- perror("os_get_top_address");
- exit(1);
+ /* The earliest variable should be after the program name in ELF */
+ for (i = 0; envp[i]; i++) {
+ if ((unsigned long) envp[i] > top_addr)
+ top_addr = (unsigned long) envp[i];
}
- top <<= UM_KERN_PAGE_SHIFT;
- printf("0x%lx\n", top);
- return top;
-}
-
-#else
+ top_addr &= ~(UM_KERN_PAGE_SIZE - 1);
+ top_addr += UM_KERN_PAGE_SIZE;
-unsigned long os_get_top_address(void)
-{
- /* The old value of CONFIG_TOP_ADDR */
- return 0x7fc0002000;
+ return top_addr;
}
-#endif
--
2.45.2
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH v7 6/7] um: clear all memory in new userspace processes
2024-07-04 16:27 [PATCH v7 0/7] Increased address space for 64 bit Benjamin Berg
` (4 preceding siblings ...)
2024-07-04 16:27 ` [PATCH v7 5/7] um: Discover host_task_size from envp Benjamin Berg
@ 2024-07-04 16:27 ` Benjamin Berg
2024-07-04 16:50 ` Johannes Berg
2024-07-04 16:27 ` [PATCH v7 7/7] um: Add 4 level page table support Benjamin Berg
6 siblings, 1 reply; 11+ messages in thread
From: Benjamin Berg @ 2024-07-04 16:27 UTC (permalink / raw)
To: linux-um; +Cc: Benjamin Berg
From: Benjamin Berg <benjamin.berg@intel.com>
With the change to use execve() we can now safely clear the memory up to
STUB_START as rseq will not be trying to use memory in that region. Also,
on 64 bit the previous changes should mean that there is no usable
memory range above the stub.
Make the change and remove the comment as it is not needed anymore.
---
arch/um/kernel/skas/mmu.c | 25 ++-----------------------
1 file changed, 2 insertions(+), 23 deletions(-)
diff --git a/arch/um/kernel/skas/mmu.c b/arch/um/kernel/skas/mmu.c
index 47f98d87ea3c..bf64702d9e04 100644
--- a/arch/um/kernel/skas/mmu.c
+++ b/arch/um/kernel/skas/mmu.c
@@ -40,29 +40,8 @@ int init_new_context(struct task_struct *task, struct mm_struct *mm)
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);
+ /* Ensure the new MM is clean and nothing unwanted is mapped */
+ unmap(new_id, 0, STUB_START);
return 0;
--
2.45.2
^ permalink raw reply related [flat|nested] 11+ messages in thread* [PATCH v7 7/7] um: Add 4 level page table support
2024-07-04 16:27 [PATCH v7 0/7] Increased address space for 64 bit Benjamin Berg
` (5 preceding siblings ...)
2024-07-04 16:27 ` [PATCH v7 6/7] um: clear all memory in new userspace processes Benjamin Berg
@ 2024-07-04 16:27 ` Benjamin Berg
6 siblings, 0 replies; 11+ messages in thread
From: Benjamin Berg @ 2024-07-04 16:27 UTC (permalink / raw)
To: linux-um; +Cc: Benjamin Berg
From: Benjamin Berg <benjamin.berg@intel.com>
The larger memory space is useful to support more applications inside
UML. One example for this is ASAN instrumentation of userspace
applications which requires addresses that would otherwise not be
available.
Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
---
v7:
- Reword options and fix documentation of x86-64 default
v2:
- Do not hide option behind the EXPERT flag
- Fix typo in new "Two-level pagetables" option
---
arch/um/Kconfig | 1 +
arch/um/include/asm/page.h | 14 +++-
arch/um/include/asm/pgalloc.h | 11 ++-
arch/um/include/asm/pgtable-4level.h | 119 +++++++++++++++++++++++++++
arch/um/include/asm/pgtable.h | 6 +-
arch/um/kernel/mem.c | 17 +++-
arch/x86/um/Kconfig | 38 ++++++---
7 files changed, 189 insertions(+), 17 deletions(-)
create mode 100644 arch/um/include/asm/pgtable-4level.h
diff --git a/arch/um/Kconfig b/arch/um/Kconfig
index dca84fd6d00a..7f93609ad63d 100644
--- a/arch/um/Kconfig
+++ b/arch/um/Kconfig
@@ -210,6 +210,7 @@ config MMAPPER
config PGTABLE_LEVELS
int
+ default 4 if 4_LEVEL_PGTABLES
default 3 if 3_LEVEL_PGTABLES
default 2
diff --git a/arch/um/include/asm/page.h b/arch/um/include/asm/page.h
index 9ef9a8aedfa6..c3b2ae03b60c 100644
--- a/arch/um/include/asm/page.h
+++ b/arch/um/include/asm/page.h
@@ -57,14 +57,22 @@ typedef unsigned long long phys_t;
typedef struct { unsigned long pte; } pte_t;
typedef struct { unsigned long pgd; } pgd_t;
-#ifdef CONFIG_3_LEVEL_PGTABLES
+#if CONFIG_PGTABLE_LEVELS > 2
+
typedef struct { unsigned long pmd; } pmd_t;
#define pmd_val(x) ((x).pmd)
#define __pmd(x) ((pmd_t) { (x) } )
-#endif
-#define pte_val(x) ((x).pte)
+#if CONFIG_PGTABLE_LEVELS > 3
+typedef struct { unsigned long pud; } pud_t;
+#define pud_val(x) ((x).pud)
+#define __pud(x) ((pud_t) { (x) } )
+
+#endif /* CONFIG_PGTABLE_LEVELS > 3 */
+#endif /* CONFIG_PGTABLE_LEVELS > 2 */
+
+#define pte_val(x) ((x).pte)
#define pte_get_bits(p, bits) ((p).pte & (bits))
#define pte_set_bits(p, bits) ((p).pte |= (bits))
diff --git a/arch/um/include/asm/pgalloc.h b/arch/um/include/asm/pgalloc.h
index de5e31c64793..04fb4e6969a4 100644
--- a/arch/um/include/asm/pgalloc.h
+++ b/arch/um/include/asm/pgalloc.h
@@ -31,7 +31,7 @@ do { \
tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte))); \
} while (0)
-#ifdef CONFIG_3_LEVEL_PGTABLES
+#if CONFIG_PGTABLE_LEVELS > 2
#define __pmd_free_tlb(tlb, pmd, address) \
do { \
@@ -39,6 +39,15 @@ do { \
tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(pmd)); \
} while (0)
+#if CONFIG_PGTABLE_LEVELS > 3
+
+#define __pud_free_tlb(tlb, pud, address) \
+do { \
+ pagetable_pud_dtor(virt_to_ptdesc(pud)); \
+ tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(pud)); \
+} while (0)
+
+#endif
#endif
#endif
diff --git a/arch/um/include/asm/pgtable-4level.h b/arch/um/include/asm/pgtable-4level.h
new file mode 100644
index 000000000000..f912fcc16b7a
--- /dev/null
+++ b/arch/um/include/asm/pgtable-4level.h
@@ -0,0 +1,119 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2003 PathScale Inc
+ * Derived from include/asm-i386/pgtable.h
+ */
+
+#ifndef __UM_PGTABLE_4LEVEL_H
+#define __UM_PGTABLE_4LEVEL_H
+
+#include <asm-generic/pgtable-nop4d.h>
+
+/* PGDIR_SHIFT determines what a fourth-level page table entry can map */
+
+#define PGDIR_SHIFT 39
+#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
+#define PGDIR_MASK (~(PGDIR_SIZE-1))
+
+/* PUD_SHIFT determines the size of the area a third-level page table can
+ * map
+ */
+
+#define PUD_SHIFT 30
+#define PUD_SIZE (1UL << PUD_SHIFT)
+#define PUD_MASK (~(PUD_SIZE-1))
+
+/* PMD_SHIFT determines the size of the area a second-level page table can
+ * map
+ */
+
+#define PMD_SHIFT 21
+#define PMD_SIZE (1UL << PMD_SHIFT)
+#define PMD_MASK (~(PMD_SIZE-1))
+
+/*
+ * entries per page directory level
+ */
+
+#define PTRS_PER_PTE 512
+#define PTRS_PER_PMD 512
+#define PTRS_PER_PUD 512
+#define PTRS_PER_PGD 512
+
+#define USER_PTRS_PER_PGD ((TASK_SIZE + (PGDIR_SIZE - 1)) / PGDIR_SIZE)
+
+#define pte_ERROR(e) \
+ printk("%s:%d: bad pte %p(%016lx).\n", __FILE__, __LINE__, &(e), \
+ pte_val(e))
+#define pmd_ERROR(e) \
+ printk("%s:%d: bad pmd %p(%016lx).\n", __FILE__, __LINE__, &(e), \
+ pmd_val(e))
+#define pud_ERROR(e) \
+ printk("%s:%d: bad pud %p(%016lx).\n", __FILE__, __LINE__, &(e), \
+ pud_val(e))
+#define pgd_ERROR(e) \
+ printk("%s:%d: bad pgd %p(%016lx).\n", __FILE__, __LINE__, &(e), \
+ pgd_val(e))
+
+#define pud_none(x) (!(pud_val(x) & ~_PAGE_NEWPAGE))
+#define pud_bad(x) ((pud_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
+#define pud_present(x) (pud_val(x) & _PAGE_PRESENT)
+#define pud_populate(mm, pud, pmd) \
+ set_pud(pud, __pud(_PAGE_TABLE + __pa(pmd)))
+
+#define set_pud(pudptr, pudval) (*(pudptr) = (pudval))
+
+#define p4d_none(x) (!(p4d_val(x) & ~_PAGE_NEWPAGE))
+#define p4d_bad(x) ((p4d_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
+#define p4d_present(x) (p4d_val(x) & _PAGE_PRESENT)
+#define p4d_populate(mm, p4d, pud) \
+ set_p4d(p4d, __p4d(_PAGE_TABLE + __pa(pud)))
+
+#define set_p4d(p4dptr, p4dval) (*(p4dptr) = (p4dval))
+
+
+static inline int pgd_newpage(pgd_t pgd)
+{
+ return(pgd_val(pgd) & _PAGE_NEWPAGE);
+}
+
+static inline void pgd_mkuptodate(pgd_t pgd) { pgd_val(pgd) &= ~_PAGE_NEWPAGE; }
+
+#define set_pmd(pmdptr, pmdval) (*(pmdptr) = (pmdval))
+
+static inline void pud_clear (pud_t *pud)
+{
+ set_pud(pud, __pud(_PAGE_NEWPAGE));
+}
+
+static inline void p4d_clear (p4d_t *p4d)
+{
+ set_p4d(p4d, __p4d(_PAGE_NEWPAGE));
+}
+
+#define pud_page(pud) phys_to_page(pud_val(pud) & PAGE_MASK)
+#define pud_pgtable(pud) ((pmd_t *) __va(pud_val(pud) & PAGE_MASK))
+
+#define p4d_page(p4d) phys_to_page(p4d_val(p4d) & PAGE_MASK)
+#define p4d_pgtable(p4d) ((pud_t *) __va(p4d_val(p4d) & PAGE_MASK))
+
+static inline unsigned long pte_pfn(pte_t pte)
+{
+ return phys_to_pfn(pte_val(pte));
+}
+
+static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
+{
+ pte_t pte;
+ phys_t phys = pfn_to_phys(page_nr);
+
+ pte_set_val(pte, phys, pgprot);
+ return pte;
+}
+
+static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
+{
+ return __pmd((page_nr << PAGE_SHIFT) | pgprot_val(pgprot));
+}
+
+#endif
diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h
index 5bb397b65efb..9ab3e34e8100 100644
--- a/arch/um/include/asm/pgtable.h
+++ b/arch/um/include/asm/pgtable.h
@@ -24,9 +24,11 @@
/* We borrow bit 10 to store the exclusive marker in swap PTEs. */
#define _PAGE_SWP_EXCLUSIVE 0x400
-#ifdef CONFIG_3_LEVEL_PGTABLES
+#if CONFIG_PGTABLE_LEVELS == 4
+#include <asm/pgtable-4level.h>
+#elif CONFIG_PGTABLE_LEVELS == 3
#include <asm/pgtable-3level.h>
-#else
+#elif CONFIG_PGTABLE_LEVELS == 2
#include <asm/pgtable-2level.h>
#endif
diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c
index a5b4fe2ad931..e7c262265c31 100644
--- a/arch/um/kernel/mem.c
+++ b/arch/um/kernel/mem.c
@@ -98,7 +98,7 @@ static void __init one_page_table_init(pmd_t *pmd)
static void __init one_md_table_init(pud_t *pud)
{
-#ifdef CONFIG_3_LEVEL_PGTABLES
+#if CONFIG_PGTABLE_LEVELS > 2
pmd_t *pmd_table = (pmd_t *) memblock_alloc_low(PAGE_SIZE, PAGE_SIZE);
if (!pmd_table)
panic("%s: Failed to allocate %lu bytes align=%lx\n",
@@ -109,6 +109,19 @@ static void __init one_md_table_init(pud_t *pud)
#endif
}
+static void __init one_ud_table_init(p4d_t *p4d)
+{
+#if CONFIG_PGTABLE_LEVELS > 3
+ pud_t *pud_table = (pud_t *) memblock_alloc_low(PAGE_SIZE, PAGE_SIZE);
+ if (!pud_table)
+ panic("%s: Failed to allocate %lu bytes align=%lx\n",
+ __func__, PAGE_SIZE, PAGE_SIZE);
+
+ set_p4d(p4d, __p4d(_KERNPG_TABLE + (unsigned long) __pa(pud_table)));
+ BUG_ON(pud_table != pud_offset(p4d, 0));
+#endif
+}
+
static void __init fixrange_init(unsigned long start, unsigned long end,
pgd_t *pgd_base)
{
@@ -126,6 +139,8 @@ static void __init fixrange_init(unsigned long start, unsigned long end,
for ( ; (i < PTRS_PER_PGD) && (vaddr < end); pgd++, i++) {
p4d = p4d_offset(pgd, vaddr);
+ if (p4d_none(*p4d))
+ one_ud_table_init(p4d);
pud = pud_offset(p4d, vaddr);
if (pud_none(*pud))
one_md_table_init(pud);
diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig
index 186f13268401..f7a527ad704c 100644
--- a/arch/x86/um/Kconfig
+++ b/arch/x86/um/Kconfig
@@ -28,16 +28,34 @@ config X86_64
def_bool 64BIT
select MODULES_USE_ELF_RELA
-config 3_LEVEL_PGTABLES
- bool "Three-level pagetables" if !64BIT
- default 64BIT
- help
- Three-level pagetables will let UML have more than 4G of physical
- memory. All the memory that can't be mapped directly will be treated
- as high memory.
-
- However, this it experimental on 32-bit architectures, so if unsure say
- N (on x86-64 it's automatically enabled, instead, as it's safe there).
+choice
+ prompt "Pagetable levels"
+ default 2_LEVEL_PGTABLES if !64BIT
+ default 4_LEVEL_PGTABLES if 64BIT
+
+ config 2_LEVEL_PGTABLES
+ bool "Two-level pagetables" if !64BIT
+ depends on !64BIT
+ help
+ Two-level page table for 32-bit architectures.
+
+ config 3_LEVEL_PGTABLES
+ bool "Three-level pagetables" if 64BIT || (!64BIT && EXPERT)
+ help
+ Three-level pagetables will let UML have more than 4G of
+ physical memory. All the memory that can't be mapped
+ directly will be treated as high memory.
+
+ However, this it experimental on 32-bit architectures, so if
+ unsure say N
+
+ config 4_LEVEL_PGTABLES
+ bool "Four-level pagetables" if 64BIT
+ depends on 64BIT
+ help
+ Four-level pagetables, results in a bigger address space
+ which can be useful for some applications (e.g. ASAN).
+endchoice
config ARCH_HAS_SC_SIGNALS
def_bool !64BIT
--
2.45.2
^ permalink raw reply related [flat|nested] 11+ messages in thread