[PATCH v7 5/7] um: Discover host_task_size from envp

[Benjamin Berg <benjamin@sipsolutions.net>]

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