summaryrefslogtreecommitdiff
path: root/arch/um/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/um/kernel')
-rw-r--r--arch/um/kernel/dtb.c1
-rw-r--r--arch/um/kernel/dyn.lds.S5
-rw-r--r--arch/um/kernel/initrd.c1
-rw-r--r--arch/um/kernel/irq.c112
-rw-r--r--arch/um/kernel/mem.c20
-rw-r--r--arch/um/kernel/physmem.c39
-rw-r--r--arch/um/kernel/process.c24
-rw-r--r--arch/um/kernel/skas/.gitignore2
-rw-r--r--arch/um/kernel/skas/Makefile38
-rw-r--r--arch/um/kernel/skas/mmu.c28
-rw-r--r--arch/um/kernel/skas/process.c4
-rw-r--r--arch/um/kernel/skas/stub.c10
-rw-r--r--arch/um/kernel/skas/stub_exe.c95
-rw-r--r--arch/um/kernel/skas/stub_exe_embed.S11
-rw-r--r--arch/um/kernel/sysrq.c8
-rw-r--r--arch/um/kernel/time.c20
-rw-r--r--arch/um/kernel/tlb.c74
-rw-r--r--arch/um/kernel/trap.c16
-rw-r--r--arch/um/kernel/um_arch.c75
-rw-r--r--arch/um/kernel/uml.lds.S2
20 files changed, 289 insertions, 296 deletions
diff --git a/arch/um/kernel/dtb.c b/arch/um/kernel/dtb.c
index 8d78ced9e08f..15c342426489 100644
--- a/arch/um/kernel/dtb.c
+++ b/arch/um/kernel/dtb.c
@@ -31,6 +31,7 @@ void uml_dtb_init(void)
static int __init uml_dtb_setup(char *line, int *add)
{
+ *add = 0;
dtb = line;
return 0;
}
diff --git a/arch/um/kernel/dyn.lds.S b/arch/um/kernel/dyn.lds.S
index 3385d653ebd0..a36b7918a011 100644
--- a/arch/um/kernel/dyn.lds.S
+++ b/arch/um/kernel/dyn.lds.S
@@ -116,8 +116,6 @@ SECTIONS
.fini_array : { *(.fini_array) }
.data : {
INIT_TASK_DATA(KERNEL_STACK_SIZE)
- . = ALIGN(KERNEL_STACK_SIZE);
- *(.data..init_irqstack)
DATA_DATA
*(.data.* .gnu.linkonce.d.*)
SORT(CONSTRUCTORS)
@@ -178,3 +176,6 @@ SECTIONS
DISCARDS
}
+
+ASSERT(__syscall_stub_end - __syscall_stub_start <= PAGE_SIZE,
+ "STUB code must not be larger than one page");
diff --git a/arch/um/kernel/initrd.c b/arch/um/kernel/initrd.c
index 47b8cb1a1156..99dba827461c 100644
--- a/arch/um/kernel/initrd.c
+++ b/arch/um/kernel/initrd.c
@@ -34,6 +34,7 @@ int __init read_initrd(void)
static int __init uml_initrd_setup(char *line, int *add)
{
+ *add = 0;
initrd = line;
return 0;
}
diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c
index 534e91797f89..338450741aac 100644
--- a/arch/um/kernel/irq.c
+++ b/arch/um/kernel/irq.c
@@ -674,115 +674,3 @@ void __init init_IRQ(void)
/* Initialize EPOLL Loop */
os_setup_epoll();
}
-
-/*
- * IRQ stack entry and exit:
- *
- * Unlike i386, UML doesn't receive IRQs on the normal kernel stack
- * and switch over to the IRQ stack after some preparation. We use
- * sigaltstack to receive signals on a separate stack from the start.
- * These two functions make sure the rest of the kernel won't be too
- * upset by being on a different stack. The IRQ stack has a
- * thread_info structure at the bottom so that current et al continue
- * to work.
- *
- * to_irq_stack copies the current task's thread_info to the IRQ stack
- * thread_info and sets the tasks's stack to point to the IRQ stack.
- *
- * from_irq_stack copies the thread_info struct back (flags may have
- * been modified) and resets the task's stack pointer.
- *
- * Tricky bits -
- *
- * What happens when two signals race each other? UML doesn't block
- * signals with sigprocmask, SA_DEFER, or sa_mask, so a second signal
- * could arrive while a previous one is still setting up the
- * thread_info.
- *
- * There are three cases -
- * The first interrupt on the stack - sets up the thread_info and
- * handles the interrupt
- * A nested interrupt interrupting the copying of the thread_info -
- * can't handle the interrupt, as the stack is in an unknown state
- * A nested interrupt not interrupting the copying of the
- * thread_info - doesn't do any setup, just handles the interrupt
- *
- * The first job is to figure out whether we interrupted stack setup.
- * This is done by xchging the signal mask with thread_info->pending.
- * If the value that comes back is zero, then there is no setup in
- * progress, and the interrupt can be handled. If the value is
- * non-zero, then there is stack setup in progress. In order to have
- * the interrupt handled, we leave our signal in the mask, and it will
- * be handled by the upper handler after it has set up the stack.
- *
- * Next is to figure out whether we are the outer handler or a nested
- * one. As part of setting up the stack, thread_info->real_thread is
- * set to non-NULL (and is reset to NULL on exit). This is the
- * nesting indicator. If it is non-NULL, then the stack is already
- * set up and the handler can run.
- */
-
-static unsigned long pending_mask;
-
-unsigned long to_irq_stack(unsigned long *mask_out)
-{
- struct thread_info *ti;
- unsigned long mask, old;
- int nested;
-
- mask = xchg(&pending_mask, *mask_out);
- if (mask != 0) {
- /*
- * If any interrupts come in at this point, we want to
- * make sure that their bits aren't lost by our
- * putting our bit in. So, this loop accumulates bits
- * until xchg returns the same value that we put in.
- * When that happens, there were no new interrupts,
- * and pending_mask contains a bit for each interrupt
- * that came in.
- */
- old = *mask_out;
- do {
- old |= mask;
- mask = xchg(&pending_mask, old);
- } while (mask != old);
- return 1;
- }
-
- ti = current_thread_info();
- nested = (ti->real_thread != NULL);
- if (!nested) {
- struct task_struct *task;
- struct thread_info *tti;
-
- task = cpu_tasks[ti->cpu].task;
- tti = task_thread_info(task);
-
- *ti = *tti;
- ti->real_thread = tti;
- task->stack = ti;
- }
-
- mask = xchg(&pending_mask, 0);
- *mask_out |= mask | nested;
- return 0;
-}
-
-unsigned long from_irq_stack(int nested)
-{
- struct thread_info *ti, *to;
- unsigned long mask;
-
- ti = current_thread_info();
-
- pending_mask = 1;
-
- to = ti->real_thread;
- current->stack = to;
- ti->real_thread = NULL;
- *to = *ti;
-
- mask = xchg(&pending_mask, 0);
- return mask & ~1;
-}
-
diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c
index a5b4fe2ad931..53248ed04771 100644
--- a/arch/um/kernel/mem.c
+++ b/arch/um/kernel/mem.c
@@ -6,7 +6,6 @@
#include <linux/stddef.h>
#include <linux/module.h>
#include <linux/memblock.h>
-#include <linux/highmem.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/slab.h>
@@ -51,8 +50,6 @@ EXPORT_SYMBOL(empty_zero_page);
pgd_t swapper_pg_dir[PTRS_PER_PGD];
/* Initialized at boot time, and readonly after that */
-unsigned long long highmem;
-EXPORT_SYMBOL(highmem);
int kmalloc_ok = 0;
/* Used during early boot */
@@ -98,7 +95,7 @@ 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 +106,19 @@ 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 +136,8 @@ 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/um/kernel/physmem.c b/arch/um/kernel/physmem.c
index fb2adfb49945..a74f17b033c4 100644
--- a/arch/um/kernel/physmem.c
+++ b/arch/um/kernel/physmem.c
@@ -22,19 +22,14 @@ static int physmem_fd = -1;
unsigned long high_physmem;
EXPORT_SYMBOL(high_physmem);
-extern unsigned long long physmem_size;
-
-void __init mem_total_pages(unsigned long physmem, unsigned long iomem,
- unsigned long highmem)
+void __init mem_total_pages(unsigned long physmem, unsigned long iomem)
{
- unsigned long phys_pages, highmem_pages;
- unsigned long iomem_pages, total_pages;
+ unsigned long phys_pages, iomem_pages, total_pages;
- phys_pages = physmem >> PAGE_SHIFT;
- iomem_pages = iomem >> PAGE_SHIFT;
- highmem_pages = highmem >> PAGE_SHIFT;
+ phys_pages = physmem >> PAGE_SHIFT;
+ iomem_pages = iomem >> PAGE_SHIFT;
- total_pages = phys_pages + iomem_pages + highmem_pages;
+ total_pages = phys_pages + iomem_pages;
max_mapnr = total_pages;
}
@@ -64,13 +59,12 @@ void map_memory(unsigned long virt, unsigned long phys, unsigned long len,
* @reserve_end: end address of the physical kernel memory.
* @len: Length of total physical memory that should be mapped/made
* available, in bytes.
- * @highmem: Number of highmem bytes that should be mapped/made available.
*
- * Creates an unlinked temporary file of size (len + highmem) and memory maps
+ * Creates an unlinked temporary file of size (len) and memory maps
* it on the last executable image address (uml_reserved).
*
* The offset is needed as the length of the total physical memory
- * (len + highmem) includes the size of the memory used be the executable image,
+ * (len) includes the size of the memory used be the executable image,
* but the mapped-to address is the last address of the executable image
* (uml_reserved == end address of executable image).
*
@@ -78,24 +72,24 @@ void map_memory(unsigned long virt, unsigned long phys, unsigned long len,
* of all user space processes/kernel tasks.
*/
void __init setup_physmem(unsigned long start, unsigned long reserve_end,
- unsigned long len, unsigned long long highmem)
+ unsigned long len)
{
unsigned long reserve = reserve_end - start;
- long map_size = len - reserve;
+ unsigned long map_size = len - reserve;
int err;
- if(map_size <= 0) {
+ if (len <= reserve) {
os_warn("Too few physical memory! Needed=%lu, given=%lu\n",
reserve, len);
exit(1);
}
- physmem_fd = create_mem_file(len + highmem);
+ physmem_fd = create_mem_file(len);
err = os_map_memory((void *) reserve_end, physmem_fd, reserve,
map_size, 1, 1, 1);
if (err < 0) {
- os_warn("setup_physmem - mapping %ld bytes of memory at 0x%p "
+ os_warn("setup_physmem - mapping %lu bytes of memory at 0x%p "
"failed - errno = %d\n", map_size,
(void *) reserve_end, err);
exit(1);
@@ -107,9 +101,8 @@ void __init setup_physmem(unsigned long start, unsigned long reserve_end,
*/
os_seek_file(physmem_fd, __pa(__syscall_stub_start));
os_write_file(physmem_fd, __syscall_stub_start, PAGE_SIZE);
- os_fsync_file(physmem_fd);
- memblock_add(__pa(start), len + highmem);
+ memblock_add(__pa(start), len);
memblock_reserve(__pa(start), reserve);
min_low_pfn = PFN_UP(__pa(reserve_end));
@@ -137,10 +130,6 @@ int phys_mapping(unsigned long phys, unsigned long long *offset_out)
region = region->next;
}
}
- else if (phys < __pa(end_iomem) + highmem) {
- fd = physmem_fd;
- *offset_out = phys - iomem_size;
- }
return fd;
}
@@ -149,6 +138,8 @@ EXPORT_SYMBOL(phys_mapping);
static int __init uml_mem_setup(char *line, int *add)
{
char *retptr;
+
+ *add = 0;
physmem_size = memparse(line,&retptr);
return 0;
}
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index be2856af6d4c..30bdc0a87dc8 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -43,7 +43,8 @@
* cares about its entry, so it's OK if another processor is modifying its
* entry.
*/
-struct cpu_task cpu_tasks[NR_CPUS] = { [0 ... NR_CPUS - 1] = { NULL } };
+struct task_struct *cpu_tasks[NR_CPUS];
+EXPORT_SYMBOL(cpu_tasks);
void free_stack(unsigned long stack, int order)
{
@@ -64,7 +65,7 @@ unsigned long alloc_stack(int order, int atomic)
static inline void set_current(struct task_struct *task)
{
- cpu_tasks[task_thread_info(task)->cpu] = ((struct cpu_task) { task });
+ cpu_tasks[task_thread_info(task)->cpu] = task;
}
struct task_struct *__switch_to(struct task_struct *from, struct task_struct *to)
@@ -116,7 +117,7 @@ void new_thread_handler(void)
* callback returns only if the kernel thread execs a process
*/
fn(arg);
- userspace(&current->thread.regs.regs, current_thread_info()->aux_fp_regs);
+ userspace(&current->thread.regs.regs);
}
/* Called magically, see new_thread_handler above */
@@ -133,7 +134,7 @@ static void fork_handler(void)
current->thread.prev_sched = NULL;
- userspace(&current->thread.regs.regs, current_thread_info()->aux_fp_regs);
+ userspace(&current->thread.regs.regs);
}
int copy_thread(struct task_struct * p, const struct kernel_clone_args *args)
@@ -187,6 +188,13 @@ void initial_thread_cb(void (*proc)(void *), void *arg)
kmalloc_ok = save_kmalloc_ok;
}
+int arch_dup_task_struct(struct task_struct *dst,
+ struct task_struct *src)
+{
+ memcpy(dst, src, arch_task_struct_size);
+ return 0;
+}
+
void um_idle_sleep(void)
{
if (time_travel_mode != TT_MODE_OFF)
@@ -287,11 +295,3 @@ unsigned long __get_wchan(struct task_struct *p)
return 0;
}
-
-int elf_core_copy_task_fpregs(struct task_struct *t, elf_fpregset_t *fpu)
-{
- int cpu = current_thread_info()->cpu;
-
- return save_i387_registers(userspace_pid[cpu], (unsigned long *) fpu);
-}
-
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..3384be42691f 100644
--- a/arch/um/kernel/skas/Makefile
+++ b/arch/um/kernel/skas/Makefile
@@ -3,14 +3,48 @@
# 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 $@ \
+ $(filter-out $(UM_GPROF_OPT) $(UM_GCOV_OPT),$(KBUILD_CFLAGS)) $(STUB_EXE_LDFLAGS) \
+ $(filter %.o,$^)
+
+STUB_EXE_LDFLAGS = -Wl,-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)
+
+# Clang will call memset() from __builtin_alloca() when stack variable
+# initialization is enabled, which is used in stub_exe.c.
+CFLAGS_stub_exe.o += $(call cc-option, -ftrivial-auto-var-init=uninitialized)
+
+UNPROFILE_OBJS := stub.o stub_exe.o
KCOV_INSTRUMENT := n
include $(srctree)/arch/um/scripts/Makefile.rules
diff --git a/arch/um/kernel/skas/mmu.c b/arch/um/kernel/skas/mmu.c
index 886ed5e65674..0eb5a1d3ba70 100644
--- a/arch/um/kernel/skas/mmu.c
+++ b/arch/um/kernel/skas/mmu.c
@@ -40,35 +40,13 @@ 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;
out_free:
- if (new_id->stack != 0)
- free_pages(new_id->stack, ilog2(STUB_DATA_PAGES));
+ free_pages(new_id->stack, ilog2(STUB_DATA_PAGES));
out:
return ret;
}
diff --git a/arch/um/kernel/skas/process.c b/arch/um/kernel/skas/process.c
index 68657988c8d1..05dcdc057af9 100644
--- a/arch/um/kernel/skas/process.c
+++ b/arch/um/kernel/skas/process.c
@@ -22,15 +22,13 @@ static int __init start_kernel_proc(void *unused)
{
block_signals_trace();
- cpu_tasks[0].task = current;
-
start_kernel();
return 0;
}
extern int userspace_pid[];
-extern char cpu0_irqstack[];
+static char cpu0_irqstack[THREAD_SIZE] __aligned(THREAD_SIZE);
int __init start_uml(void)
{
diff --git a/arch/um/kernel/skas/stub.c b/arch/um/kernel/skas/stub.c
index 5d52ffa682dc..796fc266d3bb 100644
--- a/arch/um/kernel/skas/stub.c
+++ b/arch/um/kernel/skas/stub.c
@@ -35,16 +35,6 @@ static __always_inline int syscall_handler(struct stub_data *d)
return -1;
}
break;
- case STUB_SYSCALL_MPROTECT:
- res = stub_syscall3(__NR_mprotect,
- sc->mem.addr, sc->mem.length,
- sc->mem.prot);
- if (res) {
- d->err = res;
- d->syscall_data_len = i;
- return -1;
- }
- break;
default:
d->err = -95; /* EOPNOTSUPP */
d->syscall_data_len = i;
diff --git a/arch/um/kernel/skas/stub_exe.c b/arch/um/kernel/skas/stub_exe.c
new file mode 100644
index 000000000000..23c99b285e82
--- /dev/null
+++ b/arch/um/kernel/skas/stub_exe.c
@@ -0,0 +1,95 @@
+#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 = {
+ .ss_size = STUB_DATA_PAGES * UM_KERN_PAGE_SIZE,
+ };
+ struct {
+ void *sa_handler_;
+ unsigned long sa_flags;
+ void *sa_restorer;
+ unsigned long long sa_mask;
+ } sa = {
+ /* Need to set SA_RESTORER (but the handler never returns) */
+ .sa_flags = SA_ONSTACK | SA_NODEFER | SA_SIGINFO | 0x04000000,
+ /* no need to mask any signals */
+ .sa_mask = 0,
+ };
+
+ /* set a nice name */
+ stub_syscall2(__NR_prctl, PR_SET_NAME, (unsigned long)"uml-userspace");
+
+ /* Make sure this process dies if the kernel dies */
+ stub_syscall2(__NR_prctl, PR_SET_PDEATHSIG, SIGKILL);
+
+ /* 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_sp = (void *)init_data.stub_start + UM_KERN_PAGE_SIZE;
+ stub_syscall2(__NR_sigaltstack, (unsigned long)&stack, 0);
+
+ /* register SIGSEGV handler */
+ sa.sa_handler_ = (void *) init_data.segv_handler;
+ 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();
+}
+
+__attribute__((naked)) void _start(void)
+{
+ /*
+ * Since the stack after exec() starts at the top-most address,
+ * but that's exactly where we also want to map the stub data
+ * and code, this must:
+ * - push the stack by 1 code and STUB_DATA_PAGES data pages
+ * - call real_init()
+ * This way, real_init() can use the stack normally, while the
+ * original stack further down (higher address) will become
+ * inaccessible after the mmap() calls above.
+ */
+ stub_start(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/kernel/sysrq.c b/arch/um/kernel/sysrq.c
index 4bb8622dc512..13ee5666668d 100644
--- a/arch/um/kernel/sysrq.c
+++ b/arch/um/kernel/sysrq.c
@@ -32,12 +32,6 @@ void show_stack(struct task_struct *task, unsigned long *stack,
struct pt_regs *segv_regs = current->thread.segv_regs;
int i;
- if (!segv_regs && os_is_signal_stack()) {
- pr_err("Received SIGSEGV in SIGSEGV handler,"
- " aborting stack trace!\n");
- return;
- }
-
if (!stack)
stack = get_stack_pointer(task, segv_regs);
@@ -52,5 +46,5 @@ void show_stack(struct task_struct *task, unsigned long *stack,
}
printk("%sCall Trace:\n", loglvl);
- dump_trace(current, &stackops, (void *)loglvl);
+ dump_trace(task ?: current, &stackops, (void *)loglvl);
}
diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c
index 29b27b90581f..1394568c0210 100644
--- a/arch/um/kernel/time.c
+++ b/arch/um/kernel/time.c
@@ -25,6 +25,8 @@
#include <shared/init.h>
#ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT
+#include <linux/sched/clock.h>
+
enum time_travel_mode time_travel_mode;
EXPORT_SYMBOL_GPL(time_travel_mode);
@@ -47,6 +49,15 @@ static u16 time_travel_shm_id;
static struct um_timetravel_schedshm *time_travel_shm;
static union um_timetravel_schedshm_client *time_travel_shm_client;
+unsigned long tt_extra_sched_jiffies;
+
+notrace unsigned long long sched_clock(void)
+{
+ return (unsigned long long)(jiffies - INITIAL_JIFFIES +
+ tt_extra_sched_jiffies)
+ * (NSEC_PER_SEC / HZ);
+}
+
static void time_travel_set_time(unsigned long long ns)
{
if (unlikely(ns < time_travel_time))
@@ -443,6 +454,11 @@ static void time_travel_periodic_timer(struct time_travel_event *e)
{
time_travel_add_event(&time_travel_timer_event,
time_travel_time + time_travel_timer_interval);
+
+ /* clock tick; decrease extra jiffies by keeping sched_clock constant */
+ if (tt_extra_sched_jiffies > 0)
+ tt_extra_sched_jiffies -= 1;
+
deliver_alarm();
}
@@ -594,6 +610,10 @@ EXPORT_SYMBOL_GPL(time_travel_add_irq_event);
static void time_travel_oneshot_timer(struct time_travel_event *e)
{
+ /* clock tick; decrease extra jiffies by keeping sched_clock constant */
+ if (tt_extra_sched_jiffies > 0)
+ tt_extra_sched_jiffies -= 1;
+
deliver_alarm();
}
diff --git a/arch/um/kernel/tlb.c b/arch/um/kernel/tlb.c
index 548af31d4111..cf7e0d4407f2 100644
--- a/arch/um/kernel/tlb.c
+++ b/arch/um/kernel/tlb.c
@@ -23,9 +23,6 @@ struct vm_ops {
int phys_fd, unsigned long long offset);
int (*unmap)(struct mm_id *mm_idp,
unsigned long virt, unsigned long len);
- int (*mprotect)(struct mm_id *mm_idp,
- unsigned long virt, unsigned long len,
- unsigned int prot);
};
static int kern_map(struct mm_id *mm_idp,
@@ -44,15 +41,6 @@ static int kern_unmap(struct mm_id *mm_idp,
return os_unmap_memory((void *)virt, len);
}
-static int kern_mprotect(struct mm_id *mm_idp,
- unsigned long virt, unsigned long len,
- unsigned int prot)
-{
- return os_protect_memory((void *)virt, len,
- prot & UM_PROT_READ, prot & UM_PROT_WRITE,
- 1);
-}
-
void report_enomem(void)
{
printk(KERN_ERR "UML ran out of memory on the host side! "
@@ -65,33 +53,37 @@ static inline int update_pte_range(pmd_t *pmd, unsigned long addr,
struct vm_ops *ops)
{
pte_t *pte;
- int r, w, x, prot, ret = 0;
+ int ret = 0;
pte = pte_offset_kernel(pmd, addr);
do {
- r = pte_read(*pte);
- w = pte_write(*pte);
- x = pte_exec(*pte);
- if (!pte_young(*pte)) {
- r = 0;
- w = 0;
- } else if (!pte_dirty(*pte))
- w = 0;
-
- prot = ((r ? UM_PROT_READ : 0) | (w ? UM_PROT_WRITE : 0) |
- (x ? UM_PROT_EXEC : 0));
- if (pte_newpage(*pte)) {
- if (pte_present(*pte)) {
- __u64 offset;
- unsigned long phys = pte_val(*pte) & PAGE_MASK;
- int fd = phys_mapping(phys, &offset);
-
- ret = ops->mmap(ops->mm_idp, addr, PAGE_SIZE,
- prot, fd, offset);
- } else
- ret = ops->unmap(ops->mm_idp, addr, PAGE_SIZE);
- } else if (pte_newprot(*pte))
- ret = ops->mprotect(ops->mm_idp, addr, PAGE_SIZE, prot);
+ if (!pte_needsync(*pte))
+ continue;
+
+ if (pte_present(*pte)) {
+ __u64 offset;
+ unsigned long phys = pte_val(*pte) & PAGE_MASK;
+ int fd = phys_mapping(phys, &offset);
+ int r, w, x, prot;
+
+ r = pte_read(*pte);
+ w = pte_write(*pte);
+ x = pte_exec(*pte);
+ if (!pte_young(*pte)) {
+ r = 0;
+ w = 0;
+ } else if (!pte_dirty(*pte))
+ w = 0;
+
+ prot = (r ? UM_PROT_READ : 0) |
+ (w ? UM_PROT_WRITE : 0) |
+ (x ? UM_PROT_EXEC : 0);
+
+ ret = ops->mmap(ops->mm_idp, addr, PAGE_SIZE,
+ prot, fd, offset);
+ } else
+ ret = ops->unmap(ops->mm_idp, addr, PAGE_SIZE);
+
*pte = pte_mkuptodate(*pte);
} while (pte++, addr += PAGE_SIZE, ((addr < end) && !ret));
return ret;
@@ -109,7 +101,7 @@ static inline int update_pmd_range(pud_t *pud, unsigned long addr,
do {
next = pmd_addr_end(addr, end);
if (!pmd_present(*pmd)) {
- if (pmd_newpage(*pmd)) {
+ if (pmd_needsync(*pmd)) {
ret = ops->unmap(ops->mm_idp, addr,
next - addr);
pmd_mkuptodate(*pmd);
@@ -132,7 +124,7 @@ static inline int update_pud_range(p4d_t *p4d, unsigned long addr,
do {
next = pud_addr_end(addr, end);
if (!pud_present(*pud)) {
- if (pud_newpage(*pud)) {
+ if (pud_needsync(*pud)) {
ret = ops->unmap(ops->mm_idp, addr,
next - addr);
pud_mkuptodate(*pud);
@@ -155,7 +147,7 @@ static inline int update_p4d_range(pgd_t *pgd, unsigned long addr,
do {
next = p4d_addr_end(addr, end);
if (!p4d_present(*p4d)) {
- if (p4d_newpage(*p4d)) {
+ if (p4d_needsync(*p4d)) {
ret = ops->unmap(ops->mm_idp, addr,
next - addr);
p4d_mkuptodate(*p4d);
@@ -180,18 +172,16 @@ int um_tlb_sync(struct mm_struct *mm)
if (mm == &init_mm) {
ops.mmap = kern_map;
ops.unmap = kern_unmap;
- ops.mprotect = kern_mprotect;
} else {
ops.mmap = map;
ops.unmap = unmap;
- ops.mprotect = protect;
}
pgd = pgd_offset(mm, addr);
do {
next = pgd_addr_end(addr, mm->context.sync_tlb_range_to);
if (!pgd_present(*pgd)) {
- if (pgd_newpage(*pgd)) {
+ if (pgd_needsync(*pgd)) {
ret = ops.unmap(ops.mm_idp, addr,
next - addr);
pgd_mkuptodate(*pgd);
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 97c8df9c4401..cdaee3e94273 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -201,7 +201,6 @@ void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
struct uml_pt_regs *regs)
{
- jmp_buf *catcher;
int si_code;
int err;
int is_write = FAULT_WRITE(fi);
@@ -246,15 +245,8 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
address = 0;
}
- catcher = current->thread.fault_catcher;
if (!err)
goto out;
- else if (catcher != NULL) {
- current->thread.fault_addr = (void *) address;
- UML_LONGJMP(catcher, 1);
- }
- else if (current->thread.fault_addr != NULL)
- panic("fault_addr set but no fault catcher");
else if (!is_user && arch_fixup(ip, regs))
goto out;
@@ -310,14 +302,6 @@ void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs)
}
}
-void bus_handler(int sig, struct siginfo *si, struct uml_pt_regs *regs)
-{
- if (current->thread.fault_catcher != NULL)
- UML_LONGJMP(current->thread.fault_catcher, 1);
- else
- relay_signal(sig, si, regs);
-}
-
void winch(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
{
do_IRQ(WINCH_IRQ, regs);
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index e8e8b54b3037..8037a967225d 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -65,9 +65,6 @@ struct cpuinfo_um boot_cpu_data = {
EXPORT_SYMBOL(boot_cpu_data);
-union thread_union cpu0_irqstack
- __section(".data..init_irqstack") =
- { .thread_info = INIT_THREAD_INFO(init_task) };
/* Changed in setup_arch, which is called in early boot */
static char host_info[(__NEW_UTS_LEN + 1) * 5];
@@ -131,7 +128,7 @@ static int have_root __initdata;
static int have_console __initdata;
/* Set in uml_mem_setup and modified in linux_main */
-long long physmem_size = 64 * 1024 * 1024;
+unsigned long long physmem_size = 64 * 1024 * 1024;
EXPORT_SYMBOL(physmem_size);
static const char *usage_string =
@@ -167,19 +164,6 @@ __uml_setup("root=", uml_root_setup,
" root=/dev/ubd5\n\n"
);
-static int __init no_skas_debug_setup(char *line, int *add)
-{
- os_warn("'debug' is not necessary to gdb UML in skas mode - run\n");
- os_warn("'gdb linux'\n");
-
- return 0;
-}
-
-__uml_setup("debug", no_skas_debug_setup,
-"debug\n"
-" this flag is not needed to run gdb on UML in skas mode\n\n"
-);
-
static int __init uml_console_setup(char *line, int *add)
{
have_console = 1;
@@ -257,6 +241,8 @@ static struct notifier_block panic_exit_notifier = {
void uml_finishsetup(void)
{
+ cpu_tasks[0] = &init_task;
+
atomic_notifier_chain_register(&panic_notifier_list,
&panic_exit_notifier);
@@ -302,7 +288,24 @@ static void parse_cache_line(char *line)
}
}
-int __init linux_main(int argc, char **argv)
+static unsigned long get_top_address(char **envp)
+{
+ unsigned long top_addr = (unsigned long) &top_addr;
+ int i;
+
+ /* 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_addr &= ~(UM_KERN_PAGE_SIZE - 1);
+ top_addr += UM_KERN_PAGE_SIZE;
+
+ return top_addr;
+}
+
+int __init linux_main(int argc, char **argv, char **envp)
{
unsigned long avail, diff;
unsigned long virtmem_size, max_physmem;
@@ -324,20 +327,23 @@ 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();
- /* 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);
+ host_task_size = get_top_address(envp);
+ /* reserve a few pages for the stubs */
+ stub_start = host_task_size - STUB_DATA_PAGES * PAGE_SIZE;
/* another page for the code portion */
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();
@@ -366,18 +372,15 @@ int __init linux_main(int argc, char **argv)
setup_machinename(init_utsname()->machine);
- highmem = 0;
+ physmem_size = (physmem_size + PAGE_SIZE - 1) & PAGE_MASK;
iomem_size = (iomem_size + PAGE_SIZE - 1) & PAGE_MASK;
+
max_physmem = TASK_SIZE - uml_physmem - iomem_size - MIN_VMALLOC;
- /*
- * Zones have to begin on a 1 << MAX_PAGE_ORDER page boundary,
- * so this makes sure that's true for highmem
- */
- max_physmem &= ~((1 << (PAGE_SHIFT + MAX_PAGE_ORDER)) - 1);
if (physmem_size + iomem_size > max_physmem) {
- highmem = physmem_size + iomem_size - max_physmem;
- physmem_size -= highmem;
+ physmem_size = max_physmem - iomem_size;
+ os_info("Physical memory size shrunk to %llu bytes\n",
+ physmem_size);
}
high_physmem = uml_physmem + physmem_size;
@@ -398,6 +401,8 @@ int __init linux_main(int argc, char **argv)
os_info("Kernel virtual memory size shrunk to %lu bytes\n",
virtmem_size);
+ arch_task_struct_size = sizeof(struct task_struct) + host_fp_size;
+
os_flush_stdout();
return start_uml();
@@ -412,9 +417,9 @@ void __init setup_arch(char **cmdline_p)
{
u8 rng_seed[32];
- stack_protections((unsigned long) &init_thread_info);
- setup_physmem(uml_physmem, uml_reserved, physmem_size, highmem);
- mem_total_pages(physmem_size, iomem_size, highmem);
+ stack_protections((unsigned long) init_task.stack);
+ setup_physmem(uml_physmem, uml_reserved, physmem_size);
+ mem_total_pages(physmem_size, iomem_size);
uml_dtb_init();
read_initrd();
diff --git a/arch/um/kernel/uml.lds.S b/arch/um/kernel/uml.lds.S
index 5c92d58a78e8..a409d4b66114 100644
--- a/arch/um/kernel/uml.lds.S
+++ b/arch/um/kernel/uml.lds.S
@@ -77,8 +77,6 @@ SECTIONS
.data :
{
INIT_TASK_DATA(KERNEL_STACK_SIZE)
- . = ALIGN(KERNEL_STACK_SIZE);
- *(.data..init_irqstack)
DATA_DATA
*(.gnu.linkonce.d*)
CONSTRUCTORS
generated by cgit (git 2.34.1) at 2025-03-28 10:35:53 +0000