summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Documentation/x86/efi-stub.txt65
-rw-r--r--arch/x86/Kconfig2
-rw-r--r--arch/x86/boot/compressed/eboot.c87
-rw-r--r--arch/x86/boot/compressed/eboot.h6
-rw-r--r--arch/x86/include/asm/ftrace.h2
-rw-r--r--arch/x86/kernel/cpu/common.c8
-rw-r--r--arch/x86/kernel/entry_64.S44
-rw-r--r--arch/x86/kernel/ftrace.c102
-rw-r--r--arch/x86/kernel/nmi.c6
-rw-r--r--arch/x86/kernel/ptrace.c6
-rw-r--r--arch/x86/kernel/traps.c8
11 files changed, 297 insertions, 39 deletions
diff --git a/Documentation/x86/efi-stub.txt b/Documentation/x86/efi-stub.txt
new file mode 100644
index 000000000000..44e6bb6ead10
--- /dev/null
+++ b/Documentation/x86/efi-stub.txt
@@ -0,0 +1,65 @@
+ The EFI Boot Stub
+ ---------------------------
+
+On the x86 platform, a bzImage can masquerade as a PE/COFF image,
+thereby convincing EFI firmware loaders to load it as an EFI
+executable. The code that modifies the bzImage header, along with the
+EFI-specific entry point that the firmware loader jumps to are
+collectively known as the "EFI boot stub", and live in
+arch/x86/boot/header.S and arch/x86/boot/compressed/eboot.c,
+respectively.
+
+By using the EFI boot stub it's possible to boot a Linux kernel
+without the use of a conventional EFI boot loader, such as grub or
+elilo. Since the EFI boot stub performs the jobs of a boot loader, in
+a certain sense it *IS* the boot loader.
+
+The EFI boot stub is enabled with the CONFIG_EFI_STUB kernel option.
+
+
+**** How to install bzImage.efi
+
+The bzImage located in arch/x86/boot/bzImage must be copied to the EFI
+System Partiion (ESP) and renamed with the extension ".efi". Without
+the extension the EFI firmware loader will refuse to execute it. It's
+not possible to execute bzImage.efi from the usual Linux file systems
+because EFI firmware doesn't have support for them.
+
+
+**** Passing kernel parameters from the EFI shell
+
+Arguments to the kernel can be passed after bzImage.efi, e.g.
+
+ fs0:> bzImage.efi console=ttyS0 root=/dev/sda4
+
+
+**** The "initrd=" option
+
+Like most boot loaders, the EFI stub allows the user to specify
+multiple initrd files using the "initrd=" option. This is the only EFI
+stub-specific command line parameter, everything else is passed to the
+kernel when it boots.
+
+The path to the initrd file must be an absolute path from the
+beginning of the ESP, relative path names do not work. Also, the path
+is an EFI-style path and directory elements must be separated with
+backslashes (\). For example, given the following directory layout,
+
+fs0:>
+ Kernels\
+ bzImage.efi
+ initrd-large.img
+
+ Ramdisks\
+ initrd-small.img
+ initrd-medium.img
+
+to boot with the initrd-large.img file if the current working
+directory is fs0:\Kernels, the following command must be used,
+
+ fs0:\Kernels> bzImage.efi initrd=\Kernels\initrd-large.img
+
+Notice how bzImage.efi can be specified with a relative path. That's
+because the image we're executing is interpreted by the EFI shell,
+which understands relative paths, whereas the rest of the command line
+is passed to bzImage.efi.
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d700811785ea..c70684f859e1 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1506,6 +1506,8 @@ config EFI_STUB
This kernel feature allows a bzImage to be loaded directly
by EFI firmware without the use of a bootloader.
+ See Documentation/x86/efi-stub.txt for more information.
+
config SECCOMP
def_bool y
prompt "Enable seccomp to safely compute untrusted bytecode"
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 2c14e76bb4c7..4e85f5f85837 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -16,6 +16,26 @@
static efi_system_table_t *sys_table;
+static void efi_printk(char *str)
+{
+ char *s8;
+
+ for (s8 = str; *s8; s8++) {
+ struct efi_simple_text_output_protocol *out;
+ efi_char16_t ch[2] = { 0 };
+
+ ch[0] = *s8;
+ out = (struct efi_simple_text_output_protocol *)sys_table->con_out;
+
+ if (*s8 == '\n') {
+ efi_char16_t nl[2] = { '\r', 0 };
+ efi_call_phys2(out->output_string, out, nl);
+ }
+
+ efi_call_phys2(out->output_string, out, ch);
+ }
+}
+
static efi_status_t __get_map(efi_memory_desc_t **map, unsigned long *map_size,
unsigned long *desc_size)
{
@@ -531,8 +551,10 @@ static efi_status_t handle_ramdisks(efi_loaded_image_t *image,
EFI_LOADER_DATA,
nr_initrds * sizeof(*initrds),
&initrds);
- if (status != EFI_SUCCESS)
+ if (status != EFI_SUCCESS) {
+ efi_printk("Failed to alloc mem for initrds\n");
goto fail;
+ }
str = (char *)(unsigned long)hdr->cmd_line_ptr;
for (i = 0; i < nr_initrds; i++) {
@@ -575,32 +597,42 @@ static efi_status_t handle_ramdisks(efi_loaded_image_t *image,
status = efi_call_phys3(boottime->handle_protocol,
image->device_handle, &fs_proto, &io);
- if (status != EFI_SUCCESS)
+ if (status != EFI_SUCCESS) {
+ efi_printk("Failed to handle fs_proto\n");
goto free_initrds;
+ }
status = efi_call_phys2(io->open_volume, io, &fh);
- if (status != EFI_SUCCESS)
+ if (status != EFI_SUCCESS) {
+ efi_printk("Failed to open volume\n");
goto free_initrds;
+ }
}
status = efi_call_phys5(fh->open, fh, &h, filename_16,
EFI_FILE_MODE_READ, (u64)0);
- if (status != EFI_SUCCESS)
+ if (status != EFI_SUCCESS) {
+ efi_printk("Failed to open initrd file\n");
goto close_handles;
+ }
initrd->handle = h;
info_sz = 0;
status = efi_call_phys4(h->get_info, h, &info_guid,
&info_sz, NULL);
- if (status != EFI_BUFFER_TOO_SMALL)
+ if (status != EFI_BUFFER_TOO_SMALL) {
+ efi_printk("Failed to get initrd info size\n");
goto close_handles;
+ }
grow:
status = efi_call_phys3(sys_table->boottime->allocate_pool,
EFI_LOADER_DATA, info_sz, &info);
- if (status != EFI_SUCCESS)
+ if (status != EFI_SUCCESS) {
+ efi_printk("Failed to alloc mem for initrd info\n");
goto close_handles;
+ }
status = efi_call_phys4(h->get_info, h, &info_guid,
&info_sz, info);
@@ -612,8 +644,10 @@ grow:
file_sz = info->file_size;
efi_call_phys1(sys_table->boottime->free_pool, info);
- if (status != EFI_SUCCESS)
+ if (status != EFI_SUCCESS) {
+ efi_printk("Failed to get initrd info\n");
goto close_handles;
+ }
initrd->size = file_sz;
initrd_total += file_sz;
@@ -629,11 +663,14 @@ grow:
*/
status = high_alloc(initrd_total, 0x1000,
&initrd_addr, hdr->initrd_addr_max);
- if (status != EFI_SUCCESS)
+ if (status != EFI_SUCCESS) {
+ efi_printk("Failed to alloc highmem for initrds\n");
goto close_handles;
+ }
/* We've run out of free low memory. */
if (initrd_addr > hdr->initrd_addr_max) {
+ efi_printk("We've run out of free low memory\n");
status = EFI_INVALID_PARAMETER;
goto free_initrd_total;
}
@@ -652,8 +689,10 @@ grow:
status = efi_call_phys3(fh->read,
initrds[j].handle,
&chunksize, addr);
- if (status != EFI_SUCCESS)
+ if (status != EFI_SUCCESS) {
+ efi_printk("Failed to read initrd\n");
goto free_initrd_total;
+ }
addr += chunksize;
size -= chunksize;
}
@@ -674,7 +713,7 @@ free_initrd_total:
low_free(initrd_total, initrd_addr);
close_handles:
- for (k = j; k < nr_initrds; k++)
+ for (k = j; k < i; k++)
efi_call_phys1(fh->close, initrds[k].handle);
free_initrds:
efi_call_phys1(sys_table->boottime->free_pool, initrds);
@@ -732,8 +771,10 @@ static efi_status_t make_boot_params(struct boot_params *boot_params,
options_size++; /* NUL termination */
status = low_alloc(options_size, 1, &cmdline);
- if (status != EFI_SUCCESS)
+ if (status != EFI_SUCCESS) {
+ efi_printk("Failed to alloc mem for cmdline\n");
goto fail;
+ }
s1 = (u8 *)(unsigned long)cmdline;
s2 = (u16 *)options;
@@ -895,12 +936,16 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table)
status = efi_call_phys3(sys_table->boottime->handle_protocol,
handle, &proto, (void *)&image);
- if (status != EFI_SUCCESS)
+ if (status != EFI_SUCCESS) {
+ efi_printk("Failed to get handle for LOADED_IMAGE_PROTOCOL\n");
goto fail;
+ }
status = low_alloc(0x4000, 1, (unsigned long *)&boot_params);
- if (status != EFI_SUCCESS)
+ if (status != EFI_SUCCESS) {
+ efi_printk("Failed to alloc lowmem for boot params\n");
goto fail;
+ }
memset(boot_params, 0x0, 0x4000);
@@ -933,8 +978,10 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table)
if (status != EFI_SUCCESS) {
status = low_alloc(hdr->init_size, hdr->kernel_alignment,
&start);
- if (status != EFI_SUCCESS)
+ if (status != EFI_SUCCESS) {
+ efi_printk("Failed to alloc mem for kernel\n");
goto fail;
+ }
}
hdr->code32_start = (__u32)start;
@@ -945,19 +992,25 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table)
status = efi_call_phys3(sys_table->boottime->allocate_pool,
EFI_LOADER_DATA, sizeof(*gdt),
(void **)&gdt);
- if (status != EFI_SUCCESS)
+ if (status != EFI_SUCCESS) {
+ efi_printk("Failed to alloc mem for gdt structure\n");
goto fail;
+ }
gdt->size = 0x800;
status = low_alloc(gdt->size, 8, (unsigned long *)&gdt->address);
- if (status != EFI_SUCCESS)
+ if (status != EFI_SUCCESS) {
+ efi_printk("Failed to alloc mem for gdt\n");
goto fail;
+ }
status = efi_call_phys3(sys_table->boottime->allocate_pool,
EFI_LOADER_DATA, sizeof(*idt),
(void **)&idt);
- if (status != EFI_SUCCESS)
+ if (status != EFI_SUCCESS) {
+ efi_printk("Failed to alloc mem for idt structure\n");
goto fail;
+ }
idt->size = 0;
idt->address = 0;
diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h
index 39251663e65b..3b6e15627c55 100644
--- a/arch/x86/boot/compressed/eboot.h
+++ b/arch/x86/boot/compressed/eboot.h
@@ -58,4 +58,10 @@ struct efi_uga_draw_protocol {
void *blt;
};
+struct efi_simple_text_output_protocol {
+ void *reset;
+ void *output_string;
+ void *test_string;
+};
+
#endif /* BOOT_COMPRESSED_EBOOT_H */
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 18d9005d9e4f..b0767bc08740 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -34,7 +34,7 @@
#ifndef __ASSEMBLY__
extern void mcount(void);
-extern int modifying_ftrace_code;
+extern atomic_t modifying_ftrace_code;
static inline unsigned long ftrace_call_adjust(unsigned long addr)
{
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 82f29e70d058..6b9333b429ba 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1101,14 +1101,20 @@ int is_debug_stack(unsigned long addr)
addr > (__get_cpu_var(debug_stack_addr) - DEBUG_STKSZ));
}
+static DEFINE_PER_CPU(u32, debug_stack_use_ctr);
+
void debug_stack_set_zero(void)
{
+ this_cpu_inc(debug_stack_use_ctr);
load_idt((const struct desc_ptr *)&nmi_idt_descr);
}
void debug_stack_reset(void)
{
- load_idt((const struct desc_ptr *)&idt_descr);
+ if (WARN_ON(!this_cpu_read(debug_stack_use_ctr)))
+ return;
+ if (this_cpu_dec_return(debug_stack_use_ctr) == 0)
+ load_idt((const struct desc_ptr *)&idt_descr);
}
#else /* CONFIG_X86_64 */
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 320852d02026..7d65133b51be 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -191,6 +191,44 @@ ENDPROC(native_usergs_sysret64)
.endm
/*
+ * When dynamic function tracer is enabled it will add a breakpoint
+ * to all locations that it is about to modify, sync CPUs, update
+ * all the code, sync CPUs, then remove the breakpoints. In this time
+ * if lockdep is enabled, it might jump back into the debug handler
+ * outside the updating of the IST protection. (TRACE_IRQS_ON/OFF).
+ *
+ * We need to change the IDT table before calling TRACE_IRQS_ON/OFF to
+ * make sure the stack pointer does not get reset back to the top
+ * of the debug stack, and instead just reuses the current stack.
+ */
+#if defined(CONFIG_DYNAMIC_FTRACE) && defined(CONFIG_TRACE_IRQFLAGS)
+
+.macro TRACE_IRQS_OFF_DEBUG
+ call debug_stack_set_zero
+ TRACE_IRQS_OFF
+ call debug_stack_reset
+.endm
+
+.macro TRACE_IRQS_ON_DEBUG
+ call debug_stack_set_zero
+ TRACE_IRQS_ON
+ call debug_stack_reset
+.endm
+
+.macro TRACE_IRQS_IRETQ_DEBUG offset=ARGOFFSET
+ bt $9,EFLAGS-\offset(%rsp) /* interrupts off? */
+ jnc 1f
+ TRACE_IRQS_ON_DEBUG
+1:
+.endm
+
+#else
+# define TRACE_IRQS_OFF_DEBUG TRACE_IRQS_OFF
+# define TRACE_IRQS_ON_DEBUG TRACE_IRQS_ON
+# define TRACE_IRQS_IRETQ_DEBUG TRACE_IRQS_IRETQ
+#endif
+
+/*
* C code is not supposed to know about undefined top of stack. Every time
* a C function with an pt_regs argument is called from the SYSCALL based
* fast path FIXUP_TOP_OF_STACK is needed.
@@ -1098,7 +1136,7 @@ ENTRY(\sym)
subq $ORIG_RAX-R15, %rsp
CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
call save_paranoid
- TRACE_IRQS_OFF
+ TRACE_IRQS_OFF_DEBUG
movq %rsp,%rdi /* pt_regs pointer */
xorl %esi,%esi /* no error code */
subq $EXCEPTION_STKSZ, INIT_TSS_IST(\ist)
@@ -1393,7 +1431,7 @@ paranoidzeroentry machine_check *machine_check_vector(%rip)
ENTRY(paranoid_exit)
DEFAULT_FRAME
DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
+ TRACE_IRQS_OFF_DEBUG
testl %ebx,%ebx /* swapgs needed? */
jnz paranoid_restore
testl $3,CS(%rsp)
@@ -1404,7 +1442,7 @@ paranoid_swapgs:
RESTORE_ALL 8
jmp irq_return
paranoid_restore:
- TRACE_IRQS_IRETQ 0
+ TRACE_IRQS_IRETQ_DEBUG 0
RESTORE_ALL 8
jmp irq_return
paranoid_userspace:
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 32ff36596ab1..c3a7cb4bf6e6 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -100,7 +100,7 @@ static const unsigned char *ftrace_nop_replace(void)
}
static int
-ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
+ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code,
unsigned const char *new_code)
{
unsigned char replaced[MCOUNT_INSN_SIZE];
@@ -141,7 +141,20 @@ int ftrace_make_nop(struct module *mod,
old = ftrace_call_replace(ip, addr);
new = ftrace_nop_replace();
- return ftrace_modify_code(rec->ip, old, new);
+ /*
+ * On boot up, and when modules are loaded, the MCOUNT_ADDR
+ * is converted to a nop, and will never become MCOUNT_ADDR
+ * again. This code is either running before SMP (on boot up)
+ * or before the code will ever be executed (module load).
+ * We do not want to use the breakpoint version in this case,
+ * just modify the code directly.
+ */
+ if (addr == MCOUNT_ADDR)
+ return ftrace_modify_code_direct(rec->ip, old, new);
+
+ /* Normal cases use add_brk_on_nop */
+ WARN_ONCE(1, "invalid use of ftrace_make_nop");
+ return -EINVAL;
}
int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
@@ -152,9 +165,47 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
old = ftrace_nop_replace();
new = ftrace_call_replace(ip, addr);
- return ftrace_modify_code(rec->ip, old, new);
+ /* Should only be called when module is loaded */
+ return ftrace_modify_code_direct(rec->ip, old, new);
}
+/*
+ * The modifying_ftrace_code is used to tell the breakpoint
+ * handler to call ftrace_int3_handler(). If it fails to
+ * call this handler for a breakpoint added by ftrace, then
+ * the kernel may crash.
+ *
+ * As atomic_writes on x86 do not need a barrier, we do not
+ * need to add smp_mb()s for this to work. It is also considered
+ * that we can not read the modifying_ftrace_code before
+ * executing the breakpoint. That would be quite remarkable if
+ * it could do that. Here's the flow that is required:
+ *
+ * CPU-0 CPU-1
+ *
+ * atomic_inc(mfc);
+ * write int3s
+ * <trap-int3> // implicit (r)mb
+ * if (atomic_read(mfc))
+ * call ftrace_int3_handler()
+ *
+ * Then when we are finished:
+ *
+ * atomic_dec(mfc);
+ *
+ * If we hit a breakpoint that was not set by ftrace, it does not
+ * matter if ftrace_int3_handler() is called or not. It will
+ * simply be ignored. But it is crucial that a ftrace nop/caller
+ * breakpoint is handled. No other user should ever place a
+ * breakpoint on an ftrace nop/caller location. It must only
+ * be done by this code.
+ */
+atomic_t modifying_ftrace_code __read_mostly;
+
+static int
+ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
+ unsigned const char *new_code);
+
int ftrace_update_ftrace_func(ftrace_func_t func)
{
unsigned long ip = (unsigned long)(&ftrace_call);
@@ -163,13 +214,17 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
memcpy(old, &ftrace_call, MCOUNT_INSN_SIZE);
new = ftrace_call_replace(ip, (unsigned long)func);
+
+ /* See comment above by declaration of modifying_ftrace_code */
+ atomic_inc(&modifying_ftrace_code);
+
ret = ftrace_modify_code(ip, old, new);
+ atomic_dec(&modifying_ftrace_code);
+
return ret;
}
-int modifying_ftrace_code __read_mostly;
-
/*
* A breakpoint was added to the code address we are about to
* modify, and this is the handle that will just skip over it.
@@ -489,13 +544,46 @@ void ftrace_replace_code(int enable)
}
}
+static int
+ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
+ unsigned const char *new_code)
+{
+ int ret;
+
+ ret = add_break(ip, old_code);
+ if (ret)
+ goto out;
+
+ run_sync();
+
+ ret = add_update_code(ip, new_code);
+ if (ret)
+ goto fail_update;
+
+ run_sync();
+
+ ret = ftrace_write(ip, new_code, 1);
+ if (ret) {
+ ret = -EPERM;
+ goto out;
+ }
+ run_sync();
+ out:
+ return ret;
+
+ fail_update:
+ probe_kernel_write((void *)ip, &old_code[0], 1);
+ goto out;
+}
+
void arch_ftrace_update_code(int command)
{
- modifying_ftrace_code++;
+ /* See comment above by declaration of modifying_ftrace_code */
+ atomic_inc(&modifying_ftrace_code);
ftrace_modify_all_code(command);
- modifying_ftrace_code--;
+ atomic_dec(&modifying_ftrace_code);
}
int __init ftrace_dyn_arch_init(void *data)
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 90875279ef3d..a0b2f84457be 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -444,14 +444,16 @@ static inline void nmi_nesting_preprocess(struct pt_regs *regs)
*/
if (unlikely(is_debug_stack(regs->sp))) {
debug_stack_set_zero();
- __get_cpu_var(update_debug_stack) = 1;
+ this_cpu_write(update_debug_stack, 1);
}
}
static inline void nmi_nesting_postprocess(void)
{
- if (unlikely(__get_cpu_var(update_debug_stack)))
+ if (unlikely(this_cpu_read(update_debug_stack))) {
debug_stack_reset();
+ this_cpu_write(update_debug_stack, 0);
+ }
}
#endif
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 13b1990c7c58..c4c6a5c2bf0f 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1211,12 +1211,6 @@ static long x32_arch_ptrace(struct task_struct *child,
0, sizeof(struct user_i387_struct),
datap);
- /* normal 64bit interface to access TLS data.
- Works just like arch_prctl, except that the arguments
- are reversed. */
- case PTRACE_ARCH_PRCTL:
- return do_arch_prctl(child, data, addr);
-
default:
return compat_ptrace_request(child, request, addr, data);
}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index ff08457a025d..05b31d92f69c 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -303,8 +303,12 @@ gp_in_kernel:
dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_code)
{
#ifdef CONFIG_DYNAMIC_FTRACE
- /* ftrace must be first, everything else may cause a recursive crash */
- if (unlikely(modifying_ftrace_code) && ftrace_int3_handler(regs))
+ /*
+ * ftrace must be first, everything else may cause a recursive crash.
+ * See note by declaration of modifying_ftrace_code in ftrace.c
+ */
+ if (unlikely(atomic_read(&modifying_ftrace_code)) &&
+ ftrace_int3_handler(regs))
return;
#endif
#ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-29 01:15:13 +0000