summaryrefslogtreecommitdiff
path: root/arch/x86/entry
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/entry')
-rw-r--r--arch/x86/entry/common.c9
-rw-r--r--arch/x86/entry/entry_32.S171
-rw-r--r--arch/x86/entry/entry_64.S22
-rw-r--r--arch/x86/entry/syscalls/syscall_32.tbl3
-rw-r--r--arch/x86/entry/vdso/vclock_gettime.c24
-rw-r--r--arch/x86/entry/vdso/vdso-layout.lds.S3
-rw-r--r--arch/x86/entry/vdso/vdso2c.c3
-rw-r--r--arch/x86/entry/vdso/vdso32-setup.c11
-rw-r--r--arch/x86/entry/vdso/vma.c9
9 files changed, 64 insertions, 191 deletions
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 370c42c7f046..cdefcfdd9e63 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -22,6 +22,7 @@
#include <linux/context_tracking.h>
#include <linux/user-return-notifier.h>
#include <linux/uprobes.h>
+#include <linux/livepatch.h>
#include <asm/desc.h>
#include <asm/traps.h>
@@ -130,14 +131,13 @@ static long syscall_trace_enter(struct pt_regs *regs)
#define EXIT_TO_USERMODE_LOOP_FLAGS \
(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
- _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY)
+ _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY | _TIF_PATCH_PENDING)
static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
{
/*
* In order to return to user mode, we need to have IRQs off with
- * none of _TIF_SIGPENDING, _TIF_NOTIFY_RESUME, _TIF_USER_RETURN_NOTIFY,
- * _TIF_UPROBE, or _TIF_NEED_RESCHED set. Several of these flags
+ * none of EXIT_TO_USERMODE_LOOP_FLAGS set. Several of these flags
* can be set at any time on preemptable kernels if we have IRQs on,
* so we need to loop. Disabling preemption wouldn't help: doing the
* work to clear some of the flags can sleep.
@@ -164,6 +164,9 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
if (cached_flags & _TIF_USER_RETURN_NOTIFY)
fire_user_return_notifiers();
+ if (cached_flags & _TIF_PATCH_PENDING)
+ klp_update_patch_state(current);
+
/* Disable IRQs and retry */
local_irq_disable();
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 57f7ec35216e..50bc26949e9e 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -35,16 +35,13 @@
#include <asm/errno.h>
#include <asm/segment.h>
#include <asm/smp.h>
-#include <asm/page_types.h>
#include <asm/percpu.h>
#include <asm/processor-flags.h>
-#include <asm/ftrace.h>
#include <asm/irq_vectors.h>
#include <asm/cpufeatures.h>
#include <asm/alternative-asm.h>
#include <asm/asm.h>
#include <asm/smap.h>
-#include <asm/export.h>
#include <asm/frame.h>
.section .entry.text, "ax"
@@ -585,7 +582,7 @@ ENTRY(iret_exc )
* will soon execute iret and the tracer was already set to
* the irqstate after the IRET:
*/
- DISABLE_INTERRUPTS(CLBR_EAX)
+ DISABLE_INTERRUPTS(CLBR_ANY)
lss (%esp), %esp /* switch to espfix segment */
jmp .Lrestore_nocheck
#endif
@@ -886,172 +883,6 @@ BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
#endif /* CONFIG_HYPERV */
-#ifdef CONFIG_FUNCTION_TRACER
-#ifdef CONFIG_DYNAMIC_FTRACE
-
-ENTRY(mcount)
- ret
-END(mcount)
-
-ENTRY(ftrace_caller)
- pushl %eax
- pushl %ecx
- pushl %edx
- pushl $0 /* Pass NULL as regs pointer */
- movl 4*4(%esp), %eax
- movl 0x4(%ebp), %edx
- movl function_trace_op, %ecx
- subl $MCOUNT_INSN_SIZE, %eax
-
-.globl ftrace_call
-ftrace_call:
- call ftrace_stub
-
- addl $4, %esp /* skip NULL pointer */
- popl %edx
- popl %ecx
- popl %eax
-.Lftrace_ret:
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-.globl ftrace_graph_call
-ftrace_graph_call:
- jmp ftrace_stub
-#endif
-
-/* This is weak to keep gas from relaxing the jumps */
-WEAK(ftrace_stub)
- ret
-END(ftrace_caller)
-
-ENTRY(ftrace_regs_caller)
- pushf /* push flags before compare (in cs location) */
-
- /*
- * i386 does not save SS and ESP when coming from kernel.
- * Instead, to get sp, &regs->sp is used (see ptrace.h).
- * Unfortunately, that means eflags must be at the same location
- * as the current return ip is. We move the return ip into the
- * ip location, and move flags into the return ip location.
- */
- pushl 4(%esp) /* save return ip into ip slot */
-
- pushl $0 /* Load 0 into orig_ax */
- pushl %gs
- pushl %fs
- pushl %es
- pushl %ds
- pushl %eax
- pushl %ebp
- pushl %edi
- pushl %esi
- pushl %edx
- pushl %ecx
- pushl %ebx
-
- movl 13*4(%esp), %eax /* Get the saved flags */
- movl %eax, 14*4(%esp) /* Move saved flags into regs->flags location */
- /* clobbering return ip */
- movl $__KERNEL_CS, 13*4(%esp)
-
- movl 12*4(%esp), %eax /* Load ip (1st parameter) */
- subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */
- movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */
- movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
- pushl %esp /* Save pt_regs as 4th parameter */
-
-GLOBAL(ftrace_regs_call)
- call ftrace_stub
-
- addl $4, %esp /* Skip pt_regs */
- movl 14*4(%esp), %eax /* Move flags back into cs */
- movl %eax, 13*4(%esp) /* Needed to keep addl from modifying flags */
- movl 12*4(%esp), %eax /* Get return ip from regs->ip */
- movl %eax, 14*4(%esp) /* Put return ip back for ret */
-
- popl %ebx
- popl %ecx
- popl %edx
- popl %esi
- popl %edi
- popl %ebp
- popl %eax
- popl %ds
- popl %es
- popl %fs
- popl %gs
- addl $8, %esp /* Skip orig_ax and ip */
- popf /* Pop flags at end (no addl to corrupt flags) */
- jmp .Lftrace_ret
-
- popf
- jmp ftrace_stub
-#else /* ! CONFIG_DYNAMIC_FTRACE */
-
-ENTRY(mcount)
- cmpl $__PAGE_OFFSET, %esp
- jb ftrace_stub /* Paging not enabled yet? */
-
- cmpl $ftrace_stub, ftrace_trace_function
- jnz .Ltrace
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- cmpl $ftrace_stub, ftrace_graph_return
- jnz ftrace_graph_caller
-
- cmpl $ftrace_graph_entry_stub, ftrace_graph_entry
- jnz ftrace_graph_caller
-#endif
-.globl ftrace_stub
-ftrace_stub:
- ret
-
- /* taken from glibc */
-.Ltrace:
- pushl %eax
- pushl %ecx
- pushl %edx
- movl 0xc(%esp), %eax
- movl 0x4(%ebp), %edx
- subl $MCOUNT_INSN_SIZE, %eax
-
- call *ftrace_trace_function
-
- popl %edx
- popl %ecx
- popl %eax
- jmp ftrace_stub
-END(mcount)
-#endif /* CONFIG_DYNAMIC_FTRACE */
-EXPORT_SYMBOL(mcount)
-#endif /* CONFIG_FUNCTION_TRACER */
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-ENTRY(ftrace_graph_caller)
- pushl %eax
- pushl %ecx
- pushl %edx
- movl 0xc(%esp), %eax
- lea 0x4(%ebp), %edx
- movl (%ebp), %ecx
- subl $MCOUNT_INSN_SIZE, %eax
- call prepare_ftrace_return
- popl %edx
- popl %ecx
- popl %eax
- ret
-END(ftrace_graph_caller)
-
-.globl return_to_handler
-return_to_handler:
- pushl %eax
- pushl %edx
- movl %ebp, %eax
- call ftrace_return_to_handler
- movl %eax, %ecx
- popl %edx
- popl %eax
- jmp *%ecx
-#endif
-
#ifdef CONFIG_TRACING
ENTRY(trace_page_fault)
ASM_CLAC
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 044d18ebc43c..607d72c4a485 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -212,7 +212,7 @@ entry_SYSCALL_64_fastpath:
* If we see that no exit work is required (which we are required
* to check with IRQs off), then we can go straight to SYSRET64.
*/
- DISABLE_INTERRUPTS(CLBR_NONE)
+ DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_OFF
movq PER_CPU_VAR(current_task), %r11
testl $_TIF_ALLWORK_MASK, TASK_TI_flags(%r11)
@@ -233,7 +233,7 @@ entry_SYSCALL_64_fastpath:
* raise(3) will trigger this, for example. IRQs are off.
*/
TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_NONE)
+ ENABLE_INTERRUPTS(CLBR_ANY)
SAVE_EXTRA_REGS
movq %rsp, %rdi
call syscall_return_slowpath /* returns with IRQs disabled */
@@ -265,12 +265,9 @@ return_from_SYSCALL_64:
*
* If width of "canonical tail" ever becomes variable, this will need
* to be updated to remain correct on both old and new CPUs.
+ *
+ * Change top 16 bits to be the sign-extension of 47th bit
*/
- .ifne __VIRTUAL_MASK_SHIFT - 47
- .error "virtual address width changed -- SYSRET checks need update"
- .endif
-
- /* Change top 16 bits to be the sign-extension of 47th bit */
shl $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
sar $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
@@ -343,7 +340,7 @@ ENTRY(stub_ptregs_64)
* Called from fast path -- disable IRQs again, pop return address
* and jump to slow path
*/
- DISABLE_INTERRUPTS(CLBR_NONE)
+ DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_OFF
popq %rax
jmp entry_SYSCALL64_slow_path
@@ -518,7 +515,7 @@ common_interrupt:
interrupt do_IRQ
/* 0(%rsp): old RSP */
ret_from_intr:
- DISABLE_INTERRUPTS(CLBR_NONE)
+ DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_OFF
decl PER_CPU_VAR(irq_count)
@@ -1051,7 +1048,7 @@ END(paranoid_entry)
* On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it)
*/
ENTRY(paranoid_exit)
- DISABLE_INTERRUPTS(CLBR_NONE)
+ DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_OFF_DEBUG
testl %ebx, %ebx /* swapgs needed? */
jnz paranoid_exit_no_swapgs
@@ -1156,10 +1153,9 @@ END(error_entry)
* 0: user gsbase is loaded, we need SWAPGS and standard preparation for return to usermode
*/
ENTRY(error_exit)
- movl %ebx, %eax
- DISABLE_INTERRUPTS(CLBR_NONE)
+ DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_OFF
- testl %eax, %eax
+ testl %ebx, %ebx
jnz retint_kernel
jmp retint_user
END(error_exit)
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 9ba050fe47f3..448ac2161112 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -226,7 +226,7 @@
217 i386 pivot_root sys_pivot_root
218 i386 mincore sys_mincore
219 i386 madvise sys_madvise
-220 i386 getdents64 sys_getdents64 compat_sys_getdents64
+220 i386 getdents64 sys_getdents64
221 i386 fcntl64 sys_fcntl64 compat_sys_fcntl64
# 222 is unused
# 223 is unused
@@ -390,3 +390,4 @@
381 i386 pkey_alloc sys_pkey_alloc
382 i386 pkey_free sys_pkey_free
383 i386 statx sys_statx
+384 i386 arch_prctl sys_arch_prctl compat_sys_arch_prctl
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 9d4d6e138311..fa8dbfcf7ed3 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -17,6 +17,7 @@
#include <asm/unistd.h>
#include <asm/msr.h>
#include <asm/pvclock.h>
+#include <asm/mshyperv.h>
#include <linux/math64.h>
#include <linux/time.h>
#include <linux/kernel.h>
@@ -32,6 +33,11 @@ extern u8 pvclock_page
__attribute__((visibility("hidden")));
#endif
+#ifdef CONFIG_HYPERV_TSCPAGE
+extern u8 hvclock_page
+ __attribute__((visibility("hidden")));
+#endif
+
#ifndef BUILD_VDSO32
notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
@@ -141,6 +147,20 @@ static notrace u64 vread_pvclock(int *mode)
return last;
}
#endif
+#ifdef CONFIG_HYPERV_TSCPAGE
+static notrace u64 vread_hvclock(int *mode)
+{
+ const struct ms_hyperv_tsc_page *tsc_pg =
+ (const struct ms_hyperv_tsc_page *)&hvclock_page;
+ u64 current_tick = hv_read_tsc_page(tsc_pg);
+
+ if (current_tick != U64_MAX)
+ return current_tick;
+
+ *mode = VCLOCK_NONE;
+ return 0;
+}
+#endif
notrace static u64 vread_tsc(void)
{
@@ -173,6 +193,10 @@ notrace static inline u64 vgetsns(int *mode)
else if (gtod->vclock_mode == VCLOCK_PVCLOCK)
cycles = vread_pvclock(mode);
#endif
+#ifdef CONFIG_HYPERV_TSCPAGE
+ else if (gtod->vclock_mode == VCLOCK_HVCLOCK)
+ cycles = vread_hvclock(mode);
+#endif
else
return 0;
v = (cycles - gtod->cycle_last) & gtod->mask;
diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S
index a708aa90b507..8ebb4b6454fe 100644
--- a/arch/x86/entry/vdso/vdso-layout.lds.S
+++ b/arch/x86/entry/vdso/vdso-layout.lds.S
@@ -25,7 +25,7 @@ SECTIONS
* segment.
*/
- vvar_start = . - 2 * PAGE_SIZE;
+ vvar_start = . - 3 * PAGE_SIZE;
vvar_page = vvar_start;
/* Place all vvars at the offsets in asm/vvar.h. */
@@ -36,6 +36,7 @@ SECTIONS
#undef EMIT_VVAR
pvclock_page = vvar_start + PAGE_SIZE;
+ hvclock_page = vvar_start + 2 * PAGE_SIZE;
. = SIZEOF_HEADERS;
diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c
index 491020b2826d..0780a443a53b 100644
--- a/arch/x86/entry/vdso/vdso2c.c
+++ b/arch/x86/entry/vdso/vdso2c.c
@@ -74,6 +74,7 @@ enum {
sym_vvar_page,
sym_hpet_page,
sym_pvclock_page,
+ sym_hvclock_page,
sym_VDSO_FAKE_SECTION_TABLE_START,
sym_VDSO_FAKE_SECTION_TABLE_END,
};
@@ -82,6 +83,7 @@ const int special_pages[] = {
sym_vvar_page,
sym_hpet_page,
sym_pvclock_page,
+ sym_hvclock_page,
};
struct vdso_sym {
@@ -94,6 +96,7 @@ struct vdso_sym required_syms[] = {
[sym_vvar_page] = {"vvar_page", true},
[sym_hpet_page] = {"hpet_page", true},
[sym_pvclock_page] = {"pvclock_page", true},
+ [sym_hvclock_page] = {"hvclock_page", true},
[sym_VDSO_FAKE_SECTION_TABLE_START] = {
"VDSO_FAKE_SECTION_TABLE_START", false
},
diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c
index 7853b53959cd..3f9d1a83891a 100644
--- a/arch/x86/entry/vdso/vdso32-setup.c
+++ b/arch/x86/entry/vdso/vdso32-setup.c
@@ -30,8 +30,10 @@ static int __init vdso32_setup(char *s)
{
vdso32_enabled = simple_strtoul(s, NULL, 0);
- if (vdso32_enabled > 1)
+ if (vdso32_enabled > 1) {
pr_warn("vdso32 values other than 0 and 1 are no longer allowed; vdso disabled\n");
+ vdso32_enabled = 0;
+ }
return 1;
}
@@ -62,13 +64,18 @@ subsys_initcall(sysenter_setup);
/* Register vsyscall32 into the ABI table */
#include <linux/sysctl.h>
+static const int zero;
+static const int one = 1;
+
static struct ctl_table abi_table2[] = {
{
.procname = "vsyscall32",
.data = &vdso32_enabled,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = (int *)&zero,
+ .extra2 = (int *)&one,
},
{}
};
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 226ca70dc6bd..139ad7726e10 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -22,6 +22,7 @@
#include <asm/page.h>
#include <asm/desc.h>
#include <asm/cpufeature.h>
+#include <asm/mshyperv.h>
#if defined(CONFIG_X86_64)
unsigned int __read_mostly vdso64_enabled = 1;
@@ -121,6 +122,12 @@ static int vvar_fault(const struct vm_special_mapping *sm,
vmf->address,
__pa(pvti) >> PAGE_SHIFT);
}
+ } else if (sym_offset == image->sym_hvclock_page) {
+ struct ms_hyperv_tsc_page *tsc_pg = hv_get_tsc_page();
+
+ if (tsc_pg && vclock_was_used(VCLOCK_HVCLOCK))
+ ret = vm_insert_pfn(vma, vmf->address,
+ vmalloc_to_pfn(tsc_pg));
}
if (ret == 0 || ret == -EBUSY)
@@ -354,7 +361,7 @@ static void vgetcpu_cpu_init(void *arg)
d.p = 1; /* Present */
d.d = 1; /* 32-bit */
- write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S);
+ write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S);
}
static int vgetcpu_online(unsigned int cpu)
generated by cgit v1.2.3 (git 2.39.0) at 2024-12-18 11:42:27 +0300