summaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-07-08 11:06:29 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2019-07-08 11:06:29 -0700
commit927ba67a63c72ee87d655e30183d1576c3717d3e (patch)
tree85f941aeac5581ef6b612c5b5949f2e2896103c5 /arch
parent2a1ccd31420a7b1acd6ca37b2bec2d723aa093e4 (diff)
parent9176ab1b848059a0cd9caf39f0cebaa1b7ec5ec2 (diff)
downloadlinux-927ba67a63c72ee87d655e30183d1576c3717d3e.tar.bz2
Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull timer updates from Thomas Gleixner: "The timer and timekeeping departement delivers: Core: - The consolidation of the VDSO code into a generic library including the conversion of x86 and ARM64. Conversion of ARM and MIPS are en route through the relevant maintainer trees and should end up in 5.4. This gets rid of the unnecessary different copies of the same code and brings all architectures on the same level of VDSO functionality. - Make the NTP user space interface more robust by restricting the TAI offset to prevent undefined behaviour. Includes a selftest. - Validate user input in the compat settimeofday() syscall to catch invalid values which would be turned into valid values by a multiplication overflow - Consolidate the time accessors - Small fixes, improvements and cleanups all over the place Drivers: - Support for the NXP system counter, TI davinci timer - Move the Microsoft HyperV clocksource/events code into the drivers/clocksource directory so it can be shared between x86 and ARM64. - Overhaul of the Tegra driver - Delay timer support for IXP4xx - Small fixes, improvements and cleanups as usual" * 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (71 commits) time: Validate user input in compat_settimeofday() timer: Document TIMER_PINNED clocksource/drivers: Continue making Hyper-V clocksource ISA agnostic clocksource/drivers: Make Hyper-V clocksource ISA agnostic MAINTAINERS: Fix Andy's surname and the directory entries of VDSO hrtimer: Use a bullet for the returns bullet list arm64: vdso: Fix compilation with clang older than 8 arm64: compat: Fix __arch_get_hw_counter() implementation arm64: Fix __arch_get_hw_counter() implementation lib/vdso: Make delta calculation work correctly MAINTAINERS: Add entry for the generic VDSO library arm64: compat: No need for pre-ARMv7 barriers on an ARMv8 system arm64: vdso: Remove unnecessary asm-offsets.c definitions vdso: Remove superfluous #ifdef __KERNEL__ in vdso/datapage.h clocksource/drivers/davinci: Add support for clocksource clocksource/drivers/davinci: Add support for clockevents clocksource/drivers/tegra: Set up maximum-ticks limit properly clocksource/drivers/tegra: Cycles can't be 0 clocksource/drivers/tegra: Restore base address before cleanup clocksource/drivers/tegra: Add verbose definition for 1MHz constant ...
Diffstat (limited to 'arch')
-rw-r--r--arch/arm/include/asm/arch_timer.h10
-rw-r--r--arch/arm64/Kconfig3
-rw-r--r--arch/arm64/Makefile23
-rw-r--r--arch/arm64/include/asm/arch_timer.h13
-rw-r--r--arch/arm64/include/asm/elf.h14
-rw-r--r--arch/arm64/include/asm/signal32.h46
-rw-r--r--arch/arm64/include/asm/unistd.h5
-rw-r--r--arch/arm64/include/asm/vdso.h3
-rw-r--r--arch/arm64/include/asm/vdso/compat_barrier.h44
-rw-r--r--arch/arm64/include/asm/vdso/compat_gettimeofday.h126
-rw-r--r--arch/arm64/include/asm/vdso/gettimeofday.h103
-rw-r--r--arch/arm64/include/asm/vdso/vsyscall.h53
-rw-r--r--arch/arm64/kernel/Makefile6
-rw-r--r--arch/arm64/kernel/asm-offsets.c34
-rw-r--r--arch/arm64/kernel/signal32.c72
-rw-r--r--arch/arm64/kernel/vdso.c356
-rw-r--r--arch/arm64/kernel/vdso/Makefile41
-rw-r--r--arch/arm64/kernel/vdso/gettimeofday.S323
-rw-r--r--arch/arm64/kernel/vdso/vgettimeofday.c27
-rw-r--r--arch/arm64/kernel/vdso32/.gitignore2
-rw-r--r--arch/arm64/kernel/vdso32/Makefile186
-rw-r--r--arch/arm64/kernel/vdso32/note.c15
-rw-r--r--arch/arm64/kernel/vdso32/sigreturn.S62
-rw-r--r--arch/arm64/kernel/vdso32/vdso.S19
-rw-r--r--arch/arm64/kernel/vdso32/vdso.lds.S82
-rw-r--r--arch/arm64/kernel/vdso32/vgettimeofday.c59
-rw-r--r--arch/x86/Kconfig3
-rw-r--r--arch/x86/entry/vdso/Makefile9
-rw-r--r--arch/x86/entry/vdso/vclock_gettime.c256
-rw-r--r--arch/x86/entry/vdso/vdso.lds.S2
-rw-r--r--arch/x86/entry/vdso/vdso32/vdso32.lds.S2
-rw-r--r--arch/x86/entry/vdso/vdsox32.lds.S1
-rw-r--r--arch/x86/entry/vdso/vma.c2
-rw-r--r--arch/x86/entry/vsyscall/Makefile2
-rw-r--r--arch/x86/entry/vsyscall/vsyscall_gtod.c83
-rw-r--r--arch/x86/hyperv/hv_init.c91
-rw-r--r--arch/x86/include/asm/hyperv-tlfs.h6
-rw-r--r--arch/x86/include/asm/mshyperv.h81
-rw-r--r--arch/x86/include/asm/pvclock.h2
-rw-r--r--arch/x86/include/asm/vdso/gettimeofday.h261
-rw-r--r--arch/x86/include/asm/vdso/vsyscall.h44
-rw-r--r--arch/x86/include/asm/vgtod.h75
-rw-r--r--arch/x86/include/asm/vvar.h7
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c4
-rw-r--r--arch/x86/kernel/pvclock.c1
-rw-r--r--arch/x86/kvm/pmu.c4
-rw-r--r--arch/x86/kvm/x86.c13
47 files changed, 1610 insertions, 1066 deletions
diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h
index 4b66ecd6be99..99175812d903 100644
--- a/arch/arm/include/asm/arch_timer.h
+++ b/arch/arm/include/asm/arch_timer.h
@@ -4,6 +4,7 @@
#include <asm/barrier.h>
#include <asm/errno.h>
+#include <asm/hwcap.h>
#include <linux/clocksource.h>
#include <linux/init.h>
#include <linux/types.h>
@@ -124,6 +125,15 @@ static inline void arch_timer_set_cntkctl(u32 cntkctl)
isb();
}
+static inline void arch_timer_set_evtstrm_feature(void)
+{
+ elf_hwcap |= HWCAP_EVTSTRM;
+}
+
+static inline bool arch_timer_have_evtstrm_feature(void)
+{
+ return elf_hwcap & HWCAP_EVTSTRM;
+}
#endif
#endif
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 089a834b0ed0..c1734e444fb8 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -108,6 +108,8 @@ config ARM64
select GENERIC_STRNCPY_FROM_USER
select GENERIC_STRNLEN_USER
select GENERIC_TIME_VSYSCALL
+ select GENERIC_GETTIMEOFDAY
+ select GENERIC_COMPAT_VDSO if (!CPU_BIG_ENDIAN && COMPAT)
select HANDLE_DOMAIN_IRQ
select HARDIRQS_SW_RESEND
select HAVE_PCI
@@ -161,6 +163,7 @@ config ARM64
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_KPROBES
select HAVE_KRETPROBES
+ select HAVE_GENERIC_VDSO
select IOMMU_DMA if IOMMU_SUPPORT
select IRQ_DOMAIN
select IRQ_FORCED_THREADING
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index e9d2e578cbe6..e3d3fd0a4268 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -49,10 +49,26 @@ $(warning Detected assembler with broken .inst; disassembly will be unreliable)
endif
endif
-KBUILD_CFLAGS += -mgeneral-regs-only $(lseinstr) $(brokengasinst)
+ifeq ($(CONFIG_GENERIC_COMPAT_VDSO), y)
+ CROSS_COMPILE_COMPAT ?= $(CONFIG_CROSS_COMPILE_COMPAT_VDSO:"%"=%)
+
+ ifeq ($(CONFIG_CC_IS_CLANG), y)
+ $(warning CROSS_COMPILE_COMPAT is clang, the compat vDSO will not be built)
+ else ifeq ($(CROSS_COMPILE_COMPAT),)
+ $(warning CROSS_COMPILE_COMPAT not defined or empty, the compat vDSO will not be built)
+ else ifeq ($(shell which $(CROSS_COMPILE_COMPAT)gcc 2> /dev/null),)
+ $(error $(CROSS_COMPILE_COMPAT)gcc not found, check CROSS_COMPILE_COMPAT)
+ else
+ export CROSS_COMPILE_COMPAT
+ export CONFIG_COMPAT_VDSO := y
+ compat_vdso := -DCONFIG_COMPAT_VDSO=1
+ endif
+endif
+
+KBUILD_CFLAGS += -mgeneral-regs-only $(lseinstr) $(brokengasinst) $(compat_vdso)
KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
KBUILD_CFLAGS += $(call cc-disable-warning, psabi)
-KBUILD_AFLAGS += $(lseinstr) $(brokengasinst)
+KBUILD_AFLAGS += $(lseinstr) $(brokengasinst) $(compat_vdso)
KBUILD_CFLAGS += $(call cc-option,-mabi=lp64)
KBUILD_AFLAGS += $(call cc-option,-mabi=lp64)
@@ -164,6 +180,9 @@ ifeq ($(KBUILD_EXTMOD),)
prepare: vdso_prepare
vdso_prepare: prepare0
$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso include/generated/vdso-offsets.h
+ $(if $(CONFIG_COMPAT_VDSO),$(Q)$(MAKE) \
+ $(build)=arch/arm64/kernel/vdso32 \
+ include/generated/vdso32-offsets.h)
endif
define archhelp
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index 6756178c27db..7ae54d7d333a 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -9,6 +9,7 @@
#define __ASM_ARCH_TIMER_H
#include <asm/barrier.h>
+#include <asm/hwcap.h>
#include <asm/sysreg.h>
#include <linux/bug.h>
@@ -229,4 +230,16 @@ static inline int arch_timer_arch_init(void)
return 0;
}
+static inline void arch_timer_set_evtstrm_feature(void)
+{
+ cpu_set_named_feature(EVTSTRM);
+#ifdef CONFIG_COMPAT
+ compat_elf_hwcap |= COMPAT_HWCAP_EVTSTRM;
+#endif
+}
+
+static inline bool arch_timer_have_evtstrm_feature(void)
+{
+ return cpu_have_named_feature(EVTSTRM);
+}
#endif
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index 325d9515c0f8..3c7037c6ba9b 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -202,7 +202,21 @@ typedef compat_elf_greg_t compat_elf_gregset_t[COMPAT_ELF_NGREG];
({ \
set_thread_flag(TIF_32BIT); \
})
+#ifdef CONFIG_GENERIC_COMPAT_VDSO
+#define COMPAT_ARCH_DLINFO \
+do { \
+ /* \
+ * Note that we use Elf64_Off instead of elf_addr_t because \
+ * elf_addr_t in compat is defined as Elf32_Addr and casting \
+ * current->mm->context.vdso to it triggers a cast warning of \
+ * cast from pointer to integer of different size. \
+ */ \
+ NEW_AUX_ENT(AT_SYSINFO_EHDR, \
+ (Elf64_Off)current->mm->context.vdso); \
+} while (0)
+#else
#define COMPAT_ARCH_DLINFO
+#endif
extern int aarch32_setup_additional_pages(struct linux_binprm *bprm,
int uses_interp);
#define compat_arch_setup_additional_pages \
diff --git a/arch/arm64/include/asm/signal32.h b/arch/arm64/include/asm/signal32.h
index 0418c67f2b8b..bd43d1cf724b 100644
--- a/arch/arm64/include/asm/signal32.h
+++ b/arch/arm64/include/asm/signal32.h
@@ -9,6 +9,52 @@
#ifdef CONFIG_COMPAT
#include <linux/compat.h>
+struct compat_sigcontext {
+ /* We always set these two fields to 0 */
+ compat_ulong_t trap_no;
+ compat_ulong_t error_code;
+
+ compat_ulong_t oldmask;
+ compat_ulong_t arm_r0;
+ compat_ulong_t arm_r1;
+ compat_ulong_t arm_r2;
+ compat_ulong_t arm_r3;
+ compat_ulong_t arm_r4;
+ compat_ulong_t arm_r5;
+ compat_ulong_t arm_r6;
+ compat_ulong_t arm_r7;
+ compat_ulong_t arm_r8;
+ compat_ulong_t arm_r9;
+ compat_ulong_t arm_r10;
+ compat_ulong_t arm_fp;
+ compat_ulong_t arm_ip;
+ compat_ulong_t arm_sp;
+ compat_ulong_t arm_lr;
+ compat_ulong_t arm_pc;
+ compat_ulong_t arm_cpsr;
+ compat_ulong_t fault_address;
+};
+
+struct compat_ucontext {
+ compat_ulong_t uc_flags;
+ compat_uptr_t uc_link;
+ compat_stack_t uc_stack;
+ struct compat_sigcontext uc_mcontext;
+ compat_sigset_t uc_sigmask;
+ int __unused[32 - (sizeof(compat_sigset_t) / sizeof(int))];
+ compat_ulong_t uc_regspace[128] __attribute__((__aligned__(8)));
+};
+
+struct compat_sigframe {
+ struct compat_ucontext uc;
+ compat_ulong_t retcode[2];
+};
+
+struct compat_rt_sigframe {
+ struct compat_siginfo info;
+ struct compat_sigframe sig;
+};
+
int compat_setup_frame(int usig, struct ksignal *ksig, sigset_t *set,
struct pt_regs *regs);
int compat_setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index c9f8dd421c5f..2a23614198f1 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -22,8 +22,13 @@
#define __NR_compat_exit 1
#define __NR_compat_read 3
#define __NR_compat_write 4
+#define __NR_compat_gettimeofday 78
#define __NR_compat_sigreturn 119
#define __NR_compat_rt_sigreturn 173
+#define __NR_compat_clock_getres 247
+#define __NR_compat_clock_gettime 263
+#define __NR_compat_clock_gettime64 403
+#define __NR_compat_clock_getres_time64 406
/*
* The following SVCs are ARM private.
diff --git a/arch/arm64/include/asm/vdso.h b/arch/arm64/include/asm/vdso.h
index 1f94ec19903c..9c15e0a06301 100644
--- a/arch/arm64/include/asm/vdso.h
+++ b/arch/arm64/include/asm/vdso.h
@@ -17,6 +17,9 @@
#ifndef __ASSEMBLY__
#include <generated/vdso-offsets.h>
+#ifdef CONFIG_COMPAT_VDSO
+#include <generated/vdso32-offsets.h>
+#endif
#define VDSO_SYMBOL(base, name) \
({ \
diff --git a/arch/arm64/include/asm/vdso/compat_barrier.h b/arch/arm64/include/asm/vdso/compat_barrier.h
new file mode 100644
index 000000000000..fb60a88b5ed4
--- /dev/null
+++ b/arch/arm64/include/asm/vdso/compat_barrier.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 ARM Limited
+ */
+#ifndef __COMPAT_BARRIER_H
+#define __COMPAT_BARRIER_H
+
+#ifndef __ASSEMBLY__
+/*
+ * Warning: This code is meant to be used with
+ * ENABLE_COMPAT_VDSO only.
+ */
+#ifndef ENABLE_COMPAT_VDSO
+#error This header is meant to be used with ENABLE_COMPAT_VDSO only
+#endif
+
+#ifdef dmb
+#undef dmb
+#endif
+
+#define dmb(option) __asm__ __volatile__ ("dmb " #option : : : "memory")
+
+#if __LINUX_ARM_ARCH__ >= 8
+#define aarch32_smp_mb() dmb(ish)
+#define aarch32_smp_rmb() dmb(ishld)
+#define aarch32_smp_wmb() dmb(ishst)
+#else
+#define aarch32_smp_mb() dmb(ish)
+#define aarch32_smp_rmb() aarch32_smp_mb()
+#define aarch32_smp_wmb() dmb(ishst)
+#endif
+
+
+#undef smp_mb
+#undef smp_rmb
+#undef smp_wmb
+
+#define smp_mb() aarch32_smp_mb()
+#define smp_rmb() aarch32_smp_rmb()
+#define smp_wmb() aarch32_smp_wmb()
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __COMPAT_BARRIER_H */
diff --git a/arch/arm64/include/asm/vdso/compat_gettimeofday.h b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
new file mode 100644
index 000000000000..f4812777f5c5
--- /dev/null
+++ b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
@@ -0,0 +1,126 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 ARM Limited
+ */
+#ifndef __ASM_VDSO_GETTIMEOFDAY_H
+#define __ASM_VDSO_GETTIMEOFDAY_H
+
+#ifndef __ASSEMBLY__
+
+#include <asm/unistd.h>
+#include <uapi/linux/time.h>
+
+#include <asm/vdso/compat_barrier.h>
+
+#define __VDSO_USE_SYSCALL ULLONG_MAX
+
+#define VDSO_HAS_CLOCK_GETRES 1
+
+static __always_inline
+int gettimeofday_fallback(struct __kernel_old_timeval *_tv,
+ struct timezone *_tz)
+{
+ register struct timezone *tz asm("r1") = _tz;
+ register struct __kernel_old_timeval *tv asm("r0") = _tv;
+ register long ret asm ("r0");
+ register long nr asm("r7") = __NR_compat_gettimeofday;
+
+ asm volatile(
+ " swi #0\n"
+ : "=r" (ret)
+ : "r" (tv), "r" (tz), "r" (nr)
+ : "memory");
+
+ return ret;
+}
+
+static __always_inline
+long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+ register struct __kernel_timespec *ts asm("r1") = _ts;
+ register clockid_t clkid asm("r0") = _clkid;
+ register long ret asm ("r0");
+ register long nr asm("r7") = __NR_compat_clock_gettime64;
+
+ asm volatile(
+ " swi #0\n"
+ : "=r" (ret)
+ : "r" (clkid), "r" (ts), "r" (nr)
+ : "memory");
+
+ return ret;
+}
+
+static __always_inline
+int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+ register struct __kernel_timespec *ts asm("r1") = _ts;
+ register clockid_t clkid asm("r0") = _clkid;
+ register long ret asm ("r0");
+ register long nr asm("r7") = __NR_compat_clock_getres_time64;
+
+ /* The checks below are required for ABI consistency with arm */
+ if ((_clkid >= MAX_CLOCKS) && (_ts == NULL))
+ return -EINVAL;
+
+ asm volatile(
+ " swi #0\n"
+ : "=r" (ret)
+ : "r" (clkid), "r" (ts), "r" (nr)
+ : "memory");
+
+ return ret;
+}
+
+static __always_inline u64 __arch_get_hw_counter(s32 clock_mode)
+{
+ u64 res;
+
+ /*
+ * clock_mode == 0 implies that vDSO are enabled otherwise
+ * fallback on syscall.
+ */
+ if (clock_mode)
+ return __VDSO_USE_SYSCALL;
+
+ /*
+ * This isb() is required to prevent that the counter value
+ * is speculated.
+ */
+ isb();
+ asm volatile("mrrc p15, 1, %Q0, %R0, c14" : "=r" (res));
+ /*
+ * This isb() is required to prevent that the seq lock is
+ * speculated.
+ */
+ isb();
+
+ return res;
+}
+
+static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
+{
+ const struct vdso_data *ret;
+
+ /*
+ * This simply puts &_vdso_data into ret. The reason why we don't use
+ * `ret = _vdso_data` is that the compiler tends to optimise this in a
+ * very suboptimal way: instead of keeping &_vdso_data in a register,
+ * it goes through a relocation almost every time _vdso_data must be
+ * accessed (even in subfunctions). This is both time and space
+ * consuming: each relocation uses a word in the code section, and it
+ * has to be loaded at runtime.
+ *
+ * This trick hides the assignment from the compiler. Since it cannot
+ * track where the pointer comes from, it will only use one relocation
+ * where __arch_get_vdso_data() is called, and then keep the result in
+ * a register.
+ */
+ asm volatile("mov %0, %1" : "=r"(ret) : "r"(_vdso_data));
+
+ return ret;
+}
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/arm64/include/asm/vdso/gettimeofday.h b/arch/arm64/include/asm/vdso/gettimeofday.h
new file mode 100644
index 000000000000..b08f476b72b4
--- /dev/null
+++ b/arch/arm64/include/asm/vdso/gettimeofday.h
@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 ARM Limited
+ */
+#ifndef __ASM_VDSO_GETTIMEOFDAY_H
+#define __ASM_VDSO_GETTIMEOFDAY_H
+
+#ifndef __ASSEMBLY__
+
+#include <asm/unistd.h>
+#include <uapi/linux/time.h>
+
+#define __VDSO_USE_SYSCALL ULLONG_MAX
+
+#define VDSO_HAS_CLOCK_GETRES 1
+
+static __always_inline
+int gettimeofday_fallback(struct __kernel_old_timeval *_tv,
+ struct timezone *_tz)
+{
+ register struct timezone *tz asm("x1") = _tz;
+ register struct __kernel_old_timeval *tv asm("x0") = _tv;
+ register long ret asm ("x0");
+ register long nr asm("x8") = __NR_gettimeofday;
+
+ asm volatile(
+ " svc #0\n"
+ : "=r" (ret)
+ : "r" (tv), "r" (tz), "r" (nr)
+ : "memory");
+
+ return ret;
+}
+
+static __always_inline
+long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+ register struct __kernel_timespec *ts asm("x1") = _ts;
+ register clockid_t clkid asm("x0") = _clkid;
+ register long ret asm ("x0");
+ register long nr asm("x8") = __NR_clock_gettime;
+
+ asm volatile(
+ " svc #0\n"
+ : "=r" (ret)
+ : "r" (clkid), "r" (ts), "r" (nr)
+ : "memory");
+
+ return ret;
+}
+
+static __always_inline
+int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+ register struct __kernel_timespec *ts asm("x1") = _ts;
+ register clockid_t clkid asm("x0") = _clkid;
+ register long ret asm ("x0");
+ register long nr asm("x8") = __NR_clock_getres;
+
+ asm volatile(
+ " svc #0\n"
+ : "=r" (ret)
+ : "r" (clkid), "r" (ts), "r" (nr)
+ : "memory");
+
+ return ret;
+}
+
+static __always_inline u64 __arch_get_hw_counter(s32 clock_mode)
+{
+ u64 res;
+
+ /*
+ * clock_mode == 0 implies that vDSO are enabled otherwise
+ * fallback on syscall.
+ */
+ if (clock_mode)
+ return __VDSO_USE_SYSCALL;
+
+ /*
+ * This isb() is required to prevent that the counter value
+ * is speculated.
+ */
+ isb();
+ asm volatile("mrs %0, cntvct_el0" : "=r" (res) :: "memory");
+ /*
+ * This isb() is required to prevent that the seq lock is
+ * speculated.#
+ */
+ isb();
+
+ return res;
+}
+
+static __always_inline
+const struct vdso_data *__arch_get_vdso_data(void)
+{
+ return _vdso_data;
+}
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/arm64/include/asm/vdso/vsyscall.h b/arch/arm64/include/asm/vdso/vsyscall.h
new file mode 100644
index 000000000000..0c731bfc7c8c
--- /dev/null
+++ b/arch/arm64/include/asm/vdso/vsyscall.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_VDSO_VSYSCALL_H
+#define __ASM_VDSO_VSYSCALL_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/timekeeper_internal.h>
+#include <vdso/datapage.h>
+
+#define VDSO_PRECISION_MASK ~(0xFF00ULL<<48)
+
+extern struct vdso_data *vdso_data;
+
+/*
+ * Update the vDSO data page to keep in sync with kernel timekeeping.
+ */
+static __always_inline
+struct vdso_data *__arm64_get_k_vdso_data(void)
+{
+ return vdso_data;
+}
+#define __arch_get_k_vdso_data __arm64_get_k_vdso_data
+
+static __always_inline
+int __arm64_get_clock_mode(struct timekeeper *tk)
+{
+ u32 use_syscall = !tk->tkr_mono.clock->archdata.vdso_direct;
+
+ return use_syscall;
+}
+#define __arch_get_clock_mode __arm64_get_clock_mode
+
+static __always_inline
+int __arm64_use_vsyscall(struct vdso_data *vdata)
+{
+ return !vdata[CS_HRES_COARSE].clock_mode;
+}
+#define __arch_use_vsyscall __arm64_use_vsyscall
+
+static __always_inline
+void __arm64_update_vsyscall(struct vdso_data *vdata, struct timekeeper *tk)
+{
+ vdata[CS_HRES_COARSE].mask = VDSO_PRECISION_MASK;
+ vdata[CS_RAW].mask = VDSO_PRECISION_MASK;
+}
+#define __arch_update_vsyscall __arm64_update_vsyscall
+
+/* The asm-generic header needs to be included after the definitions above */
+#include <asm-generic/vdso/vsyscall.h>
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_VSYSCALL_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 9e7dcb2c31c7..478491f07b4f 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -28,7 +28,10 @@ $(obj)/%.stub.o: $(obj)/%.o FORCE
$(call if_changed,objcopy)
obj-$(CONFIG_COMPAT) += sys32.o signal32.o \
- sigreturn32.o sys_compat.o
+ sys_compat.o
+ifneq ($(CONFIG_COMPAT_VDSO), y)
+obj-$(CONFIG_COMPAT) += sigreturn32.o
+endif
obj-$(CONFIG_KUSER_HELPERS) += kuser32.o
obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o entry-ftrace.o
obj-$(CONFIG_MODULES) += module.o
@@ -62,6 +65,7 @@ obj-$(CONFIG_ARM64_SSBD) += ssbd.o
obj-$(CONFIG_ARM64_PTR_AUTH) += pointer_auth.o
obj-y += vdso/ probes/
+obj-$(CONFIG_COMPAT_VDSO) += vdso32/
head-y := head.o
extra-y += $(head-y) vmlinux.lds
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 02f08768c298..214685760e1c 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -18,9 +18,9 @@
#include <asm/fixmap.h>
#include <asm/thread_info.h>
#include <asm/memory.h>
+#include <asm/signal32.h>
#include <asm/smp_plat.h>
#include <asm/suspend.h>
-#include <asm/vdso_datapage.h>
#include <linux/kbuild.h>
#include <linux/arm-smccc.h>
@@ -66,6 +66,11 @@ int main(void)
DEFINE(S_STACKFRAME, offsetof(struct pt_regs, stackframe));
DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs));
BLANK();
+#ifdef CONFIG_COMPAT
+ DEFINE(COMPAT_SIGFRAME_REGS_OFFSET, offsetof(struct compat_sigframe, uc.uc_mcontext.arm_r0));
+ DEFINE(COMPAT_RT_SIGFRAME_REGS_OFFSET, offsetof(struct compat_rt_sigframe, sig.uc.uc_mcontext.arm_r0));
+ BLANK();
+#endif
DEFINE(MM_CONTEXT_ID, offsetof(struct mm_struct, context.id.counter));
BLANK();
DEFINE(VMA_VM_MM, offsetof(struct vm_area_struct, vm_mm));
@@ -80,33 +85,6 @@ int main(void)
BLANK();
DEFINE(PREEMPT_DISABLE_OFFSET, PREEMPT_DISABLE_OFFSET);
BLANK();
- DEFINE(CLOCK_REALTIME, CLOCK_REALTIME);
- DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC);
- DEFINE(CLOCK_MONOTONIC_RAW, CLOCK_MONOTONIC_RAW);
- DEFINE(CLOCK_REALTIME_RES, offsetof(struct vdso_data, hrtimer_res));
- DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
- DEFINE(CLOCK_MONOTONIC_COARSE,CLOCK_MONOTONIC_COARSE);
- DEFINE(CLOCK_COARSE_RES, LOW_RES_NSEC);
- DEFINE(NSEC_PER_SEC, NSEC_PER_SEC);
- BLANK();
- DEFINE(VDSO_CS_CYCLE_LAST, offsetof(struct vdso_data, cs_cycle_last));
- DEFINE(VDSO_RAW_TIME_SEC, offsetof(struct vdso_data, raw_time_sec));
- DEFINE(VDSO_XTIME_CLK_SEC, offsetof(struct vdso_data, xtime_clock_sec));
- DEFINE(VDSO_XTIME_CRS_SEC, offsetof(struct vdso_data, xtime_coarse_sec));
- DEFINE(VDSO_XTIME_CRS_NSEC, offsetof(struct vdso_data, xtime_coarse_nsec));
- DEFINE(VDSO_WTM_CLK_SEC, offsetof(struct vdso_data, wtm_clock_sec));
- DEFINE(VDSO_TB_SEQ_COUNT, offsetof(struct vdso_data, tb_seq_count));
- DEFINE(VDSO_CS_MONO_MULT, offsetof(struct vdso_data, cs_mono_mult));
- DEFINE(VDSO_CS_SHIFT, offsetof(struct vdso_data, cs_shift));
- DEFINE(VDSO_TZ_MINWEST, offsetof(struct vdso_data, tz_minuteswest));
- DEFINE(VDSO_USE_SYSCALL, offsetof(struct vdso_data, use_syscall));
- BLANK();
- DEFINE(TVAL_TV_SEC, offsetof(struct timeval, tv_sec));
- DEFINE(TSPEC_TV_SEC, offsetof(struct timespec, tv_sec));
- BLANK();
- DEFINE(TZ_MINWEST, offsetof(struct timezone, tz_minuteswest));
- DEFINE(TZ_DSTTIME, offsetof(struct timezone, tz_dsttime));
- BLANK();
DEFINE(CPU_BOOT_STACK, offsetof(struct secondary_data, stack));
DEFINE(CPU_BOOT_TASK, offsetof(struct secondary_data, task));
BLANK();
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 331d1e5acad4..12a585386c2f 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -18,42 +18,7 @@
#include <asm/traps.h>
#include <linux/uaccess.h>
#include <asm/unistd.h>
-
-struct compat_sigcontext {
- /* We always set these two fields to 0 */
- compat_ulong_t trap_no;
- compat_ulong_t error_code;
-
- compat_ulong_t oldmask;
- compat_ulong_t arm_r0;
- compat_ulong_t arm_r1;
- compat_ulong_t arm_r2;
- compat_ulong_t arm_r3;
- compat_ulong_t arm_r4;
- compat_ulong_t arm_r5;
- compat_ulong_t arm_r6;
- compat_ulong_t arm_r7;
- compat_ulong_t arm_r8;
- compat_ulong_t arm_r9;
- compat_ulong_t arm_r10;
- compat_ulong_t arm_fp;
- compat_ulong_t arm_ip;
- compat_ulong_t arm_sp;
- compat_ulong_t arm_lr;
- compat_ulong_t arm_pc;
- compat_ulong_t arm_cpsr;
- compat_ulong_t fault_address;
-};
-
-struct compat_ucontext {
- compat_ulong_t uc_flags;
- compat_uptr_t uc_link;
- compat_stack_t uc_stack;
- struct compat_sigcontext uc_mcontext;
- compat_sigset_t uc_sigmask;
- int __unused[32 - (sizeof (compat_sigset_t) / sizeof (int))];
- compat_ulong_t uc_regspace[128] __attribute__((__aligned__(8)));
-};
+#include <asm/vdso.h>
struct compat_vfp_sigframe {
compat_ulong_t magic;
@@ -81,16 +46,6 @@ struct compat_aux_sigframe {
unsigned long end_magic;
} __attribute__((__aligned__(8)));
-struct compat_sigframe {
- struct compat_ucontext uc;
- compat_ulong_t retcode[2];
-};
-
-struct compat_rt_sigframe {
- struct compat_siginfo info;
- struct compat_sigframe sig;
-};
-
#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
static inline int put_sigset_t(compat_sigset_t __user *uset, sigset_t *set)
@@ -387,6 +342,30 @@ static void compat_setup_return(struct pt_regs *regs, struct k_sigaction *ka,
retcode = ptr_to_compat(ka->sa.sa_restorer);
} else {
/* Set up sigreturn pointer */
+#ifdef CONFIG_COMPAT_VDSO
+ void *vdso_base = current->mm->context.vdso;
+ void *vdso_trampoline;
+
+ if (ka->sa.sa_flags & SA_SIGINFO) {
+ if (thumb) {
+ vdso_trampoline = VDSO_SYMBOL(vdso_base,
+ compat_rt_sigreturn_thumb);
+ } else {
+ vdso_trampoline = VDSO_SYMBOL(vdso_base,
+ compat_rt_sigreturn_arm);
+ }
+ } else {
+ if (thumb) {
+ vdso_trampoline = VDSO_SYMBOL(vdso_base,
+ compat_sigreturn_thumb);
+ } else {
+ vdso_trampoline = VDSO_SYMBOL(vdso_base,
+ compat_sigreturn_arm);
+ }
+ }
+
+ retcode = ptr_to_compat(vdso_trampoline) + thumb;
+#else
unsigned int idx = thumb << 1;
if (ka->sa.sa_flags & SA_SIGINFO)
@@ -394,6 +373,7 @@ static void compat_setup_return(struct pt_regs *regs, struct k_sigaction *ka,
retcode = (unsigned long)current->mm->context.vdso +
(idx << 2) + thumb;
+#endif
}
regs->regs[0] = usig;
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 663b166241d0..354b11e27c07 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -20,41 +20,212 @@
#include <linux/slab.h>
#include <linux/timekeeper_internal.h>
#include <linux/vmalloc.h>
+#include <vdso/datapage.h>
+#include <vdso/helpers.h>
+#include <vdso/vsyscall.h>
#include <asm/cacheflush.h>
#include <asm/signal32.h>
#include <asm/vdso.h>
-#include <asm/vdso_datapage.h>
extern char vdso_start[], vdso_end[];
-static unsigned long vdso_pages __ro_after_init;
+#ifdef CONFIG_COMPAT_VDSO
+extern char vdso32_start[], vdso32_end[];
+#endif /* CONFIG_COMPAT_VDSO */
+
+/* vdso_lookup arch_index */
+enum arch_vdso_type {
+ ARM64_VDSO = 0,
+#ifdef CONFIG_COMPAT_VDSO
+ ARM64_VDSO32 = 1,
+#endif /* CONFIG_COMPAT_VDSO */
+};
+#ifdef CONFIG_COMPAT_VDSO
+#define VDSO_TYPES (ARM64_VDSO32 + 1)
+#else
+#define VDSO_TYPES (ARM64_VDSO + 1)
+#endif /* CONFIG_COMPAT_VDSO */
+
+struct __vdso_abi {
+ const char *name;
+ const char *vdso_code_start;
+ const char *vdso_code_end;
+ unsigned long vdso_pages;
+ /* Data Mapping */
+ struct vm_special_mapping *dm;
+ /* Code Mapping */
+ struct vm_special_mapping *cm;
+};
+
+static struct __vdso_abi vdso_lookup[VDSO_TYPES] __ro_after_init = {
+ {
+ .name = "vdso",
+ .vdso_code_start = vdso_start,
+ .vdso_code_end = vdso_end,
+ },
+#ifdef CONFIG_COMPAT_VDSO
+ {
+ .name = "vdso32",
+ .vdso_code_start = vdso32_start,
+ .vdso_code_end = vdso32_end,
+ },
+#endif /* CONFIG_COMPAT_VDSO */
+};
/*
* The vDSO data page.
*/
static union {
- struct vdso_data data;
+ struct vdso_data data[CS_BASES];
u8 page[PAGE_SIZE];
} vdso_data_store __page_aligned_data;
-struct vdso_data *vdso_data = &vdso_data_store.data;
+struct vdso_data *vdso_data = vdso_data_store.data;
+
+static int __vdso_remap(enum arch_vdso_type arch_index,
+ const struct vm_special_mapping *sm,
+ struct vm_area_struct *new_vma)
+{
+ unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
+ unsigned long vdso_size = vdso_lookup[arch_index].vdso_code_end -
+ vdso_lookup[arch_index].vdso_code_start;
+
+ if (vdso_size != new_size)
+ return -EINVAL;
+
+ current->mm->context.vdso = (void *)new_vma->vm_start;
+
+ return 0;
+}
+
+static int __vdso_init(enum arch_vdso_type arch_index)
+{
+ int i;
+ struct page **vdso_pagelist;
+ unsigned long pfn;
+
+ if (memcmp(vdso_lookup[arch_index].vdso_code_start, "\177ELF", 4)) {
+ pr_err("vDSO is not a valid ELF object!\n");
+ return -EINVAL;
+ }
+
+ vdso_lookup[arch_index].vdso_pages = (
+ vdso_lookup[arch_index].vdso_code_end -
+ vdso_lookup[arch_index].vdso_code_start) >>
+ PAGE_SHIFT;
+
+ /* Allocate the vDSO pagelist, plus a page for the data. */
+ vdso_pagelist = kcalloc(vdso_lookup[arch_index].vdso_pages + 1,
+ sizeof(struct page *),
+ GFP_KERNEL);
+ if (vdso_pagelist == NULL)
+ return -ENOMEM;
+
+ /* Grab the vDSO data page. */
+ vdso_pagelist[0] = phys_to_page(__pa_symbol(vdso_data));
+
+
+ /* Grab the vDSO code pages. */
+ pfn = sym_to_pfn(vdso_lookup[arch_index].vdso_code_start);
+
+ for (i = 0; i < vdso_lookup[arch_index].vdso_pages; i++)
+ vdso_pagelist[i + 1] = pfn_to_page(pfn + i);
+
+ vdso_lookup[arch_index].dm->pages = &vdso_pagelist[0];
+ vdso_lookup[arch_index].cm->pages = &vdso_pagelist[1];
+
+ return 0;
+}
+
+static int __setup_additional_pages(enum arch_vdso_type arch_index,
+ struct mm_struct *mm,
+ struct linux_binprm *bprm,
+ int uses_interp)
+{
+ unsigned long vdso_base, vdso_text_len, vdso_mapping_len;
+ void *ret;
+
+ vdso_text_len = vdso_lookup[arch_index].vdso_pages << PAGE_SHIFT;
+ /* Be sure to map the data page */
+ vdso_mapping_len = vdso_text_len + PAGE_SIZE;
+
+ vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0);
+ if (IS_ERR_VALUE(vdso_base)) {
+ ret = ERR_PTR(vdso_base);
+ goto up_fail;
+ }
+
+ ret = _install_special_mapping(mm, vdso_base, PAGE_SIZE,
+ VM_READ|VM_MAYREAD,
+ vdso_lookup[arch_index].dm);
+ if (IS_ERR(ret))
+ goto up_fail;
+
+ vdso_base += PAGE_SIZE;
+ mm->context.vdso = (void *)vdso_base;
+ ret = _install_special_mapping(mm, vdso_base, vdso_text_len,
+ VM_READ|VM_EXEC|
+ VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
+ vdso_lookup[arch_index].cm);
+ if (IS_ERR(ret))
+ goto up_fail;
+
+ return 0;
+
+up_fail:
+ mm->context.vdso = NULL;
+ return PTR_ERR(ret);
+}
#ifdef CONFIG_COMPAT
/*
* Create and map the vectors page for AArch32 tasks.
*/
+#ifdef CONFIG_COMPAT_VDSO
+static int aarch32_vdso_mremap(const struct vm_special_mapping *sm,
+ struct vm_area_struct *new_vma)
+{
+ return __vdso_remap(ARM64_VDSO32, sm, new_vma);
+}
+#endif /* CONFIG_COMPAT_VDSO */
+
+/*
+ * aarch32_vdso_pages:
+ * 0 - kuser helpers
+ * 1 - sigreturn code
+ * or (CONFIG_COMPAT_VDSO):
+ * 0 - kuser helpers
+ * 1 - vdso data
+ * 2 - vdso code
+ */
#define C_VECTORS 0
+#ifdef CONFIG_COMPAT_VDSO
+#define C_VVAR 1
+#define C_VDSO 2
+#define C_PAGES (C_VDSO + 1)
+#else
#define C_SIGPAGE 1
#define C_PAGES (C_SIGPAGE + 1)
+#endif /* CONFIG_COMPAT_VDSO */
static struct page *aarch32_vdso_pages[C_PAGES] __ro_after_init;
-static const struct vm_special_mapping aarch32_vdso_spec[C_PAGES] = {
+static struct vm_special_mapping aarch32_vdso_spec[C_PAGES] = {
{
.name = "[vectors]", /* ABI */
.pages = &aarch32_vdso_pages[C_VECTORS],
},
+#ifdef CONFIG_COMPAT_VDSO
+ {
+ .name = "[vvar]",
+ },
+ {
+ .name = "[vdso]",
+ .mremap = aarch32_vdso_mremap,
+ },
+#else
{
.name = "[sigpage]", /* ABI */
.pages = &aarch32_vdso_pages[C_SIGPAGE],
},
+#endif /* CONFIG_COMPAT_VDSO */
};
static int aarch32_alloc_kuser_vdso_page(void)
@@ -77,7 +248,33 @@ static int aarch32_alloc_kuser_vdso_page(void)
return 0;
}
-static int __init aarch32_alloc_vdso_pages(void)
+#ifdef CONFIG_COMPAT_VDSO
+static int __aarch32_alloc_vdso_pages(void)
+{
+ int ret;
+
+ vdso_lookup[ARM64_VDSO32].dm = &aarch32_vdso_spec[C_VVAR];
+ vdso_lookup[ARM64_VDSO32].cm = &aarch32_vdso_spec[C_VDSO];
+
+ ret = __vdso_init(ARM64_VDSO32);
+ if (ret)
+ return ret;
+
+ ret = aarch32_alloc_kuser_vdso_page();
+ if (ret) {
+ unsigned long c_vvar =
+ (unsigned long)page_to_virt(aarch32_vdso_pages[C_VVAR]);
+ unsigned long c_vdso =
+ (unsigned long)page_to_virt(aarch32_vdso_pages[C_VDSO]);
+
+ free_page(c_vvar);
+ free_page(c_vdso);
+ }
+
+ return ret;
+}
+#else
+static int __aarch32_alloc_vdso_pages(void)
{
extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[];
int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start;
@@ -98,6 +295,12 @@ static int __init aarch32_alloc_vdso_pages(void)
return ret;
}
+#endif /* CONFIG_COMPAT_VDSO */
+
+static int __init aarch32_alloc_vdso_pages(void)
+{
+ return __aarch32_alloc_vdso_pages();
+}
arch_initcall(aarch32_alloc_vdso_pages);
static int aarch32_kuser_helpers_setup(struct mm_struct *mm)
@@ -119,6 +322,7 @@ static int aarch32_kuser_helpers_setup(struct mm_struct *mm)
return PTR_ERR_OR_ZERO(ret);
}
+#ifndef CONFIG_COMPAT_VDSO
static int aarch32_sigreturn_setup(struct mm_struct *mm)
{
unsigned long addr;
@@ -146,6 +350,7 @@ static int aarch32_sigreturn_setup(struct mm_struct *mm)
out:
return PTR_ERR_OR_ZERO(ret);
}
+#endif /* !CONFIG_COMPAT_VDSO */
int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
{
@@ -159,7 +364,14 @@ int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
if (ret)
goto out;
+#ifdef CONFIG_COMPAT_VDSO
+ ret = __setup_additional_pages(ARM64_VDSO32,
+ mm,
+ bprm,
+ uses_interp);
+#else
ret = aarch32_sigreturn_setup(mm);
+#endif /* CONFIG_COMPAT_VDSO */
out:
up_write(&mm->mmap_sem);
@@ -170,18 +382,18 @@ out:
static int vdso_mremap(const struct vm_special_mapping *sm,
struct vm_area_struct *new_vma)
{
- unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
- unsigned long vdso_size = vdso_end - vdso_start;
-
- if (vdso_size != new_size)
- return -EINVAL;
-
- current->mm->context.vdso = (void *)new_vma->vm_start;
-
- return 0;
+ return __vdso_remap(ARM64_VDSO, sm, new_vma);
}
-static struct vm_special_mapping vdso_spec[2] __ro_after_init = {
+/*
+ * aarch64_vdso_pages:
+ * 0 - vvar
+ * 1 - vdso
+ */
+#define A_VVAR 0
+#define A_VDSO 1
+#define A_PAGES (A_VDSO + 1)
+static struct vm_special_mapping vdso_spec[A_PAGES] __ro_after_init = {
{
.name = "[vvar]",
},
@@ -193,37 +405,10 @@ static struct vm_special_mapping vdso_spec[2] __ro_after_init = {
static int __init vdso_init(void)
{
- int i;
- struct page **vdso_pagelist;
- unsigned long pfn;
-
- if (memcmp(vdso_start, "\177ELF", 4)) {
- pr_err("vDSO is not a valid ELF object!\n");
- return -EINVAL;
- }
-
- vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT;
-
- /* Allocate the vDSO pagelist, plus a page for the data. */
- vdso_pagelist = kcalloc(vdso_pages + 1, sizeof(struct page *),
- GFP_KERNEL);
- if (vdso_pagelist == NULL)
- return -ENOMEM;
-
- /* Grab the vDSO data page. */
- vdso_pagelist[0] = phys_to_page(__pa_symbol(vdso_data));
-
-
- /* Grab the vDSO code pages. */
- pfn = sym_to_pfn(vdso_start);
-
- for (i = 0; i < vdso_pages; i++)
- vdso_pagelist[i + 1] = pfn_to_page(pfn + i);
+ vdso_lookup[ARM64_VDSO].dm = &vdso_spec[A_VVAR];
+ vdso_lookup[ARM64_VDSO].cm = &vdso_spec[A_VDSO];
- vdso_spec[0].pages = &vdso_pagelist[0];
- vdso_spec[1].pages = &vdso_pagelist[1];
-
- return 0;
+ return __vdso_init(ARM64_VDSO);
}
arch_initcall(vdso_init);
@@ -231,84 +416,17 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
int uses_interp)
{
struct mm_struct *mm = current->mm;
- unsigned long vdso_base, vdso_text_len, vdso_mapping_len;
- void *ret;
-
- vdso_text_len = vdso_pages << PAGE_SHIFT;
- /* Be sure to map the data page */
- vdso_mapping_len = vdso_text_len + PAGE_SIZE;
+ int ret;
if (down_write_killable(&mm->mmap_sem))
return -EINTR;
- vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0);
- if (IS_ERR_VALUE(vdso_base)) {
- ret = ERR_PTR(vdso_base);
- goto up_fail;
- }
- ret = _install_special_mapping(mm, vdso_base, PAGE_SIZE,
- VM_READ|VM_MAYREAD,
- &vdso_spec[0]);
- if (IS_ERR(ret))
- goto up_fail;
-
- vdso_base += PAGE_SIZE;
- mm->context.vdso = (void *)vdso_base;
- ret = _install_special_mapping(mm, vdso_base, vdso_text_len,
- VM_READ|VM_EXEC|
- VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
- &vdso_spec[1]);
- if (IS_ERR(ret))
- goto up_fail;
+ ret = __setup_additional_pages(ARM64_VDSO,
+ mm,
+ bprm,
+ uses_interp);
up_write(&mm->mmap_sem);
- return 0;
-
-up_fail:
- mm->context.vdso = NULL;
- up_write(&mm->mmap_sem);
- return PTR_ERR(ret);
-}
-/*
- * Update the vDSO data page to keep in sync with kernel timekeeping.
- */
-void update_vsyscall(struct timekeeper *tk)
-{
- u32 use_syscall = !tk->tkr_mono.clock->archdata.vdso_direct;
-
- ++vdso_data->tb_seq_count;
- smp_wmb();
-
- vdso_data->use_syscall = use_syscall;
- vdso_data->xtime_coarse_sec = tk->xtime_sec;
- vdso_data->xtime_coarse_nsec = tk->tkr_mono.xtime_nsec >>
- tk->tkr_mono.shift;
- vdso_data->wtm_clock_sec = tk->wall_to_monotonic.tv_sec;
- vdso_data->wtm_clock_nsec = tk->wall_to_monotonic.tv_nsec;
-
- /* Read without the seqlock held by clock_getres() */
- WRITE_ONCE(vdso_data->hrtimer_res, hrtimer_resolution);
-
- if (!use_syscall) {
- /* tkr_mono.cycle_last == tkr_raw.cycle_last */
- vdso_data->cs_cycle_last = tk->tkr_mono.cycle_last;
- vdso_data->raw_time_sec = tk->raw_sec;
- vdso_data->raw_time_nsec = tk->tkr_raw.xtime_nsec;
- vdso_data->xtime_clock_sec = tk->xtime_sec;
- vdso_data->xtime_clock_nsec = tk->tkr_mono.xtime_nsec;
- vdso_data->cs_mono_mult = tk->tkr_mono.mult;
- vdso_data->cs_raw_mult = tk->tkr_raw.mult;
- /* tkr_mono.shift == tkr_raw.shift */
- vdso_data->cs_shift = tk->tkr_mono.shift;
- }
-
- smp_wmb();
- ++vdso_data->tb_seq_count;
-}
-
-void update_vsyscall_tz(void)
-{
- vdso_data->tz_minuteswest = sys_tz.tz_minuteswest;
- vdso_data->tz_dsttime = sys_tz.tz_dsttime;
+ return ret;
}
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index fa230ff09aa1..4ab863045188 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -6,7 +6,12 @@
# Heavily based on the vDSO Makefiles for other archs.
#
-obj-vdso := gettimeofday.o note.o sigreturn.o
+# Absolute relocation type $(ARCH_REL_TYPE_ABS) needs to be defined before
+# the inclusion of generic Makefile.
+ARCH_REL_TYPE_ABS := R_AARCH64_JUMP_SLOT|R_AARCH64_GLOB_DAT|R_AARCH64_ABS64
+include $(srctree)/lib/vdso/Makefile
+
+obj-vdso := vgettimeofday.o note.o sigreturn.o
# Build rules
targets := $(obj-vdso) vdso.so vdso.so.dbg
@@ -15,6 +20,31 @@ obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \
--build-id -n -T
+ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18
+ccflags-y += -DDISABLE_BRANCH_PROFILING
+
+VDSO_LDFLAGS := -Bsymbolic
+
+CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os
+KBUILD_CFLAGS += $(DISABLE_LTO)
+KASAN_SANITIZE := n
+UBSAN_SANITIZE := n
+OBJECT_FILES_NON_STANDARD := y
+KCOV_INSTRUMENT := n
+
+ifeq ($(c-gettimeofday-y),)
+CFLAGS_vgettimeofday.o = -O2 -mcmodel=tiny
+else
+CFLAGS_vgettimeofday.o = -O2 -mcmodel=tiny -include $(c-gettimeofday-y)
+endif
+
+# Clang versions less than 8 do not support -mcmodel=tiny
+ifeq ($(CONFIG_CC_IS_CLANG), y)
+ ifeq ($(shell test $(CONFIG_CLANG_VERSION) -lt 80000; echo $$?),0)
+ CFLAGS_REMOVE_vgettimeofday.o += -mcmodel=tiny
+ endif
+endif
+
# Disable gcov profiling for VDSO code
GCOV_PROFILE := n
@@ -28,6 +58,7 @@ $(obj)/vdso.o : $(obj)/vdso.so
# Link rule for the .so file, .lds has to be first
$(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE
$(call if_changed,ld)
+ $(call if_changed,vdso_check)
# Strip rule for the .so file
$(obj)/%.so: OBJCOPYFLAGS := -S
@@ -42,13 +73,9 @@ quiet_cmd_vdsosym = VDSOSYM $@
include/generated/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE
$(call if_changed,vdsosym)
-# Assembly rules for the .S files
-$(obj-vdso): %.o: %.S FORCE
- $(call if_changed_dep,vdsoas)
-
# Actual build commands
-quiet_cmd_vdsoas = VDSOA $@
- cmd_vdsoas = $(CC) $(a_flags) -c -o $@ $<
+quiet_cmd_vdsocc = VDSOCC $@
+ cmd_vdsocc = $(CC) $(a_flags) $(c_flags) -c -o $@ $<
# Install commands for the unstripped file
quiet_cmd_vdso_install = INSTALL $@
diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S
index 80f780f56e0d..e69de29bb2d1 100644
--- a/arch/arm64/kernel/vdso/gettimeofday.S
+++ b/arch/arm64/kernel/vdso/gettimeofday.S
@@ -1,323 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Userspace implementations of gettimeofday() and friends.
- *
- * Copyright (C) 2012 ARM Limited
- *
- * Author: Will Deacon <will.deacon@arm.com>
- */
-
-#include <linux/linkage.h>
-#include <asm/asm-offsets.h>
-#include <asm/unistd.h>
-
-#define NSEC_PER_SEC_LO16 0xca00
-#define NSEC_PER_SEC_HI16 0x3b9a
-
-vdso_data .req x6
-seqcnt .req w7
-w_tmp .req w8
-x_tmp .req x8
-
-/*
- * Conventions for macro arguments:
- * - An argument is write-only if its name starts with "res".
- * - All other arguments are read-only, unless otherwise specified.
- */
-
- .macro seqcnt_acquire
-9999: ldr seqcnt, [vdso_data, #VDSO_TB_SEQ_COUNT]
- tbnz seqcnt, #0, 9999b
- dmb ishld
- .endm
-
- .macro seqcnt_check fail
- dmb ishld
- ldr w_tmp, [vdso_data, #VDSO_TB_SEQ_COUNT]
- cmp w_tmp, seqcnt
- b.ne \fail
- .endm
-
- .macro syscall_check fail
- ldr w_tmp, [vdso_data, #VDSO_USE_SYSCALL]
- cbnz w_tmp, \fail
- .endm
-
- .macro get_nsec_per_sec res
- mov \res, #NSEC_PER_SEC_LO16
- movk \res, #NSEC_PER_SEC_HI16, lsl #16
- .endm
-
- /*
- * Returns the clock delta, in nanoseconds left-shifted by the clock
- * shift.
- */
- .macro get_clock_shifted_nsec res, cycle_last, mult
- /* Read the virtual counter. */
- isb
- mrs x_tmp, cntvct_el0
- /* Calculate cycle delta and convert to ns. */
- sub \res, x_tmp, \cycle_last
- /* We can only guarantee 56 bits of precision. */
- movn x_tmp, #0xff00, lsl #48
- and \res, x_tmp, \res
- mul \res, \res, \mult
- /*
- * Fake address dependency from the value computed from the counter
- * register to subsequent data page accesses so that the sequence
- * locking also orders the read of the counter.
- */
- and x_tmp, \res, xzr
- add vdso_data, vdso_data, x_tmp
- .endm
-
- /*
- * Returns in res_{sec,nsec} the REALTIME timespec, based on the
- * "wall time" (xtime) and the clock_mono delta.
- */
- .macro get_ts_realtime res_sec, res_nsec, \
- clock_nsec, xtime_sec, xtime_nsec, nsec_to_sec
- add \res_nsec, \clock_nsec, \xtime_nsec
- udiv x_tmp, \res_nsec, \nsec_to_sec
- add \res_sec, \xtime_sec, x_tmp
- msub \res_nsec, x_tmp, \nsec_to_sec, \res_nsec
- .endm
-
- /*
- * Returns in res_{sec,nsec} the timespec based on the clock_raw delta,
- * used for CLOCK_MONOTONIC_RAW.
- */
- .macro get_ts_clock_raw res_sec, res_nsec, clock_nsec, nsec_to_sec
- udiv \res_sec, \clock_nsec, \nsec_to_sec
- msub \res_nsec, \res_sec, \nsec_to_sec, \clock_nsec
- .endm
-
- /* sec and nsec are modified in place. */
- .macro add_ts sec, nsec, ts_sec, ts_nsec, nsec_to_sec
- /* Add timespec. */
- add \sec, \sec, \ts_sec
- add \nsec, \nsec, \ts_nsec
-
- /* Normalise the new timespec. */
- cmp \nsec, \nsec_to_sec
- b.lt 9999f
- sub \nsec, \nsec, \nsec_to_sec
- add \sec, \sec, #1
-9999:
- cmp \nsec, #0
- b.ge 9998f
- add \nsec, \nsec, \nsec_to_sec
- sub \sec, \sec, #1
-9998:
- .endm
-
- .macro clock_gettime_return, shift=0
- .if \shift == 1
- lsr x11, x11, x12
- .endif
- stp x10, x11, [x1, #TSPEC_TV_SEC]
- mov x0, xzr
- ret
- .endm
-
- .macro jump_slot jumptable, index, label
- .if (. - \jumptable) != 4 * (\index)
- .error "Jump slot index mismatch"
- .endif
- b \label
- .endm
-
- .text
-
-/* int __kernel_gettimeofday(struct timeval *tv, struct timezone *tz); */
-ENTRY(__kernel_gettimeofday)
- .cfi_startproc
- adr vdso_data, _vdso_data
- /* If tv is NULL, skip to the timezone code. */
- cbz x0, 2f
-
- /* Compute the time of day. */
-1: seqcnt_acquire
- syscall_check fail=4f
- ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST]
- /* w11 = cs_mono_mult, w12 = cs_shift */
- ldp w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
- ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
-
- get_nsec_per_sec res=x9
- lsl x9, x9, x12
-
- get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
- seqcnt_check fail=1b
- get_ts_realtime res_sec=x10, res_nsec=x11, \
- clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
-
- /* Convert ns to us. */
- mov x13, #1000
- lsl x13, x13, x12
- udiv x11, x11, x13
- stp x10, x11, [x0, #TVAL_TV_SEC]
-2:
- /* If tz is NULL, return 0. */
- cbz x1, 3f
- ldp w4, w5, [vdso_data, #VDSO_TZ_MINWEST]
- stp w4, w5, [x1, #TZ_MINWEST]
-3:
- mov x0, xzr
- ret
-4:
- /* Syscall fallback. */
- mov x8, #__NR_gettimeofday
- svc #0
- ret
- .cfi_endproc
-ENDPROC(__kernel_gettimeofday)
-
-#define JUMPSLOT_MAX CLOCK_MONOTONIC_COARSE
-
-/* int __kernel_clock_gettime(clockid_t clock_id, struct timespec *tp); */
-ENTRY(__kernel_clock_gettime)
- .cfi_startproc
- cmp w0, #JUMPSLOT_MAX
- b.hi syscall
- adr vdso_data, _vdso_data
- adr x_tmp, jumptable
- add x_tmp, x_tmp, w0, uxtw #2
- br x_tmp
-
- ALIGN
-jumptable:
- jump_slot jumptable, CLOCK_REALTIME, realtime
- jump_slot jumptable, CLOCK_MONOTONIC, monotonic
- b syscall
- b syscall
- jump_slot jumptable, CLOCK_MONOTONIC_RAW, monotonic_raw
- jump_slot jumptable, CLOCK_REALTIME_COARSE, realtime_coarse
- jump_slot jumptable, CLOCK_MONOTONIC_COARSE, monotonic_coarse
-
- .if (. - jumptable) != 4 * (JUMPSLOT_MAX + 1)
- .error "Wrong jumptable size"
- .endif
-
- ALIGN
-realtime:
- seqcnt_acquire
- syscall_check fail=syscall
- ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST]
- /* w11 = cs_mono_mult, w12 = cs_shift */
- ldp w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
- ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
-
- /* All computations are done with left-shifted nsecs. */
- get_nsec_per_sec res=x9
- lsl x9, x9, x12
-
- get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
- seqcnt_check fail=realtime
- get_ts_realtime res_sec=x10, res_nsec=x11, \
- clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
- clock_gettime_return, shift=1
-
- ALIGN
-monotonic:
- seqcnt_acquire
- syscall_check fail=syscall
- ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST]
- /* w11 = cs_mono_mult, w12 = cs_shift */
- ldp w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
- ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
- ldp x3, x4, [vdso_data, #VDSO_WTM_CLK_SEC]
-
- /* All computations are done with left-shifted nsecs. */
- lsl x4, x4, x12
- get_nsec_per_sec res=x9
- lsl x9, x9, x12
-
- get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
- seqcnt_check fail=monotonic
- get_ts_realtime res_sec=x10, res_nsec=x11, \
- clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
-
- add_ts sec=x10, nsec=x11, ts_sec=x3, ts_nsec=x4, nsec_to_sec=x9
- clock_gettime_return, shift=1
-
- ALIGN
-monotonic_raw:
- seqcnt_acquire
- syscall_check fail=syscall
- ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST]
- /* w11 = cs_raw_mult, w12 = cs_shift */
- ldp w12, w11, [vdso_data, #VDSO_CS_SHIFT]
- ldp x13, x14, [vdso_data, #VDSO_RAW_TIME_SEC]
-
- /* All computations are done with left-shifted nsecs. */
- get_nsec_per_sec res=x9
- lsl x9, x9, x12
-
- get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
- seqcnt_check fail=monotonic_raw
- get_ts_clock_raw res_sec=x10, res_nsec=x11, \
- clock_nsec=x15, nsec_to_sec=x9
-
- add_ts sec=x10, nsec=x11, ts_sec=x13, ts_nsec=x14, nsec_to_sec=x9
- clock_gettime_return, shift=1
-
- ALIGN
-realtime_coarse:
- seqcnt_acquire
- ldp x10, x11, [vdso_data, #VDSO_XTIME_CRS_SEC]
- seqcnt_check fail=realtime_coarse
- clock_gettime_return
-
- ALIGN
-monotonic_coarse:
- seqcnt_acquire
- ldp x10, x11, [vdso_data, #VDSO_XTIME_CRS_SEC]
- ldp x13, x14, [vdso_data, #VDSO_WTM_CLK_SEC]
- seqcnt_check fail=monotonic_coarse
-
- /* Computations are done in (non-shifted) nsecs. */
- get_nsec_per_sec res=x9
- add_ts sec=x10, nsec=x11, ts_sec=x13, ts_nsec=x14, nsec_to_sec=x9
- clock_gettime_return
-
- ALIGN
-syscall: /* Syscall fallback. */
- mov x8, #__NR_clock_gettime
- svc #0
- ret
- .cfi_endproc
-ENDPROC(__kernel_clock_gettime)
-
-/* int __kernel_clock_getres(clockid_t clock_id, struct timespec *res); */
-ENTRY(__kernel_clock_getres)
- .cfi_startproc
- cmp w0, #CLOCK_REALTIME
- ccmp w0, #CLOCK_MONOTONIC, #0x4, ne
- ccmp w0, #CLOCK_MONOTONIC_RAW, #0x4, ne
- b.ne 1f
-
- adr vdso_data, _vdso_data
- ldr w2, [vdso_data, #CLOCK_REALTIME_RES]
- b 2f
-1:
- cmp w0, #CLOCK_REALTIME_COARSE
- ccmp w0, #CLOCK_MONOTONIC_COARSE, #0x4, ne
- b.ne 4f
- ldr x2, 5f
-2:
- cbz x1, 3f
- stp xzr, x2, [x1]
-
-3: /* res == NULL. */
- mov w0, wzr
- ret
-
-4: /* Syscall fallback. */
- mov x8, #__NR_clock_getres
- svc #0
- ret
-5:
- .quad CLOCK_COARSE_RES
- .cfi_endproc
-ENDPROC(__kernel_clock_getres)
diff --git a/arch/arm64/kernel/vdso/vgettimeofday.c b/arch/arm64/kernel/vdso/vgettimeofday.c
new file mode 100644
index 000000000000..747635501a14
--- /dev/null
+++ b/arch/arm64/kernel/vdso/vgettimeofday.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ARM64 userspace implementations of gettimeofday() and similar.
+ *
+ * Copyright (C) 2018 ARM Limited
+ *
+ */
+#include <linux/time.h>
+#include <linux/types.h>
+
+int __kernel_clock_gettime(clockid_t clock,
+ struct __kernel_timespec *ts)
+{
+ return __cvdso_clock_gettime(clock, ts);
+}
+
+int __kernel_gettimeofday(struct __kernel_old_timeval *tv,
+ struct timezone *tz)
+{
+ return __cvdso_gettimeofday(tv, tz);
+}
+
+int __kernel_clock_getres(clockid_t clock_id,
+ struct __kernel_timespec *res)
+{
+ return __cvdso_clock_getres(clock_id, res);
+}
diff --git a/arch/arm64/kernel/vdso32/.gitignore b/arch/arm64/kernel/vdso32/.gitignore
new file mode 100644
index 000000000000..4fea950fa5ed
--- /dev/null
+++ b/arch/arm64/kernel/vdso32/.gitignore
@@ -0,0 +1,2 @@
+vdso.lds
+vdso.so.raw
diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
new file mode 100644
index 000000000000..288c14d30b45
--- /dev/null
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -0,0 +1,186 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for vdso32
+#
+
+# Absolute relocation type $(ARCH_REL_TYPE_ABS) needs to be defined before
+# the inclusion of generic Makefile.
+ARCH_REL_TYPE_ABS := R_ARM_JUMP_SLOT|R_ARM_GLOB_DAT|R_ARM_ABS32
+include $(srctree)/lib/vdso/Makefile
+
+COMPATCC := $(CROSS_COMPILE_COMPAT)gcc
+
+# Same as cc-*option, but using COMPATCC instead of CC
+cc32-option = $(call try-run,\
+ $(COMPATCC) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
+cc32-disable-warning = $(call try-run,\
+ $(COMPATCC) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1)))
+cc32-ldoption = $(call try-run,\
+ $(COMPATCC) $(1) -nostdlib -x c /dev/null -o "$$TMP",$(1),$(2))
+
+# We cannot use the global flags to compile the vDSO files, the main reason
+# being that the 32-bit compiler may be older than the main (64-bit) compiler
+# and therefore may not understand flags set using $(cc-option ...). Besides,
+# arch-specific options should be taken from the arm Makefile instead of the
+# arm64 one.
+# As a result we set our own flags here.
+
+# From top-level Makefile
+# NOSTDINC_FLAGS
+VDSO_CPPFLAGS := -nostdinc -isystem $(shell $(COMPATCC) -print-file-name=include)
+VDSO_CPPFLAGS += $(LINUXINCLUDE)
+VDSO_CPPFLAGS += $(KBUILD_CPPFLAGS)
+
+# Common C and assembly flags
+# From top-level Makefile
+VDSO_CAFLAGS := $(VDSO_CPPFLAGS)
+VDSO_CAFLAGS += $(call cc32-option,-fno-PIE)
+ifdef CONFIG_DEBUG_INFO
+VDSO_CAFLAGS += -g
+endif
+ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(COMPATCC)), y)
+VDSO_CAFLAGS += -DCC_HAVE_ASM_GOTO
+endif
+
+# From arm Makefile
+VDSO_CAFLAGS += $(call cc32-option,-fno-dwarf2-cfi-asm)
+VDSO_CAFLAGS += -mabi=aapcs-linux -mfloat-abi=soft
+ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
+VDSO_CAFLAGS += -mbig-endian
+else
+VDSO_CAFLAGS += -mlittle-endian
+endif
+
+# From arm vDSO Makefile
+VDSO_CAFLAGS += -fPIC -fno-builtin -fno-stack-protector
+VDSO_CAFLAGS += -DDISABLE_BRANCH_PROFILING
+
+# Try to compile for ARMv8. If the compiler is too old and doesn't support it,
+# fall back to v7. There is no easy way to check for what architecture the code
+# is being compiled, so define a macro specifying that (see arch/arm/Makefile).
+VDSO_CAFLAGS += $(call cc32-option,-march=armv8-a -D__LINUX_ARM_ARCH__=8,\
+ -march=armv7-a -D__LINUX_ARM_ARCH__=7)
+
+VDSO_CFLAGS := $(VDSO_CAFLAGS)
+VDSO_CFLAGS += -DENABLE_COMPAT_VDSO=1
+# KBUILD_CFLAGS from top-level Makefile
+VDSO_CFLAGS += -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
+ -fno-strict-aliasing -fno-common \
+ -Werror-implicit-function-declaration \
+ -Wno-format-security \
+ -std=gnu89
+VDSO_CFLAGS += -O2
+# Some useful compiler-dependent flags from top-level Makefile
+VDSO_CFLAGS += $(call cc32-option,-Wdeclaration-after-statement,)
+VDSO_CFLAGS += $(call cc32-option,-Wno-pointer-sign)
+VDSO_CFLAGS += $(call cc32-option,-fno-strict-overflow)
+VDSO_CFLAGS += $(call cc32-option,-Werror=strict-prototypes)
+VDSO_CFLAGS += $(call cc32-option,-Werror=date-time)
+VDSO_CFLAGS += $(call cc32-option,-Werror=incompatible-pointer-types)
+
+# The 32-bit compiler does not provide 128-bit integers, which are used in
+# some headers that are indirectly included from the vDSO code.
+# This hack makes the compiler happy and should trigger a warning/error if
+# variables of such type are referenced.
+VDSO_CFLAGS += -D__uint128_t='void*'
+# Silence some warnings coming from headers that operate on long's
+# (on GCC 4.8 or older, there is unfortunately no way to silence this warning)
+VDSO_CFLAGS += $(call cc32-disable-warning,shift-count-overflow)
+VDSO_CFLAGS += -Wno-int-to-pointer-cast
+
+VDSO_AFLAGS := $(VDSO_CAFLAGS)
+VDSO_AFLAGS += -D__ASSEMBLY__
+
+VDSO_LDFLAGS := $(VDSO_CPPFLAGS)
+# From arm vDSO Makefile
+VDSO_LDFLAGS += -Wl,-Bsymbolic -Wl,--no-undefined -Wl,-soname=linux-vdso.so.1
+VDSO_LDFLAGS += -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096
+VDSO_LDFLAGS += -nostdlib -shared -mfloat-abi=soft
+VDSO_LDFLAGS += $(call cc32-ldoption,-Wl$(comma)--hash-style=sysv)
+VDSO_LDFLAGS += $(call cc32-ldoption,-Wl$(comma)--build-id)
+VDSO_LDFLAGS += $(call cc32-ldoption,-fuse-ld=bfd)
+
+
+# Borrow vdsomunge.c from the arm vDSO
+# We have to use a relative path because scripts/Makefile.host prefixes
+# $(hostprogs-y) with $(obj)
+munge := ../../../arm/vdso/vdsomunge
+hostprogs-y := $(munge)
+
+c-obj-vdso := note.o
+c-obj-vdso-gettimeofday := vgettimeofday.o
+asm-obj-vdso := sigreturn.o
+
+ifneq ($(c-gettimeofday-y),)
+VDSO_CFLAGS_gettimeofday_o += -include $(c-gettimeofday-y)
+endif
+
+VDSO_CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os
+
+# Build rules
+targets := $(c-obj-vdso) $(c-obj-vdso-gettimeofday) $(asm-obj-vdso) vdso.so vdso.so.dbg vdso.so.raw
+c-obj-vdso := $(addprefix $(obj)/, $(c-obj-vdso))
+c-obj-vdso-gettimeofday := $(addprefix $(obj)/, $(c-obj-vdso-gettimeofday))
+asm-obj-vdso := $(addprefix $(obj)/, $(asm-obj-vdso))
+obj-vdso := $(c-obj-vdso) $(c-obj-vdso-gettimeofday) $(asm-obj-vdso)
+
+obj-y += vdso.o
+extra-y += vdso.lds
+CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
+
+# Force dependency (vdso.s includes vdso.so through incbin)
+$(obj)/vdso.o: $(obj)/vdso.so
+
+include/generated/vdso32-offsets.h: $(obj)/vdso.so.dbg FORCE
+ $(call if_changed,vdsosym)
+
+# Strip rule for vdso.so
+$(obj)/vdso.so: OBJCOPYFLAGS := -S
+$(obj)/vdso.so: $(obj)/vdso.so.dbg FORCE
+ $(call if_changed,objcopy)
+
+$(obj)/vdso.so.dbg: $(obj)/vdso.so.raw $(obj)/$(munge) FORCE
+ $(call if_changed,vdsomunge)
+
+# Link rule for the .so file, .lds has to be first
+$(obj)/vdso.so.raw: $(src)/vdso.lds $(obj-vdso) FORCE
+ $(call if_changed,vdsold)
+ $(call if_changed,vdso_check)
+
+# Compilation rules for the vDSO sources
+$(c-obj-vdso): %.o: %.c FORCE
+ $(call if_changed_dep,vdsocc)
+$(c-obj-vdso-gettimeofday): %.o: %.c FORCE
+ $(call if_changed_dep,vdsocc_gettimeofday)
+$(asm-obj-vdso): %.o: %.S FORCE
+ $(call if_changed_dep,vdsoas)
+
+# Actual build commands
+quiet_cmd_vdsold = VDSOL $@
+ cmd_vdsold = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_LDFLAGS) \
+ -Wl,-T $(filter %.lds,$^) $(filter %.o,$^) -o $@
+quiet_cmd_vdsocc = VDSOC $@
+ cmd_vdsocc = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) -c -o $@ $<
+quiet_cmd_vdsocc_gettimeofday = VDSOC_GTD $@
+ cmd_vdsocc_gettimeofday = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) $(VDSO_CFLAGS_gettimeofday_o) -c -o $@ $<
+quiet_cmd_vdsoas = VDSOA $@
+ cmd_vdsoas = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_AFLAGS) -c -o $@ $<
+
+quiet_cmd_vdsomunge = MUNGE $@
+ cmd_vdsomunge = $(obj)/$(munge) $< $@
+
+# Generate vDSO offsets using helper script (borrowed from the 64-bit vDSO)
+gen-vdsosym := $(srctree)/$(src)/../vdso/gen_vdso_offsets.sh
+quiet_cmd_vdsosym = VDSOSYM $@
+# The AArch64 nm should be able to read an AArch32 binary
+ cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@
+
+# Install commands for the unstripped file
+quiet_cmd_vdso_install = INSTALL $@
+ cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/vdso32.so
+
+vdso.so: $(obj)/vdso.so.dbg
+ @mkdir -p $(MODLIB)/vdso
+ $(call cmd,vdso_install)
+
+vdso_install: vdso.so
diff --git a/arch/arm64/kernel/vdso32/note.c b/arch/arm64/kernel/vdso32/note.c
new file mode 100644
index 000000000000..eff5bf9efb8b
--- /dev/null
+++ b/arch/arm64/kernel/vdso32/note.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2012-2018 ARM Limited
+ *
+ * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
+ * Here we can supply some information useful to userland.
+ */
+
+#include <linux/uts.h>
+#include <linux/version.h>
+#include <linux/elfnote.h>
+#include <linux/build-salt.h>
+
+ELFNOTE32("Linux", 0, LINUX_VERSION_CODE);
+BUILD_SALT;
diff --git a/arch/arm64/kernel/vdso32/sigreturn.S b/arch/arm64/kernel/vdso32/sigreturn.S
new file mode 100644
index 000000000000..1a81277c2d09
--- /dev/null
+++ b/arch/arm64/kernel/vdso32/sigreturn.S
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This file provides both A32 and T32 versions, in accordance with the
+ * arm sigreturn code.
+ *
+ * Copyright (C) 2018 ARM Limited
+ */
+
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/unistd.h>
+
+#define ARM_ENTRY(name) \
+ ENTRY(name)
+
+#define ARM_ENDPROC(name) \
+ .type name, %function; \
+ END(name)
+
+ .text
+
+ .arm
+ .fnstart
+ .save {r0-r15}
+ .pad #COMPAT_SIGFRAME_REGS_OFFSET
+ nop
+ARM_ENTRY(__kernel_sigreturn_arm)
+ mov r7, #__NR_compat_sigreturn
+ svc #0
+ .fnend
+ARM_ENDPROC(__kernel_sigreturn_arm)
+
+ .fnstart
+ .save {r0-r15}
+ .pad #COMPAT_RT_SIGFRAME_REGS_OFFSET
+ nop
+ARM_ENTRY(__kernel_rt_sigreturn_arm)
+ mov r7, #__NR_compat_rt_sigreturn
+ svc #0
+ .fnend
+ARM_ENDPROC(__kernel_rt_sigreturn_arm)
+
+ .thumb
+ .fnstart
+ .save {r0-r15}
+ .pad #COMPAT_SIGFRAME_REGS_OFFSET
+ nop
+ARM_ENTRY(__kernel_sigreturn_thumb)
+ mov r7, #__NR_compat_sigreturn
+ svc #0
+ .fnend
+ARM_ENDPROC(__kernel_sigreturn_thumb)
+
+ .fnstart
+ .save {r0-r15}
+ .pad #COMPAT_RT_SIGFRAME_REGS_OFFSET
+ nop
+ARM_ENTRY(__kernel_rt_sigreturn_thumb)
+ mov r7, #__NR_compat_rt_sigreturn
+ svc #0
+ .fnend
+ARM_ENDPROC(__kernel_rt_sigreturn_thumb)
diff --git a/arch/arm64/kernel/vdso32/vdso.S b/arch/arm64/kernel/vdso32/vdso.S
new file mode 100644
index 000000000000..e72ac7bc4c04
--- /dev/null
+++ b/arch/arm64/kernel/vdso32/vdso.S
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2012 ARM Limited
+ */
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <linux/const.h>
+#include <asm/page.h>
+
+ .globl vdso32_start, vdso32_end
+ .section .rodata
+ .balign PAGE_SIZE
+vdso32_start:
+ .incbin "arch/arm64/kernel/vdso32/vdso.so"
+ .balign PAGE_SIZE
+vdso32_end:
+
+ .previous
diff --git a/arch/arm64/kernel/vdso32/vdso.lds.S b/arch/arm64/kernel/vdso32/vdso.lds.S
new file mode 100644
index 000000000000..a3944927eaeb
--- /dev/null
+++ b/arch/arm64/kernel/vdso32/vdso.lds.S
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Adapted from arm64 version.
+ *
+ * GNU linker script for the VDSO library.
+ * Heavily based on the vDSO linker scripts for other archs.
+ *
+ * Copyright (C) 2012-2018 ARM Limited
+ */
+
+#include <linux/const.h>
+#include <asm/page.h>
+#include <asm/vdso.h>
+
+OUTPUT_FORMAT("elf32-littlearm", "elf32-bigarm", "elf32-littlearm")
+OUTPUT_ARCH(arm)
+
+SECTIONS
+{
+ PROVIDE_HIDDEN(_vdso_data = . - PAGE_SIZE);
+ . = VDSO_LBASE + SIZEOF_HEADERS;
+
+ .hash : { *(.hash) } :text
+ .gnu.hash : { *(.gnu.hash) }
+ .dynsym : { *(.dynsym) }
+ .dynstr : { *(.dynstr) }
+ .gnu.version : { *(.gnu.version) }
+ .gnu.version_d : { *(.gnu.version_d) }
+ .gnu.version_r : { *(.gnu.version_r) }
+
+ .note : { *(.note.*) } :text :note
+
+ .dynamic : { *(.dynamic) } :text :dynamic
+
+ .rodata : { *(.rodata*) } :text
+
+ .text : { *(.text*) } :text =0xe7f001f2
+
+ .got : { *(.got) }
+ .rel.plt : { *(.rel.plt) }
+
+ /DISCARD/ : {
+ *(.note.GNU-stack)
+ *(.data .data.* .gnu.linkonce.d.* .sdata*)
+ *(.bss .sbss .dynbss .dynsbss)
+ }
+}
+
+/*
+ * We must supply the ELF program headers explicitly to get just one
+ * PT_LOAD segment, and set the flags explicitly to make segments read-only.
+ */
+PHDRS
+{
+ text PT_LOAD FLAGS(5) FILEHDR PHDRS; /* PF_R|PF_X */
+ dynamic PT_DYNAMIC FLAGS(4); /* PF_R */
+ note PT_NOTE FLAGS(4); /* PF_R */
+}
+
+VERSION
+{
+ LINUX_2.6 {
+ global:
+ __vdso_clock_gettime;
+ __vdso_gettimeofday;
+ __vdso_clock_getres;
+ __kernel_sigreturn_arm;
+ __kernel_sigreturn_thumb;
+ __kernel_rt_sigreturn_arm;
+ __kernel_rt_sigreturn_thumb;
+ __vdso_clock_gettime64;
+ local: *;
+ };
+}
+
+/*
+ * Make the sigreturn code visible to the kernel.
+ */
+VDSO_compat_sigreturn_arm = __kernel_sigreturn_arm;
+VDSO_compat_sigreturn_thumb = __kernel_sigreturn_thumb;
+VDSO_compat_rt_sigreturn_arm = __kernel_rt_sigreturn_arm;
+VDSO_compat_rt_sigreturn_thumb = __kernel_rt_sigreturn_thumb;
diff --git a/arch/arm64/kernel/vdso32/vgettimeofday.c b/arch/arm64/kernel/vdso32/vgettimeofday.c
new file mode 100644
index 000000000000..54fc1c2ce93f
--- /dev/null
+++ b/arch/arm64/kernel/vdso32/vgettimeofday.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ARM64 compat userspace implementations of gettimeofday() and similar.
+ *
+ * Copyright (C) 2018 ARM Limited
+ *
+ */
+#include <linux/time.h>
+#include <linux/types.h>
+
+int __vdso_clock_gettime(clockid_t clock,
+ struct old_timespec32 *ts)
+{
+ /* The checks below are required for ABI consistency with arm */
+ if ((u32)ts >= TASK_SIZE_32)
+ return -EFAULT;
+
+ return __cvdso_clock_gettime32(clock, ts);
+}
+
+int __vdso_clock_gettime64(clockid_t clock,
+ struct __kernel_timespec *ts)
+{
+ /* The checks below are required for ABI consistency with arm */
+ if ((u32)ts >= TASK_SIZE_32)
+ return -EFAULT;
+
+ return __cvdso_clock_gettime(clock, ts);
+}
+
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv,
+ struct timezone *tz)
+{
+ return __cvdso_gettimeofday(tv, tz);
+}
+
+int __vdso_clock_getres(clockid_t clock_id,
+ struct old_timespec32 *res)
+{
+ /* The checks below are required for ABI consistency with arm */
+ if ((u32)res >= TASK_SIZE_32)
+ return -EFAULT;
+
+ return __cvdso_clock_getres_time32(clock_id, res);
+}
+
+/* Avoid unresolved references emitted by GCC */
+
+void __aeabi_unwind_cpp_pr0(void)
+{
+}
+
+void __aeabi_unwind_cpp_pr1(void)
+{
+}
+
+void __aeabi_unwind_cpp_pr2(void)
+{
+}
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 2bbbd4d1ba31..51a98d6eae8e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -17,6 +17,7 @@ config X86_32
select HAVE_DEBUG_STACKOVERFLOW
select MODULES_USE_ELF_REL
select OLD_SIGACTION
+ select GENERIC_VDSO_32
config X86_64
def_bool y
@@ -121,6 +122,7 @@ config X86
select GENERIC_STRNCPY_FROM_USER
select GENERIC_STRNLEN_USER
select GENERIC_TIME_VSYSCALL
+ select GENERIC_GETTIMEOFDAY
select HARDLOCKUP_CHECK_TIMESTAMP if X86_64
select HAVE_ACPI_APEI if ACPI
select HAVE_ACPI_APEI_NMI if ACPI
@@ -202,6 +204,7 @@ config X86
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_UNSTABLE_SCHED_CLOCK
select HAVE_USER_RETURN_NOTIFIER
+ select HAVE_GENERIC_VDSO
select HOTPLUG_SMT if SMP
select IRQ_FORCED_THREADING
select NEED_SG_DMA_LENGTH
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 42fe42e82baf..39106111be86 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -3,6 +3,12 @@
# Building vDSO images for x86.
#
+# Absolute relocation type $(ARCH_REL_TYPE_ABS) needs to be defined before
+# the inclusion of generic Makefile.
+ARCH_REL_TYPE_ABS := R_X86_64_JUMP_SLOT|R_X86_64_GLOB_DAT|R_X86_64_RELATIVE|
+ARCH_REL_TYPE_ABS += R_386_GLOB_DAT|R_386_JMP_SLOT|R_386_RELATIVE
+include $(srctree)/lib/vdso/Makefile
+
KBUILD_CFLAGS += $(DISABLE_LTO)
KASAN_SANITIZE := n
UBSAN_SANITIZE := n
@@ -51,6 +57,7 @@ VDSO_LDFLAGS_vdso.lds = -m elf_x86_64 -soname linux-vdso.so.1 --no-undefined \
$(obj)/vdso64.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE
$(call if_changed,vdso)
+ $(call if_changed,vdso_check)
HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(srctree)/arch/$(SUBARCH)/include/uapi
hostprogs-y += vdso2c
@@ -121,6 +128,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
$(obj)/vdsox32.so.dbg: $(obj)/vdsox32.lds $(vobjx32s) FORCE
$(call if_changed,vdso)
+ $(call if_changed,vdso_check)
CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds)
VDSO_LDFLAGS_vdso32.lds = -m elf_i386 -soname linux-gate.so.1
@@ -160,6 +168,7 @@ $(obj)/vdso32.so.dbg: FORCE \
$(obj)/vdso32/system_call.o \
$(obj)/vdso32/sigreturn.o
$(call if_changed,vdso)
+ $(call if_changed,vdso_check)
#
# The DSO images are built using a special linker script.
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 4aed41f638bb..d9ff616bb0f6 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -1,251 +1,85 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
- * Copyright 2006 Andi Kleen, SUSE Labs.
- *
* Fast user context implementation of clock_gettime, gettimeofday, and time.
*
+ * Copyright 2006 Andi Kleen, SUSE Labs.
+ * Copyright 2019 ARM Limited
+ *
* 32 Bit compat layer by Stefani Seibold <stefani@seibold.net>
* sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany
- *
- * The code should have no internal unresolved relocations.
- * Check with readelf after changing.
*/
-
-#include <uapi/linux/time.h>
-#include <asm/vgtod.h>
-#include <asm/vvar.h>
-#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>
+#include <linux/types.h>
-#define gtod (&VVAR(vsyscall_gtod_data))
+#include "../../../../lib/vdso/gettimeofday.c"
-extern int __vdso_clock_gettime(clockid_t clock, struct timespec *ts);
-extern int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz);
+extern int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
extern time_t __vdso_time(time_t *t);
-#ifdef CONFIG_PARAVIRT_CLOCK
-extern u8 pvclock_page[PAGE_SIZE]
- __attribute__((visibility("hidden")));
-#endif
-
-#ifdef CONFIG_HYPERV_TSCPAGE
-extern u8 hvclock_page[PAGE_SIZE]
- __attribute__((visibility("hidden")));
-#endif
-
-#ifndef BUILD_VDSO32
-
-notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
{
- long ret;
- asm ("syscall" : "=a" (ret), "=m" (*ts) :
- "0" (__NR_clock_gettime), "D" (clock), "S" (ts) :
- "rcx", "r11");
- return ret;
+ return __cvdso_gettimeofday(tv, tz);
}
-#else
+int gettimeofday(struct __kernel_old_timeval *, struct timezone *)
+ __attribute__((weak, alias("__vdso_gettimeofday")));
-notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
+time_t __vdso_time(time_t *t)
{
- long ret;
-
- asm (
- "mov %%ebx, %%edx \n"
- "mov %[clock], %%ebx \n"
- "call __kernel_vsyscall \n"
- "mov %%edx, %%ebx \n"
- : "=a" (ret), "=m" (*ts)
- : "0" (__NR_clock_gettime), [clock] "g" (clock), "c" (ts)
- : "edx");
- return ret;
+ return __cvdso_time(t);
}
-#endif
+time_t time(time_t *t) __attribute__((weak, alias("__vdso_time")));
-#ifdef CONFIG_PARAVIRT_CLOCK
-static notrace const struct pvclock_vsyscall_time_info *get_pvti0(void)
-{
- return (const struct pvclock_vsyscall_time_info *)&pvclock_page;
-}
-static notrace u64 vread_pvclock(void)
-{
- const struct pvclock_vcpu_time_info *pvti = &get_pvti0()->pvti;
- u32 version;
- u64 ret;
-
- /*
- * Note: The kernel and hypervisor must guarantee that cpu ID
- * number maps 1:1 to per-CPU pvclock time info.
- *
- * Because the hypervisor is entirely unaware of guest userspace
- * preemption, it cannot guarantee that per-CPU pvclock time
- * info is updated if the underlying CPU changes or that that
- * version is increased whenever underlying CPU changes.
- *
- * On KVM, we are guaranteed that pvti updates for any vCPU are
- * atomic as seen by *all* vCPUs. This is an even stronger
- * guarantee than we get with a normal seqlock.
- *
- * On Xen, we don't appear to have that guarantee, but Xen still
- * supplies a valid seqlock using the version field.
- *
- * We only do pvclock vdso timing at all if
- * PVCLOCK_TSC_STABLE_BIT is set, and we interpret that bit to
- * mean that all vCPUs have matching pvti and that the TSC is
- * synced, so we can just look at vCPU 0's pvti.
- */
-
- do {
- version = pvclock_read_begin(pvti);
-
- if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT)))
- return U64_MAX;
-
- ret = __pvclock_read_cycles(pvti, rdtsc_ordered());
- } while (pvclock_read_retry(pvti, version));
-
- return ret;
-}
-#endif
-#ifdef CONFIG_HYPERV_TSCPAGE
-static notrace u64 vread_hvclock(void)
-{
- const struct ms_hyperv_tsc_page *tsc_pg =
- (const struct ms_hyperv_tsc_page *)&hvclock_page;
+#if defined(CONFIG_X86_64) && !defined(BUILD_VDSO32_64)
+/* both 64-bit and x32 use these */
+extern int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts);
+extern int __vdso_clock_getres(clockid_t clock, struct __kernel_timespec *res);
- return hv_read_tsc_page(tsc_pg);
-}
-#endif
-
-notrace static inline u64 vgetcyc(int mode)
+int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
{
- if (mode == VCLOCK_TSC)
- return (u64)rdtsc_ordered();
-
- /*
- * For any memory-mapped vclock type, we need to make sure that gcc
- * doesn't cleverly hoist a load before the mode check. Otherwise we
- * might end up touching the memory-mapped page even if the vclock in
- * question isn't enabled, which will segfault. Hence the barriers.
- */
-#ifdef CONFIG_PARAVIRT_CLOCK
- if (mode == VCLOCK_PVCLOCK) {
- barrier();
- return vread_pvclock();
- }
-#endif
-#ifdef CONFIG_HYPERV_TSCPAGE
- if (mode == VCLOCK_HVCLOCK) {
- barrier();
- return vread_hvclock();
- }
-#endif
- return U64_MAX;
+ return __cvdso_clock_gettime(clock, ts);
}
-notrace static int do_hres(clockid_t clk, struct timespec *ts)
-{
- struct vgtod_ts *base = &gtod->basetime[clk];
- u64 cycles, last, sec, ns;
- unsigned int seq;
-
- do {
- seq = gtod_read_begin(gtod);
- cycles = vgetcyc(gtod->vclock_mode);
- ns = base->nsec;
- last = gtod->cycle_last;
- if (unlikely((s64)cycles < 0))
- return vdso_fallback_gettime(clk, ts);
- if (cycles > last)
- ns += (cycles - last) * gtod->mult;
- ns >>= gtod->shift;
- sec = base->sec;
- } while (unlikely(gtod_read_retry(gtod, seq)));
-
- /*
- * Do this outside the loop: a race inside the loop could result
- * in __iter_div_u64_rem() being extremely slow.
- */
- ts->tv_sec = sec + __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
- ts->tv_nsec = ns;
-
- return 0;
-}
+int clock_gettime(clockid_t, struct __kernel_timespec *)
+ __attribute__((weak, alias("__vdso_clock_gettime")));
-notrace static void do_coarse(clockid_t clk, struct timespec *ts)
+int __vdso_clock_getres(clockid_t clock,
+ struct __kernel_timespec *res)
{
- struct vgtod_ts *base = &gtod->basetime[clk];
- unsigned int seq;
-
- do {
- seq = gtod_read_begin(gtod);
- ts->tv_sec = base->sec;
- ts->tv_nsec = base->nsec;
- } while (unlikely(gtod_read_retry(gtod, seq)));
+ return __cvdso_clock_getres(clock, res);
}
+int clock_getres(clockid_t, struct __kernel_timespec *)
+ __attribute__((weak, alias("__vdso_clock_getres")));
-notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
+#else
+/* i386 only */
+extern int __vdso_clock_gettime(clockid_t clock, struct old_timespec32 *ts);
+extern int __vdso_clock_getres(clockid_t clock, struct old_timespec32 *res);
+
+int __vdso_clock_gettime(clockid_t clock, struct old_timespec32 *ts)
{
- unsigned int msk;
-
- /* Sort out negative (CPU/FD) and invalid clocks */
- if (unlikely((unsigned int) clock >= MAX_CLOCKS))
- return vdso_fallback_gettime(clock, ts);
-
- /*
- * Convert the clockid to a bitmask and use it to check which
- * clocks are handled in the VDSO directly.
- */
- msk = 1U << clock;
- if (likely(msk & VGTOD_HRES)) {
- return do_hres(clock, ts);
- } else if (msk & VGTOD_COARSE) {
- do_coarse(clock, ts);
- return 0;
- }
- return vdso_fallback_gettime(clock, ts);
+ return __cvdso_clock_gettime32(clock, ts);
}
-int clock_gettime(clockid_t, struct timespec *)
+int clock_gettime(clockid_t, struct old_timespec32 *)
__attribute__((weak, alias("__vdso_clock_gettime")));
-notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
+int __vdso_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts)
{
- if (likely(tv != NULL)) {
- struct timespec *ts = (struct timespec *) tv;
-
- do_hres(CLOCK_REALTIME, ts);
- tv->tv_usec /= 1000;
- }
- if (unlikely(tz != NULL)) {
- tz->tz_minuteswest = gtod->tz_minuteswest;
- tz->tz_dsttime = gtod->tz_dsttime;
- }
-
- return 0;
+ return __cvdso_clock_gettime(clock, ts);
}
-int gettimeofday(struct timeval *, struct timezone *)
- __attribute__((weak, alias("__vdso_gettimeofday")));
-/*
- * This will break when the xtime seconds get inaccurate, but that is
- * unlikely
- */
-notrace time_t __vdso_time(time_t *t)
-{
- /* This is atomic on x86 so we don't need any locks. */
- time_t result = READ_ONCE(gtod->basetime[CLOCK_REALTIME].sec);
+int clock_gettime64(clockid_t, struct __kernel_timespec *)
+ __attribute__((weak, alias("__vdso_clock_gettime64")));
- if (t)
- *t = result;
- return result;
+int __vdso_clock_getres(clockid_t clock, struct old_timespec32 *res)
+{
+ return __cvdso_clock_getres_time32(clock, res);
}
-time_t time(time_t *t)
- __attribute__((weak, alias("__vdso_time")));
+
+int clock_getres(clockid_t, struct old_timespec32 *)
+ __attribute__((weak, alias("__vdso_clock_getres")));
+#endif
diff --git a/arch/x86/entry/vdso/vdso.lds.S b/arch/x86/entry/vdso/vdso.lds.S
index d3a2dce4cfa9..36b644e16272 100644
--- a/arch/x86/entry/vdso/vdso.lds.S
+++ b/arch/x86/entry/vdso/vdso.lds.S
@@ -25,6 +25,8 @@ VERSION {
__vdso_getcpu;
time;
__vdso_time;
+ clock_getres;
+ __vdso_clock_getres;
local: *;
};
}
diff --git a/arch/x86/entry/vdso/vdso32/vdso32.lds.S b/arch/x86/entry/vdso/vdso32/vdso32.lds.S
index 422764a81d32..c7720995ab1a 100644
--- a/arch/x86/entry/vdso/vdso32/vdso32.lds.S
+++ b/arch/x86/entry/vdso/vdso32/vdso32.lds.S
@@ -26,6 +26,8 @@ VERSION
__vdso_clock_gettime;
__vdso_gettimeofday;
__vdso_time;
+ __vdso_clock_getres;
+ __vdso_clock_gettime64;
};
LINUX_2.5 {
diff --git a/arch/x86/entry/vdso/vdsox32.lds.S b/arch/x86/entry/vdso/vdsox32.lds.S
index 05cd1c5c4a15..16a8050a4fb6 100644
--- a/arch/x86/entry/vdso/vdsox32.lds.S
+++ b/arch/x86/entry/vdso/vdsox32.lds.S
@@ -21,6 +21,7 @@ VERSION {
__vdso_gettimeofday;
__vdso_getcpu;
__vdso_time;
+ __vdso_clock_getres;
local: *;
};
}
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 8db1f594e8b1..349a61d8bf34 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -22,7 +22,7 @@
#include <asm/page.h>
#include <asm/desc.h>
#include <asm/cpufeature.h>
-#include <asm/mshyperv.h>
+#include <clocksource/hyperv_timer.h>
#if defined(CONFIG_X86_64)
unsigned int __read_mostly vdso64_enabled = 1;
diff --git a/arch/x86/entry/vsyscall/Makefile b/arch/x86/entry/vsyscall/Makefile
index 1ac4dd116c26..93c1b3e949a7 100644
--- a/arch/x86/entry/vsyscall/Makefile
+++ b/arch/x86/entry/vsyscall/Makefile
@@ -2,7 +2,5 @@
#
# Makefile for the x86 low level vsyscall code
#
-obj-y := vsyscall_gtod.o
-
obj-$(CONFIG_X86_VSYSCALL_EMULATION) += vsyscall_64.o vsyscall_emu_64.o
diff --git a/arch/x86/entry/vsyscall/vsyscall_gtod.c b/arch/x86/entry/vsyscall/vsyscall_gtod.c
deleted file mode 100644
index cfcdba082feb..000000000000
--- a/arch/x86/entry/vsyscall/vsyscall_gtod.c
+++ /dev/null
@@ -1,83 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
- * Copyright 2003 Andi Kleen, SuSE Labs.
- *
- * Modified for x86 32 bit architecture by
- * Stefani Seibold <stefani@seibold.net>
- * sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany
- *
- * Thanks to hpa@transmeta.com for some useful hint.
- * Special thanks to Ingo Molnar for his early experience with
- * a different vsyscall implementation for Linux/IA32 and for the name.
- *
- */
-
-#include <linux/timekeeper_internal.h>
-#include <asm/vgtod.h>
-#include <asm/vvar.h>
-
-int vclocks_used __read_mostly;
-
-DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data);
-
-void update_vsyscall_tz(void)
-{
- vsyscall_gtod_data.tz_minuteswest = sys_tz.tz_minuteswest;
- vsyscall_gtod_data.tz_dsttime = sys_tz.tz_dsttime;
-}
-
-void update_vsyscall(struct timekeeper *tk)
-{
- int vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode;
- struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data;
- struct vgtod_ts *base;
- u64 nsec;
-
- /* Mark the new vclock used. */
- BUILD_BUG_ON(VCLOCK_MAX >= 32);
- WRITE_ONCE(vclocks_used, READ_ONCE(vclocks_used) | (1 << vclock_mode));
-
- gtod_write_begin(vdata);
-
- /* copy vsyscall data */
- vdata->vclock_mode = vclock_mode;
- vdata->cycle_last = tk->tkr_mono.cycle_last;
- vdata->mask = tk->tkr_mono.mask;
- vdata->mult = tk->tkr_mono.mult;
- vdata->shift = tk->tkr_mono.shift;
-
- base = &vdata->basetime[CLOCK_REALTIME];
- base->sec = tk->xtime_sec;
- base->nsec = tk->tkr_mono.xtime_nsec;
-
- base = &vdata->basetime[CLOCK_TAI];
- base->sec = tk->xtime_sec + (s64)tk->tai_offset;
- base->nsec = tk->tkr_mono.xtime_nsec;
-
- base = &vdata->basetime[CLOCK_MONOTONIC];
- base->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
- nsec = tk->tkr_mono.xtime_nsec;
- nsec += ((u64)tk->wall_to_monotonic.tv_nsec << tk->tkr_mono.shift);
- while (nsec >= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) {
- nsec -= ((u64)NSEC_PER_SEC) << tk->tkr_mono.shift;
- base->sec++;
- }
- base->nsec = nsec;
-
- base = &vdata->basetime[CLOCK_REALTIME_COARSE];
- base->sec = tk->xtime_sec;
- base->nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
-
- base = &vdata->basetime[CLOCK_MONOTONIC_COARSE];
- base->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
- nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
- nsec += tk->wall_to_monotonic.tv_nsec;
- while (nsec >= NSEC_PER_SEC) {
- nsec -= NSEC_PER_SEC;
- base->sec++;
- }
- base->nsec = nsec;
-
- gtod_write_end(vdata);
-}
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 1608050e9df9..0e033ef11a9f 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -17,64 +17,13 @@
#include <linux/version.h>
#include <linux/vmalloc.h>
#include <linux/mm.h>
-#include <linux/clockchips.h>
#include <linux/hyperv.h>
#include <linux/slab.h>
#include <linux/cpuhotplug.h>
-
-#ifdef CONFIG_HYPERV_TSCPAGE
-
-static struct ms_hyperv_tsc_page *tsc_pg;
-
-struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
-{
- return tsc_pg;
-}
-EXPORT_SYMBOL_GPL(hv_get_tsc_page);
-
-static u64 read_hv_clock_tsc(struct clocksource *arg)
-{
- u64 current_tick = hv_read_tsc_page(tsc_pg);
-
- if (current_tick == U64_MAX)
- rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
-
- return current_tick;
-}
-
-static struct clocksource hyperv_cs_tsc = {
- .name = "hyperv_clocksource_tsc_page",
- .rating = 400,
- .read = read_hv_clock_tsc,
- .mask = CLOCKSOURCE_MASK(64),
- .flags = CLOCK_SOURCE_IS_CONTINUOUS,
-};
-#endif
-
-static u64 read_hv_clock_msr(struct clocksource *arg)
-{
- u64 current_tick;
- /*
- * Read the partition counter to get the current tick count. This count
- * is set to 0 when the partition is created and is incremented in
- * 100 nanosecond units.
- */
- rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
- return current_tick;
-}
-
-static struct clocksource hyperv_cs_msr = {
- .name = "hyperv_clocksource_msr",
- .rating = 400,
- .read = read_hv_clock_msr,
- .mask = CLOCKSOURCE_MASK(64),
- .flags = CLOCK_SOURCE_IS_CONTINUOUS,
-};
+#include <clocksource/hyperv_timer.h>
void *hv_hypercall_pg;
EXPORT_SYMBOL_GPL(hv_hypercall_pg);
-struct clocksource *hyperv_cs;
-EXPORT_SYMBOL_GPL(hyperv_cs);
u32 *hv_vp_index;
EXPORT_SYMBOL_GPL(hv_vp_index);
@@ -343,42 +292,8 @@ void __init hyperv_init(void)
x86_init.pci.arch_init = hv_pci_init;
- /*
- * Register Hyper-V specific clocksource.
- */
-#ifdef CONFIG_HYPERV_TSCPAGE
- if (ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE) {
- union hv_x64_msr_hypercall_contents tsc_msr;
-
- tsc_pg = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL);
- if (!tsc_pg)
- goto register_msr_cs;
-
- hyperv_cs = &hyperv_cs_tsc;
-
- rdmsrl(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64);
-
- tsc_msr.enable = 1;
- tsc_msr.guest_physical_address = vmalloc_to_pfn(tsc_pg);
-
- wrmsrl(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64);
-
- hyperv_cs_tsc.archdata.vclock_mode = VCLOCK_HVCLOCK;
-
- clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100);
- return;
- }
-register_msr_cs:
-#endif
- /*
- * For 32 bit guests just use the MSR based mechanism for reading
- * the partition counter.
- */
-
- hyperv_cs = &hyperv_cs_msr;
- if (ms_hyperv.features & HV_MSR_TIME_REF_COUNT_AVAILABLE)
- clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100);
-
+ /* Register Hyper-V specific clocksource */
+ hv_init_clocksource();
return;
remove_cpuhp_state:
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index cdf44aa9a501..af78cd72b8f3 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -401,6 +401,12 @@ enum HV_GENERIC_SET_FORMAT {
#define HV_STATUS_INVALID_CONNECTION_ID 18
#define HV_STATUS_INSUFFICIENT_BUFFERS 19
+/*
+ * The Hyper-V TimeRefCount register and the TSC
+ * page provide a guest VM clock with 100ns tick rate
+ */
+#define HV_CLOCK_HZ (NSEC_PER_SEC/100)
+
typedef struct _HV_REFERENCE_TSC_PAGE {
__u32 tsc_sequence;
__u32 res1;
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index cc60e617931c..f4fa8a9d5d0b 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -105,6 +105,17 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
#define hv_get_crash_ctl(val) \
rdmsrl(HV_X64_MSR_CRASH_CTL, val)
+#define hv_get_time_ref_count(val) \
+ rdmsrl(HV_X64_MSR_TIME_REF_COUNT, val)
+
+#define hv_get_reference_tsc(val) \
+ rdmsrl(HV_X64_MSR_REFERENCE_TSC, val)
+#define hv_set_reference_tsc(val) \
+ wrmsrl(HV_X64_MSR_REFERENCE_TSC, val)
+#define hv_set_clocksource_vdso(val) \
+ ((val).archdata.vclock_mode = VCLOCK_HVCLOCK)
+#define hv_get_raw_timer() rdtsc_ordered()
+
void hyperv_callback_vector(void);
void hyperv_reenlightenment_vector(void);
#ifdef CONFIG_TRACING
@@ -133,7 +144,6 @@ static inline void hv_disable_stimer0_percpu_irq(int irq) {}
#if IS_ENABLED(CONFIG_HYPERV)
-extern struct clocksource *hyperv_cs;
extern void *hv_hypercall_pg;
extern void __percpu **hyperv_pcpu_input_arg;
@@ -387,73 +397,4 @@ static inline int hyperv_flush_guest_mapping_range(u64 as,
}
#endif /* CONFIG_HYPERV */
-#ifdef CONFIG_HYPERV_TSCPAGE
-struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
-static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
- u64 *cur_tsc)
-{
- u64 scale, offset;
- u32 sequence;
-
- /*
- * The protocol for reading Hyper-V TSC page is specified in Hypervisor
- * Top-Level Functional Specification ver. 3.0 and above. To get the
- * reference time we must do the following:
- * - READ ReferenceTscSequence
- * A special '0' value indicates the time source is unreliable and we
- * need to use something else. The currently published specification
- * versions (up to 4.0b) contain a mistake and wrongly claim '-1'
- * instead of '0' as the special value, see commit c35b82ef0294.
- * - ReferenceTime =
- * ((RDTSC() * ReferenceTscScale) >> 64) + ReferenceTscOffset
- * - READ ReferenceTscSequence again. In case its value has changed
- * since our first reading we need to discard ReferenceTime and repeat
- * the whole sequence as the hypervisor was updating the page in
- * between.
- */
- do {
- sequence = READ_ONCE(tsc_pg->tsc_sequence);
- if (!sequence)
- return U64_MAX;
- /*
- * Make sure we read sequence before we read other values from
- * TSC page.
- */
- smp_rmb();
-
- scale = READ_ONCE(tsc_pg->tsc_scale);
- offset = READ_ONCE(tsc_pg->tsc_offset);
- *cur_tsc = rdtsc_ordered();
-
- /*
- * Make sure we read sequence after we read all other values
- * from TSC page.
- */
- smp_rmb();
-
- } while (READ_ONCE(tsc_pg->tsc_sequence) != sequence);
-
- return mul_u64_u64_shr(*cur_tsc, scale, 64) + offset;
-}
-
-static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
-{
- u64 cur_tsc;
-
- return hv_read_tsc_page_tsc(tsc_pg, &cur_tsc);
-}
-
-#else
-static inline struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
-{
- return NULL;
-}
-
-static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
- u64 *cur_tsc)
-{
- BUG();
- return U64_MAX;
-}
-#endif
#endif
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index b6033680d458..19b695ff2c68 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -2,7 +2,7 @@
#ifndef _ASM_X86_PVCLOCK_H
#define _ASM_X86_PVCLOCK_H
-#include <linux/clocksource.h>
+#include <asm/clocksource.h>
#include <asm/pvclock-abi.h>
/* some helper functions for xen and kvm pv clock sources */
diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h
new file mode 100644
index 000000000000..ae91429129a6
--- /dev/null
+++ b/arch/x86/include/asm/vdso/gettimeofday.h
@@ -0,0 +1,261 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Fast user context implementation of clock_gettime, gettimeofday, and time.
+ *
+ * Copyright (C) 2019 ARM Limited.
+ * Copyright 2006 Andi Kleen, SUSE Labs.
+ * 32 Bit compat layer by Stefani Seibold <stefani@seibold.net>
+ * sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany
+ */
+#ifndef __ASM_VDSO_GETTIMEOFDAY_H
+#define __ASM_VDSO_GETTIMEOFDAY_H
+
+#ifndef __ASSEMBLY__
+
+#include <uapi/linux/time.h>
+#include <asm/vgtod.h>
+#include <asm/vvar.h>
+#include <asm/unistd.h>
+#include <asm/msr.h>
+#include <asm/pvclock.h>
+#include <clocksource/hyperv_timer.h>
+
+#define __vdso_data (VVAR(_vdso_data))
+
+#define VDSO_HAS_TIME 1
+
+#define VDSO_HAS_CLOCK_GETRES 1
+
+/*
+ * Declare the memory-mapped vclock data pages. These come from hypervisors.
+ * If we ever reintroduce something like direct access to an MMIO clock like
+ * the HPET again, it will go here as well.
+ *
+ * A load from any of these pages will segfault if the clock in question is
+ * disabled, so appropriate compiler barriers and checks need to be used
+ * to prevent stray loads.
+ *
+ * These declarations MUST NOT be const. The compiler will assume that
+ * an extern const variable has genuinely constant contents, and the
+ * resulting code won't work, since the whole point is that these pages
+ * change over time, possibly while we're accessing them.
+ */
+
+#ifdef CONFIG_PARAVIRT_CLOCK
+/*
+ * This is the vCPU 0 pvclock page. We only use pvclock from the vDSO
+ * if the hypervisor tells us that all vCPUs can get valid data from the
+ * vCPU 0 page.
+ */
+extern struct pvclock_vsyscall_time_info pvclock_page
+ __attribute__((visibility("hidden")));
+#endif
+
+#ifdef CONFIG_HYPERV_TSCPAGE
+extern struct ms_hyperv_tsc_page hvclock_page
+ __attribute__((visibility("hidden")));
+#endif
+
+#ifndef BUILD_VDSO32
+
+static __always_inline
+long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+ long ret;
+
+ asm ("syscall" : "=a" (ret), "=m" (*_ts) :
+ "0" (__NR_clock_gettime), "D" (_clkid), "S" (_ts) :
+ "rcx", "r11");
+
+ return ret;
+}
+
+static __always_inline
+long gettimeofday_fallback(struct __kernel_old_timeval *_tv,
+ struct timezone *_tz)
+{
+ long ret;
+
+ asm("syscall" : "=a" (ret) :
+ "0" (__NR_gettimeofday), "D" (_tv), "S" (_tz) : "memory");
+
+ return ret;
+}
+
+static __always_inline
+long clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+ long ret;
+
+ asm ("syscall" : "=a" (ret), "=m" (*_ts) :
+ "0" (__NR_clock_getres), "D" (_clkid), "S" (_ts) :
+ "rcx", "r11");
+
+ return ret;
+}
+
+#else
+
+static __always_inline
+long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+ long ret;
+
+ asm (
+ "mov %%ebx, %%edx \n"
+ "mov %[clock], %%ebx \n"
+ "call __kernel_vsyscall \n"
+ "mov %%edx, %%ebx \n"
+ : "=a" (ret), "=m" (*_ts)
+ : "0" (__NR_clock_gettime64), [clock] "g" (_clkid), "c" (_ts)
+ : "edx");
+
+ return ret;
+}
+
+static __always_inline
+long gettimeofday_fallback(struct __kernel_old_timeval *_tv,
+ struct timezone *_tz)
+{
+ long ret;
+
+ asm(
+ "mov %%ebx, %%edx \n"
+ "mov %2, %%ebx \n"
+ "call __kernel_vsyscall \n"
+ "mov %%edx, %%ebx \n"
+ : "=a" (ret)
+ : "0" (__NR_gettimeofday), "g" (_tv), "c" (_tz)
+ : "memory", "edx");
+
+ return ret;
+}
+
+static __always_inline long
+clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+ long ret;
+
+ asm (
+ "mov %%ebx, %%edx \n"
+ "mov %[clock], %%ebx \n"
+ "call __kernel_vsyscall \n"
+ "mov %%edx, %%ebx \n"
+ : "=a" (ret), "=m" (*_ts)
+ : "0" (__NR_clock_getres_time64), [clock] "g" (_clkid), "c" (_ts)
+ : "edx");
+
+ return ret;
+}
+
+#endif
+
+#ifdef CONFIG_PARAVIRT_CLOCK
+static u64 vread_pvclock(void)
+{
+ const struct pvclock_vcpu_time_info *pvti = &pvclock_page.pvti;
+ u32 version;
+ u64 ret;
+
+ /*
+ * Note: The kernel and hypervisor must guarantee that cpu ID
+ * number maps 1:1 to per-CPU pvclock time info.
+ *
+ * Because the hypervisor is entirely unaware of guest userspace
+ * preemption, it cannot guarantee that per-CPU pvclock time
+ * info is updated if the underlying CPU changes or that that
+ * version is increased whenever underlying CPU changes.
+ *
+ * On KVM, we are guaranteed that pvti updates for any vCPU are
+ * atomic as seen by *all* vCPUs. This is an even stronger
+ * guarantee than we get with a normal seqlock.
+ *
+ * On Xen, we don't appear to have that guarantee, but Xen still
+ * supplies a valid seqlock using the version field.
+ *
+ * We only do pvclock vdso timing at all if
+ * PVCLOCK_TSC_STABLE_BIT is set, and we interpret that bit to
+ * mean that all vCPUs have matching pvti and that the TSC is
+ * synced, so we can just look at vCPU 0's pvti.
+ */
+
+ do {
+ version = pvclock_read_begin(pvti);
+
+ if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT)))
+ return U64_MAX;
+
+ ret = __pvclock_read_cycles(pvti, rdtsc_ordered());
+ } while (pvclock_read_retry(pvti, version));
+
+ return ret;
+}
+#endif
+
+#ifdef CONFIG_HYPERV_TSCPAGE
+static u64 vread_hvclock(void)
+{
+ return hv_read_tsc_page(&hvclock_page);
+}
+#endif
+
+static inline u64 __arch_get_hw_counter(s32 clock_mode)
+{
+ if (clock_mode == VCLOCK_TSC)
+ return (u64)rdtsc_ordered();
+ /*
+ * For any memory-mapped vclock type, we need to make sure that gcc
+ * doesn't cleverly hoist a load before the mode check. Otherwise we
+ * might end up touching the memory-mapped page even if the vclock in
+ * question isn't enabled, which will segfault. Hence the barriers.
+ */
+#ifdef CONFIG_PARAVIRT_CLOCK
+ if (clock_mode == VCLOCK_PVCLOCK) {
+ barrier();
+ return vread_pvclock();
+ }
+#endif
+#ifdef CONFIG_HYPERV_TSCPAGE
+ if (clock_mode == VCLOCK_HVCLOCK) {
+ barrier();
+ return vread_hvclock();
+ }
+#endif
+ return U64_MAX;
+}
+
+static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
+{
+ return __vdso_data;
+}
+
+/*
+ * x86 specific delta calculation.
+ *
+ * The regular implementation assumes that clocksource reads are globally
+ * monotonic. The TSC can be slightly off across sockets which can cause
+ * the regular delta calculation (@cycles - @last) to return a huge time
+ * jump.
+ *
+ * Therefore it needs to be verified that @cycles are greater than
+ * @last. If not then use @last, which is the base time of the current
+ * conversion period.
+ *
+ * This variant also removes the masking of the subtraction because the
+ * clocksource mask of all VDSO capable clocksources on x86 is U64_MAX
+ * which would result in a pointless operation. The compiler cannot
+ * optimize it away as the mask comes from the vdso data and is not compile
+ * time constant.
+ */
+static __always_inline
+u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult)
+{
+ if (cycles > last)
+ return (cycles - last) * mult;
+ return 0;
+}
+#define vdso_calc_delta vdso_calc_delta
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/x86/include/asm/vdso/vsyscall.h b/arch/x86/include/asm/vdso/vsyscall.h
new file mode 100644
index 000000000000..0026ab2123ce
--- /dev/null
+++ b/arch/x86/include/asm/vdso/vsyscall.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_VDSO_VSYSCALL_H
+#define __ASM_VDSO_VSYSCALL_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/hrtimer.h>
+#include <linux/timekeeper_internal.h>
+#include <vdso/datapage.h>
+#include <asm/vgtod.h>
+#include <asm/vvar.h>
+
+int vclocks_used __read_mostly;
+
+DEFINE_VVAR(struct vdso_data, _vdso_data);
+/*
+ * Update the vDSO data page to keep in sync with kernel timekeeping.
+ */
+static __always_inline
+struct vdso_data *__x86_get_k_vdso_data(void)
+{
+ return _vdso_data;
+}
+#define __arch_get_k_vdso_data __x86_get_k_vdso_data
+
+static __always_inline
+int __x86_get_clock_mode(struct timekeeper *tk)
+{
+ int vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode;
+
+ /* Mark the new vclock used. */
+ BUILD_BUG_ON(VCLOCK_MAX >= 32);
+ WRITE_ONCE(vclocks_used, READ_ONCE(vclocks_used) | (1 << vclock_mode));
+
+ return vclock_mode;
+}
+#define __arch_get_clock_mode __x86_get_clock_mode
+
+/* The asm-generic header needs to be included after the definitions above */
+#include <asm-generic/vdso/vsyscall.h>
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_VSYSCALL_H */
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index 913a133f8e6f..a2638c6124ed 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -3,7 +3,9 @@
#define _ASM_X86_VGTOD_H
#include <linux/compiler.h>
-#include <linux/clocksource.h>
+#include <asm/clocksource.h>
+#include <vdso/datapage.h>
+#include <vdso/helpers.h>
#include <uapi/linux/time.h>
@@ -13,81 +15,10 @@ typedef u64 gtod_long_t;
typedef unsigned long gtod_long_t;
#endif
-/*
- * There is one of these objects in the vvar page for each
- * vDSO-accelerated clockid. For high-resolution clocks, this encodes
- * the time corresponding to vsyscall_gtod_data.cycle_last. For coarse
- * clocks, this encodes the actual time.
- *
- * To confuse the reader, for high-resolution clocks, nsec is left-shifted
- * by vsyscall_gtod_data.shift.
- */
-struct vgtod_ts {
- u64 sec;
- u64 nsec;
-};
-
-#define VGTOD_BASES (CLOCK_TAI + 1)
-#define VGTOD_HRES (BIT(CLOCK_REALTIME) | BIT(CLOCK_MONOTONIC) | BIT(CLOCK_TAI))
-#define VGTOD_COARSE (BIT(CLOCK_REALTIME_COARSE) | BIT(CLOCK_MONOTONIC_COARSE))
-
-/*
- * vsyscall_gtod_data will be accessed by 32 and 64 bit code at the same time
- * so be carefull by modifying this structure.
- */
-struct vsyscall_gtod_data {
- unsigned int seq;
-
- int vclock_mode;
- u64 cycle_last;
- u64 mask;
- u32 mult;
- u32 shift;
-
- struct vgtod_ts basetime[VGTOD_BASES];
-
- int tz_minuteswest;
- int tz_dsttime;
-};
-extern struct vsyscall_gtod_data vsyscall_gtod_data;
-
extern int vclocks_used;
static inline bool vclock_was_used(int vclock)
{
return READ_ONCE(vclocks_used) & (1 << vclock);
}
-static inline unsigned int gtod_read_begin(const struct vsyscall_gtod_data *s)
-{
- unsigned int ret;
-
-repeat:
- ret = READ_ONCE(s->seq);
- if (unlikely(ret & 1)) {
- cpu_relax();
- goto repeat;
- }
- smp_rmb();
- return ret;
-}
-
-static inline int gtod_read_retry(const struct vsyscall_gtod_data *s,
- unsigned int start)
-{
- smp_rmb();
- return unlikely(s->seq != start);
-}
-
-static inline void gtod_write_begin(struct vsyscall_gtod_data *s)
-{
- ++s->seq;
- smp_wmb();
-}
-
-static inline void gtod_write_end(struct vsyscall_gtod_data *s)
-{
- smp_wmb();
- ++s->seq;
-}
-
#endif /* _ASM_X86_VGTOD_H */
diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h
index e474f5c6e387..32f5d9a0b90e 100644
--- a/arch/x86/include/asm/vvar.h
+++ b/arch/x86/include/asm/vvar.h
@@ -32,19 +32,20 @@
extern char __vvar_page;
#define DECLARE_VVAR(offset, type, name) \
- extern type vvar_ ## name __attribute__((visibility("hidden")));
+ extern type vvar_ ## name[CS_BASES] \
+ __attribute__((visibility("hidden")));
#define VVAR(name) (vvar_ ## name)
#define DEFINE_VVAR(type, name) \
- type name \
+ type name[CS_BASES] \
__attribute__((section(".vvar_" #name), aligned(16))) __visible
#endif
/* DECLARE_VVAR(offset, type, name) */
-DECLARE_VVAR(128, struct vsyscall_gtod_data, vsyscall_gtod_data)
+DECLARE_VVAR(128, struct vdso_data, _vdso_data)
#undef DECLARE_VVAR
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 7df29f08871b..1e5f7a03ddf5 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -17,6 +17,7 @@
#include <linux/irq.h>
#include <linux/kexec.h>
#include <linux/i8253.h>
+#include <linux/random.h>
#include <asm/processor.h>
#include <asm/hypervisor.h>
#include <asm/hyperv-tlfs.h>
@@ -80,6 +81,7 @@ __visible void __irq_entry hv_stimer0_vector_handler(struct pt_regs *regs)
inc_irq_stat(hyperv_stimer0_count);
if (hv_stimer0_handler)
hv_stimer0_handler();
+ add_interrupt_randomness(HYPERV_STIMER0_VECTOR, 0);
ack_APIC_irq();
exiting_irq();
@@ -89,7 +91,7 @@ __visible void __irq_entry hv_stimer0_vector_handler(struct pt_regs *regs)
int hv_setup_stimer0_irq(int *irq, int *vector, void (*handler)(void))
{
*vector = HYPERV_STIMER0_VECTOR;
- *irq = 0; /* Unused on x86/x64 */
+ *irq = -1; /* Unused on x86/x64 */
hv_stimer0_handler = handler;
return 0;
}
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 0ff3e294d0e5..10125358b9c4 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -3,6 +3,7 @@
*/
+#include <linux/clocksource.h>
#include <linux/kernel.h>
#include <linux/percpu.h>
#include <linux/notifier.h>
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 132d149494d6..ab73a9a639ae 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -261,10 +261,10 @@ static int kvm_pmu_rdpmc_vmware(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
ctr_val = rdtsc();
break;
case VMWARE_BACKDOOR_PMC_REAL_TIME:
- ctr_val = ktime_get_boot_ns();
+ ctr_val = ktime_get_boottime_ns();
break;
case VMWARE_BACKDOOR_PMC_APPARENT_TIME:
- ctr_val = ktime_get_boot_ns() +
+ ctr_val = ktime_get_boottime_ns() +
vcpu->kvm->arch.kvmclock_offset;
break;
default:
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index fafd81d2c9ea..63bb1ee8258e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -67,6 +67,7 @@
#include <asm/mshyperv.h>
#include <asm/hypervisor.h>
#include <asm/intel_pt.h>
+#include <clocksource/hyperv_timer.h>
#define CREATE_TRACE_POINTS
#include "trace.h"
@@ -1728,7 +1729,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
offset = kvm_compute_tsc_offset(vcpu, data);
- ns = ktime_get_boot_ns();
+ ns = ktime_get_boottime_ns();
elapsed = ns - kvm->arch.last_tsc_nsec;
if (vcpu->arch.virtual_tsc_khz) {
@@ -2070,7 +2071,7 @@ u64 get_kvmclock_ns(struct kvm *kvm)
spin_lock(&ka->pvclock_gtod_sync_lock);
if (!ka->use_master_clock) {
spin_unlock(&ka->pvclock_gtod_sync_lock);
- return ktime_get_boot_ns() + ka->kvmclock_offset;
+ return ktime_get_boottime_ns() + ka->kvmclock_offset;
}
hv_clock.tsc_timestamp = ka->master_cycle_now;
@@ -2086,7 +2087,7 @@ u64 get_kvmclock_ns(struct kvm *kvm)
&hv_clock.tsc_to_system_mul);
ret = __pvclock_read_cycles(&hv_clock, rdtsc());
} else
- ret = ktime_get_boot_ns() + ka->kvmclock_offset;
+ ret = ktime_get_boottime_ns() + ka->kvmclock_offset;
put_cpu();
@@ -2185,7 +2186,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
}
if (!use_master_clock) {
host_tsc = rdtsc();
- kernel_ns = ktime_get_boot_ns();
+ kernel_ns = ktime_get_boottime_ns();
}
tsc_timestamp = kvm_read_l1_tsc(v, host_tsc);
@@ -9015,7 +9016,7 @@ int kvm_arch_hardware_enable(void)
* before any KVM threads can be running. Unfortunately, we can't
* bring the TSCs fully up to date with real time, as we aren't yet far
* enough into CPU bringup that we know how much real time has actually
- * elapsed; our helper function, ktime_get_boot_ns() will be using boot
+ * elapsed; our helper function, ktime_get_boottime_ns() will be using boot
* variables that haven't been updated yet.
*
* So we simply find the maximum observed TSC above, then record the
@@ -9243,7 +9244,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
mutex_init(&kvm->arch.apic_map_lock);
spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock);
- kvm->arch.kvmclock_offset = -ktime_get_boot_ns();
+ kvm->arch.kvmclock_offset = -ktime_get_boottime_ns();
pvclock_update_vm_gtod_copy(kvm);
kvm->arch.guest_can_read_msr_platform_info = true;