@@ -207,17 +207,7 @@ static inline void set_compat_ssbs_bit(struct pt_regs *regs)
regs->pstate |= PSR_AA32_SSBS_BIT;
}
-static inline void start_thread(struct pt_regs *regs, unsigned long pc,
- unsigned long sp)
-{
- start_thread_common(regs, pc);
- regs->pstate = PSR_MODE_EL0t;
-
- if (arm64_get_ssbd_state() != ARM64_SSBD_FORCE_ENABLE)
- set_ssbs_bit(regs);
-
- regs->sp = sp;
-}
+void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp);
static inline bool is_ttbr0_addr(unsigned long addr)
{
new file mode 100644
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020 ARM Limited
+ */
+#ifndef __ASM_VDSO_DATAPAGE_H
+#define __ASM_VDSO_DATAPAGE_H
+
+#include <vdso/datapage.h>
+
+struct vdso_cpu_data {
+ unsigned int cpu;
+ unsigned int node;
+};
+
+struct arm64_vdso_data {
+ /* Must be first in struct, we cast to vdso_data */
+ struct vdso_data data[CS_BASES];
+ struct vdso_cpu_data cpu_data[];
+};
+
+#ifdef __VDSO__
+static inline struct vdso_cpu_data *__vdso_cpu_data(void)
+{
+ unsigned long offset;
+
+ asm volatile(
+ "mrs %0, tpidrro_el0\n"
+ : "=r" (offset)
+ :
+ : "cc");
+
+ if (offset)
+ return (void *)(_vdso_data) + offset;
+
+ return NULL;
+}
+#else
+static inline size_t vdso_cpu_offset(void)
+{
+ size_t offset, data_end;
+
+ offset = offsetof(struct arm64_vdso_data, cpu_data) +
+ smp_processor_id() * sizeof(struct vdso_cpu_data);
+ data_end = offset + sizeof(struct vdso_cpu_data) + 1;
+
+ /* We only map a single page for vDSO data currently */
+ if (data_end > PAGE_SIZE)
+ return 0;
+
+ return offset;
+}
+#endif
+
+#endif
@@ -55,6 +55,7 @@
#include <asm/processor.h>
#include <asm/pointer_auth.h>
#include <asm/stacktrace.h>
+#include <asm/vdso/datapage.h>
#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK)
#include <linux/stackprotector.h>
@@ -309,6 +310,28 @@ void show_regs(struct pt_regs * regs)
dump_backtrace(regs, NULL, KERN_DEFAULT);
}
+void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp)
+{
+ start_thread_common(regs, pc);
+ regs->pstate = PSR_MODE_EL0t;
+
+ if (arm64_get_ssbd_state() != ARM64_SSBD_FORCE_ENABLE)
+ set_ssbs_bit(regs);
+
+ regs->sp = sp;
+
+ /*
+ * Store the vDSO per-CPU offset if supported. Disable
+ * preemption to make sure we read the CPU offset on the CPU
+ * we write it on.
+ */
+ if (!arm64_kernel_unmapped_at_el0()) {
+ preempt_disable();
+ write_sysreg(vdso_cpu_offset(), tpidrro_el0);
+ preempt_enable();
+ }
+}
+
static void tls_thread_flush(void)
{
write_sysreg(0, tpidr_el0);
@@ -452,7 +475,8 @@ static void tls_thread_switch(struct task_struct *next)
if (is_compat_thread(task_thread_info(next)))
write_sysreg(next->thread.uw.tp_value, tpidrro_el0);
else if (!arm64_kernel_unmapped_at_el0())
- write_sysreg(0, tpidrro_el0);
+ /* Used as scratch in KPTI trampoline so don't set here. */
+ write_sysreg(vdso_cpu_offset(), tpidrro_el0);
write_sysreg(*task_user_tls(next), tpidr_el0);
}
@@ -28,6 +28,7 @@
#include <asm/cacheflush.h>
#include <asm/signal32.h>
#include <asm/vdso.h>
+#include <asm/vdso/datapage.h>
extern char vdso_start[], vdso_end[];
#ifdef CONFIG_COMPAT_VDSO
@@ -77,10 +78,10 @@ static struct vdso_abi_info vdso_info[] __ro_after_init = {
* The vDSO data page.
*/
static union {
- struct vdso_data data[CS_BASES];
+ struct arm64_vdso_data data;
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.data;
static int __vdso_remap(enum vdso_abi abi,
const struct vm_special_mapping *sm,
In order to support a vDSO getcpu() implementation add per-CPU data to the vDSO data page. Do this by wrapping the generic vdso_data struct in an arm64 specific one with an array of per-CPU data. The offset of the per-CPU data applying to a CPU will be stored in TPIDRRO_EL0, this allows us to get to the per-CPU data without doing any multiplications. Since we currently only map a single data page for the vDSO but support very large numbers of CPUs TPIDRRO may be set to zero for CPUs which don't fit in the data page. This will also happen when KPTI is active since kernel_ventry uses TPIDRRO_EL0 as a scratch register in that case, add a comment to the code explaining this. Acessors for the data are provided in the header since they will be needed in multiple files and it seems neater to keep things together. Signed-off-by: Mark Brown <broonie@kernel.org> --- arch/arm64/include/asm/processor.h | 12 +----- arch/arm64/include/asm/vdso/datapage.h | 54 ++++++++++++++++++++++++++ arch/arm64/kernel/process.c | 26 ++++++++++++- arch/arm64/kernel/vdso.c | 5 ++- 4 files changed, 83 insertions(+), 14 deletions(-) create mode 100644 arch/arm64/include/asm/vdso/datapage.h