aboutsummaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/arm/boot/compressed/Makefile2
-rw-r--r--arch/arm/kernel/Makefile1
-rw-r--r--arch/arm/kvm/guest.c2
-rw-r--r--arch/arm/mm/pageattr.c3
-rw-r--r--arch/arm64/include/asm/pgtable.h6
-rw-r--r--arch/arm64/kernel/sleep.S4
-rw-r--r--arch/arm64/kvm/guest.c2
-rw-r--r--arch/arm64/mm/hugetlbpage.c14
-rw-r--r--arch/arm64/mm/init.c4
-rw-r--r--arch/mips/jz4740/gpio.c2
-rw-r--r--arch/mips/kernel/r2300_fpu.S2
-rw-r--r--arch/mips/kernel/r4k_fpu.S2
-rw-r--r--arch/mips/kernel/traps.c13
-rw-r--r--arch/mips/kvm/mips.c4
-rw-r--r--arch/mips/mm/sc-mips.c13
-rw-r--r--arch/parisc/include/asm/floppy.h2
-rw-r--r--arch/parisc/include/uapi/asm/unistd.h3
-rw-r--r--arch/parisc/kernel/ptrace.c16
-rw-r--r--arch/parisc/kernel/syscall.S5
-rw-r--r--arch/parisc/kernel/syscall_table.S1
-rw-r--r--arch/powerpc/kernel/hw_breakpoint.c3
-rw-r--r--arch/powerpc/kvm/book3s_hv_rmhandlers.S14
-rw-r--r--arch/powerpc/mm/hugetlbpage-book3e.c13
-rw-r--r--arch/s390/include/asm/mmu_context.h16
-rw-r--r--arch/s390/include/asm/pgalloc.h24
-rw-r--r--arch/s390/kernel/head64.S2
-rw-r--r--arch/s390/kvm/kvm-s390.c2
-rw-r--r--arch/sparc/Makefile6
-rw-r--r--arch/sparc/include/uapi/asm/unistd.h3
-rw-r--r--arch/sparc/kernel/entry.S17
-rw-r--r--arch/sparc/kernel/hvcalls.S3
-rw-r--r--arch/sparc/kernel/signal_64.c2
-rw-r--r--arch/sparc/kernel/sparc_ksyms_64.c1
-rw-r--r--arch/sparc/kernel/syscalls.S36
-rw-r--r--arch/sparc/kernel/systbls_32.S2
-rw-r--r--arch/sparc/kernel/systbls_64.S4
-rw-r--r--arch/um/kernel/reboot.c1
-rw-r--r--arch/um/kernel/signal.c2
-rw-r--r--arch/x86/kernel/acpi/sleep.c7
-rw-r--r--arch/x86/kvm/mmu.c4
-rw-r--r--arch/x86/kvm/vmx.c57
-rw-r--r--arch/x86/kvm/x86.c9
-rw-r--r--arch/x86/um/os-Linux/task_size.c4
43 files changed, 243 insertions, 90 deletions
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 7a6a58ef8aaf..43788b1a1ac5 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -195,5 +195,7 @@ CFLAGS_font.o := -Dstatic=
$(obj)/font.c: $(FONTC)
$(call cmd,shipped)
+AFLAGS_hyp-stub.o := -Wa,-march=armv7-a
+
$(obj)/hyp-stub.S: $(srctree)/arch/$(SRCARCH)/kernel/hyp-stub.S
$(call cmd,shipped)
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 2c5f160be65e..ad325a8c7e1e 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -88,6 +88,7 @@ obj-$(CONFIG_DEBUG_LL) += debug.o
obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
obj-$(CONFIG_ARM_VIRT_EXT) += hyp-stub.o
+AFLAGS_hyp-stub.o :=-Wa,-march=armv7-a
ifeq ($(CONFIG_ARM_PSCI),y)
obj-$(CONFIG_SMP) += psci_smp.o
endif
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index 5fa69d7bae58..99361f11354a 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -161,7 +161,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
u64 val;
val = kvm_arm_timer_get_reg(vcpu, reg->id);
- return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id));
+ return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0;
}
static unsigned long num_core_regs(void)
diff --git a/arch/arm/mm/pageattr.c b/arch/arm/mm/pageattr.c
index cf30daff8932..d19b1ad29b07 100644
--- a/arch/arm/mm/pageattr.c
+++ b/arch/arm/mm/pageattr.c
@@ -49,6 +49,9 @@ static int change_memory_common(unsigned long addr, int numpages,
WARN_ON_ONCE(1);
}
+ if (!numpages)
+ return 0;
+
if (start < MODULES_VADDR || start >= MODULES_END)
return -EINVAL;
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index bf464de33f52..819aff5d593f 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -34,7 +34,7 @@
/*
* VMALLOC and SPARSEMEM_VMEMMAP ranges.
*
- * VMEMAP_SIZE: allows the whole VA space to be covered by a struct page array
+ * VMEMAP_SIZE: allows the whole linear region to be covered by a struct page array
* (rounded up to PUD_SIZE).
* VMALLOC_START: beginning of the kernel VA space
* VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space,
@@ -51,7 +51,9 @@
#define VMALLOC_END (PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K)
-#define vmemmap ((struct page *)(VMALLOC_END + SZ_64K))
+#define VMEMMAP_START (VMALLOC_END + SZ_64K)
+#define vmemmap ((struct page *)VMEMMAP_START - \
+ SECTION_ALIGN_DOWN(memstart_addr >> PAGE_SHIFT))
#define FIRST_USER_ADDRESS 0UL
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index e33fe33876ab..fd10eb663868 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -145,6 +145,10 @@ ENTRY(cpu_resume_mmu)
ENDPROC(cpu_resume_mmu)
.popsection
cpu_resume_after_mmu:
+#ifdef CONFIG_KASAN
+ mov x0, sp
+ bl kasan_unpoison_remaining_stack
+#endif
mov x0, #0 // return zero on success
ldp x19, x20, [sp, #16]
ldp x21, x22, [sp, #32]
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index fcb778899a38..9e54ad7c240a 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -194,7 +194,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
u64 val;
val = kvm_arm_timer_get_reg(vcpu, reg->id);
- return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id));
+ return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0;
}
/**
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 82d607c3614e..da30529bb1f6 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -306,10 +306,6 @@ static __init int setup_hugepagesz(char *opt)
hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
} else if (ps == PUD_SIZE) {
hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
- } else if (ps == (PAGE_SIZE * CONT_PTES)) {
- hugetlb_add_hstate(CONT_PTE_SHIFT);
- } else if (ps == (PMD_SIZE * CONT_PMDS)) {
- hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT);
} else {
pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
return 0;
@@ -317,13 +313,3 @@ static __init int setup_hugepagesz(char *opt)
return 1;
}
__setup("hugepagesz=", setup_hugepagesz);
-
-#ifdef CONFIG_ARM64_64K_PAGES
-static __init int add_default_hugepagesz(void)
-{
- if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL)
- hugetlb_add_hstate(CONT_PMD_SHIFT);
- return 0;
-}
-arch_initcall(add_default_hugepagesz);
-#endif
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index f3b061e67bfe..7802f216a67a 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -319,8 +319,8 @@ void __init mem_init(void)
#endif
MLG(VMALLOC_START, VMALLOC_END),
#ifdef CONFIG_SPARSEMEM_VMEMMAP
- MLG((unsigned long)vmemmap,
- (unsigned long)vmemmap + VMEMMAP_SIZE),
+ MLG(VMEMMAP_START,
+ VMEMMAP_START + VMEMMAP_SIZE),
MLM((unsigned long)virt_to_page(PAGE_OFFSET),
(unsigned long)virt_to_page(high_memory)),
#endif
diff --git a/arch/mips/jz4740/gpio.c b/arch/mips/jz4740/gpio.c
index 8c6d76c9b2d6..d9907e57e9b9 100644
--- a/arch/mips/jz4740/gpio.c
+++ b/arch/mips/jz4740/gpio.c
@@ -270,7 +270,7 @@ uint32_t jz_gpio_port_get_value(int port, uint32_t mask)
}
EXPORT_SYMBOL(jz_gpio_port_get_value);
-#define IRQ_TO_BIT(irq) BIT(irq_to_gpio(irq) & 0x1f)
+#define IRQ_TO_BIT(irq) BIT((irq - JZ4740_IRQ_GPIO(0)) & 0x1f)
static void jz_gpio_check_trigger_both(struct jz_gpio_chip *chip, unsigned int irq)
{
diff --git a/arch/mips/kernel/r2300_fpu.S b/arch/mips/kernel/r2300_fpu.S
index 5ce3b746cedc..b4ac6374a38f 100644
--- a/arch/mips/kernel/r2300_fpu.S
+++ b/arch/mips/kernel/r2300_fpu.S
@@ -125,7 +125,7 @@ LEAF(_restore_fp_context)
END(_restore_fp_context)
.set reorder
- .type fault@function
+ .type fault, @function
.ent fault
fault: li v0, -EFAULT
jr ra
diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S
index f09546ee2cdc..17732f876eff 100644
--- a/arch/mips/kernel/r4k_fpu.S
+++ b/arch/mips/kernel/r4k_fpu.S
@@ -358,7 +358,7 @@ LEAF(_restore_msa_all_upper)
.set reorder
- .type fault@function
+ .type fault, @function
.ent fault
fault: li v0, -EFAULT # failure
jr ra
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index ae790c575d4f..bf14da9f3e33 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -690,15 +690,15 @@ static int simulate_sync(struct pt_regs *regs, unsigned int opcode)
asmlinkage void do_ov(struct pt_regs *regs)
{
enum ctx_state prev_state;
- siginfo_t info;
+ siginfo_t info = {
+ .si_signo = SIGFPE,
+ .si_code = FPE_INTOVF,
+ .si_addr = (void __user *)regs->cp0_epc,
+ };
prev_state = exception_enter();
die_if_kernel("Integer overflow", regs);
- info.si_code = FPE_INTOVF;
- info.si_signo = SIGFPE;
- info.si_errno = 0;
- info.si_addr = (void __user *) regs->cp0_epc;
force_sig_info(SIGFPE, &info, current);
exception_exit(prev_state);
}
@@ -874,7 +874,7 @@ out:
void do_trap_or_bp(struct pt_regs *regs, unsigned int code,
const char *str)
{
- siginfo_t info;
+ siginfo_t info = { 0 };
char b[40];
#ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
@@ -903,7 +903,6 @@ void do_trap_or_bp(struct pt_regs *regs, unsigned int code,
else
info.si_code = FPE_INTOVF;
info.si_signo = SIGFPE;
- info.si_errno = 0;
info.si_addr = (void __user *) regs->cp0_epc;
force_sig_info(SIGFPE, &info, current);
break;
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 8bc3977576e6..3110447ab1e9 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -702,7 +702,7 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu,
} else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) {
void __user *uaddr = (void __user *)(long)reg->addr;
- return copy_to_user(uaddr, vs, 16);
+ return copy_to_user(uaddr, vs, 16) ? -EFAULT : 0;
} else {
return -EINVAL;
}
@@ -732,7 +732,7 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu,
} else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) {
void __user *uaddr = (void __user *)(long)reg->addr;
- return copy_from_user(vs, uaddr, 16);
+ return copy_from_user(vs, uaddr, 16) ? -EFAULT : 0;
} else {
return -EINVAL;
}
diff --git a/arch/mips/mm/sc-mips.c b/arch/mips/mm/sc-mips.c
index 249647578e58..91dec32c77b7 100644
--- a/arch/mips/mm/sc-mips.c
+++ b/arch/mips/mm/sc-mips.c
@@ -164,11 +164,13 @@ static int __init mips_sc_probe_cm3(void)
sets = cfg & CM_GCR_L2_CONFIG_SET_SIZE_MSK;
sets >>= CM_GCR_L2_CONFIG_SET_SIZE_SHF;
- c->scache.sets = 64 << sets;
+ if (sets)
+ c->scache.sets = 64 << sets;
line_sz = cfg & CM_GCR_L2_CONFIG_LINE_SIZE_MSK;
line_sz >>= CM_GCR_L2_CONFIG_LINE_SIZE_SHF;
- c->scache.linesz = 2 << line_sz;
+ if (line_sz)
+ c->scache.linesz = 2 << line_sz;
assoc = cfg & CM_GCR_L2_CONFIG_ASSOC_MSK;
assoc >>= CM_GCR_L2_CONFIG_ASSOC_SHF;
@@ -176,9 +178,12 @@ static int __init mips_sc_probe_cm3(void)
c->scache.waysize = c->scache.sets * c->scache.linesz;
c->scache.waybit = __ffs(c->scache.waysize);
- c->scache.flags &= ~MIPS_CACHE_NOT_PRESENT;
+ if (c->scache.linesz) {
+ c->scache.flags &= ~MIPS_CACHE_NOT_PRESENT;
+ return 1;
+ }
- return 1;
+ return 0;
}
static inline int __init mips_sc_probe(void)
diff --git a/arch/parisc/include/asm/floppy.h b/arch/parisc/include/asm/floppy.h
index f84ff12574b7..6d8276cd25ca 100644
--- a/arch/parisc/include/asm/floppy.h
+++ b/arch/parisc/include/asm/floppy.h
@@ -33,7 +33,7 @@
* floppy accesses go through the track buffer.
*/
#define _CROSS_64KB(a,s,vdma) \
-(!vdma && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64))
+(!(vdma) && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64))
#define CROSS_64KB(a,s) _CROSS_64KB(a,s,use_virtual_dma & 1)
diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h
index 35bdccbb2036..b75039f92116 100644
--- a/arch/parisc/include/uapi/asm/unistd.h
+++ b/arch/parisc/include/uapi/asm/unistd.h
@@ -361,8 +361,9 @@
#define __NR_membarrier (__NR_Linux + 343)
#define __NR_userfaultfd (__NR_Linux + 344)
#define __NR_mlock2 (__NR_Linux + 345)
+#define __NR_copy_file_range (__NR_Linux + 346)
-#define __NR_Linux_syscalls (__NR_mlock2 + 1)
+#define __NR_Linux_syscalls (__NR_copy_file_range + 1)
#define __IGNORE_select /* newselect */
diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c
index 9585c81f755f..ce0b2b4075c7 100644
--- a/arch/parisc/kernel/ptrace.c
+++ b/arch/parisc/kernel/ptrace.c
@@ -269,14 +269,19 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
long do_syscall_trace_enter(struct pt_regs *regs)
{
- long ret = 0;
-
/* Do the secure computing check first. */
secure_computing_strict(regs->gr[20]);
if (test_thread_flag(TIF_SYSCALL_TRACE) &&
- tracehook_report_syscall_entry(regs))
- ret = -1L;
+ tracehook_report_syscall_entry(regs)) {
+ /*
+ * Tracing decided this syscall should not happen or the
+ * debugger stored an invalid system call number. Skip
+ * the system call and the system call restart handling.
+ */
+ regs->gr[20] = -1UL;
+ goto out;
+ }
#ifdef CONFIG_64BIT
if (!is_compat_task())
@@ -290,7 +295,8 @@ long do_syscall_trace_enter(struct pt_regs *regs)
regs->gr[24] & 0xffffffff,
regs->gr[23] & 0xffffffff);
- return ret ? : regs->gr[20];
+out:
+ return regs->gr[20];
}
void do_syscall_trace_exit(struct pt_regs *regs)
diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index 3fbd7252a4b2..fbafa0d0e2bf 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -343,7 +343,7 @@ tracesys_next:
#endif
comiclr,>>= __NR_Linux_syscalls, %r20, %r0
- b,n .Lsyscall_nosys
+ b,n .Ltracesys_nosys
LDREGX %r20(%r19), %r19
@@ -359,6 +359,9 @@ tracesys_next:
be 0(%sr7,%r19)
ldo R%tracesys_exit(%r2),%r2
+.Ltracesys_nosys:
+ ldo -ENOSYS(%r0),%r28 /* set errno */
+
/* Do *not* call this function on the gateway page, because it
makes a direct call to syscall_trace. */
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index d4ffcfbc9885..585d50fc75c0 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -441,6 +441,7 @@
ENTRY_SAME(membarrier)
ENTRY_SAME(userfaultfd)
ENTRY_SAME(mlock2) /* 345 */
+ ENTRY_SAME(copy_file_range)
.ifne (. - 90b) - (__NR_Linux_syscalls * (91b - 90b))
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 05e804cdecaa..aec9a1b1d25b 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -109,8 +109,9 @@ void arch_unregister_hw_breakpoint(struct perf_event *bp)
* If the breakpoint is unregistered between a hw_breakpoint_handler()
* and the single_step_dabr_instruction(), then cleanup the breakpoint
* restoration variables to prevent dangling pointers.
+ * FIXME, this should not be using bp->ctx at all! Sayeth peterz.
*/
- if (bp->ctx && bp->ctx->task)
+ if (bp->ctx && bp->ctx->task && bp->ctx->task != ((void *)-1L))
bp->ctx->task->thread.last_hit_ubp = NULL;
}
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 6ee26de9a1de..25ae2c9913c3 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1370,6 +1370,20 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
std r6, VCPU_ACOP(r9)
stw r7, VCPU_GUEST_PID(r9)
std r8, VCPU_WORT(r9)
+ /*
+ * Restore various registers to 0, where non-zero values
+ * set by the guest could disrupt the host.
+ */
+ li r0, 0
+ mtspr SPRN_IAMR, r0
+ mtspr SPRN_CIABR, r0
+ mtspr SPRN_DAWRX, r0
+ mtspr SPRN_TCSCR, r0
+ mtspr SPRN_WORT, r0
+ /* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */
+ li r0, 1
+ sldi r0, r0, 31
+ mtspr SPRN_MMCRS, r0
8:
/* Save and reset AMR and UAMOR before turning on the MMU */
diff --git a/arch/powerpc/mm/hugetlbpage-book3e.c b/arch/powerpc/mm/hugetlbpage-book3e.c
index 7e6d0880813f..83a8be791e06 100644
--- a/arch/powerpc/mm/hugetlbpage-book3e.c
+++ b/arch/powerpc/mm/hugetlbpage-book3e.c
@@ -8,6 +8,8 @@
#include <linux/mm.h>
#include <linux/hugetlb.h>
+#include <asm/mmu.h>
+
#ifdef CONFIG_PPC_FSL_BOOK3E
#ifdef CONFIG_PPC64
static inline int tlb1_next(void)
@@ -60,6 +62,14 @@ static inline void book3e_tlb_lock(void)
unsigned long tmp;
int token = smp_processor_id() + 1;
+ /*
+ * Besides being unnecessary in the absence of SMT, this
+ * check prevents trying to do lbarx/stbcx. on e5500 which
+ * doesn't implement either feature.
+ */
+ if (!cpu_has_feature(CPU_FTR_SMT))
+ return;
+
asm volatile("1: lbarx %0, 0, %1;"
"cmpwi %0, 0;"
"bne 2f;"
@@ -80,6 +90,9 @@ static inline void book3e_tlb_unlock(void)
{
struct paca_struct *paca = get_paca();
+ if (!cpu_has_feature(CPU_FTR_SMT))
+ return;
+
isync();
paca->tcd_ptr->lock = 0;
}
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index fb1b93ea3e3f..e485817f7b1a 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -15,17 +15,25 @@
static inline int init_new_context(struct task_struct *tsk,
struct mm_struct *mm)
{
+ spin_lock_init(&mm->context.list_lock);
+ INIT_LIST_HEAD(&mm->context.pgtable_list);
+ INIT_LIST_HEAD(&mm->context.gmap_list);
cpumask_clear(&mm->context.cpu_attach_mask);
atomic_set(&mm->context.attach_count, 0);
mm->context.flush_mm = 0;
- mm->context.asce_bits = _ASCE_TABLE_LENGTH | _ASCE_USER_BITS;
- mm->context.asce_bits |= _ASCE_TYPE_REGION3;
#ifdef CONFIG_PGSTE
mm->context.alloc_pgste = page_table_allocate_pgste;
mm->context.has_pgste = 0;
mm->context.use_skey = 0;
#endif
- mm->context.asce_limit = STACK_TOP_MAX;
+ if (mm->context.asce_limit == 0) {
+ /* context created by exec, set asce limit to 4TB */
+ mm->context.asce_bits = _ASCE_TABLE_LENGTH |
+ _ASCE_USER_BITS | _ASCE_TYPE_REGION3;
+ mm->context.asce_limit = STACK_TOP_MAX;
+ } else if (mm->context.asce_limit == (1UL << 31)) {
+ mm_inc_nr_pmds(mm);
+ }
crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
return 0;
}
@@ -111,8 +119,6 @@ static inline void activate_mm(struct mm_struct *prev,
static inline void arch_dup_mmap(struct mm_struct *oldmm,
struct mm_struct *mm)
{
- if (oldmm->context.asce_limit < mm->context.asce_limit)
- crst_table_downgrade(mm, oldmm->context.asce_limit);
}
static inline void arch_exit_mmap(struct mm_struct *mm)
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index 7b7858f158b4..d7cc79fb6191 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -100,12 +100,26 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
static inline pgd_t *pgd_alloc(struct mm_struct *mm)
{
- spin_lock_init(&mm->context.list_lock);
- INIT_LIST_HEAD(&mm->context.pgtable_list);
- INIT_LIST_HEAD(&mm->context.gmap_list);
- return (pgd_t *) crst_table_alloc(mm);
+ unsigned long *table = crst_table_alloc(mm);
+
+ if (!table)
+ return NULL;
+ if (mm->context.asce_limit == (1UL << 31)) {
+ /* Forking a compat process with 2 page table levels */
+ if (!pgtable_pmd_page_ctor(virt_to_page(table))) {
+ crst_table_free(mm, table);
+ return NULL;
+ }
+ }
+ return (pgd_t *) table;
+}
+
+static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+ if (mm->context.asce_limit == (1UL << 31))
+ pgtable_pmd_page_dtor(virt_to_page(pgd));
+ crst_table_free(mm, (unsigned long *) pgd);
}
-#define pgd_free(mm, pgd) crst_table_free(mm, (unsigned long *) pgd)
static inline void pmd_populate(struct mm_struct *mm,
pmd_t *pmd, pgtable_t pte)
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index c5febe84eba6..03c2b469c472 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -16,7 +16,7 @@
__HEAD
ENTRY(startup_continue)
- tm __LC_STFLE_FAC_LIST+6,0x80 # LPP available ?
+ tm __LC_STFLE_FAC_LIST+5,0x80 # LPP available ?
jz 0f
xc __LC_LPP+1(7,0),__LC_LPP+1 # clear lpp and current_pid
mvi __LC_LPP,0x80 # and set LPP_MAGIC
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 4af21c771f9b..03dfe9c667f4 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2381,7 +2381,7 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
/* manually convert vector registers if necessary */
if (MACHINE_HAS_VX) {
- convert_vx_to_fp(fprs, current->thread.fpu.vxrs);
+ convert_vx_to_fp(fprs, (__vector128 *) vcpu->run->s.regs.vrs);
rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
fprs, 128);
} else {
diff --git a/arch/sparc/Makefile b/arch/sparc/Makefile
index eaee14637d93..8496a074bd0e 100644
--- a/arch/sparc/Makefile
+++ b/arch/sparc/Makefile
@@ -24,7 +24,13 @@ LDFLAGS := -m elf32_sparc
export BITS := 32
UTS_MACHINE := sparc
+# We are adding -Wa,-Av8 to KBUILD_CFLAGS to deal with a specs bug in some
+# versions of gcc. Some gcc versions won't pass -Av8 to binutils when you
+# give -mcpu=v8. This silently worked with older bintutils versions but
+# does not any more.
KBUILD_CFLAGS += -m32 -mcpu=v8 -pipe -mno-fpu -fcall-used-g5 -fcall-used-g7
+KBUILD_CFLAGS += -Wa,-Av8
+
KBUILD_AFLAGS += -m32 -Wa,-Av8
else
diff --git a/arch/sparc/include/uapi/asm/unistd.h b/arch/sparc/include/uapi/asm/unistd.h
index 1c26d440d288..b6de8b10a55b 100644
--- a/arch/sparc/include/uapi/asm/unistd.h
+++ b/arch/sparc/include/uapi/asm/unistd.h
@@ -422,8 +422,9 @@
#define __NR_listen 354
#define __NR_setsockopt 355
#define __NR_mlock2 356
+#define __NR_copy_file_range 357
-#define NR_syscalls 357
+#define NR_syscalls 358
/* Bitmask values returned from kern_features system call. */
#define KERN_FEATURE_MIXED_MODE_STACK 0x00000001
diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S
index 33c02b15f478..a83707c83be8 100644
--- a/arch/sparc/kernel/entry.S
+++ b/arch/sparc/kernel/entry.S
@@ -948,7 +948,24 @@ linux_syscall_trace:
cmp %o0, 0
bne 3f
mov -ENOSYS, %o0
+
+ /* Syscall tracing can modify the registers. */
+ ld [%sp + STACKFRAME_SZ + PT_G1], %g1
+ sethi %hi(sys_call_table), %l7
+ ld [%sp + STACKFRAME_SZ + PT_I0], %i0
+ or %l7, %lo(sys_call_table), %l7
+ ld [%sp + STACKFRAME_SZ + PT_I1], %i1
+ ld [%sp + STACKFRAME_SZ + PT_I2], %i2
+ ld [%sp + STACKFRAME_SZ + PT_I3], %i3
+ ld [%sp + STACKFRAME_SZ + PT_I4], %i4
+ ld [%sp + STACKFRAME_SZ + PT_I5], %i5
+ cmp %g1, NR_syscalls
+ bgeu 3f
+ mov -ENOSYS, %o0
+
+ sll %g1, 2, %l4
mov %i0, %o0
+ ld [%l7 + %l4], %l7
mov %i1, %o1
mov %i2, %o2
mov %i3, %o3
diff --git a/arch/sparc/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S
index afbaba52d2f1..d127130bf424 100644
--- a/arch/sparc/kernel/hvcalls.S
+++ b/arch/sparc/kernel/hvcalls.S
@@ -338,8 +338,9 @@ ENTRY(sun4v_mach_set_watchdog)
mov %o1, %o4
mov HV_FAST_MACH_SET_WATCHDOG, %o5
ta HV_FAST_TRAP
+ brnz,a,pn %o4, 0f
stx %o1, [%o4]
- retl
+0: retl
nop
ENDPROC(sun4v_mach_set_watchdog)
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index d88beff47bab..39aaec173f66 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -52,7 +52,7 @@ asmlinkage void sparc64_set_context(struct pt_regs *regs)
unsigned char fenab;
int err;
- flush_user_windows();
+ synchronize_user_stack();
if (get_thread_wsaved() ||
(((unsigned long)ucp) & (sizeof(unsigned long)-1)) ||
(!__access_ok(ucp, sizeof(*ucp))))
diff --git a/arch/sparc/kernel/sparc_ksyms_64.c b/arch/sparc/kernel/sparc_ksyms_64.c
index a92d5d2c46a3..9e034f29dcc5 100644
--- a/arch/sparc/kernel/sparc_ksyms_64.c
+++ b/arch/sparc/kernel/sparc_ksyms_64.c
@@ -37,6 +37,7 @@ EXPORT_SYMBOL(sun4v_niagara_getperf);
EXPORT_SYMBOL(sun4v_niagara_setperf);
EXPORT_SYMBOL(sun4v_niagara2_getperf);
EXPORT_SYMBOL(sun4v_niagara2_setperf);
+EXPORT_SYMBOL(sun4v_mach_set_watchdog);
/* from hweight.S */
EXPORT_SYMBOL(__arch_hweight8);
diff --git a/arch/sparc/kernel/syscalls.S b/arch/sparc/kernel/syscalls.S
index bb0008927598..c4a1b5c40e4e 100644
--- a/arch/sparc/kernel/syscalls.S
+++ b/arch/sparc/kernel/syscalls.S
@@ -158,7 +158,25 @@ linux_syscall_trace32:
add %sp, PTREGS_OFF, %o0
brnz,pn %o0, 3f
mov -ENOSYS, %o0
+
+ /* Syscall tracing can modify the registers. */
+ ldx [%sp + PTREGS_OFF + PT_V9_G1], %g1
+ sethi %hi(sys_call_table32), %l7
+ ldx [%sp + PTREGS_OFF + PT_V9_I0], %i0
+ or %l7, %lo(sys_call_table32), %l7
+ ldx [%sp + PTREGS_OFF + PT_V9_I1], %i1
+ ldx [%sp + PTREGS_OFF + PT_V9_I2], %i2
+ ldx [%sp + PTREGS_OFF + PT_V9_I3], %i3
+ ldx [%sp + PTREGS_OFF + PT_V9_I4], %i4
+ ldx [%sp + PTREGS_OFF + PT_V9_I5], %i5
+
+ cmp %g1, NR_syscalls
+ bgeu,pn %xcc, 3f
+ mov -ENOSYS, %o0
+
+ sll %g1, 2, %l4
srl %i0, 0, %o0
+ lduw [%l7 + %l4], %l7
srl %i4, 0, %o4
srl %i1, 0, %o1
srl %i2, 0, %o2
@@ -170,7 +188,25 @@ linux_syscall_trace:
add %sp, PTREGS_OFF, %o0
brnz,pn %o0, 3f
mov -ENOSYS, %o0
+
+ /* Syscall tracing can modify the registers. */
+ ldx [%sp + PTREGS_OFF + PT_V9_G1], %g1
+ sethi %hi(sys_call_table64), %l7
+ ldx [%sp + PTREGS_OFF + PT_V9_I0], %i0
+ or %l7, %lo(sys_call_table64), %l7
+ ldx [%sp + PTREGS_OFF + PT_V9_I1], %i1
+ ldx [%sp + PTREGS_OFF + PT_V9_I2], %i2
+ ldx [%sp + PTREGS_OFF + PT_V9_I3], %i3
+ ldx [%sp + PTREGS_OFF + PT_V9_I4], %i4
+ ldx [%sp + PTREGS_OFF + PT_V9_I5], %i5
+
+ cmp %g1, NR_syscalls
+ bgeu,pn %xcc, 3f
+ mov -ENOSYS, %o0
+
+ sll %g1, 2, %l4
mov %i0, %o0
+ lduw [%l7 + %l4], %l7
mov %i1, %o1
mov %i2, %o2
mov %i3, %o3
diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S
index e663b6c78de2..6c3dd6c52f8b 100644
--- a/arch/sparc/kernel/systbls_32.S
+++ b/arch/sparc/kernel/systbls_32.S
@@ -88,4 +88,4 @@ sys_call_table:
/*340*/ .long sys_ni_syscall, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr
/*345*/ .long sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf
/*350*/ .long sys_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen
-/*355*/ .long sys_setsockopt, sys_mlock2
+/*355*/ .long sys_setsockopt, sys_mlock2, sys_copy_file_range
diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S
index 1557121f4cdc..12b524cfcfa0 100644
--- a/arch/sparc/kernel/systbls_64.S
+++ b/arch/sparc/kernel/systbls_64.S
@@ -89,7 +89,7 @@ sys_call_table32:
/*340*/ .word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr
.word sys32_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf
/*350*/ .word sys32_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen
- .word compat_sys_setsockopt, sys_mlock2
+ .word compat_sys_setsockopt, sys_mlock2, sys_copy_file_range
#endif /* CONFIG_COMPAT */
@@ -170,4 +170,4 @@ sys_call_table:
/*340*/ .word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr
.word sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf
/*350*/ .word sys64_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen
- .word sys_setsockopt, sys_mlock2
+ .word sys_setsockopt, sys_mlock2, sys_copy_file_range
diff --git a/arch/um/kernel/reboot.c b/arch/um/kernel/reboot.c
index 9bdf67a092a5..b60a9f8cda75 100644
--- a/arch/um/kernel/reboot.c
+++ b/arch/um/kernel/reboot.c
@@ -12,6 +12,7 @@
#include <skas.h>
void (*pm_power_off)(void);
+EXPORT_SYMBOL(pm_power_off);
static void kill_off_processes(void)
{
diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c
index fc8be0e3a4ff..57acbd67d85d 100644
--- a/arch/um/kernel/signal.c
+++ b/arch/um/kernel/signal.c
@@ -69,7 +69,7 @@ void do_signal(struct pt_regs *regs)
struct ksignal ksig;
int handled_sig = 0;
- if (get_signal(&ksig)) {
+ while (get_signal(&ksig)) {
handled_sig = 1;
/* Whee! Actually deliver the signal. */
handle_signal(&ksig, regs);
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index d1daead5fcdd..adb3eaf8fe2a 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -16,6 +16,7 @@
#include <asm/cacheflush.h>
#include <asm/realmode.h>
+#include <linux/ftrace.h>
#include "../../realmode/rm/wakeup.h"
#include "sleep.h"
@@ -107,7 +108,13 @@ int x86_acpi_suspend_lowlevel(void)
saved_magic = 0x123456789abcdef0L;
#endif /* CONFIG_64BIT */
+ /*
+ * Pause/unpause graph tracing around do_suspend_lowlevel as it has
+ * inconsistent call/return info after it jumps to the wakeup vector.
+ */
+ pause_graph_tracing();
do_suspend_lowlevel();
+ unpause_graph_tracing();
return 0;
}
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 95a955de5964..1e7a49bfc94f 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3721,13 +3721,15 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
void
reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
{
+ bool uses_nx = context->nx || context->base_role.smep_andnot_wp;
+
/*
* Passing "true" to the last argument is okay; it adds a check
* on bit 8 of the SPTEs which KVM doesn't use anyway.
*/
__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
boot_cpu_data.x86_phys_bits,
- context->shadow_root_level, context->nx,
+ context->shadow_root_level, uses_nx,
guest_cpuid_has_gbpages(vcpu), is_pse(vcpu),
true);
}
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index e2951b6edbbc..9bd8f44baded 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -596,6 +596,8 @@ struct vcpu_vmx {
/* Support for PML */
#define PML_ENTITY_NUM 512
struct page *pml_pg;
+
+ u64 current_tsc_ratio;
};
enum segment_cache_field {
@@ -1811,6 +1813,13 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
return;
}
break;
+ case MSR_IA32_PEBS_ENABLE:
+ /* PEBS needs a quiescent period after being disabled (to write
+ * a record). Disabling PEBS through VMX MSR swapping doesn't
+ * provide that period, so a CPU could write host's record into
+ * guest's memory.
+ */
+ wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
}
for (i = 0; i < m->nr; ++i)
@@ -1848,26 +1857,31 @@ static void reload_tss(void)
static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
{
- u64 guest_efer;
- u64 ignore_bits;
+ u64 guest_efer = vmx->vcpu.arch.efer;
+ u64 ignore_bits = 0;
- guest_efer = vmx->vcpu.arch.efer;
+ if (!enable_ept) {
+ /*
+ * NX is needed to handle CR0.WP=1, CR4.SMEP=1. Testing
+ * host CPUID is more efficient than testing guest CPUID
+ * or CR4. Host SMEP is anyway a requirement for guest SMEP.
+ */
+ if (boot_cpu_has(X86_FEATURE_SMEP))
+ guest_efer |= EFER_NX;
+ else if (!(guest_efer & EFER_NX))
+ ignore_bits |= EFER_NX;
+ }
/*
- * NX is emulated; LMA and LME handled by hardware; SCE meaningless
- * outside long mode
+ * LMA and LME handled by hardware; SCE meaningless outside long mode.
*/
- ignore_bits = EFER_NX | EFER_SCE;
+ ignore_bits |= EFER_SCE;
#ifdef CONFIG_X86_64
ignore_bits |= EFER_LMA | EFER_LME;
/* SCE is meaningful only in long mode on Intel */
if (guest_efer & EFER_LMA)
ignore_bits &= ~(u64)EFER_SCE;
#endif
- guest_efer &= ~ignore_bits;
- guest_efer |= host_efer & ignore_bits;
- vmx->guest_msrs[efer_offset].data = guest_efer;
- vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
clear_atomic_switch_msr(vmx, MSR_EFER);
@@ -1878,16 +1892,21 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
*/
if (cpu_has_load_ia32_efer ||
(enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) {
- guest_efer = vmx->vcpu.arch.efer;
if (!(guest_efer & EFER_LMA))
guest_efer &= ~EFER_LME;
if (guest_efer != host_efer)
add_atomic_switch_msr(vmx, MSR_EFER,
guest_efer, host_efer);
return false;
- }
+ } else {
+ guest_efer &= ~ignore_bits;
+ guest_efer |= host_efer & ignore_bits;
- return true;
+ vmx->guest_msrs[efer_offset].data = guest_efer;
+ vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
+
+ return true;
+ }
}
static unsigned long segment_base(u16 selector)
@@ -2127,14 +2146,16 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp);
vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
- /* Setup TSC multiplier */
- if (cpu_has_vmx_tsc_scaling())
- vmcs_write64(TSC_MULTIPLIER,
- vcpu->arch.tsc_scaling_ratio);
-
vmx->loaded_vmcs->cpu = cpu;
}
+ /* Setup TSC multiplier */
+ if (kvm_has_tsc_control &&
+ vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) {
+ vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio;
+ vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
+ }
+
vmx_vcpu_pi_load(vcpu, cpu);
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f4891f2ece23..eaf6ee8c28b8 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2752,7 +2752,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
}
kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
- vcpu->arch.switch_db_regs |= KVM_DEBUGREG_RELOAD;
}
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
@@ -6619,12 +6618,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
* KVM_DEBUGREG_WONT_EXIT again.
*/
if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) {
- int i;
-
WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP);
kvm_x86_ops->sync_dirty_debug_regs(vcpu);
- for (i = 0; i < KVM_NR_DB_REGS; i++)
- vcpu->arch.eff_db[i] = vcpu->arch.db[i];
+ kvm_update_dr0123(vcpu);
+ kvm_update_dr6(vcpu);
+ kvm_update_dr7(vcpu);
+ vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD;
}
/*
diff --git a/arch/x86/um/os-Linux/task_size.c b/arch/x86/um/os-Linux/task_size.c
index 8502ad30e61b..5adb6a2fd117 100644
--- a/arch/x86/um/os-Linux/task_size.c
+++ b/arch/x86/um/os-Linux/task_size.c
@@ -109,7 +109,7 @@ unsigned long os_get_top_address(void)
exit(1);
}
- printf("0x%x\n", bottom << UM_KERN_PAGE_SHIFT);
+ printf("0x%lx\n", bottom << UM_KERN_PAGE_SHIFT);
printf("Locating the top of the address space ... ");
fflush(stdout);
@@ -134,7 +134,7 @@ out:
exit(1);
}
top <<= UM_KERN_PAGE_SHIFT;
- printf("0x%x\n", top);
+ printf("0x%lx\n", top);
return top;
}