7 files changed, 134 insertions, 82 deletions

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 4b4f78c9ba19..cfa9b5b2c27a 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -146,6 +146,8 @@ EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
 
 static int __init x86_xsave_setup(char *s)
 {
+        if (strlen(s))
+                return 0;
         setup_clear_cpu_cap(X86_FEATURE_XSAVE);
         setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
         setup_clear_cpu_cap(X86_FEATURE_XSAVES);
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index dd9d6190b08d..08fe6e8a726e 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -465,6 +465,16 @@ static void mc_bp_resume(void)
 
         if (uci->valid && uci->mc)
                 microcode_ops->apply_microcode(cpu);
+#ifdef CONFIG_X86_64
+        else if (!uci->mc)
+                /*
+                 * We might resume and not have applied late microcode but still
+                 * have a newer patch stashed from the early loader. We don't
+                 * have it in uci->mc so we have to load it the same way we're
+                 * applying patches early on the APs.
+                 */
+                load_ucode_ap();
+#endif
 }
 
 static struct syscore_ops mc_syscore_ops = {
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
index adf138eac85c..f9ed429d6e4f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -486,14 +486,17 @@ static struct attribute_group snbep_uncore_qpi_format_group = {
         .attrs = snbep_uncore_qpi_formats_attr,
 };
 
-#define SNBEP_UNCORE_MSR_OPS_COMMON_INIT()                      \
-        .init_box       = snbep_uncore_msr_init_box,            \
+#define __SNBEP_UNCORE_MSR_OPS_COMMON_INIT()                    \
         .disable_box    = snbep_uncore_msr_disable_box,         \
         .enable_box     = snbep_uncore_msr_enable_box,          \
         .disable_event  = snbep_uncore_msr_disable_event,       \
         .enable_event   = snbep_uncore_msr_enable_event,        \
         .read_counter   = uncore_msr_read_counter
 
+#define SNBEP_UNCORE_MSR_OPS_COMMON_INIT()                      \
+        __SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),                   \
+        .init_box       = snbep_uncore_msr_init_box             \
+
 static struct intel_uncore_ops snbep_uncore_msr_ops = {
         SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
 };
@@ -1919,6 +1922,30 @@ static struct intel_uncore_type hswep_uncore_cbox = {
         .format_group           = &hswep_uncore_cbox_format_group,
 };
 
+/*
+ * Write SBOX Initialization register bit by bit to avoid spurious #GPs
+ */
+static void hswep_uncore_sbox_msr_init_box(struct intel_uncore_box *box)
+{
+        unsigned msr = uncore_msr_box_ctl(box);
+
+        if (msr) {
+                u64 init = SNBEP_PMON_BOX_CTL_INT;
+                u64 flags = 0;
+                int i;
+
+                for_each_set_bit(i, (unsigned long *)&init, 64) {
+                        flags |= (1ULL << i);
+                        wrmsrl(msr, flags);
+                }
+        }
+}
+
+static struct intel_uncore_ops hswep_uncore_sbox_msr_ops = {
+        __SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+        .init_box               = hswep_uncore_sbox_msr_init_box
+};
+
 static struct attribute *hswep_uncore_sbox_formats_attr[] = {
         &format_attr_event.attr,
         &format_attr_umask.attr,
@@ -1944,7 +1971,7 @@ static struct intel_uncore_type hswep_uncore_sbox = {
         .event_mask             = HSWEP_S_MSR_PMON_RAW_EVENT_MASK,
         .box_ctl                = HSWEP_S0_MSR_PMON_BOX_CTL,
         .msr_offset             = HSWEP_SBOX_MSR_OFFSET,
-        .ops                    = &snbep_uncore_msr_ops,
+        .ops                    = &hswep_uncore_sbox_msr_ops,
         .format_group           = &hswep_uncore_sbox_format_group,
 };
 
@@ -2025,13 +2052,27 @@ static struct intel_uncore_type hswep_uncore_imc = {
         SNBEP_UNCORE_PCI_COMMON_INIT(),
 };
 
+static unsigned hswep_uncore_irp_ctrs[] = {0xa0, 0xa8, 0xb0, 0xb8};
+
+static u64 hswep_uncore_irp_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+        struct pci_dev *pdev = box->pci_dev;
+        struct hw_perf_event *hwc = &event->hw;
+        u64 count = 0;
+
+        pci_read_config_dword(pdev, hswep_uncore_irp_ctrs[hwc->idx], (u32 *)&count);
+        pci_read_config_dword(pdev, hswep_uncore_irp_ctrs[hwc->idx] + 4, (u32 *)&count + 1);
+
+        return count;
+}
+
 static struct intel_uncore_ops hswep_uncore_irp_ops = {
         .init_box       = snbep_uncore_pci_init_box,
         .disable_box    = snbep_uncore_pci_disable_box,
         .enable_box     = snbep_uncore_pci_enable_box,
         .disable_event  = ivbep_uncore_irp_disable_event,
         .enable_event   = ivbep_uncore_irp_enable_event,
-        .read_counter   = ivbep_uncore_irp_read_counter,
+        .read_counter   = hswep_uncore_irp_read_counter,
 };
 
 static struct intel_uncore_type hswep_uncore_irp = {
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 1abcb50b48ae..ff86f19b5758 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -24,7 +24,6 @@ static char x86_stack_ids[][8] = {
                 [ DEBUG_STACK-1                 ]       = "#DB",
                 [ NMI_STACK-1                   ]       = "NMI",
                 [ DOUBLEFAULT_STACK-1           ]       = "#DF",
-                [ STACKFAULT_STACK-1            ]       = "#SS",
                 [ MCE_STACK-1                   ]       = "#MC",
 #if DEBUG_STKSZ > EXCEPTION_STKSZ
                 [ N_EXCEPTION_STACKS ...
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index df088bb03fb3..c0226ab54106 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -828,9 +828,15 @@ ENTRY(native_iret)
         jnz native_irq_return_ldt
 #endif
 
+.global native_irq_return_iret
 native_irq_return_iret:
+        /*
+         * This may fault.  Non-paranoid faults on return to userspace are
+         * handled by fixup_bad_iret.  These include #SS, #GP, and #NP.
+         * Double-faults due to espfix64 are handled in do_double_fault.
+         * Other faults here are fatal.
+         */
         iretq
-        _ASM_EXTABLE(native_irq_return_iret, bad_iret)
 
 #ifdef CONFIG_X86_ESPFIX64
 native_irq_return_ldt:
@@ -858,25 +864,6 @@ native_irq_return_ldt:
         jmp native_irq_return_iret
 #endif
 
-        .section .fixup,"ax"
-bad_iret:
-        /*
-         * The iret traps when the %cs or %ss being restored is bogus.
-         * We've lost the original trap vector and error code.
-         * #GPF is the most likely one to get for an invalid selector.
-         * So pretend we completed the iret and took the #GPF in user mode.
-         *
-         * We are now running with the kernel GS after exception recovery.
-         * But error_entry expects us to have user GS to match the user %cs,
-         * so swap back.
-         */
-        pushq $0
-
-        SWAPGS
-        jmp general_protection
-
-        .previous
-
         /* edi: workmask, edx: work */
 retint_careful:
         CFI_RESTORE_STATE
@@ -922,37 +909,6 @@ ENTRY(retint_kernel)
         CFI_ENDPROC
 END(common_interrupt)
 
-        /*
-         * If IRET takes a fault on the espfix stack, then we
-         * end up promoting it to a doublefault.  In that case,
-         * modify the stack to make it look like we just entered
-         * the #GP handler from user space, similar to bad_iret.
-         */
-#ifdef CONFIG_X86_ESPFIX64
-        ALIGN
-__do_double_fault:
-        XCPT_FRAME 1 RDI+8
-        movq RSP(%rdi),%rax             /* Trap on the espfix stack? */
-        sarq $PGDIR_SHIFT,%rax
-        cmpl $ESPFIX_PGD_ENTRY,%eax
-        jne do_double_fault             /* No, just deliver the fault */
-        cmpl $__KERNEL_CS,CS(%rdi)
-        jne do_double_fault
-        movq RIP(%rdi),%rax
-        cmpq $native_irq_return_iret,%rax
-        jne do_double_fault             /* This shouldn't happen... */
-        movq PER_CPU_VAR(kernel_stack),%rax
-        subq $(6*8-KERNEL_STACK_OFFSET),%rax    /* Reset to original stack */
-        movq %rax,RSP(%rdi)
-        movq $0,(%rax)                  /* Missing (lost) #GP error code */
-        movq $general_protection,RIP(%rdi)
-        retq
-        CFI_ENDPROC
-END(__do_double_fault)
-#else
-# define __do_double_fault do_double_fault
-#endif
-
 /*
  * APIC interrupts.
  */
@@ -1124,7 +1080,7 @@ idtentry overflow do_overflow has_error_code=0
 idtentry bounds do_bounds has_error_code=0
 idtentry invalid_op do_invalid_op has_error_code=0
 idtentry device_not_available do_device_not_available has_error_code=0
-idtentry double_fault __do_double_fault has_error_code=1 paranoid=1
+idtentry double_fault do_double_fault has_error_code=1 paranoid=1
 idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0
 idtentry invalid_TSS do_invalid_TSS has_error_code=1
 idtentry segment_not_present do_segment_not_present has_error_code=1
@@ -1289,7 +1245,7 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
 
 idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
 idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
-idtentry stack_segment do_stack_segment has_error_code=1 paranoid=1
+idtentry stack_segment do_stack_segment has_error_code=1
 #ifdef CONFIG_XEN
 idtentry xen_debug do_debug has_error_code=0
 idtentry xen_int3 do_int3 has_error_code=0
@@ -1399,17 +1355,16 @@ error_sti:
 
 /*
  * There are two places in the kernel that can potentially fault with
- * usergs. Handle them here. The exception handlers after iret run with
- * kernel gs again, so don't set the user space flag. B stepping K8s
- * sometimes report an truncated RIP for IRET exceptions returning to
- * compat mode. Check for these here too.
+ * usergs. Handle them here.  B stepping K8s sometimes report a
+ * truncated RIP for IRET exceptions returning to compat mode. Check
+ * for these here too.
  */
 error_kernelspace:
         CFI_REL_OFFSET rcx, RCX+8
         incl %ebx
         leaq native_irq_return_iret(%rip),%rcx
         cmpq %rcx,RIP+8(%rsp)
-        je error_swapgs
+        je error_bad_iret
         movl %ecx,%eax  /* zero extend */
         cmpq %rax,RIP+8(%rsp)
         je bstep_iret
@@ -1420,7 +1375,15 @@ error_kernelspace:
 bstep_iret:
         /* Fix truncated RIP */
         movq %rcx,RIP+8(%rsp)
-        jmp error_swapgs
+        /* fall through */
+
+error_bad_iret:
+        SWAPGS
+        mov %rsp,%rdi
+        call fixup_bad_iret
+        mov %rax,%rsp
+        decl %ebx       /* Return to usergs */
+        jmp error_sti
         CFI_ENDPROC
 END(error_entry)
 
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 749b0e423419..e510618b2e91 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1484,7 +1484,7 @@ unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch)
          */
         if (work & _TIF_NOHZ) {
                 user_exit();
-                work &= ~TIF_NOHZ;
+                work &= ~_TIF_NOHZ;
         }
 
 #ifdef CONFIG_SECCOMP
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 0d0e922fafc1..de801f22128a 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -233,32 +233,40 @@ DO_ERROR(X86_TRAP_UD,     SIGILL,  "invalid opcode",		invalid_op)
 DO_ERROR(X86_TRAP_OLD_MF, SIGFPE,  "coprocessor segment overrun",coprocessor_segment_overrun)
 DO_ERROR(X86_TRAP_TS,     SIGSEGV, "invalid TSS",               invalid_TSS)
 DO_ERROR(X86_TRAP_NP,     SIGBUS,  "segment not present",       segment_not_present)
-#ifdef CONFIG_X86_32
 DO_ERROR(X86_TRAP_SS,     SIGBUS,  "stack segment",             stack_segment)
-#endif
 DO_ERROR(X86_TRAP_AC,     SIGBUS,  "alignment check",           alignment_check)
 
 #ifdef CONFIG_X86_64
 /* Runs on IST stack */
-dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code)
-{
-        enum ctx_state prev_state;
-
-        prev_state = exception_enter();
-        if (notify_die(DIE_TRAP, "stack segment", regs, error_code,
-                       X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) {
-                preempt_conditional_sti(regs);
-                do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL);
-                preempt_conditional_cli(regs);
-        }
-        exception_exit(prev_state);
-}
-
 dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 {
         static const char str[] = "double fault";
         struct task_struct *tsk = current;
 
+#ifdef CONFIG_X86_ESPFIX64
+        extern unsigned char native_irq_return_iret[];
+
+        /*
+         * If IRET takes a non-IST fault on the espfix64 stack, then we
+         * end up promoting it to a doublefault.  In that case, modify
+         * the stack to make it look like we just entered the #GP
+         * handler from user space, similar to bad_iret.
+         */
+        if (((long)regs->sp >> PGDIR_SHIFT) == ESPFIX_PGD_ENTRY &&
+                regs->cs == __KERNEL_CS &&
+                regs->ip == (unsigned long)native_irq_return_iret)
+        {
+                struct pt_regs *normal_regs = task_pt_regs(current);
+
+                /* Fake a #GP(0) from userspace. */
+                memmove(&normal_regs->ip, (void *)regs->sp, 5*8);
+                normal_regs->orig_ax = 0;  /* Missing (lost) #GP error code */
+                regs->ip = (unsigned long)general_protection;
+                regs->sp = (unsigned long)&normal_regs->orig_ax;
+                return;
+        }
+#endif
+
         exception_enter();
         /* Return not checked because double check cannot be ignored */
         notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
@@ -399,6 +407,35 @@ asmlinkage __visible struct pt_regs *sync_regs(struct pt_regs *eregs)
         return regs;
 }
 NOKPROBE_SYMBOL(sync_regs);
+
+struct bad_iret_stack {
+        void *error_entry_ret;
+        struct pt_regs regs;
+};
+
+asmlinkage __visible
+struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
+{
+        /*
+         * This is called from entry_64.S early in handling a fault
+         * caused by a bad iret to user mode.  To handle the fault
+         * correctly, we want move our stack frame to task_pt_regs
+         * and we want to pretend that the exception came from the
+         * iret target.
+         */
+        struct bad_iret_stack *new_stack =
+                container_of(task_pt_regs(current),
+                             struct bad_iret_stack, regs);
+
+        /* Copy the IRET target to the new stack. */
+        memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8);
+
+        /* Copy the remainder of the stack from the current stack. */
+        memmove(new_stack, s, offsetof(struct bad_iret_stack, regs.ip));
+
+        BUG_ON(!user_mode_vm(&new_stack->regs));
+        return new_stack;
+}
 #endif
 
 /*
@@ -778,7 +815,7 @@ void __init trap_init(void)
         set_intr_gate(X86_TRAP_OLD_MF, coprocessor_segment_overrun);
         set_intr_gate(X86_TRAP_TS, invalid_TSS);
         set_intr_gate(X86_TRAP_NP, segment_not_present);
-        set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK);
+        set_intr_gate(X86_TRAP_SS, stack_segment);
         set_intr_gate(X86_TRAP_GP, general_protection);
         set_intr_gate(X86_TRAP_SPURIOUS, spurious_interrupt_bug);
         set_intr_gate(X86_TRAP_MF, coprocessor_error);