Merge commit 3669ef9fa7d3 ("x86, tls: Interpret an all-zero struct user_desc as 'no segment'") into x86/asm

Pick up the latestest asm fixes before advancing it any further.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

14 files changed, 143 insertions, 91 deletions

diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index dcc1c536cc21..a950864a64da 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -373,6 +373,8 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
                                   unsigned long output_len,
                                   unsigned long run_size)
 {
+        unsigned char *output_orig = output;
+
         real_mode = rmode;
 
         sanitize_boot_params(real_mode);
@@ -421,7 +423,12 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
         debug_putstr("\nDecompressing Linux... ");
         decompress(input_data, input_len, NULL, NULL, output, NULL, error);
         parse_elf(output);
-        handle_relocations(output, output_len);
+        /*
+         * 32-bit always performs relocations. 64-bit relocations are only
+         * needed if kASLR has chosen a different load address.
+         */
+        if (!IS_ENABLED(CONFIG_X86_64) || output != output_orig)
+                handle_relocations(output, output_len);
         debug_putstr("done.\nBooting the kernel.\n");
         return output;
 }
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 0ab4f9fd2687..3a45668f6dc3 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -50,6 +50,7 @@ void acpi_pic_sci_set_trigger(unsigned int, u16);
 
 extern int (*__acpi_register_gsi)(struct device *dev, u32 gsi,
                                   int trigger, int polarity);
+extern void (*__acpi_unregister_gsi)(u32 gsi);
 
 static inline void disable_acpi(void)
 {
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 50d033a8947d..a94b82e8f156 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -251,7 +251,8 @@ static inline void native_load_tls(struct thread_struct *t, unsigned int cpu)
                 gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i];
 }
 
-#define _LDT_empty(info)                                \
+/* This intentionally ignores lm, since 32-bit apps don't have that field. */
+#define LDT_empty(info)                                 \
         ((info)->base_addr              == 0    &&      \
          (info)->limit                  == 0    &&      \
          (info)->contents               == 0    &&      \
@@ -261,11 +262,18 @@ static inline void native_load_tls(struct thread_struct *t, unsigned int cpu)
          (info)->seg_not_present        == 1    &&      \
          (info)->useable                == 0)
 
-#ifdef CONFIG_X86_64
-#define LDT_empty(info) (_LDT_empty(info) && ((info)->lm == 0))
-#else
-#define LDT_empty(info) (_LDT_empty(info))
-#endif
+/* Lots of programs expect an all-zero user_desc to mean "no segment at all". */
+static inline bool LDT_zero(const struct user_desc *info)
+{
+        return (info->base_addr         == 0 &&
+                info->limit             == 0 &&
+                info->contents          == 0 &&
+                info->read_exec_only    == 0 &&
+                info->seg_32bit         == 0 &&
+                info->limit_in_pages    == 0 &&
+                info->seg_not_present   == 0 &&
+                info->useable           == 0);
+}
 
 static inline void clear_LDT(void)
 {
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 40269a2bf6f9..4b75d591eb5e 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -130,7 +130,25 @@ static inline void arch_bprm_mm_init(struct mm_struct *mm,
 static inline void arch_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
                               unsigned long start, unsigned long end)
 {
-        mpx_notify_unmap(mm, vma, start, end);
+        /*
+         * mpx_notify_unmap() goes and reads a rarely-hot
+         * cacheline in the mm_struct.  That can be expensive
+         * enough to be seen in profiles.
+         *
+         * The mpx_notify_unmap() call and its contents have been
+         * observed to affect munmap() performance on hardware
+         * where MPX is not present.
+         *
+         * The unlikely() optimizes for the fast case: no MPX
+         * in the CPU, or no MPX use in the process.  Even if
+         * we get this wrong (in the unlikely event that MPX
+         * is widely enabled on some system) the overhead of
+         * MPX itself (reading bounds tables) is expected to
+         * overwhelm the overhead of getting this unlikely()
+         * consistently wrong.
+         */
+        if (unlikely(cpu_feature_enabled(X86_FEATURE_MPX)))
+                mpx_notify_unmap(mm, vma, start, end);
 }
 
 #endif /* _ASM_X86_MMU_CONTEXT_H */
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index d1626364a28a..b9e30daa0881 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -611,20 +611,20 @@ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger)
 
 int acpi_gsi_to_irq(u32 gsi, unsigned int *irqp)
 {
-        int irq;
-
-        if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) {
-                *irqp = gsi;
-        } else {
-                mutex_lock(&acpi_ioapic_lock);
-                irq = mp_map_gsi_to_irq(gsi,
-                                        IOAPIC_MAP_ALLOC | IOAPIC_MAP_CHECK);
-                mutex_unlock(&acpi_ioapic_lock);
-                if (irq < 0)
-                        return -1;
-                *irqp = irq;
+        int rc, irq, trigger, polarity;
+
+        rc = acpi_get_override_irq(gsi, &trigger, &polarity);
+        if (rc == 0) {
+                trigger = trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE;
+                polarity = polarity ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH;
+                irq = acpi_register_gsi(NULL, gsi, trigger, polarity);
+                if (irq >= 0) {
+                        *irqp = irq;
+                        return 0;
+                }
         }
-        return 0;
+
+        return -1;
 }
 EXPORT_SYMBOL_GPL(acpi_gsi_to_irq);
 
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index a450373e8e91..939155ffdece 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -107,6 +107,7 @@ static struct clocksource hyperv_cs = {
         .rating         = 400, /* use this when running on Hyperv*/
         .read           = read_hv_clock,
         .mask           = CLOCKSOURCE_MASK(64),
+        .flags          = CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
 static void __init ms_hyperv_init_platform(void)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 3c895d480cd7..073983398364 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -568,8 +568,8 @@ struct event_constraint intel_atom_pebs_event_constraints[] = {
 };
 
 struct event_constraint intel_slm_pebs_event_constraints[] = {
-        /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
-        INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+        /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
+        INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x1),
         /* Allow all events as PEBS with no flags */
         INTEL_ALL_EVENT_CONSTRAINT(0, 0x1),
         EVENT_CONSTRAINT_END
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 673f930c700f..6e434f8e5fc8 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -103,6 +103,13 @@ static struct kobj_attribute format_attr_##_var =		\
 
 #define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */
 
+#define RAPL_EVENT_ATTR_STR(_name, v, str)                              \
+static struct perf_pmu_events_attr event_attr_##v = {                   \
+        .attr           = __ATTR(_name, 0444, rapl_sysfs_show, NULL),   \
+        .id             = 0,                                            \
+        .event_str      = str,                                          \
+};
+
 struct rapl_pmu {
         spinlock_t       lock;
         int              hw_unit;  /* 1/2^hw_unit Joule */
@@ -379,23 +386,36 @@ static struct attribute_group rapl_pmu_attr_group = {
         .attrs = rapl_pmu_attrs,
 };
 
-EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01");
-EVENT_ATTR_STR(energy-pkg  ,   rapl_pkg, "event=0x02");
-EVENT_ATTR_STR(energy-ram  ,   rapl_ram, "event=0x03");
-EVENT_ATTR_STR(energy-gpu  ,   rapl_gpu, "event=0x04");
+static ssize_t rapl_sysfs_show(struct device *dev,
+                               struct device_attribute *attr,
+                               char *page)
+{
+        struct perf_pmu_events_attr *pmu_attr = \
+                container_of(attr, struct perf_pmu_events_attr, attr);
+
+        if (pmu_attr->event_str)
+                return sprintf(page, "%s", pmu_attr->event_str);
+
+        return 0;
+}
+
+RAPL_EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01");
+RAPL_EVENT_ATTR_STR(energy-pkg  ,   rapl_pkg, "event=0x02");
+RAPL_EVENT_ATTR_STR(energy-ram  ,   rapl_ram, "event=0x03");
+RAPL_EVENT_ATTR_STR(energy-gpu  ,   rapl_gpu, "event=0x04");
 
-EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules");
-EVENT_ATTR_STR(energy-pkg.unit  ,   rapl_pkg_unit, "Joules");
-EVENT_ATTR_STR(energy-ram.unit  ,   rapl_ram_unit, "Joules");
-EVENT_ATTR_STR(energy-gpu.unit  ,   rapl_gpu_unit, "Joules");
+RAPL_EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules");
+RAPL_EVENT_ATTR_STR(energy-pkg.unit  ,   rapl_pkg_unit, "Joules");
+RAPL_EVENT_ATTR_STR(energy-ram.unit  ,   rapl_ram_unit, "Joules");
+RAPL_EVENT_ATTR_STR(energy-gpu.unit  ,   rapl_gpu_unit, "Joules");
 
 /*
  * we compute in 0.23 nJ increments regardless of MSR
  */
-EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890625e-10");
-EVENT_ATTR_STR(energy-pkg.scale,     rapl_pkg_scale, "2.3283064365386962890625e-10");
-EVENT_ATTR_STR(energy-ram.scale,     rapl_ram_scale, "2.3283064365386962890625e-10");
-EVENT_ATTR_STR(energy-gpu.scale,     rapl_gpu_scale, "2.3283064365386962890625e-10");
+RAPL_EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890625e-10");
+RAPL_EVENT_ATTR_STR(energy-pkg.scale,     rapl_pkg_scale, "2.3283064365386962890625e-10");
+RAPL_EVENT_ATTR_STR(energy-ram.scale,     rapl_ram_scale, "2.3283064365386962890625e-10");
+RAPL_EVENT_ATTR_STR(energy-gpu.scale,     rapl_gpu_scale, "2.3283064365386962890625e-10");
 
 static struct attribute *rapl_events_srv_attr[] = {
         EVENT_PTR(rapl_cores),
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 6307a0f0cf17..705ef8d48e2d 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -127,7 +127,7 @@ int arch_show_interrupts(struct seq_file *p, int prec)
         seq_puts(p, "  Machine check polls\n");
 #endif
 #if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN)
-        seq_printf(p, "%*s: ", prec, "THR");
+        seq_printf(p, "%*s: ", prec, "HYP");
         for_each_online_cpu(j)
                 seq_printf(p, "%10u ", irq_stats(j)->irq_hv_callback_count);
         seq_puts(p, "  Hypervisor callback interrupts\n");
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index f7e3cd50ece0..98f654d466e5 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -1020,6 +1020,15 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
         regs->flags &= ~X86_EFLAGS_IF;
         trace_hardirqs_off();
         regs->ip = (unsigned long)(jp->entry);
+
+        /*
+         * jprobes use jprobe_return() which skips the normal return
+         * path of the function, and this messes up the accounting of the
+         * function graph tracer to get messed up.
+         *
+         * Pause function graph tracing while performing the jprobe function.
+         */
+        pause_graph_tracing();
         return 1;
 }
 NOKPROBE_SYMBOL(setjmp_pre_handler);
@@ -1048,24 +1057,25 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
         struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
         u8 *addr = (u8 *) (regs->ip - 1);
         struct jprobe *jp = container_of(p, struct jprobe, kp);
+        void *saved_sp = kcb->jprobe_saved_sp;
 
         if ((addr > (u8 *) jprobe_return) &&
             (addr < (u8 *) jprobe_return_end)) {
-                if (stack_addr(regs) != kcb->jprobe_saved_sp) {
+                if (stack_addr(regs) != saved_sp) {
                         struct pt_regs *saved_regs = &kcb->jprobe_saved_regs;
                         printk(KERN_ERR
                                "current sp %p does not match saved sp %p\n",
-                               stack_addr(regs), kcb->jprobe_saved_sp);
+                               stack_addr(regs), saved_sp);
                         printk(KERN_ERR "Saved registers for jprobe %p\n", jp);
                         show_regs(saved_regs);
                         printk(KERN_ERR "Current registers\n");
                         show_regs(regs);
                         BUG();
                 }
+                /* It's OK to start function graph tracing again */
+                unpause_graph_tracing();
                 *regs = kcb->jprobe_saved_regs;
-                memcpy((kprobe_opcode_t *)(kcb->jprobe_saved_sp),
-                       kcb->jprobes_stack,
-                       MIN_STACK_SIZE(kcb->jprobe_saved_sp));
+                memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp));
                 preempt_enable_no_resched();
                 return 1;
         }
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index 4e942f31b1a7..7fc5e843f247 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -29,7 +29,28 @@ static int get_free_idx(void)
 
 static bool tls_desc_okay(const struct user_desc *info)
 {
-        if (LDT_empty(info))
+        /*
+         * For historical reasons (i.e. no one ever documented how any
+         * of the segmentation APIs work), user programs can and do
+         * assume that a struct user_desc that's all zeros except for
+         * entry_number means "no segment at all".  This never actually
+         * worked.  In fact, up to Linux 3.19, a struct user_desc like
+         * this would create a 16-bit read-write segment with base and
+         * limit both equal to zero.
+         *
+         * That was close enough to "no segment at all" until we
+         * hardened this function to disallow 16-bit TLS segments.  Fix
+         * it up by interpreting these zeroed segments the way that they
+         * were almost certainly intended to be interpreted.
+         *
+         * The correct way to ask for "no segment at all" is to specify
+         * a user_desc that satisfies LDT_empty.  To keep everything
+         * working, we accept both.
+         *
+         * Note that there's a similar kludge in modify_ldt -- look at
+         * the distinction between modes 1 and 0x11.
+         */
+        if (LDT_empty(info) || LDT_zero(info))
                 return true;
 
         /*
@@ -71,7 +92,7 @@ static void set_tls_desc(struct task_struct *p, int idx,
         cpu = get_cpu();
 
         while (n-- > 0) {
-                if (LDT_empty(info))
+                if (LDT_empty(info) || LDT_zero(info))
                         desc->a = desc->b = 0;
                 else
                         fill_ldt(desc, info);
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index 67ebf5751222..c439ec478216 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -349,6 +349,12 @@ static __user void *task_get_bounds_dir(struct task_struct *tsk)
                 return MPX_INVALID_BOUNDS_DIR;
 
         /*
+         * 32-bit binaries on 64-bit kernels are currently
+         * unsupported.
+         */
+        if (IS_ENABLED(CONFIG_X86_64) && test_thread_flag(TIF_IA32))
+                return MPX_INVALID_BOUNDS_DIR;
+        /*
          * The bounds directory pointer is stored in a register
          * only accessible if we first do an xsave.
          */
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index edf299c8ff6c..7ac68698406c 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -234,8 +234,13 @@ void pat_init(void)
               PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC);
 
         /* Boot CPU check */
-        if (!boot_pat_state)
+        if (!boot_pat_state) {
                 rdmsrl(MSR_IA32_CR_PAT, boot_pat_state);
+                if (!boot_pat_state) {
+                        pat_disable("PAT read returns always zero, disabled.");
+                        return;
+                }
+        }
 
         wrmsrl(MSR_IA32_CR_PAT, pat);
 
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index c489ef2c1a39..9098d880c476 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -458,6 +458,7 @@ int __init pci_xen_hvm_init(void)
          * just how GSIs get registered.
          */
         __acpi_register_gsi = acpi_register_gsi_xen_hvm;
+        __acpi_unregister_gsi = NULL;
 #endif
 
 #ifdef CONFIG_PCI_MSI
@@ -471,52 +472,6 @@ int __init pci_xen_hvm_init(void)
 }
 
 #ifdef CONFIG_XEN_DOM0
-static __init void xen_setup_acpi_sci(void)
-{
-        int rc;
-        int trigger, polarity;
-        int gsi = acpi_sci_override_gsi;
-        int irq = -1;
-        int gsi_override = -1;
-
-        if (!gsi)
-                return;
-
-        rc = acpi_get_override_irq(gsi, &trigger, &polarity);
-        if (rc) {
-                printk(KERN_WARNING "xen: acpi_get_override_irq failed for acpi"
-                                " sci, rc=%d\n", rc);
-                return;
-        }
-        trigger = trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE;
-        polarity = polarity ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH;
-
-        printk(KERN_INFO "xen: sci override: global_irq=%d trigger=%d "
-                        "polarity=%d\n", gsi, trigger, polarity);
-
-        /* Before we bind the GSI to a Linux IRQ, check whether
-         * we need to override it with bus_irq (IRQ) value. Usually for
-         * IRQs below IRQ_LEGACY_IRQ this holds IRQ == GSI, as so:
-         *  ACPI: INT_SRC_OVR (bus 0 bus_irq 9 global_irq 9 low level)
-         * but there are oddballs where the IRQ != GSI:
-         *  ACPI: INT_SRC_OVR (bus 0 bus_irq 9 global_irq 20 low level)
-         * which ends up being: gsi_to_irq[9] == 20
-         * (which is what acpi_gsi_to_irq ends up calling when starting the
-         * the ACPI interpreter and keels over since IRQ 9 has not been
-         * setup as we had setup IRQ 20 for it).
-         */
-        if (acpi_gsi_to_irq(gsi, &irq) == 0) {
-                /* Use the provided value if it's valid. */
-                if (irq >= 0)
-                        gsi_override = irq;
-        }
-
-        gsi = xen_register_gsi(gsi, gsi_override, trigger, polarity);
-        printk(KERN_INFO "xen: acpi sci %d\n", gsi);
-
-        return;
-}
-
 int __init pci_xen_initial_domain(void)
 {
         int irq;
@@ -527,8 +482,8 @@ int __init pci_xen_initial_domain(void)
         x86_msi.restore_msi_irqs = xen_initdom_restore_msi_irqs;
         pci_msi_ignore_mask = 1;
 #endif
-        xen_setup_acpi_sci();
         __acpi_register_gsi = acpi_register_gsi_xen;
+        __acpi_unregister_gsi = NULL;
         /* Pre-allocate legacy irqs */
         for (irq = 0; irq < nr_legacy_irqs(); irq++) {
                 int trigger, polarity;