summaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/alpha/kernel/srmcons.c7
-rw-r--r--arch/arc/Kconfig2
-rw-r--r--arch/arc/boot/dts/axs10x_mb.dtsi8
-rw-r--r--arch/arc/include/asm/arcregs.h33
-rw-r--r--arch/arc/kernel/perf_event.c40
-rw-r--r--arch/arc/kernel/setup.c43
-rw-r--r--arch/arc/mm/tlb.c57
-rw-r--r--arch/arc/plat-axs10x/Kconfig2
-rw-r--r--arch/arc/plat-axs10x/axs10x.c7
-rw-r--r--arch/arm/Kconfig.debug4
-rw-r--r--arch/arm/include/asm/assembler.h18
-rw-r--r--arch/arm/include/asm/pgtable-3level.h1
-rw-r--r--arch/arm/include/asm/pgtable.h12
-rw-r--r--arch/arm/kernel/entry-header.S6
-rw-r--r--arch/arm/kvm/Kconfig5
-rw-r--r--arch/arm/kvm/Makefile1
-rw-r--r--arch/arm/mach-iop32x/n2100.c5
-rw-r--r--arch/arm/mach-ixp4xx/dsmg600-setup.c4
-rw-r--r--arch/arm/mach-ixp4xx/nas100d-setup.c4
-rw-r--r--arch/arm/mach-orion5x/db88f5281-setup.c4
-rw-r--r--arch/arm/mach-pxa/cm-x255.c19
-rw-r--r--arch/arm/mach-uniphier/Makefile1
-rw-r--r--arch/arm/mm/dump.c4
-rw-r--r--arch/arm/mm/init.c4
-rw-r--r--arch/arm64/include/asm/pgtable.h1
-rw-r--r--arch/arm64/kvm/Kconfig3
-rw-r--r--arch/arm64/kvm/Makefile1
-rw-r--r--arch/blackfin/kernel/nmi.c5
-rw-r--r--arch/m68k/amiga/amisound.c4
-rw-r--r--arch/m68k/mac/macboing.c8
-rw-r--r--arch/microblaze/include/asm/mmu_context_mm.h1
-rw-r--r--arch/mips/boot/dts/brcm/Makefile3
-rw-r--r--arch/mips/boot/dts/cavium-octeon/Makefile3
-rw-r--r--arch/mips/boot/dts/img/Makefile3
-rw-r--r--arch/mips/boot/dts/ingenic/Makefile3
-rw-r--r--arch/mips/boot/dts/lantiq/Makefile3
-rw-r--r--arch/mips/boot/dts/mti/Makefile3
-rw-r--r--arch/mips/boot/dts/netlogic/Makefile3
-rw-r--r--arch/mips/boot/dts/ni/Makefile3
-rw-r--r--arch/mips/boot/dts/pic32/Makefile3
-rw-r--r--arch/mips/boot/dts/qca/Makefile3
-rw-r--r--arch/mips/boot/dts/ralink/Makefile3
-rw-r--r--arch/mips/boot/dts/xilfpga/Makefile3
-rw-r--r--arch/mips/include/asm/pgtable.h2
-rw-r--r--arch/mips/lasat/picvue_proc.c4
-rw-r--r--arch/mips/mti-malta/malta-display.c4
-rw-r--r--arch/parisc/kernel/pdc_cons.c4
-rw-r--r--arch/powerpc/include/asm/book3s/64/pgtable.h1
-rw-r--r--arch/powerpc/include/asm/imc-pmu.h6
-rw-r--r--arch/powerpc/kernel/dt_cpu_ftrs.c4
-rw-r--r--arch/powerpc/kernel/tau_6xx.c4
-rw-r--r--arch/powerpc/kvm/booke.c7
-rw-r--r--arch/powerpc/lib/code-patching.c6
-rw-r--r--arch/powerpc/mm/slice.c34
-rw-r--r--arch/powerpc/oprofile/op_model_cell.c8
-rw-r--r--arch/powerpc/perf/imc-pmu.c27
-rw-r--r--arch/powerpc/platforms/cell/spufs/sched.c8
-rw-r--r--arch/powerpc/platforms/powermac/low_i2c.c6
-rw-r--r--arch/powerpc/platforms/powernv/opal-imc.c22
-rw-r--r--arch/powerpc/platforms/powernv/vas.c1
-rw-r--r--arch/s390/include/asm/pgtable.h8
-rw-r--r--arch/s390/kernel/time.c4
-rw-r--r--arch/s390/mm/cmm.c8
-rw-r--r--arch/sh/drivers/heartbeat.c6
-rw-r--r--arch/sh/drivers/pci/common.c16
-rw-r--r--arch/sh/drivers/push-switch.c9
-rw-r--r--arch/sparc/include/asm/pgtable_64.h2
-rw-r--r--arch/sparc/lib/Makefile2
-rw-r--r--arch/sparc/mm/gup.c4
-rw-r--r--arch/tile/include/asm/pgtable.h1
-rw-r--r--arch/um/Kconfig.common1
-rw-r--r--arch/x86/Kconfig12
-rw-r--r--arch/x86/boot/compressed/kaslr.c5
-rw-r--r--arch/x86/entry/entry_64.S14
-rw-r--r--arch/x86/events/intel/core.c35
-rw-r--r--arch/x86/events/intel/uncore.c4
-rw-r--r--arch/x86/events/intel/uncore.h2
-rw-r--r--arch/x86/events/intel/uncore_snbep.c10
-rw-r--r--arch/x86/include/asm/elf.h1
-rw-r--r--arch/x86/include/asm/hw_irq.h8
-rw-r--r--arch/x86/include/asm/hypertransport.h46
-rw-r--r--arch/x86/include/asm/insn-eval.h2
-rw-r--r--arch/x86/include/asm/io.h4
-rw-r--r--arch/x86/include/asm/irqdomain.h6
-rw-r--r--arch/x86/include/asm/pgtable.h8
-rw-r--r--arch/x86/include/asm/processor.h1
-rw-r--r--arch/x86/kernel/acpi/boot.c61
-rw-r--r--arch/x86/kernel/apic/Makefile1
-rw-r--r--arch/x86/kernel/apic/htirq.c198
-rw-r--r--arch/x86/kernel/apic/vector.c5
-rw-r--r--arch/x86/kernel/cpu/common.c2
-rw-r--r--arch/x86/kernel/mpparse.c6
-rw-r--r--arch/x86/kernel/smpboot.c128
-rw-r--r--arch/x86/kernel/sys_x86_64.c10
-rw-r--r--arch/x86/kernel/umip.c88
-rw-r--r--arch/x86/kvm/svm.c7
-rw-r--r--arch/x86/kvm/vmx.c161
-rw-r--r--arch/x86/lib/insn-eval.c4
-rw-r--r--arch/x86/lib/x86-opcode-map.txt2
-rw-r--r--arch/x86/mm/hugetlbpage.c11
-rw-r--r--arch/x86/mm/mmap.c62
101 files changed, 772 insertions, 691 deletions
diff --git a/arch/alpha/kernel/srmcons.c b/arch/alpha/kernel/srmcons.c
index 5da0aec8ce90..438b10c44d73 100644
--- a/arch/alpha/kernel/srmcons.c
+++ b/arch/alpha/kernel/srmcons.c
@@ -65,9 +65,9 @@ srmcons_do_receive_chars(struct tty_port *port)
}
static void
-srmcons_receive_chars(unsigned long data)
+srmcons_receive_chars(struct timer_list *t)
{
- struct srmcons_private *srmconsp = (struct srmcons_private *)data;
+ struct srmcons_private *srmconsp = from_timer(srmconsp, t, timer);
struct tty_port *port = &srmconsp->port;
unsigned long flags;
int incr = 10;
@@ -206,8 +206,7 @@ static const struct tty_operations srmcons_ops = {
static int __init
srmcons_init(void)
{
- setup_timer(&srmcons_singleton.timer, srmcons_receive_chars,
- (unsigned long)&srmcons_singleton);
+ timer_setup(&srmcons_singleton.timer, srmcons_receive_chars, 0);
if (srm_is_registered_console) {
struct tty_driver *driver;
int err;
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 5c7adf100a58..9d5fd00d9e91 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -39,7 +39,7 @@ config ARC
select OF
select OF_EARLY_FLATTREE
select OF_RESERVED_MEM
- select PERF_USE_VMALLOC
+ select PERF_USE_VMALLOC if ARC_CACHE_VIPT_ALIASING
select HAVE_DEBUG_STACKOVERFLOW
select HAVE_GENERIC_DMA_COHERENT
select HAVE_KERNEL_GZIP
diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi
index e114000a84f5..74d070cd3c13 100644
--- a/arch/arc/boot/dts/axs10x_mb.dtsi
+++ b/arch/arc/boot/dts/axs10x_mb.dtsi
@@ -16,6 +16,12 @@
ranges = <0x00000000 0x0 0xe0000000 0x10000000>;
interrupt-parent = <&mb_intc>;
+ creg_rst: reset-controller@11220 {
+ compatible = "snps,axs10x-reset";
+ #reset-cells = <1>;
+ reg = <0x11220 0x4>;
+ };
+
i2sclk: i2sclk@100a0 {
compatible = "snps,axs10x-i2s-pll-clock";
reg = <0x100a0 0x10>;
@@ -73,6 +79,8 @@
clocks = <&apbclk>;
clock-names = "stmmaceth";
max-speed = <100>;
+ resets = <&creg_rst 5>;
+ reset-names = "stmmaceth";
};
ehci@0x40000 {
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index b1c56d35f2a9..49bfbd879caa 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -11,12 +11,14 @@
/* Build Configuration Registers */
#define ARC_REG_AUX_DCCM 0x18 /* DCCM Base Addr ARCv2 */
+#define ARC_REG_ERP_CTRL 0x3F /* ARCv2 Error protection control */
#define ARC_REG_DCCM_BASE_BUILD 0x61 /* DCCM Base Addr ARCompact */
#define ARC_REG_CRC_BCR 0x62
#define ARC_REG_VECBASE_BCR 0x68
#define ARC_REG_PERIBASE_BCR 0x69
#define ARC_REG_FP_BCR 0x6B /* ARCompact: Single-Precision FPU */
#define ARC_REG_DPFP_BCR 0x6C /* ARCompact: Dbl Precision FPU */
+#define ARC_REG_ERP_BUILD 0xc7 /* ARCv2 Error protection Build: ECC/Parity */
#define ARC_REG_FP_V2_BCR 0xc8 /* ARCv2 FPU */
#define ARC_REG_SLC_BCR 0xce
#define ARC_REG_DCCM_BUILD 0x74 /* DCCM size (common) */
@@ -32,11 +34,14 @@
#define ARC_REG_D_UNCACH_BCR 0x6A
#define ARC_REG_BPU_BCR 0xc0
#define ARC_REG_ISA_CFG_BCR 0xc1
+#define ARC_REG_LPB_BUILD 0xE9 /* ARCv2 Loop Buffer Build */
#define ARC_REG_RTT_BCR 0xF2
#define ARC_REG_IRQ_BCR 0xF3
+#define ARC_REG_MICRO_ARCH_BCR 0xF9 /* ARCv2 Product revision */
#define ARC_REG_SMART_BCR 0xFF
#define ARC_REG_CLUSTER_BCR 0xcf
#define ARC_REG_AUX_ICCM 0x208 /* ICCM Base Addr (ARCv2) */
+#define ARC_REG_LPB_CTRL 0x488 /* ARCv2 Loop Buffer control */
/* Common for ARCompact and ARCv2 status register */
#define ARC_REG_STATUS32 0x0A
@@ -229,6 +234,32 @@ struct bcr_bpu_arcv2 {
#endif
};
+/* Error Protection Build: ECC/Parity */
+struct bcr_erp {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+ unsigned int pad3:5, mmu:3, pad2:4, ic:3, dc:3, pad1:6, ver:8;
+#else
+ unsigned int ver:8, pad1:6, dc:3, ic:3, pad2:4, mmu:3, pad3:5;
+#endif
+};
+
+/* Error Protection Control */
+struct ctl_erp {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+ unsigned int pad2:27, mpd:1, pad1:2, dpd:1, dpi:1;
+#else
+ unsigned int dpi:1, dpd:1, pad1:2, mpd:1, pad2:27;
+#endif
+};
+
+struct bcr_lpb {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+ unsigned int pad:16, entries:8, ver:8;
+#else
+ unsigned int ver:8, entries:8, pad:16;
+#endif
+};
+
struct bcr_generic {
#ifdef CONFIG_CPU_BIG_ENDIAN
unsigned int info:24, ver:8;
@@ -270,7 +301,7 @@ struct cpuinfo_arc {
struct cpuinfo_arc_ccm iccm, dccm;
struct {
unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, swape:1, pad1:2,
- fpu_sp:1, fpu_dp:1, dual_iss_enb:1, dual_iss_exist:1, pad2:4,
+ fpu_sp:1, fpu_dp:1, dual:1, dual_enb:1, pad2:4,
debug:1, ap:1, smart:1, rtt:1, pad3:4,
timer0:1, timer1:1, rtc:1, gfrc:1, pad4:4;
} extn;
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 2ce24e74f879..8aec462d90fb 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -336,15 +336,12 @@ static int arc_pmu_add(struct perf_event *event, int flags)
struct hw_perf_event *hwc = &event->hw;
int idx = hwc->idx;
- if (__test_and_set_bit(idx, pmu_cpu->used_mask)) {
- idx = find_first_zero_bit(pmu_cpu->used_mask,
- arc_pmu->n_counters);
- if (idx == arc_pmu->n_counters)
- return -EAGAIN;
-
- __set_bit(idx, pmu_cpu->used_mask);
- hwc->idx = idx;
- }
+ idx = ffz(pmu_cpu->used_mask[0]);
+ if (idx == arc_pmu->n_counters)
+ return -EAGAIN;
+
+ __set_bit(idx, pmu_cpu->used_mask);
+ hwc->idx = idx;
write_aux_reg(ARC_REG_PCT_INDEX, idx);
@@ -377,21 +374,22 @@ static irqreturn_t arc_pmu_intr(int irq, void *dev)
struct perf_sample_data data;
struct arc_pmu_cpu *pmu_cpu = this_cpu_ptr(&arc_pmu_cpu);
struct pt_regs *regs;
- int active_ints;
+ unsigned int active_ints;
int idx;
arc_pmu_disable(&arc_pmu->pmu);
active_ints = read_aux_reg(ARC_REG_PCT_INT_ACT);
+ if (!active_ints)
+ goto done;
regs = get_irq_regs();
- for (idx = 0; idx < arc_pmu->n_counters; idx++) {
- struct perf_event *event = pmu_cpu->act_counter[idx];
+ do {
+ struct perf_event *event;
struct hw_perf_event *hwc;
- if (!(active_ints & (1 << idx)))
- continue;
+ idx = __ffs(active_ints);
/* Reset interrupt flag by writing of 1 */
write_aux_reg(ARC_REG_PCT_INT_ACT, 1 << idx);
@@ -404,19 +402,22 @@ static irqreturn_t arc_pmu_intr(int irq, void *dev)
write_aux_reg(ARC_REG_PCT_INT_CTRL,
read_aux_reg(ARC_REG_PCT_INT_CTRL) | (1 << idx));
+ event = pmu_cpu->act_counter[idx];
hwc = &event->hw;
WARN_ON_ONCE(hwc->idx != idx);
arc_perf_event_update(event, &event->hw, event->hw.idx);
perf_sample_data_init(&data, 0, hwc->last_period);
- if (!arc_pmu_event_set_period(event))
- continue;
+ if (arc_pmu_event_set_period(event)) {
+ if (perf_event_overflow(event, &data, regs))
+ arc_pmu_stop(event, 0);
+ }
- if (perf_event_overflow(event, &data, regs))
- arc_pmu_stop(event, 0);
- }
+ active_ints &= ~(1U << idx);
+ } while (active_ints);
+done:
arc_pmu_enable(&arc_pmu->pmu);
return IRQ_HANDLED;
@@ -461,6 +462,7 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
pr_err("This core does not have performance counters!\n");
return -ENODEV;
}
+ BUILD_BUG_ON(ARC_PERF_MAX_COUNTERS > 32);
BUG_ON(pct_bcr.c > ARC_PERF_MAX_COUNTERS);
READ_BCR(ARC_REG_CC_BUILD, cc_bcr);
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index fb83844daeea..7ef7d9a8ff89 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -199,8 +199,10 @@ static void read_arc_build_cfg_regs(void)
unsigned int exec_ctrl;
READ_BCR(AUX_EXEC_CTRL, exec_ctrl);
- cpu->extn.dual_iss_exist = 1;
- cpu->extn.dual_iss_enb = exec_ctrl & 1;
+ cpu->extn.dual_enb = exec_ctrl & 1;
+
+ /* dual issue always present for this core */
+ cpu->extn.dual = 1;
}
}
@@ -253,7 +255,7 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
cpu_id, cpu->name, cpu->details,
is_isa_arcompact() ? "ARCompact" : "ARCv2",
IS_AVAIL1(cpu->isa.be, "[Big-Endian]"),
- IS_AVAIL3(cpu->extn.dual_iss_exist, cpu->extn.dual_iss_enb, " Dual-Issue"));
+ IS_AVAIL3(cpu->extn.dual, cpu->extn.dual_enb, " Dual-Issue "));
n += scnprintf(buf + n, len - n, "Timers\t\t: %s%s%s%s%s%s\nISA Extn\t: ",
IS_AVAIL1(cpu->extn.timer0, "Timer0 "),
@@ -293,11 +295,26 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
if (cpu->bpu.ver)
n += scnprintf(buf + n, len - n,
- "BPU\t\t: %s%s match, cache:%d, Predict Table:%d\n",
+ "BPU\t\t: %s%s match, cache:%d, Predict Table:%d",
IS_AVAIL1(cpu->bpu.full, "full"),
IS_AVAIL1(!cpu->bpu.full, "partial"),
cpu->bpu.num_cache, cpu->bpu.num_pred);
+ if (is_isa_arcv2()) {
+ struct bcr_lpb lpb;
+
+ READ_BCR(ARC_REG_LPB_BUILD, lpb);
+ if (lpb.ver) {
+ unsigned int ctl;
+ ctl = read_aux_reg(ARC_REG_LPB_CTRL);
+
+ n += scnprintf(buf + n, len - n, " Loop Buffer:%d %s",
+ lpb.entries,
+ IS_DISABLED_RUN(!ctl));
+ }
+ }
+
+ n += scnprintf(buf + n, len - n, "\n");
return buf;
}
@@ -326,6 +343,24 @@ static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len)
cpu->dccm.base_addr, TO_KB(cpu->dccm.sz),
cpu->iccm.base_addr, TO_KB(cpu->iccm.sz));
+ if (is_isa_arcv2()) {
+
+ /* Error Protection: ECC/Parity */
+ struct bcr_erp erp;
+ READ_BCR(ARC_REG_ERP_BUILD, erp);
+
+ if (erp.ver) {
+ struct ctl_erp ctl;
+ READ_BCR(ARC_REG_ERP_CTRL, ctl);
+
+ /* inverted bits: 0 means enabled */
+ n += scnprintf(buf + n, len - n, "Extn [ECC]\t: %s%s%s%s%s%s\n",
+ IS_AVAIL3(erp.ic, !ctl.dpi, "IC "),
+ IS_AVAIL3(erp.dc, !ctl.dpd, "DC "),
+ IS_AVAIL3(erp.mmu, !ctl.mpd, "MMU "));
+ }
+ }
+
n += scnprintf(buf + n, len - n, "OS ABI [v%d]\t: %s\n",
EF_ARC_OSABI_CURRENT >> 8,
EF_ARC_OSABI_CURRENT == EF_ARC_OSABI_V3 ?
diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c
index 8ceefbf72fb0..4097764fea23 100644
--- a/arch/arc/mm/tlb.c
+++ b/arch/arc/mm/tlb.c
@@ -762,21 +762,23 @@ void read_decode_mmu_bcr(void)
tmp = read_aux_reg(ARC_REG_MMU_BCR);
mmu->ver = (tmp >> 24);
- if (mmu->ver <= 2) {
- mmu2 = (struct bcr_mmu_1_2 *)&tmp;
- mmu->pg_sz_k = TO_KB(0x2000);
- mmu->sets = 1 << mmu2->sets;
- mmu->ways = 1 << mmu2->ways;
- mmu->u_dtlb = mmu2->u_dtlb;
- mmu->u_itlb = mmu2->u_itlb;
- } else if (mmu->ver == 3) {
- mmu3 = (struct bcr_mmu_3 *)&tmp;
- mmu->pg_sz_k = 1 << (mmu3->pg_sz - 1);
- mmu->sets = 1 << mmu3->sets;
- mmu->ways = 1 << mmu3->ways;
- mmu->u_dtlb = mmu3->u_dtlb;
- mmu->u_itlb = mmu3->u_itlb;
- mmu->sasid = mmu3->sasid;
+ if (is_isa_arcompact()) {
+ if (mmu->ver <= 2) {
+ mmu2 = (struct bcr_mmu_1_2 *)&tmp;
+ mmu->pg_sz_k = TO_KB(0x2000);
+ mmu->sets = 1 << mmu2->sets;
+ mmu->ways = 1 << mmu2->ways;
+ mmu->u_dtlb = mmu2->u_dtlb;
+ mmu->u_itlb = mmu2->u_itlb;
+ } else {
+ mmu3 = (struct bcr_mmu_3 *)&tmp;
+ mmu->pg_sz_k = 1 << (mmu3->pg_sz - 1);
+ mmu->sets = 1 << mmu3->sets;
+ mmu->ways = 1 << mmu3->ways;
+ mmu->u_dtlb = mmu3->u_dtlb;
+ mmu->u_itlb = mmu3->u_itlb;
+ mmu->sasid = mmu3->sasid;
+ }
} else {
mmu4 = (struct bcr_mmu_4 *)&tmp;
mmu->pg_sz_k = 1 << (mmu4->sz0 - 1);
@@ -818,8 +820,9 @@ int pae40_exist_but_not_enab(void)
void arc_mmu_init(void)
{
- char str[256];
struct cpuinfo_arc_mmu *mmu = &cpuinfo_arc700[smp_processor_id()].mmu;
+ char str[256];
+ int compat = 0;
pr_info("%s", arc_mmu_mumbojumbo(0, str, sizeof(str)));
@@ -834,15 +837,21 @@ void arc_mmu_init(void)
*/
BUILD_BUG_ON(!IS_ALIGNED(STACK_TOP, PMD_SIZE));
- /* For efficiency sake, kernel is compile time built for a MMU ver
- * This must match the hardware it is running on.
- * Linux built for MMU V2, if run on MMU V1 will break down because V1
- * hardware doesn't understand cmds such as WriteNI, or IVUTLB
- * On the other hand, Linux built for V1 if run on MMU V2 will do
- * un-needed workarounds to prevent memcpy thrashing.
- * Similarly MMU V3 has new features which won't work on older MMU
+ /*
+ * Ensure that MMU features assumed by kernel exist in hardware.
+ * For older ARC700 cpus, it has to be exact match, since the MMU
+ * revisions were not backwards compatible (MMUv3 TLB layout changed
+ * so even if kernel for v2 didn't use any new cmds of v3, it would
+ * still not work.
+ * For HS cpus, MMUv4 was baseline and v5 is backwards compatible
+ * (will run older software).
*/
- if (mmu->ver != CONFIG_ARC_MMU_VER) {
+ if (is_isa_arcompact() && mmu->ver == CONFIG_ARC_MMU_VER)
+ compat = 1;
+ else if (is_isa_arcv2() && mmu->ver >= CONFIG_ARC_MMU_VER)
+ compat = 1;
+
+ if (!compat) {
panic("MMU ver %d doesn't match kernel built for %d...\n",
mmu->ver, CONFIG_ARC_MMU_VER);
}
diff --git a/arch/arc/plat-axs10x/Kconfig b/arch/arc/plat-axs10x/Kconfig
index c54d1ae57fe0..4e0df7b7a248 100644
--- a/arch/arc/plat-axs10x/Kconfig
+++ b/arch/arc/plat-axs10x/Kconfig
@@ -14,6 +14,8 @@ menuconfig ARC_PLAT_AXS10X
select MIGHT_HAVE_PCI
select GENERIC_IRQ_CHIP
select GPIOLIB
+ select AXS101 if ISA_ARCOMPACT
+ select AXS103 if ISA_ARCV2
help
Support for the ARC AXS10x Software Development Platforms.
diff --git a/arch/arc/plat-axs10x/axs10x.c b/arch/arc/plat-axs10x/axs10x.c
index cf14ebc36916..f1ac6790da5f 100644
--- a/arch/arc/plat-axs10x/axs10x.c
+++ b/arch/arc/plat-axs10x/axs10x.c
@@ -111,13 +111,6 @@ static void __init axs10x_early_init(void)
axs10x_enable_gpio_intc_wire();
- /*
- * Reset ethernet IP core.
- * TODO: get rid of this quirk after axs10x reset driver (or simple
- * reset driver) will be available in upstream.
- */
- iowrite32((1 << 5), (void __iomem *) CREG_MB_SW_RESET);
-
scnprintf(mb, 32, "MainBoard v%d", mb_rev);
axs10x_print_board_ver(CREG_MB_VER, mb);
}
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 12b8c8f8ec07..17685e19aed8 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -1776,9 +1776,9 @@ config DEBUG_UART_8250_FLOW_CONTROL
default y if ARCH_EBSA110 || DEBUG_FOOTBRIDGE_COM1 || DEBUG_GEMINI || ARCH_RPC
config DEBUG_UNCOMPRESS
- bool
+ bool "Enable decompressor debugging via DEBUG_LL output"
depends on ARCH_MULTIPLATFORM || PLAT_SAMSUNG || ARM_SINGLE_ARMV7M
- default y if DEBUG_LL && !DEBUG_OMAP2PLUS_UART && \
+ depends on DEBUG_LL && !DEBUG_OMAP2PLUS_UART && \
(!DEBUG_TEGRA_UART || !ZBOOT_ROM) && \
!DEBUG_BRCMSTB_UART
help
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index ad301f107dd2..bc8d4bbd82e2 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -518,4 +518,22 @@ THUMB( orr \reg , \reg , #PSR_T_BIT )
#endif
.endm
+ .macro bug, msg, line
+#ifdef CONFIG_THUMB2_KERNEL
+1: .inst 0xde02
+#else
+1: .inst 0xe7f001f2
+#endif
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+ .pushsection .rodata.str, "aMS", %progbits, 1
+2: .asciz "\msg"
+ .popsection
+ .pushsection __bug_table, "aw"
+ .align 2
+ .word 1b, 2b
+ .hword \line
+ .popsection
+#endif
+ .endm
+
#endif /* __ASM_ASSEMBLER_H__ */
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index 2a029bceaf2f..1a7a17b2a1ba 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -221,7 +221,6 @@ static inline pte_t pte_mkspecial(pte_t pte)
}
#define __HAVE_ARCH_PTE_SPECIAL
-#define __HAVE_ARCH_PMD_WRITE
#define pmd_write(pmd) (pmd_isclear((pmd), L_PMD_SECT_RDONLY))
#define pmd_dirty(pmd) (pmd_isset((pmd), L_PMD_SECT_DIRTY))
#define pud_page(pud) pmd_page(__pmd(pud_val(pud)))
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 1c462381c225..150ece66ddf3 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -232,6 +232,18 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
#define pte_valid_user(pte) \
(pte_valid(pte) && pte_isset((pte), L_PTE_USER) && pte_young(pte))
+static inline bool pte_access_permitted(pte_t pte, bool write)
+{
+ pteval_t mask = L_PTE_PRESENT | L_PTE_USER;
+ pteval_t needed = mask;
+
+ if (write)
+ mask |= L_PTE_RDONLY;
+
+ return (pte_val(pte) & mask) == needed;
+}
+#define pte_access_permitted pte_access_permitted
+
#if __LINUX_ARM_ARCH__ < 6
static inline void __sync_icache_dcache(pte_t pteval)
{
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index d523cd8439a3..7f4d80c2db6b 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -300,6 +300,8 @@
mov r2, sp
ldr r1, [r2, #\offset + S_PSR] @ get calling cpsr
ldr lr, [r2, #\offset + S_PC]! @ get pc
+ tst r1, #0xcf
+ bne 1f
msr spsr_cxsf, r1 @ save in spsr_svc
#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K)
@ We must avoid clrex due to Cortex-A15 erratum #830321
@@ -314,6 +316,7 @@
@ after ldm {}^
add sp, sp, #\offset + PT_REGS_SIZE
movs pc, lr @ return & move spsr_svc into cpsr
+1: bug "Returning to usermode but unexpected PSR bits set?", \@
#elif defined(CONFIG_CPU_V7M)
@ V7M restore.
@ Note that we don't need to do clrex here as clearing the local
@@ -329,6 +332,8 @@
ldr r1, [sp, #\offset + S_PSR] @ get calling cpsr
ldr lr, [sp, #\offset + S_PC] @ get pc
add sp, sp, #\offset + S_SP
+ tst r1, #0xcf
+ bne 1f
msr spsr_cxsf, r1 @ save in spsr_svc
@ We must avoid clrex due to Cortex-A15 erratum #830321
@@ -341,6 +346,7 @@
.endif
add sp, sp, #PT_REGS_SIZE - S_SP
movs pc, lr @ return & move spsr_svc into cpsr
+1: bug "Returning to usermode but unexpected PSR bits set?", \@
#endif /* !CONFIG_THUMB2_KERNEL */
.endm
diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index f24628db5409..e2bd35b6780c 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -4,6 +4,7 @@
#
source "virt/kvm/Kconfig"
+source "virt/lib/Kconfig"
menuconfig VIRTUALIZATION
bool "Virtualization"
@@ -23,6 +24,8 @@ config KVM
select PREEMPT_NOTIFIERS
select ANON_INODES
select ARM_GIC
+ select ARM_GIC_V3
+ select ARM_GIC_V3_ITS
select HAVE_KVM_CPU_RELAX_INTERCEPT
select HAVE_KVM_ARCH_TLB_FLUSH_ALL
select KVM_MMIO
@@ -36,6 +39,8 @@ config KVM
select HAVE_KVM_IRQCHIP
select HAVE_KVM_IRQ_ROUTING
select HAVE_KVM_MSI
+ select IRQ_BYPASS_MANAGER
+ select HAVE_KVM_IRQ_BYPASS
depends on ARM_VIRT_EXT && ARM_LPAE && ARM_ARCH_TIMER
---help---
Support hosting virtualized guest machines.
diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile
index f550abd64a25..48de846f2246 100644
--- a/arch/arm/kvm/Makefile
+++ b/arch/arm/kvm/Makefile
@@ -32,6 +32,7 @@ obj-y += $(KVM)/arm/vgic/vgic-init.o
obj-y += $(KVM)/arm/vgic/vgic-irqfd.o
obj-y += $(KVM)/arm/vgic/vgic-v2.o
obj-y += $(KVM)/arm/vgic/vgic-v3.o
+obj-y += $(KVM)/arm/vgic/vgic-v4.o
obj-y += $(KVM)/arm/vgic/vgic-mmio.o
obj-y += $(KVM)/arm/vgic/vgic-mmio-v2.o
obj-y += $(KVM)/arm/vgic/vgic-mmio-v3.o
diff --git a/arch/arm/mach-iop32x/n2100.c b/arch/arm/mach-iop32x/n2100.c
index c1cd80ecc219..3b73813c6b04 100644
--- a/arch/arm/mach-iop32x/n2100.c
+++ b/arch/arm/mach-iop32x/n2100.c
@@ -305,7 +305,7 @@ static void n2100_restart(enum reboot_mode mode, const char *cmd)
static struct timer_list power_button_poll_timer;
-static void power_button_poll(unsigned long dummy)
+static void power_button_poll(struct timer_list *unused)
{
if (gpio_get_value(N2100_POWER_BUTTON) == 0) {
ctrl_alt_del();
@@ -336,8 +336,7 @@ static int __init n2100_request_gpios(void)
pr_err("could not set power GPIO as input\n");
}
/* Set up power button poll timer */
- init_timer(&power_button_poll_timer);
- power_button_poll_timer.function = power_button_poll;
+ timer_setup(&power_button_poll_timer, power_button_poll, 0);
power_button_poll_timer.expires = jiffies + (HZ / 10);
add_timer(&power_button_poll_timer);
return 0;
diff --git a/arch/arm/mach-ixp4xx/dsmg600-setup.c b/arch/arm/mach-ixp4xx/dsmg600-setup.c
index ac97a4599034..0f5c99941a7d 100644
--- a/arch/arm/mach-ixp4xx/dsmg600-setup.c
+++ b/arch/arm/mach-ixp4xx/dsmg600-setup.c
@@ -179,10 +179,10 @@ static int power_button_countdown;
/* Must hold the button down for at least this many counts to be processed */
#define PBUTTON_HOLDDOWN_COUNT 4 /* 2 secs */
-static void dsmg600_power_handler(unsigned long data);
+static void dsmg600_power_handler(struct timer_list *unused);
static DEFINE_TIMER(dsmg600_power_timer, dsmg600_power_handler);
-static void dsmg600_power_handler(unsigned long data)
+static void dsmg600_power_handler(struct timer_list *unused)
{
/* This routine is called twice per second to check the
* state of the power button.
diff --git a/arch/arm/mach-ixp4xx/nas100d-setup.c b/arch/arm/mach-ixp4xx/nas100d-setup.c
index 435602085408..76dfff03cb71 100644
--- a/arch/arm/mach-ixp4xx/nas100d-setup.c
+++ b/arch/arm/mach-ixp4xx/nas100d-setup.c
@@ -202,10 +202,10 @@ static int power_button_countdown;
/* Must hold the button down for at least this many counts to be processed */
#define PBUTTON_HOLDDOWN_COUNT 4 /* 2 secs */
-static void nas100d_power_handler(unsigned long data);
+static void nas100d_power_handler(struct timer_list *unused);
static DEFINE_TIMER(nas100d_power_timer, nas100d_power_handler);
-static void nas100d_power_handler(unsigned long data)
+static void nas100d_power_handler(struct timer_list *unused)
{
/* This routine is called twice per second to check the
* state of the power button.
diff --git a/arch/arm/mach-orion5x/db88f5281-setup.c b/arch/arm/mach-orion5x/db88f5281-setup.c
index 3f5863de766a..39eae10ac8de 100644
--- a/arch/arm/mach-orion5x/db88f5281-setup.c
+++ b/arch/arm/mach-orion5x/db88f5281-setup.c
@@ -172,7 +172,7 @@ static struct platform_device db88f5281_nand_flash = {
static void __iomem *db88f5281_7seg;
static struct timer_list db88f5281_timer;
-static void db88f5281_7seg_event(unsigned long data)
+static void db88f5281_7seg_event(struct timer_list *unused)
{
static int count = 0;
writel(0, db88f5281_7seg + (count << 4));
@@ -189,7 +189,7 @@ static int __init db88f5281_7seg_init(void)
printk(KERN_ERR "Failed to ioremap db88f5281_7seg\n");
return -EIO;
}
- setup_timer(&db88f5281_timer, db88f5281_7seg_event, 0);
+ timer_setup(&db88f5281_timer, db88f5281_7seg_event, 0);
mod_timer(&db88f5281_timer, jiffies + 2 * HZ);
}
diff --git a/arch/arm/mach-pxa/cm-x255.c b/arch/arm/mach-pxa/cm-x255.c
index b592f79a1742..fa8e7dd4d898 100644
--- a/arch/arm/mach-pxa/cm-x255.c
+++ b/arch/arm/mach-pxa/cm-x255.c
@@ -14,7 +14,7 @@
#include <linux/mtd/partitions.h>
#include <linux/mtd/physmap.h>
#include <linux/mtd/nand-gpio.h>
-
+#include <linux/gpio/machine.h>
#include <linux/spi/spi.h>
#include <linux/spi/pxa2xx_spi.h>
@@ -176,6 +176,17 @@ static inline void cmx255_init_nor(void) {}
#endif
#if defined(CONFIG_MTD_NAND_GPIO) || defined(CONFIG_MTD_NAND_GPIO_MODULE)
+
+static struct gpiod_lookup_table cmx255_nand_gpiod_table = {
+ .dev_id = "gpio-nand",
+ .table = {
+ GPIO_LOOKUP("gpio-pxa", GPIO_NAND_CS, "nce", GPIO_ACTIVE_HIGH),
+ GPIO_LOOKUP("gpio-pxa", GPIO_NAND_CLE, "cle", GPIO_ACTIVE_HIGH),
+ GPIO_LOOKUP("gpio-pxa", GPIO_NAND_ALE, "ale", GPIO_ACTIVE_HIGH),
+ GPIO_LOOKUP("gpio-pxa", GPIO_NAND_RB, "rdy", GPIO_ACTIVE_HIGH),
+ },
+};
+
static struct resource cmx255_nand_resource[] = {
[0] = {
.start = PXA_CS1_PHYS,
@@ -198,11 +209,6 @@ static struct mtd_partition cmx255_nand_parts[] = {
};
static struct gpio_nand_platdata cmx255_nand_platdata = {
- .gpio_nce = GPIO_NAND_CS,
- .gpio_cle = GPIO_NAND_CLE,
- .gpio_ale = GPIO_NAND_ALE,
- .gpio_rdy = GPIO_NAND_RB,
- .gpio_nwp = -1,
.parts = cmx255_nand_parts,
.num_parts = ARRAY_SIZE(cmx255_nand_parts),
.chip_delay = 25,
@@ -220,6 +226,7 @@ static struct platform_device cmx255_nand = {
static void __init cmx255_init_nand(void)
{
+ gpiod_add_lookup_table(&cmx255_nand_gpiod_table);
platform_device_register(&cmx255_nand);
}
#else
diff --git a/arch/arm/mach-uniphier/Makefile b/arch/arm/mach-uniphier/Makefile
index 6bea3d3a2dd7..e69de29bb2d1 100644
--- a/arch/arm/mach-uniphier/Makefile
+++ b/arch/arm/mach-uniphier/Makefile
@@ -1 +0,0 @@
-obj- += dummy.o
diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c
index 35ff45470dbf..fc3b44028cfb 100644
--- a/arch/arm/mm/dump.c
+++ b/arch/arm/mm/dump.c
@@ -129,8 +129,8 @@ static const struct prot_bits section_bits[] = {
.val = PMD_SECT_USER,
.set = "USR",
}, {
- .mask = L_PMD_SECT_RDONLY,
- .val = L_PMD_SECT_RDONLY,
+ .mask = L_PMD_SECT_RDONLY | PMD_SECT_AP2,
+ .val = L_PMD_SECT_RDONLY | PMD_SECT_AP2,
.set = "ro",
.clear = "RW",
#elif __LINUX_ARM_ARCH__ >= 6
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 81d4482b6861..a1f11a7ee81b 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -629,8 +629,8 @@ static struct section_perm ro_perms[] = {
.start = (unsigned long)_stext,
.end = (unsigned long)__init_begin,
#ifdef CONFIG_ARM_LPAE
- .mask = ~L_PMD_SECT_RDONLY,
- .prot = L_PMD_SECT_RDONLY,
+ .mask = ~(L_PMD_SECT_RDONLY | PMD_SECT_AP2),
+ .prot = L_PMD_SECT_RDONLY | PMD_SECT_AP2,
#else
.mask = ~(PMD_SECT_APX | PMD_SECT_AP_WRITE),
.prot = PMD_SECT_APX | PMD_SECT_AP_WRITE,
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index c9530b5b5ca8..149d05fb9421 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -345,7 +345,6 @@ static inline int pmd_protnone(pmd_t pmd)
#define pmd_thp_or_huge(pmd) (pmd_huge(pmd) || pmd_trans_huge(pmd))
-#define __HAVE_ARCH_PMD_WRITE
#define pmd_write(pmd) pte_write(pmd_pte(pmd))
#define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 13f81f971390..2257dfcc44cc 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -4,6 +4,7 @@
#
source "virt/kvm/Kconfig"
+source "virt/lib/Kconfig"
menuconfig VIRTUALIZATION
bool "Virtualization"
@@ -36,6 +37,8 @@ config KVM
select HAVE_KVM_MSI
select HAVE_KVM_IRQCHIP
select HAVE_KVM_IRQ_ROUTING
+ select IRQ_BYPASS_MANAGER
+ select HAVE_KVM_IRQ_BYPASS
---help---
Support hosting virtualized guest machines.
We don't support KVM with 16K page tables yet, due to the multiple
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 861acbbac385..87c4f7ae24de 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -27,6 +27,7 @@ kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-init.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-irqfd.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-v2.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-v3.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-v4.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio-v2.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio-v3.o
diff --git a/arch/blackfin/kernel/nmi.c b/arch/blackfin/kernel/nmi.c
index 1e714329fe8a..8a211d95821f 100644
--- a/arch/blackfin/kernel/nmi.c
+++ b/arch/blackfin/kernel/nmi.c
@@ -166,7 +166,7 @@ int check_nmi_wdt_touched(void)
return 1;
}
-static void nmi_wdt_timer(unsigned long data)
+static void nmi_wdt_timer(struct timer_list *unused)
{
if (check_nmi_wdt_touched())
nmi_wdt_keepalive();
@@ -180,8 +180,7 @@ static int __init init_nmi_wdt(void)
nmi_wdt_start();
nmi_active = true;
- init_timer(&ntimer);
- ntimer.function = nmi_wdt_timer;
+ timer_setup(&ntimer, nmi_wdt_timer, 0);
ntimer.expires = jiffies + NMI_CHECK_TIMEOUT;
add_timer(&ntimer);
diff --git a/arch/m68k/amiga/amisound.c b/arch/m68k/amiga/amisound.c
index a23f48181fd6..442bdeee6bd7 100644
--- a/arch/m68k/amiga/amisound.c
+++ b/arch/m68k/amiga/amisound.c
@@ -65,7 +65,7 @@ void __init amiga_init_sound(void)
#endif
}
-static void nosound( unsigned long ignored );
+static void nosound(struct timer_list *unused);
static DEFINE_TIMER(sound_timer, nosound);
void amiga_mksound( unsigned int hz, unsigned int ticks )
@@ -107,7 +107,7 @@ void amiga_mksound( unsigned int hz, unsigned int ticks )
}
-static void nosound( unsigned long ignored )
+static void nosound(struct timer_list *unused)
{
/* turn off DMA for audio channel 2 */
custom.dmacon = DMAF_AUD2;
diff --git a/arch/m68k/mac/macboing.c b/arch/m68k/mac/macboing.c
index d17668649641..388780797f7d 100644
--- a/arch/m68k/mac/macboing.c
+++ b/arch/m68k/mac/macboing.c
@@ -48,9 +48,9 @@ static unsigned long mac_bell_phasepersample;
* some function protos
*/
static void mac_init_asc( void );
-static void mac_nosound( unsigned long );
+static void mac_nosound(struct timer_list *);
static void mac_quadra_start_bell( unsigned int, unsigned int, unsigned int );
-static void mac_quadra_ring_bell( unsigned long );
+static void mac_quadra_ring_bell(struct timer_list *);
static void mac_av_start_bell( unsigned int, unsigned int, unsigned int );
static void ( *mac_special_bell )( unsigned int, unsigned int, unsigned int );
@@ -216,7 +216,7 @@ void mac_mksound( unsigned int freq, unsigned int length )
/*
* regular ASC: stop whining ..
*/
-static void mac_nosound( unsigned long ignored )
+static void mac_nosound(struct timer_list *unused)
{
mac_asc_regs[ ASC_ENABLE ] = 0;
}
@@ -270,7 +270,7 @@ static void mac_quadra_start_bell( unsigned int freq, unsigned int length, unsig
* already load the wave table, or at least call this one...
* This piece keeps reloading the wave table until done.
*/
-static void mac_quadra_ring_bell( unsigned long ignored )
+static void mac_quadra_ring_bell(struct timer_list *unused)
{
int i, count = mac_asc_samplespersec / HZ;
unsigned long flags;
diff --git a/arch/microblaze/include/asm/mmu_context_mm.h b/arch/microblaze/include/asm/mmu_context_mm.h
index 99472d2ca340..97559fe0b953 100644
--- a/arch/microblaze/include/asm/mmu_context_mm.h
+++ b/arch/microblaze/include/asm/mmu_context_mm.h
@@ -13,6 +13,7 @@
#include <linux/atomic.h>
#include <linux/mm_types.h>
+#include <linux/sched.h>
#include <asm/bitops.h>
#include <asm/mmu.h>
diff --git a/arch/mips/boot/dts/brcm/Makefile b/arch/mips/boot/dts/brcm/Makefile
index 09ba7e894bad..d8787c9a499e 100644
--- a/arch/mips/boot/dts/brcm/Makefile
+++ b/arch/mips/boot/dts/brcm/Makefile
@@ -35,6 +35,3 @@ dtb-$(CONFIG_DT_NONE) += \
bcm97435svmb.dtb
obj-y += $(patsubst %.dtb, %.dtb.o, $(dtb-y))
-
-# Force kbuild to make empty built-in.o if necessary
-obj- += dummy.o
diff --git a/arch/mips/boot/dts/cavium-octeon/Makefile b/arch/mips/boot/dts/cavium-octeon/Makefile
index f5d01b31df50..24a8efcd7b03 100644
--- a/arch/mips/boot/dts/cavium-octeon/Makefile
+++ b/arch/mips/boot/dts/cavium-octeon/Makefile
@@ -2,6 +2,3 @@
dtb-$(CONFIG_CAVIUM_OCTEON_SOC) += octeon_3xxx.dtb octeon_68xx.dtb
obj-y += $(patsubst %.dtb, %.dtb.o, $(dtb-y))
-
-# Force kbuild to make empty built-in.o if necessary
-obj- += dummy.o
diff --git a/arch/mips/boot/dts/img/Makefile b/arch/mips/boot/dts/img/Makefile
index 3eb2597a4d6c..441a3c16efb0 100644
--- a/arch/mips/boot/dts/img/Makefile
+++ b/arch/mips/boot/dts/img/Makefile
@@ -3,6 +3,3 @@ dtb-$(CONFIG_FIT_IMAGE_FDT_BOSTON) += boston.dtb
dtb-$(CONFIG_MACH_PISTACHIO) += pistachio_marduk.dtb
obj-$(CONFIG_MACH_PISTACHIO) += pistachio_marduk.dtb.o
-
-# Force kbuild to make empty built-in.o if necessary
-obj- += dummy.o
diff --git a/arch/mips/boot/dts/ingenic/Makefile b/arch/mips/boot/dts/ingenic/Makefile
index 035769269cbc..6a31759839b4 100644
--- a/arch/mips/boot/dts/ingenic/Makefile
+++ b/arch/mips/boot/dts/ingenic/Makefile
@@ -3,6 +3,3 @@ dtb-$(CONFIG_JZ4740_QI_LB60) += qi_lb60.dtb
dtb-$(CONFIG_JZ4780_CI20) += ci20.dtb
obj-y += $(patsubst %.dtb, %.dtb.o, $(dtb-y))
-
-# Force kbuild to make empty built-in.o if necessary
-obj- += dummy.o
diff --git a/arch/mips/boot/dts/lantiq/Makefile b/arch/mips/boot/dts/lantiq/Makefile
index 00e2e540ed3f..51ab9c1dff42 100644
--- a/arch/mips/boot/dts/lantiq/Makefile
+++ b/arch/mips/boot/dts/lantiq/Makefile
@@ -2,6 +2,3 @@
dtb-$(CONFIG_DT_EASY50712) += easy50712.dtb
obj-y += $(patsubst %.dtb, %.dtb.o, $(dtb-y))
-
-# Force kbuild to make empty built-in.o if necessary
-obj- += dummy.o
diff --git a/arch/mips/boot/dts/mti/Makefile b/arch/mips/boot/dts/mti/Makefile
index 480af498a9dd..3508720cb6d9 100644
--- a/arch/mips/boot/dts/mti/Makefile
+++ b/arch/mips/boot/dts/mti/Makefile
@@ -3,6 +3,3 @@ dtb-$(CONFIG_MIPS_MALTA) += malta.dtb
dtb-$(CONFIG_LEGACY_BOARD_SEAD3) += sead3.dtb
obj-y += $(patsubst %.dtb, %.dtb.o, $(dtb-y))
-
-# Force kbuild to make empty built-in.o if necessary
-obj- += dummy.o
diff --git a/arch/mips/boot/dts/netlogic/Makefile b/arch/mips/boot/dts/netlogic/Makefile
index 2b99450d7433..d630b27950f0 100644
--- a/arch/mips/boot/dts/netlogic/Makefile
+++ b/arch/mips/boot/dts/netlogic/Makefile
@@ -6,6 +6,3 @@ dtb-$(CONFIG_DT_XLP_GVP) += xlp_gvp.dtb
dtb-$(CONFIG_DT_XLP_RVP) += xlp_rvp.dtb
obj-y += $(patsubst %.dtb, %.dtb.o, $(dtb-y))
-
-# Force kbuild to make empty built-in.o if necessary
-obj- += dummy.o
diff --git a/arch/mips/boot/dts/ni/Makefile b/arch/mips/boot/dts/ni/Makefile
index 6cd9c606f025..9e2c9faede47 100644
--- a/arch/mips/boot/dts/ni/Makefile
+++ b/arch/mips/boot/dts/ni/Makefile
@@ -1,4 +1 @@
dtb-$(CONFIG_FIT_IMAGE_FDT_NI169445) += 169445.dtb
-
-# Force kbuild to make empty built-in.o if necessary
-obj- += dummy.o
diff --git a/arch/mips/boot/dts/pic32/Makefile b/arch/mips/boot/dts/pic32/Makefile
index a139a0fbd7b7..ba9bcef8fde9 100644
--- a/arch/mips/boot/dts/pic32/Makefile
+++ b/arch/mips/boot/dts/pic32/Makefile
@@ -5,6 +5,3 @@ dtb-$(CONFIG_DTB_PIC32_NONE) += \
pic32mzda_sk.dtb
obj-y += $(patsubst %.dtb, %.dtb.o, $(dtb-y))
-
-# Force kbuild to make empty built-in.o if necessary
-obj- += dummy.o
diff --git a/arch/mips/boot/dts/qca/Makefile b/arch/mips/boot/dts/qca/Makefile
index 639adeac90af..4451cf45b0ad 100644
--- a/arch/mips/boot/dts/qca/Makefile
+++ b/arch/mips/boot/dts/qca/Makefile
@@ -5,6 +5,3 @@ dtb-$(CONFIG_ATH79) += ar9331_dpt_module.dtb
dtb-$(CONFIG_ATH79) += ar9331_dragino_ms14.dtb
dtb-$(CONFIG_ATH79) += ar9331_omega.dtb
dtb-$(CONFIG_ATH79) += ar9331_tl_mr3020.dtb
-
-# Force kbuild to make empty built-in.o if necessary
-obj- += dummy.o
diff --git a/arch/mips/boot/dts/ralink/Makefile b/arch/mips/boot/dts/ralink/Makefile
index 323c8bcfb602..94bee5b38b53 100644
--- a/arch/mips/boot/dts/ralink/Makefile
+++ b/arch/mips/boot/dts/ralink/Makefile
@@ -7,6 +7,3 @@ dtb-$(CONFIG_DTB_OMEGA2P) += omega2p.dtb
dtb-$(CONFIG_DTB_VOCORE2) += vocore2.dtb
obj-y += $(patsubst %.dtb, %.dtb.o, $(dtb-y))
-
-# Force kbuild to make empty built-in.o if necessary
-obj- += dummy.o
diff --git a/arch/mips/boot/dts/xilfpga/Makefile b/arch/mips/boot/dts/xilfpga/Makefile
index 616322405ade..9987e0e378c5 100644
--- a/arch/mips/boot/dts/xilfpga/Makefile
+++ b/arch/mips/boot/dts/xilfpga/Makefile
@@ -2,6 +2,3 @@
dtb-$(CONFIG_FIT_IMAGE_FDT_XILFPGA) += nexys4ddr.dtb
obj-y += $(patsubst %.dtb, %.dtb.o, $(dtb-y))
-
-# Force kbuild to make empty built-in.o if necessary
-obj- += dummy.o
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 9e9e94415d08..1a508a74d48d 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -552,7 +552,7 @@ static inline pmd_t pmd_mkhuge(pmd_t pmd)
extern void set_pmd_at(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp, pmd_t pmd);
-#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write pmd_write
static inline int pmd_write(pmd_t pmd)
{
return !!(pmd_val(pmd) & _PAGE_WRITE);
diff --git a/arch/mips/lasat/picvue_proc.c b/arch/mips/lasat/picvue_proc.c
index a8103f6972cd..5d89e1ec5fcc 100644
--- a/arch/mips/lasat/picvue_proc.c
+++ b/arch/mips/lasat/picvue_proc.c
@@ -156,7 +156,7 @@ static const struct file_operations pvc_scroll_proc_fops = {
.write = pvc_scroll_proc_write,
};
-void pvc_proc_timerfunc(unsigned long data)
+void pvc_proc_timerfunc(struct timer_list *unused)
{
if (scroll_dir < 0)
pvc_move(DISPLAY|RIGHT);
@@ -197,7 +197,7 @@ static int __init pvc_proc_init(void)
if (proc_entry == NULL)
goto error;
- setup_timer(&timer, pvc_proc_timerfunc, 0UL);
+ timer_setup(&timer, pvc_proc_timerfunc, 0);
return 0;
error:
diff --git a/arch/mips/mti-malta/malta-display.c b/arch/mips/mti-malta/malta-display.c
index 063de44675ce..ee0bd50f754b 100644
--- a/arch/mips/mti-malta/malta-display.c
+++ b/arch/mips/mti-malta/malta-display.c
@@ -36,10 +36,10 @@ void mips_display_message(const char *str)
}
}
-static void scroll_display_message(unsigned long unused);
+static void scroll_display_message(struct timer_list *unused);
static DEFINE_TIMER(mips_scroll_timer, scroll_display_message);
-static void scroll_display_message(unsigned long unused)
+static void scroll_display_message(struct timer_list *unused)
{
mips_display_message(&display_string[display_count++]);
if (display_count == max_display_count)
diff --git a/arch/parisc/kernel/pdc_cons.c b/arch/parisc/kernel/pdc_cons.c
index 27a2dd616a7d..c46bf29ae412 100644
--- a/arch/parisc/kernel/pdc_cons.c
+++ b/arch/parisc/kernel/pdc_cons.c
@@ -91,7 +91,7 @@ static int pdc_console_setup(struct console *co, char *options)
#define PDC_CONS_POLL_DELAY (30 * HZ / 1000)
-static void pdc_console_poll(unsigned long unused);
+static void pdc_console_poll(struct timer_list *unused);
static DEFINE_TIMER(pdc_console_timer, pdc_console_poll);
static struct tty_port tty_port;
@@ -135,7 +135,7 @@ static const struct tty_operations pdc_console_tty_ops = {
.chars_in_buffer = pdc_console_tty_chars_in_buffer,
};
-static void pdc_console_poll(unsigned long unused)
+static void pdc_console_poll(struct timer_list *unused)
{
int data, count = 0;
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 9a677cd5997f..44697817ccc6 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -1005,7 +1005,6 @@ static inline int pmd_protnone(pmd_t pmd)
}
#endif /* CONFIG_NUMA_BALANCING */
-#define __HAVE_ARCH_PMD_WRITE
#define pmd_write(pmd) pte_write(pmd_pte(pmd))
#define __pmd_write(pmd) __pte_write(pmd_pte(pmd))
#define pmd_savedwrite(pmd) pte_savedwrite(pmd_pte(pmd))
diff --git a/arch/powerpc/include/asm/imc-pmu.h b/arch/powerpc/include/asm/imc-pmu.h
index 7f74c282710f..fad0e6ff460f 100644
--- a/arch/powerpc/include/asm/imc-pmu.h
+++ b/arch/powerpc/include/asm/imc-pmu.h
@@ -21,11 +21,6 @@
#include <asm/opal.h>
/*
- * For static allocation of some of the structures.
- */
-#define IMC_MAX_PMUS 32
-
-/*
* Compatibility macros for IMC devices
*/
#define IMC_DTB_COMPAT "ibm,opal-in-memory-counters"
@@ -125,4 +120,5 @@ enum {
extern int init_imc_pmu(struct device_node *parent,
struct imc_pmu *pmu_ptr, int pmu_id);
extern void thread_imc_disable(void);
+extern int get_max_nest_dev(void);
#endif /* __ASM_POWERPC_IMC_PMU_H */
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 602e0fde19b4..8bdc2f96c5d6 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -735,8 +735,8 @@ static __init void cpufeatures_cpu_quirks(void)
*/
if ((version & 0xffffff00) == 0x004e0100)
cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD1;
- else if ((version & 0xffffefff) == 0x004e0200)
- cur_cpu_spec->cpu_features &= ~CPU_FTR_POWER9_DD2_1;
+ else if ((version & 0xffffefff) == 0x004e0201)
+ cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
}
static void __init cpufeatures_setup_finished(void)
diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c
index e3c5f75d137c..8cdd852aedd1 100644
--- a/arch/powerpc/kernel/tau_6xx.c
+++ b/arch/powerpc/kernel/tau_6xx.c
@@ -188,7 +188,7 @@ static void tau_timeout(void * info)
local_irq_restore(flags);
}
-static void tau_timeout_smp(unsigned long unused)
+static void tau_timeout_smp(struct timer_list *unused)
{
/* schedule ourselves to be run again */
@@ -230,7 +230,7 @@ int __init TAU_init(void)
/* first, set up the window shrinking timer */
- setup_timer(&tau_timer, tau_timeout_smp, 0UL);
+ timer_setup(&tau_timer, tau_timeout_smp, 0);
tau_timer.expires = jiffies + shrink_timer;
add_timer(&tau_timer);
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 071b87ee682f..83b485810aea 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -599,9 +599,9 @@ static void arm_next_watchdog(struct kvm_vcpu *vcpu)
spin_unlock_irqrestore(&vcpu->arch.wdt_lock, flags);
}
-void kvmppc_watchdog_func(unsigned long data)
+void kvmppc_watchdog_func(struct timer_list *t)
{
- struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
+ struct kvm_vcpu *vcpu = from_timer(vcpu, t, arch.wdt_timer);
u32 tsr, new_tsr;
int final;
@@ -1412,8 +1412,7 @@ int kvmppc_subarch_vcpu_init(struct kvm_vcpu *vcpu)
{
/* setup watchdog timer once */
spin_lock_init(&vcpu->arch.wdt_lock);
- setup_timer(&vcpu->arch.wdt_timer, kvmppc_watchdog_func,
- (unsigned long)vcpu);
+ timer_setup(&vcpu->arch.wdt_timer, kvmppc_watchdog_func, 0);
/*
* Clear DBSR.MRR to avoid guest debug interrupt as
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index c9de03e0c1f1..d469224c4ada 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -21,6 +21,7 @@
#include <asm/tlbflush.h>
#include <asm/page.h>
#include <asm/code-patching.h>
+#include <asm/setup.h>
static int __patch_instruction(unsigned int *addr, unsigned int instr)
{
@@ -146,11 +147,8 @@ int patch_instruction(unsigned int *addr, unsigned int instr)
* During early early boot patch_instruction is called
* when text_poke_area is not ready, but we still need
* to allow patching. We just do the plain old patching
- * We use slab_is_available and per cpu read * via this_cpu_read
- * of text_poke_area. Per-CPU areas might not be up early
- * this can create problems with just using this_cpu_read()
*/
- if (!slab_is_available() || !this_cpu_read(text_poke_area))
+ if (!this_cpu_read(*PTRRELOC(&text_poke_area)))
return __patch_instruction(addr, instr);
local_irq_save(flags);
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index 564fff06f5c1..23ec2c5e3b78 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -122,7 +122,8 @@ static int slice_high_has_vma(struct mm_struct *mm, unsigned long slice)
return !slice_area_is_free(mm, start, end - start);
}
-static void slice_mask_for_free(struct mm_struct *mm, struct slice_mask *ret)
+static void slice_mask_for_free(struct mm_struct *mm, struct slice_mask *ret,
+ unsigned long high_limit)
{
unsigned long i;
@@ -133,15 +134,16 @@ static void slice_mask_for_free(struct mm_struct *mm, struct slice_mask *ret)
if (!slice_low_has_vma(mm, i))
ret->low_slices |= 1u << i;
- if (mm->context.slb_addr_limit <= SLICE_LOW_TOP)
+ if (high_limit <= SLICE_LOW_TOP)
return;
- for (i = 0; i < GET_HIGH_SLICE_INDEX(mm->context.slb_addr_limit); i++)
+ for (i = 0; i < GET_HIGH_SLICE_INDEX(high_limit); i++)
if (!slice_high_has_vma(mm, i))
__set_bit(i, ret->high_slices);
}
-static void slice_mask_for_size(struct mm_struct *mm, int psize, struct slice_mask *ret)
+static void slice_mask_for_size(struct mm_struct *mm, int psize, struct slice_mask *ret,
+ unsigned long high_limit)
{
unsigned char *hpsizes;
int index, mask_index;
@@ -156,8 +158,11 @@ static void slice_mask_for_size(struct mm_struct *mm, int psize, struct slice_ma
if (((lpsizes >> (i * 4)) & 0xf) == psize)
ret->low_slices |= 1u << i;
+ if (high_limit <= SLICE_LOW_TOP)
+ return;
+
hpsizes = mm->context.high_slices_psize;
- for (i = 0; i < GET_HIGH_SLICE_INDEX(mm->context.slb_addr_limit); i++) {
+ for (i = 0; i < GET_HIGH_SLICE_INDEX(high_limit); i++) {
mask_index = i & 0x1;
index = i >> 1;
if (((hpsizes[index] >> (mask_index * 4)) & 0xf) == psize)
@@ -169,6 +174,10 @@ static int slice_check_fit(struct mm_struct *mm,
struct slice_mask mask, struct slice_mask available)
{
DECLARE_BITMAP(result, SLICE_NUM_HIGH);
+ /*
+ * Make sure we just do bit compare only to the max
+ * addr limit and not the full bit map size.
+ */
unsigned long slice_count = GET_HIGH_SLICE_INDEX(mm->context.slb_addr_limit);
bitmap_and(result, mask.high_slices,
@@ -472,7 +481,7 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
/* First make up a "good" mask of slices that have the right size
* already
*/
- slice_mask_for_size(mm, psize, &good_mask);
+ slice_mask_for_size(mm, psize, &good_mask, high_limit);
slice_print_mask(" good_mask", good_mask);
/*
@@ -497,7 +506,7 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
#ifdef CONFIG_PPC_64K_PAGES
/* If we support combo pages, we can allow 64k pages in 4k slices */
if (psize == MMU_PAGE_64K) {
- slice_mask_for_size(mm, MMU_PAGE_4K, &compat_mask);
+ slice_mask_for_size(mm, MMU_PAGE_4K, &compat_mask, high_limit);
if (fixed)
slice_or_mask(&good_mask, &compat_mask);
}
@@ -530,11 +539,11 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
return newaddr;
}
}
-
- /* We don't fit in the good mask, check what other slices are
+ /*
+ * We don't fit in the good mask, check what other slices are
* empty and thus can be converted
*/
- slice_mask_for_free(mm, &potential_mask);
+ slice_mask_for_free(mm, &potential_mask, high_limit);
slice_or_mask(&potential_mask, &good_mask);
slice_print_mask(" potential", potential_mask);
@@ -744,17 +753,18 @@ int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
{
struct slice_mask mask, available;
unsigned int psize = mm->context.user_psize;
+ unsigned long high_limit = mm->context.slb_addr_limit;
if (radix_enabled())
return 0;
slice_range_to_mask(addr, len, &mask);
- slice_mask_for_size(mm, psize, &available);
+ slice_mask_for_size(mm, psize, &available, high_limit);
#ifdef CONFIG_PPC_64K_PAGES
/* We need to account for 4k slices too */
if (psize == MMU_PAGE_64K) {
struct slice_mask compat_mask;
- slice_mask_for_size(mm, MMU_PAGE_4K, &compat_mask);
+ slice_mask_for_size(mm, MMU_PAGE_4K, &compat_mask, high_limit);
slice_or_mask(&available, &compat_mask);
}
#endif
diff --git a/arch/powerpc/oprofile/op_model_cell.c b/arch/powerpc/oprofile/op_model_cell.c
index 264b6ab11978..b90a21bc2f3f 100644
--- a/arch/powerpc/oprofile/op_model_cell.c
+++ b/arch/powerpc/oprofile/op_model_cell.c
@@ -451,7 +451,7 @@ static inline void enable_ctr(u32 cpu, u32 ctr, u32 *pm07_cntrl)
* This routine will alternate loading the virtual counters for
* virtual CPUs
*/
-static void cell_virtual_cntr(unsigned long data)
+static void cell_virtual_cntr(struct timer_list *unused)
{
int i, prev_hdw_thread, next_hdw_thread;
u32 cpu;
@@ -555,7 +555,7 @@ static void cell_virtual_cntr(unsigned long data)
static void start_virt_cntrs(void)
{
- setup_timer(&timer_virt_cntr, cell_virtual_cntr, 0UL);
+ timer_setup(&timer_virt_cntr, cell_virtual_cntr, 0);
timer_virt_cntr.expires = jiffies + HZ / 10;
add_timer(&timer_virt_cntr);
}
@@ -587,7 +587,7 @@ static int cell_reg_setup_spu_cycles(struct op_counter_config *ctr,
* periodically based on kernel timer to switch which SPU is
* being monitored in a round robbin fashion.
*/
-static void spu_evnt_swap(unsigned long data)
+static void spu_evnt_swap(struct timer_list *unused)
{
int node;
int cur_phys_spu, nxt_phys_spu, cur_spu_evnt_phys_spu_indx;
@@ -677,7 +677,7 @@ static void spu_evnt_swap(unsigned long data)
static void start_spu_event_swap(void)
{
- setup_timer(&timer_spu_event_swap, spu_evnt_swap, 0UL);
+ timer_setup(&timer_spu_event_swap, spu_evnt_swap, 0);
timer_spu_event_swap.expires = jiffies + HZ / 25;
add_timer(&timer_spu_event_swap);
}
diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
index 36344117c680..0ead3cd73caa 100644
--- a/arch/powerpc/perf/imc-pmu.c
+++ b/arch/powerpc/perf/imc-pmu.c
@@ -26,7 +26,7 @@
*/
static DEFINE_MUTEX(nest_init_lock);
static DEFINE_PER_CPU(struct imc_pmu_ref *, local_nest_imc_refc);
-static struct imc_pmu *per_nest_pmu_arr[IMC_MAX_PMUS];
+static struct imc_pmu **per_nest_pmu_arr;
static cpumask_t nest_imc_cpumask;
struct imc_pmu_ref *nest_imc_refc;
static int nest_pmus;
@@ -286,13 +286,14 @@ static struct imc_pmu_ref *get_nest_pmu_ref(int cpu)
static void nest_change_cpu_context(int old_cpu, int new_cpu)
{
struct imc_pmu **pn = per_nest_pmu_arr;
- int i;
if (old_cpu < 0 || new_cpu < 0)
return;
- for (i = 0; *pn && i < IMC_MAX_PMUS; i++, pn++)
+ while (*pn) {
perf_pmu_migrate_context(&(*pn)->pmu, old_cpu, new_cpu);
+ pn++;
+ }
}
static int ppc_nest_imc_cpu_offline(unsigned int cpu)
@@ -467,7 +468,7 @@ static int nest_imc_event_init(struct perf_event *event)
* Nest HW counter memory resides in a per-chip reserve-memory (HOMER).
* Get the base memory addresss for this cpu.
*/
- chip_id = topology_physical_package_id(event->cpu);
+ chip_id = cpu_to_chip_id(event->cpu);
pcni = pmu->mem_info;
do {
if (pcni->id == chip_id) {
@@ -524,19 +525,19 @@ static int nest_imc_event_init(struct perf_event *event)
*/
static int core_imc_mem_init(int cpu, int size)
{
- int phys_id, rc = 0, core_id = (cpu / threads_per_core);
+ int nid, rc = 0, core_id = (cpu / threads_per_core);
struct imc_mem_info *mem_info;
/*
* alloc_pages_node() will allocate memory for core in the
* local node only.
*/
- phys_id = topology_physical_package_id(cpu);
+ nid = cpu_to_node(cpu);
mem_info = &core_imc_pmu->mem_info[core_id];
mem_info->id = core_id;
/* We need only vbase for core counters */
- mem_info->vbase = page_address(alloc_pages_node(phys_id,
+ mem_info->vbase = page_address(alloc_pages_node(nid,
GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE |
__GFP_NOWARN, get_order(size)));
if (!mem_info->vbase)
@@ -797,14 +798,14 @@ static int core_imc_event_init(struct perf_event *event)
static int thread_imc_mem_alloc(int cpu_id, int size)
{
u64 ldbar_value, *local_mem = per_cpu(thread_imc_mem, cpu_id);
- int phys_id = topology_physical_package_id(cpu_id);
+ int nid = cpu_to_node(cpu_id);
if (!local_mem) {
/*
* This case could happen only once at start, since we dont
* free the memory in cpu offline path.
*/
- local_mem = page_address(alloc_pages_node(phys_id,
+ local_mem = page_address(alloc_pages_node(nid,
GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE |
__GFP_NOWARN, get_order(size)));
if (!local_mem)
@@ -1194,6 +1195,7 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr)
kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs);
kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]);
kfree(pmu_ptr);
+ kfree(per_nest_pmu_arr);
return;
}
@@ -1218,6 +1220,13 @@ static int imc_mem_init(struct imc_pmu *pmu_ptr, struct device_node *parent,
return -ENOMEM;
/* Needed for hotplug/migration */
+ if (!per_nest_pmu_arr) {
+ per_nest_pmu_arr = kcalloc(get_max_nest_dev() + 1,
+ sizeof(struct imc_pmu *),
+ GFP_KERNEL);
+ if (!per_nest_pmu_arr)
+ return -ENOMEM;
+ }
per_nest_pmu_arr[pmu_index] = pmu_ptr;
break;
case IMC_DOMAIN_CORE:
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index e47761cdcb98..9033c8194eda 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -992,13 +992,13 @@ static void spu_calc_load(void)
CALC_LOAD(spu_avenrun[2], EXP_15, active_tasks);
}
-static void spusched_wake(unsigned long data)
+static void spusched_wake(struct timer_list *unused)
{
mod_timer(&spusched_timer, jiffies + SPUSCHED_TICK);
wake_up_process(spusched_task);
}
-static void spuloadavg_wake(unsigned long data)
+static void spuloadavg_wake(struct timer_list *unused)
{
mod_timer(&spuloadavg_timer, jiffies + LOAD_FREQ);
spu_calc_load();
@@ -1124,8 +1124,8 @@ int __init spu_sched_init(void)
}
spin_lock_init(&spu_prio->runq_lock);
- setup_timer(&spusched_timer, spusched_wake, 0);
- setup_timer(&spuloadavg_timer, spuloadavg_wake, 0);
+ timer_setup(&spusched_timer, spusched_wake, 0);
+ timer_setup(&spuloadavg_timer, spuloadavg_wake, 0);
spusched_task = kthread_run(spusched_thread, NULL, "spusched");
if (IS_ERR(spusched_task)) {
diff --git a/arch/powerpc/platforms/powermac/low_i2c.c b/arch/powerpc/platforms/powermac/low_i2c.c
index 39a1d4225e0f..3408f315ef48 100644
--- a/arch/powerpc/platforms/powermac/low_i2c.c
+++ b/arch/powerpc/platforms/powermac/low_i2c.c
@@ -361,9 +361,9 @@ static irqreturn_t kw_i2c_irq(int irq, void *dev_id)
return IRQ_HANDLED;
}
-static void kw_i2c_timeout(unsigned long data)
+static void kw_i2c_timeout(struct timer_list *t)
{
- struct pmac_i2c_host_kw *host = (struct pmac_i2c_host_kw *)data;
+ struct pmac_i2c_host_kw *host = from_timer(host, t, timeout_timer);
unsigned long flags;
spin_lock_irqsave(&host->lock, flags);
@@ -513,7 +513,7 @@ static struct pmac_i2c_host_kw *__init kw_i2c_host_init(struct device_node *np)
mutex_init(&host->mutex);
init_completion(&host->complete);
spin_lock_init(&host->lock);
- setup_timer(&host->timeout_timer, kw_i2c_timeout, (unsigned long)host);
+ timer_setup(&host->timeout_timer, kw_i2c_timeout, 0);
psteps = of_get_property(np, "AAPL,address-step", NULL);
steps = psteps ? (*psteps) : 0x10;
diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c
index 21f6531fae20..465ea105b771 100644
--- a/arch/powerpc/platforms/powernv/opal-imc.c
+++ b/arch/powerpc/platforms/powernv/opal-imc.c
@@ -153,6 +153,22 @@ static void disable_core_pmu_counters(void)
put_online_cpus();
}
+int get_max_nest_dev(void)
+{
+ struct device_node *node;
+ u32 pmu_units = 0, type;
+
+ for_each_compatible_node(node, NULL, IMC_DTB_UNIT_COMPAT) {
+ if (of_property_read_u32(node, "type", &type))
+ continue;
+
+ if (type == IMC_TYPE_CHIP)
+ pmu_units++;
+ }
+
+ return pmu_units;
+}
+
static int opal_imc_counters_probe(struct platform_device *pdev)
{
struct device_node *imc_dev = pdev->dev.of_node;
@@ -191,8 +207,10 @@ static int opal_imc_counters_probe(struct platform_device *pdev)
break;
}
- if (!imc_pmu_create(imc_dev, pmu_count, domain))
- pmu_count++;
+ if (!imc_pmu_create(imc_dev, pmu_count, domain)) {
+ if (domain == IMC_DOMAIN_NEST)
+ pmu_count++;
+ }
}
return 0;
diff --git a/arch/powerpc/platforms/powernv/vas.c b/arch/powerpc/platforms/powernv/vas.c
index c488621dbec3..aebbe95c9230 100644
--- a/arch/powerpc/platforms/powernv/vas.c
+++ b/arch/powerpc/platforms/powernv/vas.c
@@ -135,6 +135,7 @@ int chip_to_vas_id(int chipid)
}
return -1;
}
+EXPORT_SYMBOL(chip_to_vas_id);
static int vas_probe(struct platform_device *pdev)
{
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index d7fe9838084d..57d7bc92e0b8 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -709,7 +709,7 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
return (pmd_val(pmd) & origin_mask) >> PAGE_SHIFT;
}
-#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write pmd_write
static inline int pmd_write(pmd_t pmd)
{
return (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) != 0;
@@ -1264,6 +1264,12 @@ static inline pud_t pud_mkwrite(pud_t pud)
return pud;
}
+#define pud_write pud_write
+static inline int pud_write(pud_t pud)
+{
+ return (pud_val(pud) & _REGION3_ENTRY_WRITE) != 0;
+}
+
static inline pud_t pud_mkclean(pud_t pud)
{
if (pud_large(pud)) {
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 44c012c866d2..cf561160ea88 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -524,7 +524,7 @@ static void __init stp_reset(void)
}
}
-static void stp_timeout(unsigned long dummy)
+static void stp_timeout(struct timer_list *unused)
{
queue_work(time_sync_wq, &stp_work);
}
@@ -533,7 +533,7 @@ static int __init stp_init(void)
{
if (!test_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags))
return 0;
- setup_timer(&stp_timer, stp_timeout, 0UL);
+ timer_setup(&stp_timer, stp_timeout, 0);
time_init_wq();
if (!stp_online)
return 0;
diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c
index 3596ef91cf68..6cf024eb2085 100644
--- a/arch/s390/mm/cmm.c
+++ b/arch/s390/mm/cmm.c
@@ -57,10 +57,10 @@ static DEFINE_SPINLOCK(cmm_lock);
static struct task_struct *cmm_thread_ptr;
static DECLARE_WAIT_QUEUE_HEAD(cmm_thread_wait);
-static DEFINE_TIMER(cmm_timer, NULL);
-static void cmm_timer_fn(unsigned long);
+static void cmm_timer_fn(struct timer_list *);
static void cmm_set_timer(void);
+static DEFINE_TIMER(cmm_timer, cmm_timer_fn);
static long cmm_alloc_pages(long nr, long *counter,
struct cmm_page_array **list)
@@ -195,13 +195,11 @@ static void cmm_set_timer(void)
if (mod_timer(&cmm_timer, jiffies + cmm_timeout_seconds*HZ))
return;
}
- cmm_timer.function = cmm_timer_fn;
- cmm_timer.data = 0;
cmm_timer.expires = jiffies + cmm_timeout_seconds*HZ;
add_timer(&cmm_timer);
}
-static void cmm_timer_fn(unsigned long ignored)
+static void cmm_timer_fn(struct timer_list *unused)
{
long nr;
diff --git a/arch/sh/drivers/heartbeat.c b/arch/sh/drivers/heartbeat.c
index c6d96049a0bb..e8af2ff29bc3 100644
--- a/arch/sh/drivers/heartbeat.c
+++ b/arch/sh/drivers/heartbeat.c
@@ -59,9 +59,9 @@ static inline void heartbeat_toggle_bit(struct heartbeat_data *hd,
}
}
-static void heartbeat_timer(unsigned long data)
+static void heartbeat_timer(struct timer_list *t)
{
- struct heartbeat_data *hd = (struct heartbeat_data *)data;
+ struct heartbeat_data *hd = from_timer(hd, t, timer);
static unsigned bit = 0, up = 1;
heartbeat_toggle_bit(hd, bit, hd->flags & HEARTBEAT_INVERTED);
@@ -133,7 +133,7 @@ static int heartbeat_drv_probe(struct platform_device *pdev)
}
}
- setup_timer(&hd->timer, heartbeat_timer, (unsigned long)hd);
+ timer_setup(&hd->timer, heartbeat_timer, 0);
platform_set_drvdata(pdev, hd);
return mod_timer(&hd->timer, jiffies + 1);
diff --git a/arch/sh/drivers/pci/common.c b/arch/sh/drivers/pci/common.c
index cae707f3472d..fe163ecd0719 100644
--- a/arch/sh/drivers/pci/common.c
+++ b/arch/sh/drivers/pci/common.c
@@ -85,18 +85,18 @@ int __init pci_is_66mhz_capable(struct pci_channel *hose,
return cap66 > 0;
}
-static void pcibios_enable_err(unsigned long __data)
+static void pcibios_enable_err(struct timer_list *t)
{
- struct pci_channel *hose = (struct pci_channel *)__data;
+ struct pci_channel *hose = from_timer(hose, t, err_timer);
del_timer(&hose->err_timer);
printk(KERN_DEBUG "PCI: re-enabling error IRQ.\n");
enable_irq(hose->err_irq);
}
-static void pcibios_enable_serr(unsigned long __data)
+static void pcibios_enable_serr(struct timer_list *t)
{
- struct pci_channel *hose = (struct pci_channel *)__data;
+ struct pci_channel *hose = from_timer(hose, t, serr_timer);
del_timer(&hose->serr_timer);
printk(KERN_DEBUG "PCI: re-enabling system error IRQ.\n");
@@ -106,15 +106,11 @@ static void pcibios_enable_serr(unsigned long __data)
void pcibios_enable_timers(struct pci_channel *hose)
{
if (hose->err_irq) {
- init_timer(&hose->err_timer);
- hose->err_timer.data = (unsigned long)hose;
- hose->err_timer.function = pcibios_enable_err;
+ timer_setup(&hose->err_timer, pcibios_enable_err, 0);
}
if (hose->serr_irq) {
- init_timer(&hose->serr_timer);
- hose->serr_timer.data = (unsigned long)hose;
- hose->serr_timer.function = pcibios_enable_serr;
+ timer_setup(&hose->serr_timer, pcibios_enable_serr, 0);
}
}
diff --git a/arch/sh/drivers/push-switch.c b/arch/sh/drivers/push-switch.c
index 5bfb341cc5c4..a17181160233 100644
--- a/arch/sh/drivers/push-switch.c
+++ b/arch/sh/drivers/push-switch.c
@@ -26,9 +26,9 @@ static ssize_t switch_show(struct device *dev,
}
static DEVICE_ATTR(switch, S_IRUGO, switch_show, NULL);
-static void switch_timer(unsigned long data)
+static void switch_timer(struct timer_list *t)
{
- struct push_switch *psw = (struct push_switch *)data;
+ struct push_switch *psw = from_timer(psw, t, debounce);
schedule_work(&psw->work);
}
@@ -78,10 +78,7 @@ static int switch_drv_probe(struct platform_device *pdev)
}
INIT_WORK(&psw->work, switch_work_handler);
- init_timer(&psw->debounce);
-
- psw->debounce.function = switch_timer;
- psw->debounce.data = (unsigned long)psw;
+ timer_setup(&psw->debounce, switch_timer, 0);
/* Workqueue API brain-damage */
psw->pdev = pdev;
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 5a9e96be1665..9937c5ff94a9 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -715,7 +715,7 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
return pte_pfn(pte);
}
-#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write pmd_write
static inline unsigned long pmd_write(pmd_t pmd)
{
pte_t pte = __pte(pmd_val(pmd));
diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile
index 0f0f76b4f6cd..063556fe2cb1 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -19,7 +19,7 @@ lib-$(CONFIG_SPARC32) += muldi3.o bitext.o cmpdi2.o
lib-$(CONFIG_SPARC64) += multi3.o
lib-$(CONFIG_SPARC64) += fls.o
lib-$(CONFIG_SPARC64) += fls64.o
-obj-$(CONFIG_SPARC64) += NG4fls.o
+lib-$(CONFIG_SPARC64) += NG4fls.o
lib-$(CONFIG_SPARC64) += copy_page.o clear_page.o bzero.o
lib-$(CONFIG_SPARC64) += csum_copy.o csum_copy_from_user.o csum_copy_to_user.o
diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c
index 5335ba3c850e..33c0f8bb0f33 100644
--- a/arch/sparc/mm/gup.c
+++ b/arch/sparc/mm/gup.c
@@ -75,7 +75,7 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
if (!(pmd_val(pmd) & _PAGE_VALID))
return 0;
- if (write && !pmd_write(pmd))
+ if (!pmd_access_permitted(pmd, write))
return 0;
refs = 0;
@@ -114,7 +114,7 @@ static int gup_huge_pud(pud_t *pudp, pud_t pud, unsigned long addr,
if (!(pud_val(pud) & _PAGE_VALID))
return 0;
- if (write && !pud_write(pud))
+ if (!pud_access_permitted(pud, write))
return 0;
refs = 0;
diff --git a/arch/tile/include/asm/pgtable.h b/arch/tile/include/asm/pgtable.h
index 2a26cc4fefc2..adfa21b18488 100644
--- a/arch/tile/include/asm/pgtable.h
+++ b/arch/tile/include/asm/pgtable.h
@@ -475,7 +475,6 @@ static inline void pmd_clear(pmd_t *pmdp)
#define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd)))
#define pmd_huge_page(pmd) pte_huge(pmd_pte(pmd))
#define pmd_mkhuge(pmd) pte_pmd(pte_mkhuge(pmd_pte(pmd)))
-#define __HAVE_ARCH_PMD_WRITE
#define pfn_pmd(pfn, pgprot) pte_pmd(pfn_pte((pfn), (pgprot)))
#define pmd_pfn(pmd) pte_pfn(pmd_pte(pmd))
diff --git a/arch/um/Kconfig.common b/arch/um/Kconfig.common
index d9280482a2f8..c68add8df3ae 100644
--- a/arch/um/Kconfig.common
+++ b/arch/um/Kconfig.common
@@ -10,7 +10,6 @@ config UML
select HAVE_DEBUG_KMEMLEAK
select GENERIC_IRQ_SHOW
select GENERIC_CPU_DEVICES
- select GENERIC_IO
select GENERIC_CLOCKEVENTS
select HAVE_GCC_PLUGINS
select TTY # Needed for line.c
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index df3276d6bfe3..8eed3f94bfc7 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1804,14 +1804,20 @@ config X86_SMAP
If unsure, say Y.
config X86_INTEL_UMIP
- def_bool n
+ def_bool y
depends on CPU_SUP_INTEL
prompt "Intel User Mode Instruction Prevention" if EXPERT
---help---
The User Mode Instruction Prevention (UMIP) is a security
feature in newer Intel processors. If enabled, a general
- protection fault is issued if the instructions SGDT, SLDT,
- SIDT, SMSW and STR are executed in user mode.
+ protection fault is issued if the SGDT, SLDT, SIDT, SMSW
+ or STR instructions are executed in user mode. These instructions
+ unnecessarily expose information about the hardware state.
+
+ The vast majority of applications do not use these instructions.
+ For the very few that do, software emulation is provided in
+ specific cases in protected and virtual-8086 modes. Emulated
+ results are dummy.
config X86_INTEL_MPX
prompt "Intel MPX (Memory Protection Extensions)"
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index a63fbc25ce84..8199a6187251 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -171,7 +171,6 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size)
static void mem_avoid_memmap(char *str)
{
static int i;
- int rc;
if (i >= MAX_MEMMAP_REGIONS)
return;
@@ -219,7 +218,7 @@ static int handle_mem_memmap(void)
return 0;
tmp_cmdline = malloc(len + 1);
- if (!tmp_cmdline )
+ if (!tmp_cmdline)
error("Failed to allocate space for tmp_cmdline");
memcpy(tmp_cmdline, args, len);
@@ -363,7 +362,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
cmd_line |= boot_params->hdr.cmd_line_ptr;
/* Calculate size of cmd_line. */
ptr = (char *)(unsigned long)cmd_line;
- for (cmd_line_size = 0; ptr[cmd_line_size++]; )
+ for (cmd_line_size = 0; ptr[cmd_line_size++];)
;
mem_avoid[MEM_AVOID_CMDLINE].start = cmd_line;
mem_avoid[MEM_AVOID_CMDLINE].size = cmd_line_size;
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index a2b30ec69497..f81d50d7ceac 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -51,15 +51,19 @@ ENTRY(native_usergs_sysret64)
END(native_usergs_sysret64)
#endif /* CONFIG_PARAVIRT */
-.macro TRACE_IRQS_IRETQ
+.macro TRACE_IRQS_FLAGS flags:req
#ifdef CONFIG_TRACE_IRQFLAGS
- bt $9, EFLAGS(%rsp) /* interrupts off? */
+ bt $9, \flags /* interrupts off? */
jnc 1f
TRACE_IRQS_ON
1:
#endif
.endm
+.macro TRACE_IRQS_IRETQ
+ TRACE_IRQS_FLAGS EFLAGS(%rsp)
+.endm
+
/*
* When dynamic function tracer is enabled it will add a breakpoint
* to all locations that it is about to modify, sync CPUs, update
@@ -148,8 +152,6 @@ ENTRY(entry_SYSCALL_64)
movq %rsp, PER_CPU_VAR(rsp_scratch)
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
- TRACE_IRQS_OFF
-
/* Construct struct pt_regs on stack */
pushq $__USER_DS /* pt_regs->ss */
pushq PER_CPU_VAR(rsp_scratch) /* pt_regs->sp */
@@ -170,6 +172,8 @@ GLOBAL(entry_SYSCALL_64_after_hwframe)
sub $(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */
UNWIND_HINT_REGS extra=0
+ TRACE_IRQS_OFF
+
/*
* If we need to do entry work or if we guess we'll need to do
* exit work, go straight to the slow path.
@@ -943,11 +947,13 @@ ENTRY(native_load_gs_index)
FRAME_BEGIN
pushfq
DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
+ TRACE_IRQS_OFF
SWAPGS
.Lgs_change:
movl %edi, %gs
2: ALTERNATIVE "", "mfence", X86_BUG_SWAPGS_FENCE
SWAPGS
+ TRACE_IRQS_FLAGS (%rsp)
popfq
FRAME_END
ret
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 43445da30cea..09c26a4f139c 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3734,6 +3734,19 @@ EVENT_ATTR_STR(cycles-t, cycles_t, "event=0x3c,in_tx=1");
EVENT_ATTR_STR(cycles-ct, cycles_ct, "event=0x3c,in_tx=1,in_tx_cp=1");
static struct attribute *hsw_events_attrs[] = {
+ EVENT_PTR(mem_ld_hsw),
+ EVENT_PTR(mem_st_hsw),
+ EVENT_PTR(td_slots_issued),
+ EVENT_PTR(td_slots_retired),
+ EVENT_PTR(td_fetch_bubbles),
+ EVENT_PTR(td_total_slots),
+ EVENT_PTR(td_total_slots_scale),
+ EVENT_PTR(td_recovery_bubbles),
+ EVENT_PTR(td_recovery_bubbles_scale),
+ NULL
+};
+
+static struct attribute *hsw_tsx_events_attrs[] = {
EVENT_PTR(tx_start),
EVENT_PTR(tx_commit),
EVENT_PTR(tx_abort),
@@ -3746,18 +3759,16 @@ static struct attribute *hsw_events_attrs[] = {
EVENT_PTR(el_conflict),
EVENT_PTR(cycles_t),
EVENT_PTR(cycles_ct),
- EVENT_PTR(mem_ld_hsw),
- EVENT_PTR(mem_st_hsw),
- EVENT_PTR(td_slots_issued),
- EVENT_PTR(td_slots_retired),
- EVENT_PTR(td_fetch_bubbles),
- EVENT_PTR(td_total_slots),
- EVENT_PTR(td_total_slots_scale),
- EVENT_PTR(td_recovery_bubbles),
- EVENT_PTR(td_recovery_bubbles_scale),
NULL
};
+static __init struct attribute **get_hsw_events_attrs(void)
+{
+ return boot_cpu_has(X86_FEATURE_RTM) ?
+ merge_attr(hsw_events_attrs, hsw_tsx_events_attrs) :
+ hsw_events_attrs;
+}
+
static ssize_t freeze_on_smi_show(struct device *cdev,
struct device_attribute *attr,
char *buf)
@@ -4186,7 +4197,7 @@ __init int intel_pmu_init(void)
x86_pmu.hw_config = hsw_hw_config;
x86_pmu.get_event_constraints = hsw_get_event_constraints;
- x86_pmu.cpu_events = hsw_events_attrs;
+ x86_pmu.cpu_events = get_hsw_events_attrs();
x86_pmu.lbr_double_abort = true;
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
hsw_format_attr : nhm_format_attr;
@@ -4225,7 +4236,7 @@ __init int intel_pmu_init(void)
x86_pmu.hw_config = hsw_hw_config;
x86_pmu.get_event_constraints = hsw_get_event_constraints;
- x86_pmu.cpu_events = hsw_events_attrs;
+ x86_pmu.cpu_events = get_hsw_events_attrs();
x86_pmu.limit_period = bdw_limit_period;
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
hsw_format_attr : nhm_format_attr;
@@ -4283,7 +4294,7 @@ __init int intel_pmu_init(void)
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
hsw_format_attr : nhm_format_attr;
extra_attr = merge_attr(extra_attr, skl_format_attr);
- x86_pmu.cpu_events = hsw_events_attrs;
+ x86_pmu.cpu_events = get_hsw_events_attrs();
intel_pmu_pebs_data_source_skl(
boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X);
pr_cont("Skylake events, ");
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index d45e06346f14..7874c980d569 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -975,10 +975,10 @@ static void uncore_pci_remove(struct pci_dev *pdev)
int i, phys_id, pkg;
phys_id = uncore_pcibus_to_physid(pdev->bus);
- pkg = topology_phys_to_logical_pkg(phys_id);
box = pci_get_drvdata(pdev);
if (!box) {
+ pkg = topology_phys_to_logical_pkg(phys_id);
for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) {
if (uncore_extra_pci_dev[pkg].dev[i] == pdev) {
uncore_extra_pci_dev[pkg].dev[i] = NULL;
@@ -994,7 +994,7 @@ static void uncore_pci_remove(struct pci_dev *pdev)
return;
pci_set_drvdata(pdev, NULL);
- pmu->boxes[pkg] = NULL;
+ pmu->boxes[box->pkgid] = NULL;
if (atomic_dec_return(&pmu->activeboxes) == 0)
uncore_pmu_unregister(pmu);
uncore_box_exit(box);
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 4364191e7c6b..414dc7e7c950 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -100,7 +100,7 @@ struct intel_uncore_extra_reg {
struct intel_uncore_box {
int pci_phys_id;
- int pkgid;
+ int pkgid; /* Logical package ID */
int n_active; /* number of active events */
int n_events;
int cpu; /* cpu to collect events */
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 95cb19f4e06f..6d8044ab1060 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1057,7 +1057,7 @@ static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_eve
if (reg1->idx != EXTRA_REG_NONE) {
int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER;
- int pkg = topology_phys_to_logical_pkg(box->pci_phys_id);
+ int pkg = box->pkgid;
struct pci_dev *filter_pdev = uncore_extra_pci_dev[pkg].dev[idx];
if (filter_pdev) {
@@ -3035,11 +3035,19 @@ static struct intel_uncore_type *bdx_msr_uncores[] = {
NULL,
};
+/* Bit 7 'Use Occupancy' is not available for counter 0 on BDX */
+static struct event_constraint bdx_uncore_pcu_constraints[] = {
+ EVENT_CONSTRAINT(0x80, 0xe, 0x80),
+ EVENT_CONSTRAINT_END
+};
+
void bdx_uncore_cpu_init(void)
{
if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
uncore_msr_uncores = bdx_msr_uncores;
+
+ hswep_uncore_pcu.constraints = bdx_uncore_pcu_constraints;
}
static struct intel_uncore_type bdx_uncore_ha = {
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 3a091cea36c5..0d157d2a1e2a 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -309,6 +309,7 @@ static inline int mmap_is_ia32(void)
extern unsigned long task_size_32bit(void);
extern unsigned long task_size_64bit(int full_addr_space);
extern unsigned long get_mmap_base(int is_legacy);
+extern bool mmap_address_hint_valid(unsigned long addr, unsigned long len);
#ifdef CONFIG_X86_32
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index b80e46733909..2851077b6051 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -99,14 +99,6 @@ struct irq_alloc_info {
void *dmar_data;
};
#endif
-#ifdef CONFIG_HT_IRQ
- struct {
- int ht_pos;
- int ht_idx;
- struct pci_dev *ht_dev;
- void *ht_update;
- };
-#endif
#ifdef CONFIG_X86_UV
struct {
int uv_limit;
diff --git a/arch/x86/include/asm/hypertransport.h b/arch/x86/include/asm/hypertransport.h
deleted file mode 100644
index 5d55df352879..000000000000
--- a/arch/x86/include/asm/hypertransport.h
+++ /dev/null
@@ -1,46 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_HYPERTRANSPORT_H
-#define _ASM_X86_HYPERTRANSPORT_H
-
-/*
- * Constants for x86 Hypertransport Interrupts.
- */
-
-#define HT_IRQ_LOW_BASE 0xf8000000
-
-#define HT_IRQ_LOW_VECTOR_SHIFT 16
-#define HT_IRQ_LOW_VECTOR_MASK 0x00ff0000
-#define HT_IRQ_LOW_VECTOR(v) \
- (((v) << HT_IRQ_LOW_VECTOR_SHIFT) & HT_IRQ_LOW_VECTOR_MASK)
-
-#define HT_IRQ_LOW_DEST_ID_SHIFT 8
-#define HT_IRQ_LOW_DEST_ID_MASK 0x0000ff00
-#define HT_IRQ_LOW_DEST_ID(v) \
- (((v) << HT_IRQ_LOW_DEST_ID_SHIFT) & HT_IRQ_LOW_DEST_ID_MASK)
-
-#define HT_IRQ_LOW_DM_PHYSICAL 0x0000000
-#define HT_IRQ_LOW_DM_LOGICAL 0x0000040
-
-#define HT_IRQ_LOW_RQEOI_EDGE 0x0000000
-#define HT_IRQ_LOW_RQEOI_LEVEL 0x0000020
-
-
-#define HT_IRQ_LOW_MT_FIXED 0x0000000
-#define HT_IRQ_LOW_MT_ARBITRATED 0x0000004
-#define HT_IRQ_LOW_MT_SMI 0x0000008
-#define HT_IRQ_LOW_MT_NMI 0x000000c
-#define HT_IRQ_LOW_MT_INIT 0x0000010
-#define HT_IRQ_LOW_MT_STARTUP 0x0000014
-#define HT_IRQ_LOW_MT_EXTINT 0x0000018
-#define HT_IRQ_LOW_MT_LINT1 0x000008c
-#define HT_IRQ_LOW_MT_LINT0 0x0000098
-
-#define HT_IRQ_LOW_IRQ_MASKED 0x0000001
-
-
-#define HT_IRQ_HIGH_DEST_ID_SHIFT 0
-#define HT_IRQ_HIGH_DEST_ID_MASK 0x00ffffff
-#define HT_IRQ_HIGH_DEST_ID(v) \
- ((((v) >> 8) << HT_IRQ_HIGH_DEST_ID_SHIFT) & HT_IRQ_HIGH_DEST_ID_MASK)
-
-#endif /* _ASM_X86_HYPERTRANSPORT_H */
diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h
index e1d3b4ce8a92..2b6ccf2c49f1 100644
--- a/arch/x86/include/asm/insn-eval.h
+++ b/arch/x86/include/asm/insn-eval.h
@@ -18,6 +18,6 @@
void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs);
int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs);
unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx);
-char insn_get_code_seg_params(struct pt_regs *regs);
+int insn_get_code_seg_params(struct pt_regs *regs);
#endif /* _ASM_X86_INSN_EVAL_H */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 93ae8aee1780..95e948627fd0 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -111,6 +111,10 @@ build_mmio_write(__writeq, "q", unsigned long, "r", )
#endif
+#define ARCH_HAS_VALID_PHYS_ADDR_RANGE
+extern int valid_phys_addr_range(phys_addr_t addr, size_t size);
+extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size);
+
/**
* virt_to_phys - map virtual addresses to physical
* @address: address to remap
diff --git a/arch/x86/include/asm/irqdomain.h b/arch/x86/include/asm/irqdomain.h
index f695cc6b8e1f..139feef467f7 100644
--- a/arch/x86/include/asm/irqdomain.h
+++ b/arch/x86/include/asm/irqdomain.h
@@ -56,10 +56,4 @@ extern void arch_init_msi_domain(struct irq_domain *domain);
static inline void arch_init_msi_domain(struct irq_domain *domain) { }
#endif
-#ifdef CONFIG_HT_IRQ
-extern void arch_init_htirq_domain(struct irq_domain *domain);
-#else
-static inline void arch_init_htirq_domain(struct irq_domain *domain) { }
-#endif
-
#endif
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 09f9e1e00e3b..95e2dfd75521 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1061,7 +1061,7 @@ extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp);
-#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write pmd_write
static inline int pmd_write(pmd_t pmd)
{
return pmd_flags(pmd) & _PAGE_RW;
@@ -1088,6 +1088,12 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp);
}
+#define pud_write pud_write
+static inline int pud_write(pud_t pud)
+{
+ return pud_flags(pud) & _PAGE_RW;
+}
+
/*
* clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
*
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 2db7cf720b04..cc16fa882e3e 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -132,6 +132,7 @@ struct cpuinfo_x86 {
/* Index into per_cpu list: */
u16 cpu_index;
u32 microcode;
+ unsigned initialized : 1;
} __randomize_layout;
struct cpuid_regs {
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index ef9e02e614d0..f4c463df8b08 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -342,13 +342,12 @@ acpi_parse_lapic_nmi(struct acpi_subtable_header * header, const unsigned long e
#ifdef CONFIG_X86_IO_APIC
#define MP_ISA_BUS 0
+static int __init mp_register_ioapic_irq(u8 bus_irq, u8 polarity,
+ u8 trigger, u32 gsi);
+
static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
u32 gsi)
{
- int ioapic;
- int pin;
- struct mpc_intsrc mp_irq;
-
/*
* Check bus_irq boundary.
*/
@@ -358,14 +357,6 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
}
/*
- * Convert 'gsi' to 'ioapic.pin'.
- */
- ioapic = mp_find_ioapic(gsi);
- if (ioapic < 0)
- return;
- pin = mp_find_ioapic_pin(ioapic, gsi);
-
- /*
* TBD: This check is for faulty timer entries, where the override
* erroneously sets the trigger to level, resulting in a HUGE
* increase of timer interrupts!
@@ -373,16 +364,8 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
if ((bus_irq == 0) && (trigger == 3))
trigger = 1;
- mp_irq.type = MP_INTSRC;
- mp_irq.irqtype = mp_INT;
- mp_irq.irqflag = (trigger << 2) | polarity;
- mp_irq.srcbus = MP_ISA_BUS;
- mp_irq.srcbusirq = bus_irq; /* IRQ */
- mp_irq.dstapic = mpc_ioapic_id(ioapic); /* APIC ID */
- mp_irq.dstirq = pin; /* INTIN# */
-
- mp_save_irq(&mp_irq);
-
+ if (mp_register_ioapic_irq(bus_irq, polarity, trigger, gsi) < 0)
+ return;
/*
* Reset default identity mapping if gsi is also an legacy IRQ,
* otherwise there will be more than one entry with the same GSI
@@ -429,6 +412,34 @@ static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger,
return 0;
}
+static int __init mp_register_ioapic_irq(u8 bus_irq, u8 polarity,
+ u8 trigger, u32 gsi)
+{
+ struct mpc_intsrc mp_irq;
+ int ioapic, pin;
+
+ /* Convert 'gsi' to 'ioapic.pin'(INTIN#) */
+ ioapic = mp_find_ioapic(gsi);
+ if (ioapic < 0) {
+ pr_warn("Failed to find ioapic for gsi : %u\n", gsi);
+ return ioapic;
+ }
+
+ pin = mp_find_ioapic_pin(ioapic, gsi);
+
+ mp_irq.type = MP_INTSRC;
+ mp_irq.irqtype = mp_INT;
+ mp_irq.irqflag = (trigger << 2) | polarity;
+ mp_irq.srcbus = MP_ISA_BUS;
+ mp_irq.srcbusirq = bus_irq;
+ mp_irq.dstapic = mpc_ioapic_id(ioapic);
+ mp_irq.dstirq = pin;
+
+ mp_save_irq(&mp_irq);
+
+ return 0;
+}
+
static int __init
acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end)
{
@@ -473,7 +484,11 @@ static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger,
if (acpi_sci_flags & ACPI_MADT_POLARITY_MASK)
polarity = acpi_sci_flags & ACPI_MADT_POLARITY_MASK;
- mp_override_legacy_irq(bus_irq, polarity, trigger, gsi);
+ if (bus_irq < NR_IRQS_LEGACY)
+ mp_override_legacy_irq(bus_irq, polarity, trigger, gsi);
+ else
+ mp_register_ioapic_irq(bus_irq, polarity, trigger, gsi);
+
acpi_penalize_sci_irq(bus_irq, trigger, polarity);
/*
diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile
index a9e08924927e..a6fcaf16cdbf 100644
--- a/arch/x86/kernel/apic/Makefile
+++ b/arch/x86/kernel/apic/Makefile
@@ -12,7 +12,6 @@ obj-y += hw_nmi.o
obj-$(CONFIG_X86_IO_APIC) += io_apic.o
obj-$(CONFIG_PCI_MSI) += msi.o
-obj-$(CONFIG_HT_IRQ) += htirq.o
obj-$(CONFIG_SMP) += ipi.o
ifeq ($(CONFIG_X86_64),y)
diff --git a/arch/x86/kernel/apic/htirq.c b/arch/x86/kernel/apic/htirq.c
deleted file mode 100644
index b07075dce8b7..000000000000
--- a/arch/x86/kernel/apic/htirq.c
+++ /dev/null
@@ -1,198 +0,0 @@
-/*
- * Support Hypertransport IRQ
- *
- * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
- * Moved from arch/x86/kernel/apic/io_apic.c.
- * Jiang Liu <jiang.liu@linux.intel.com>
- * Add support of hierarchical irqdomain
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/mm.h>
-#include <linux/interrupt.h>
-#include <linux/init.h>
-#include <linux/device.h>
-#include <linux/pci.h>
-#include <linux/htirq.h>
-#include <asm/irqdomain.h>
-#include <asm/hw_irq.h>
-#include <asm/apic.h>
-#include <asm/hypertransport.h>
-
-static struct irq_domain *htirq_domain;
-
-/*
- * Hypertransport interrupt support
- */
-static int
-ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
-{
- struct irq_data *parent = data->parent_data;
- int ret;
-
- ret = parent->chip->irq_set_affinity(parent, mask, force);
- if (ret >= 0) {
- struct ht_irq_msg msg;
- struct irq_cfg *cfg = irqd_cfg(data);
-
- fetch_ht_irq_msg(data->irq, &msg);
- msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK |
- HT_IRQ_LOW_DEST_ID_MASK);
- msg.address_lo |= HT_IRQ_LOW_VECTOR(cfg->vector) |
- HT_IRQ_LOW_DEST_ID(cfg->dest_apicid);
- msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK);
- msg.address_hi |= HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid);
- write_ht_irq_msg(data->irq, &msg);
- }
-
- return ret;
-}
-
-static struct irq_chip ht_irq_chip = {
- .name = "PCI-HT",
- .irq_mask = mask_ht_irq,
- .irq_unmask = unmask_ht_irq,
- .irq_ack = irq_chip_ack_parent,
- .irq_set_affinity = ht_set_affinity,
- .irq_retrigger = irq_chip_retrigger_hierarchy,
- .flags = IRQCHIP_SKIP_SET_WAKE,
-};
-
-static int htirq_domain_alloc(struct irq_domain *domain, unsigned int virq,
- unsigned int nr_irqs, void *arg)
-{
- struct ht_irq_cfg *ht_cfg;
- struct irq_alloc_info *info = arg;
- struct pci_dev *dev;
- irq_hw_number_t hwirq;
- int ret;
-
- if (nr_irqs > 1 || !info)
- return -EINVAL;
-
- dev = info->ht_dev;
- hwirq = (info->ht_idx & 0xFF) |
- PCI_DEVID(dev->bus->number, dev->devfn) << 8 |
- (pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 24;
- if (irq_find_mapping(domain, hwirq) > 0)
- return -EEXIST;
-
- ht_cfg = kmalloc(sizeof(*ht_cfg), GFP_KERNEL);
- if (!ht_cfg)
- return -ENOMEM;
-
- ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info);
- if (ret < 0) {
- kfree(ht_cfg);
- return ret;
- }
-
- /* Initialize msg to a value that will never match the first write. */
- ht_cfg->msg.address_lo = 0xffffffff;
- ht_cfg->msg.address_hi = 0xffffffff;
- ht_cfg->dev = info->ht_dev;
- ht_cfg->update = info->ht_update;
- ht_cfg->pos = info->ht_pos;
- ht_cfg->idx = 0x10 + (info->ht_idx * 2);
- irq_domain_set_info(domain, virq, hwirq, &ht_irq_chip, ht_cfg,
- handle_edge_irq, ht_cfg, "edge");
-
- return 0;
-}
-
-static void htirq_domain_free(struct irq_domain *domain, unsigned int virq,
- unsigned int nr_irqs)
-{
- struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq);
-
- BUG_ON(nr_irqs != 1);
- kfree(irq_data->chip_data);
- irq_domain_free_irqs_top(domain, virq, nr_irqs);
-}
-
-static int htirq_domain_activate(struct irq_domain *domain,
- struct irq_data *irq_data, bool early)
-{
- struct ht_irq_msg msg;
- struct irq_cfg *cfg = irqd_cfg(irq_data);
-
- msg.address_hi = HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid);
- msg.address_lo =
- HT_IRQ_LOW_BASE |
- HT_IRQ_LOW_DEST_ID(cfg->dest_apicid) |
- HT_IRQ_LOW_VECTOR(cfg->vector) |
- ((apic->irq_dest_mode == 0) ?
- HT_IRQ_LOW_DM_PHYSICAL :
- HT_IRQ_LOW_DM_LOGICAL) |
- HT_IRQ_LOW_RQEOI_EDGE |
- ((apic->irq_delivery_mode != dest_LowestPrio) ?
- HT_IRQ_LOW_MT_FIXED :
- HT_IRQ_LOW_MT_ARBITRATED) |
- HT_IRQ_LOW_IRQ_MASKED;
- write_ht_irq_msg(irq_data->irq, &msg);
- return 0;
-}
-
-static void htirq_domain_deactivate(struct irq_domain *domain,
- struct irq_data *irq_data)
-{
- struct ht_irq_msg msg;
-
- memset(&msg, 0, sizeof(msg));
- write_ht_irq_msg(irq_data->irq, &msg);
-}
-
-static const struct irq_domain_ops htirq_domain_ops = {
- .alloc = htirq_domain_alloc,
- .free = htirq_domain_free,
- .activate = htirq_domain_activate,
- .deactivate = htirq_domain_deactivate,
-};
-
-void __init arch_init_htirq_domain(struct irq_domain *parent)
-{
- struct fwnode_handle *fn;
-
- if (disable_apic)
- return;
-
- fn = irq_domain_alloc_named_fwnode("PCI-HT");
- if (!fn)
- goto warn;
-
- htirq_domain = irq_domain_create_tree(fn, &htirq_domain_ops, NULL);
- irq_domain_free_fwnode(fn);
- if (!htirq_domain)
- goto warn;
-
- htirq_domain->parent = parent;
- return;
-
-warn:
- pr_warn("Failed to initialize irqdomain for HTIRQ.\n");
-}
-
-int arch_setup_ht_irq(int idx, int pos, struct pci_dev *dev,
- ht_irq_update_t *update)
-{
- struct irq_alloc_info info;
-
- if (!htirq_domain)
- return -ENOSYS;
-
- init_irq_alloc_info(&info, NULL);
- info.ht_idx = idx;
- info.ht_pos = pos;
- info.ht_dev = dev;
- info.ht_update = update;
-
- return irq_domain_alloc_irqs(htirq_domain, 1, dev_to_node(&dev->dev),
- &info);
-}
-
-void arch_teardown_ht_irq(unsigned int irq)
-{
- irq_domain_free_irqs(irq, 1);
-}
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 05c85e693a5d..6a823a25eaff 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -1,5 +1,5 @@
/*
- * Local APIC related interfaces to support IOAPIC, MSI, HT_IRQ etc.
+ * Local APIC related interfaces to support IOAPIC, MSI, etc.
*
* Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
* Moved from arch/x86/kernel/apic/io_apic.c.
@@ -601,7 +601,7 @@ int __init arch_probe_nr_irqs(void)
nr_irqs = NR_VECTORS * nr_cpu_ids;
nr = (gsi_top + nr_legacy_irqs()) + 8 * nr_cpu_ids;
-#if defined(CONFIG_PCI_MSI) || defined(CONFIG_HT_IRQ)
+#if defined(CONFIG_PCI_MSI)
/*
* for MSI and HT dyn irq
*/
@@ -663,7 +663,6 @@ int __init arch_early_irq_init(void)
irq_set_default_host(x86_vector_domain);
arch_init_msi_domain(x86_vector_domain);
- arch_init_htirq_domain(x86_vector_domain);
BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL));
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 13ae9e5eec2f..fa998ca8aa5a 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -341,6 +341,8 @@ static __always_inline void setup_umip(struct cpuinfo_x86 *c)
cr4_set_bits(X86_CR4_UMIP);
+ pr_info("x86/cpu: Activated the Intel User Mode Instruction Prevention (UMIP) CPU feature\n");
+
return;
out:
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 410c5dadcee3..3a4b12809ab5 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -431,6 +431,7 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type)
}
static unsigned long mpf_base;
+static bool mpf_found;
static unsigned long __init get_mpc_size(unsigned long physptr)
{
@@ -504,7 +505,7 @@ void __init default_get_smp_config(unsigned int early)
if (!smp_found_config)
return;
- if (!mpf_base)
+ if (!mpf_found)
return;
if (acpi_lapic && early)
@@ -593,6 +594,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length)
smp_found_config = 1;
#endif
mpf_base = base;
+ mpf_found = true;
pr_info("found SMP MP-table at [mem %#010lx-%#010lx] mapped at [%p]\n",
base, base + sizeof(*mpf) - 1, mpf);
@@ -858,7 +860,7 @@ static int __init update_mp_table(void)
if (!enable_update_mptable)
return 0;
- if (!mpf_base)
+ if (!mpf_found)
return 0;
mpf = early_memremap(mpf_base, sizeof(*mpf));
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 5f59e6bee123..3d01df7d7cf6 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -101,9 +101,6 @@ DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
EXPORT_PER_CPU_SYMBOL(cpu_info);
/* Logical package management. We might want to allocate that dynamically */
-static int *physical_to_logical_pkg __read_mostly;
-static unsigned long *physical_package_map __read_mostly;;
-static unsigned int max_physical_pkg_id __read_mostly;
unsigned int __max_logical_packages __read_mostly;
EXPORT_SYMBOL(__max_logical_packages);
static unsigned int logical_packages __read_mostly;
@@ -281,108 +278,48 @@ static void notrace start_secondary(void *unused)
}
/**
+ * topology_phys_to_logical_pkg - Map a physical package id to a logical
+ *
+ * Returns logical package id or -1 if not found
+ */
+int topology_phys_to_logical_pkg(unsigned int phys_pkg)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+ if (c->initialized && c->phys_proc_id == phys_pkg)
+ return c->logical_proc_id;
+ }
+ return -1;
+}
+EXPORT_SYMBOL(topology_phys_to_logical_pkg);
+
+/**
* topology_update_package_map - Update the physical to logical package map
* @pkg: The physical package id as retrieved via CPUID
* @cpu: The cpu for which this is updated
*/
int topology_update_package_map(unsigned int pkg, unsigned int cpu)
{
- unsigned int new;
+ int new;
- /* Called from early boot ? */
- if (!physical_package_map)
- return 0;
-
- if (pkg >= max_physical_pkg_id)
- return -EINVAL;
-
- /* Set the logical package id */
- if (test_and_set_bit(pkg, physical_package_map))
+ /* Already available somewhere? */
+ new = topology_phys_to_logical_pkg(pkg);
+ if (new >= 0)
goto found;
- if (logical_packages >= __max_logical_packages) {
- pr_warn("Package %u of CPU %u exceeds BIOS package data %u.\n",
- logical_packages, cpu, __max_logical_packages);
- return -ENOSPC;
- }
-
new = logical_packages++;
if (new != pkg) {
pr_info("CPU %u Converting physical %u to logical package %u\n",
cpu, pkg, new);
}
- physical_to_logical_pkg[pkg] = new;
-
found:
- cpu_data(cpu).logical_proc_id = physical_to_logical_pkg[pkg];
+ cpu_data(cpu).logical_proc_id = new;
return 0;
}
-/**
- * topology_phys_to_logical_pkg - Map a physical package id to a logical
- *
- * Returns logical package id or -1 if not found
- */
-int topology_phys_to_logical_pkg(unsigned int phys_pkg)
-{
- if (phys_pkg >= max_physical_pkg_id)
- return -1;
- return physical_to_logical_pkg[phys_pkg];
-}
-EXPORT_SYMBOL(topology_phys_to_logical_pkg);
-
-static void __init smp_init_package_map(struct cpuinfo_x86 *c, unsigned int cpu)
-{
- unsigned int ncpus;
- size_t size;
-
- /*
- * Today neither Intel nor AMD support heterogenous systems. That
- * might change in the future....
- *
- * While ideally we'd want '* smp_num_siblings' in the below @ncpus
- * computation, this won't actually work since some Intel BIOSes
- * report inconsistent HT data when they disable HT.
- *
- * In particular, they reduce the APIC-IDs to only include the cores,
- * but leave the CPUID topology to say there are (2) siblings.
- * This means we don't know how many threads there will be until
- * after the APIC enumeration.
- *
- * By not including this we'll sometimes over-estimate the number of
- * logical packages by the amount of !present siblings, but this is
- * still better than MAX_LOCAL_APIC.
- *
- * We use total_cpus not nr_cpu_ids because nr_cpu_ids can be limited
- * on the command line leading to a similar issue as the HT disable
- * problem because the hyperthreads are usually enumerated after the
- * primary cores.
- */
- ncpus = boot_cpu_data.x86_max_cores;
- if (!ncpus) {
- pr_warn("x86_max_cores == zero !?!?");
- ncpus = 1;
- }
-
- __max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus);
- logical_packages = 0;
-
- /*
- * Possibly larger than what we need as the number of apic ids per
- * package can be smaller than the actual used apic ids.
- */
- max_physical_pkg_id = DIV_ROUND_UP(MAX_LOCAL_APIC, ncpus);
- size = max_physical_pkg_id * sizeof(unsigned int);
- physical_to_logical_pkg = kmalloc(size, GFP_KERNEL);
- memset(physical_to_logical_pkg, 0xff, size);
- size = BITS_TO_LONGS(max_physical_pkg_id) * sizeof(unsigned long);
- physical_package_map = kzalloc(size, GFP_KERNEL);
-
- pr_info("Max logical packages: %u\n", __max_logical_packages);
-
- topology_update_package_map(c->phys_proc_id, cpu);
-}
-
void __init smp_store_boot_cpu_info(void)
{
int id = 0; /* CPU 0 */
@@ -390,7 +327,8 @@ void __init smp_store_boot_cpu_info(void)
*c = boot_cpu_data;
c->cpu_index = id;
- smp_init_package_map(c, id);
+ topology_update_package_map(c->phys_proc_id, id);
+ c->initialized = true;
}
/*
@@ -401,13 +339,16 @@ void smp_store_cpu_info(int id)
{
struct cpuinfo_x86 *c = &cpu_data(id);
- *c = boot_cpu_data;
+ /* Copy boot_cpu_data only on the first bringup */
+ if (!c->initialized)
+ *c = boot_cpu_data;
c->cpu_index = id;
/*
* During boot time, CPU0 has this setup already. Save the info when
* bringing up AP or offlined CPU0.
*/
identify_secondary_cpu(c);
+ c->initialized = true;
}
static bool
@@ -1356,7 +1297,16 @@ void __init native_smp_prepare_boot_cpu(void)
void __init native_smp_cpus_done(unsigned int max_cpus)
{
+ int ncpus;
+
pr_debug("Boot done\n");
+ /*
+ * Today neither Intel nor AMD support heterogenous systems so
+ * extrapolate the boot cpu's data to all packages.
+ */
+ ncpus = cpu_data(0).booted_cores * smp_num_siblings;
+ __max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus);
+ pr_info("Max logical packages: %u\n", __max_logical_packages);
if (x86_has_numa_in_package)
set_sched_topology(x86_numa_in_package_topology);
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index a63fe77b3217..676774b9bb8d 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -188,6 +188,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
if (len > TASK_SIZE)
return -ENOMEM;
+ /* No address checking. See comment at mmap_address_hint_valid() */
if (flags & MAP_FIXED)
return addr;
@@ -197,12 +198,15 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
/* requesting a specific address */
if (addr) {
- addr = PAGE_ALIGN(addr);
+ addr &= PAGE_MASK;
+ if (!mmap_address_hint_valid(addr, len))
+ goto get_unmapped_area;
+
vma = find_vma(mm, addr);
- if (TASK_SIZE - len >= addr &&
- (!vma || addr + len <= vm_start_gap(vma)))
+ if (!vma || addr + len <= vm_start_gap(vma))
return addr;
}
+get_unmapped_area:
info.flags = VM_UNMAPPED_AREA_TOPDOWN;
info.length = len;
diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c
index 6ba82be68cff..f44ce0fb3583 100644
--- a/arch/x86/kernel/umip.c
+++ b/arch/x86/kernel/umip.c
@@ -78,7 +78,60 @@
#define UMIP_INST_SGDT 0 /* 0F 01 /0 */
#define UMIP_INST_SIDT 1 /* 0F 01 /1 */
-#define UMIP_INST_SMSW 3 /* 0F 01 /4 */
+#define UMIP_INST_SMSW 2 /* 0F 01 /4 */
+#define UMIP_INST_SLDT 3 /* 0F 00 /0 */
+#define UMIP_INST_STR 4 /* 0F 00 /1 */
+
+const char * const umip_insns[5] = {
+ [UMIP_INST_SGDT] = "SGDT",
+ [UMIP_INST_SIDT] = "SIDT",
+ [UMIP_INST_SMSW] = "SMSW",
+ [UMIP_INST_SLDT] = "SLDT",
+ [UMIP_INST_STR] = "STR",
+};
+
+#define umip_pr_err(regs, fmt, ...) \
+ umip_printk(regs, KERN_ERR, fmt, ##__VA_ARGS__)
+#define umip_pr_warning(regs, fmt, ...) \
+ umip_printk(regs, KERN_WARNING, fmt, ##__VA_ARGS__)
+
+/**
+ * umip_printk() - Print a rate-limited message
+ * @regs: Register set with the context in which the warning is printed
+ * @log_level: Kernel log level to print the message
+ * @fmt: The text string to print
+ *
+ * Print the text contained in @fmt. The print rate is limited to bursts of 5
+ * messages every two minutes. The purpose of this customized version of
+ * printk() is to print messages when user space processes use any of the
+ * UMIP-protected instructions. Thus, the printed text is prepended with the
+ * task name and process ID number of the current task as well as the
+ * instruction and stack pointers in @regs as seen when entering kernel mode.
+ *
+ * Returns:
+ *
+ * None.
+ */
+static __printf(3, 4)
+void umip_printk(const struct pt_regs *regs, const char *log_level,
+ const char *fmt, ...)
+{
+ /* Bursts of 5 messages every two minutes */
+ static DEFINE_RATELIMIT_STATE(ratelimit, 2 * 60 * HZ, 5);
+ struct task_struct *tsk = current;
+ struct va_format vaf;
+ va_list args;
+
+ if (!__ratelimit(&ratelimit))
+ return;
+
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ printk("%s" pr_fmt("%s[%d] ip:%lx sp:%lx: %pV"), log_level, tsk->comm,
+ task_pid_nr(tsk), regs->ip, regs->sp, &vaf);
+ va_end(args);
+}
/**
* identify_insn() - Identify a UMIP-protected instruction
@@ -118,10 +171,16 @@ static int identify_insn(struct insn *insn)
default:
return -EINVAL;
}
+ } else if (insn->opcode.bytes[1] == 0x0) {
+ if (X86_MODRM_REG(insn->modrm.value) == 0)
+ return UMIP_INST_SLDT;
+ else if (X86_MODRM_REG(insn->modrm.value) == 1)
+ return UMIP_INST_STR;
+ else
+ return -EINVAL;
+ } else {
+ return -EINVAL;
}
-
- /* SLDT AND STR are not emulated */
- return -EINVAL;
}
/**
@@ -228,10 +287,8 @@ static void force_sig_info_umip_fault(void __user *addr, struct pt_regs *regs)
if (!(show_unhandled_signals && unhandled_signal(tsk, SIGSEGV)))
return;
- pr_err_ratelimited("%s[%d] umip emulation segfault ip:%lx sp:%lx error:%x in %lx\n",
- tsk->comm, task_pid_nr(tsk), regs->ip,
- regs->sp, X86_PF_USER | X86_PF_WRITE,
- regs->ip);
+ umip_pr_err(regs, "segfault in emulation. error%x\n",
+ X86_PF_USER | X86_PF_WRITE);
}
/**
@@ -262,15 +319,11 @@ bool fixup_umip_exception(struct pt_regs *regs)
unsigned char buf[MAX_INSN_SIZE];
void __user *uaddr;
struct insn insn;
- char seg_defs;
+ int seg_defs;
if (!regs)
return false;
- /* Do not emulate 64-bit processes. */
- if (user_64bit_mode(regs))
- return false;
-
/*
* If not in user-space long mode, a custom code segment could be in
* use. This is true in protected mode (if the process defined a local
@@ -322,6 +375,15 @@ bool fixup_umip_exception(struct pt_regs *regs)
if (umip_inst < 0)
return false;
+ umip_pr_warning(regs, "%s instruction cannot be used by applications.\n",
+ umip_insns[umip_inst]);
+
+ /* Do not emulate SLDT, STR or user long mode processes. */
+ if (umip_inst == UMIP_INST_STR || umip_inst == UMIP_INST_SLDT || user_64bit_mode(regs))
+ return false;
+
+ umip_pr_warning(regs, "For now, expensive software emulation returns the result.\n");
+
if (emulate_umip_insn(&insn, umip_inst, dummy_data, &dummy_data_size))
return false;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index b71daed3cca2..59e13a79c2e3 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3671,6 +3671,13 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
u32 ecx = msr->index;
u64 data = msr->data;
switch (ecx) {
+ case MSR_IA32_CR_PAT:
+ if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
+ return 1;
+ vcpu->arch.pat = data;
+ svm->vmcb->save.g_pat = data;
+ mark_dirty(svm->vmcb, VMCB_NPT);
+ break;
case MSR_IA32_TSC:
kvm_write_tsc(vcpu, msr);
break;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 7c3522a989d0..714a0673ec3c 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -70,6 +70,9 @@ MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id);
static bool __read_mostly enable_vpid = 1;
module_param_named(vpid, enable_vpid, bool, 0444);
+static bool __read_mostly enable_vnmi = 1;
+module_param_named(vnmi, enable_vnmi, bool, S_IRUGO);
+
static bool __read_mostly flexpriority_enabled = 1;
module_param_named(flexpriority, flexpriority_enabled, bool, S_IRUGO);
@@ -202,6 +205,10 @@ struct loaded_vmcs {
bool nmi_known_unmasked;
unsigned long vmcs_host_cr3; /* May not match real cr3 */
unsigned long vmcs_host_cr4; /* May not match real cr4 */
+ /* Support for vnmi-less CPUs */
+ int soft_vnmi_blocked;
+ ktime_t entry_time;
+ s64 vnmi_blocked_time;
struct list_head loaded_vmcss_on_cpu_link;
};
@@ -1291,6 +1298,11 @@ static inline bool cpu_has_vmx_invpcid(void)
SECONDARY_EXEC_ENABLE_INVPCID;
}
+static inline bool cpu_has_virtual_nmis(void)
+{
+ return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS;
+}
+
static inline bool cpu_has_vmx_wbinvd_exit(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
@@ -1348,11 +1360,6 @@ static inline bool nested_cpu_has2(struct vmcs12 *vmcs12, u32 bit)
(vmcs12->secondary_vm_exec_control & bit);
}
-static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12)
-{
- return vmcs12->pin_based_vm_exec_control & PIN_BASED_VIRTUAL_NMIS;
-}
-
static inline bool nested_cpu_has_preemption_timer(struct vmcs12 *vmcs12)
{
return vmcs12->pin_based_vm_exec_control &
@@ -3712,9 +3719,9 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
&_vmexit_control) < 0)
return -EIO;
- min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING |
- PIN_BASED_VIRTUAL_NMIS;
- opt = PIN_BASED_POSTED_INTR | PIN_BASED_VMX_PREEMPTION_TIMER;
+ min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING;
+ opt = PIN_BASED_VIRTUAL_NMIS | PIN_BASED_POSTED_INTR |
+ PIN_BASED_VMX_PREEMPTION_TIMER;
if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PINBASED_CTLS,
&_pin_based_exec_control) < 0)
return -EIO;
@@ -5232,6 +5239,10 @@ static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx)
if (!kvm_vcpu_apicv_active(&vmx->vcpu))
pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR;
+
+ if (!enable_vnmi)
+ pin_based_exec_ctrl &= ~PIN_BASED_VIRTUAL_NMIS;
+
/* Enable the preemption timer dynamically */
pin_based_exec_ctrl &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
return pin_based_exec_ctrl;
@@ -5666,7 +5677,8 @@ static void enable_irq_window(struct kvm_vcpu *vcpu)
static void enable_nmi_window(struct kvm_vcpu *vcpu)
{
- if (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) {
+ if (!enable_vnmi ||
+ vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) {
enable_irq_window(vcpu);
return;
}
@@ -5706,6 +5718,19 @@ static void vmx_inject_nmi(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ if (!enable_vnmi) {
+ /*
+ * Tracking the NMI-blocked state in software is built upon
+ * finding the next open IRQ window. This, in turn, depends on
+ * well-behaving guests: They have to keep IRQs disabled at
+ * least as long as the NMI handler runs. Otherwise we may
+ * cause NMI nesting, maybe breaking the guest. But as this is
+ * highly unlikely, we can live with the residual risk.
+ */
+ vmx->loaded_vmcs->soft_vnmi_blocked = 1;
+ vmx->loaded_vmcs->vnmi_blocked_time = 0;
+ }
+
++vcpu->stat.nmi_injections;
vmx->loaded_vmcs->nmi_known_unmasked = false;
@@ -5724,6 +5749,8 @@ static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu)
struct vcpu_vmx *vmx = to_vmx(vcpu);
bool masked;
+ if (!enable_vnmi)
+ return vmx->loaded_vmcs->soft_vnmi_blocked;
if (vmx->loaded_vmcs->nmi_known_unmasked)
return false;
masked = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_NMI;
@@ -5735,13 +5762,20 @@ static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- vmx->loaded_vmcs->nmi_known_unmasked = !masked;
- if (masked)
- vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
- GUEST_INTR_STATE_NMI);
- else
- vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO,
- GUEST_INTR_STATE_NMI);
+ if (!enable_vnmi) {
+ if (vmx->loaded_vmcs->soft_vnmi_blocked != masked) {
+ vmx->loaded_vmcs->soft_vnmi_blocked = masked;
+ vmx->loaded_vmcs->vnmi_blocked_time = 0;
+ }
+ } else {
+ vmx->loaded_vmcs->nmi_known_unmasked = !masked;
+ if (masked)
+ vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
+ GUEST_INTR_STATE_NMI);
+ else
+ vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO,
+ GUEST_INTR_STATE_NMI);
+ }
}
static int vmx_nmi_allowed(struct kvm_vcpu *vcpu)
@@ -5749,6 +5783,10 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu)
if (to_vmx(vcpu)->nested.nested_run_pending)
return 0;
+ if (!enable_vnmi &&
+ to_vmx(vcpu)->loaded_vmcs->soft_vnmi_blocked)
+ return 0;
+
return !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
(GUEST_INTR_STATE_MOV_SS | GUEST_INTR_STATE_STI
| GUEST_INTR_STATE_NMI));
@@ -6476,6 +6514,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
* AAK134, BY25.
*/
if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) &&
+ enable_vnmi &&
(exit_qualification & INTR_INFO_UNBLOCK_NMI))
vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI);
@@ -6535,6 +6574,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
static int handle_nmi_window(struct kvm_vcpu *vcpu)
{
+ WARN_ON_ONCE(!enable_vnmi);
vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
CPU_BASED_VIRTUAL_NMI_PENDING);
++vcpu->stat.nmi_window_exits;
@@ -6758,6 +6798,9 @@ static __init int hardware_setup(void)
if (!cpu_has_vmx_flexpriority())
flexpriority_enabled = 0;
+ if (!cpu_has_virtual_nmis())
+ enable_vnmi = 0;
+
/*
* set_apic_access_page_addr() is used to reload apic access
* page upon invalidation. No need to do anything if not
@@ -6962,7 +7005,7 @@ static struct loaded_vmcs *nested_get_current_vmcs02(struct vcpu_vmx *vmx)
}
/* Create a new VMCS */
- item = kmalloc(sizeof(struct vmcs02_list), GFP_KERNEL);
+ item = kzalloc(sizeof(struct vmcs02_list), GFP_KERNEL);
if (!item)
return NULL;
item->vmcs02.vmcs = alloc_vmcs();
@@ -7979,6 +8022,7 @@ static int handle_pml_full(struct kvm_vcpu *vcpu)
* "blocked by NMI" bit has to be set before next VM entry.
*/
if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) &&
+ enable_vnmi &&
(exit_qualification & INTR_INFO_UNBLOCK_NMI))
vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
GUEST_INTR_STATE_NMI);
@@ -8823,6 +8867,25 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
return 0;
}
+ if (unlikely(!enable_vnmi &&
+ vmx->loaded_vmcs->soft_vnmi_blocked)) {
+ if (vmx_interrupt_allowed(vcpu)) {
+ vmx->loaded_vmcs->soft_vnmi_blocked = 0;
+ } else if (vmx->loaded_vmcs->vnmi_blocked_time > 1000000000LL &&
+ vcpu->arch.nmi_pending) {
+ /*
+ * This CPU don't support us in finding the end of an
+ * NMI-blocked window if the guest runs with IRQs
+ * disabled. So we pull the trigger after 1 s of
+ * futile waiting, but inform the user about this.
+ */
+ printk(KERN_WARNING "%s: Breaking out of NMI-blocked "
+ "state on VCPU %d after 1 s timeout\n",
+ __func__, vcpu->vcpu_id);
+ vmx->loaded_vmcs->soft_vnmi_blocked = 0;
+ }
+ }
+
if (exit_reason < kvm_vmx_max_exit_handlers
&& kvm_vmx_exit_handlers[exit_reason])
return kvm_vmx_exit_handlers[exit_reason](vcpu);
@@ -9105,33 +9168,38 @@ static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx)
idtv_info_valid = vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK;
- if (vmx->loaded_vmcs->nmi_known_unmasked)
- return;
- /*
- * Can't use vmx->exit_intr_info since we're not sure what
- * the exit reason is.
- */
- exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
- unblock_nmi = (exit_intr_info & INTR_INFO_UNBLOCK_NMI) != 0;
- vector = exit_intr_info & INTR_INFO_VECTOR_MASK;
- /*
- * SDM 3: 27.7.1.2 (September 2008)
- * Re-set bit "block by NMI" before VM entry if vmexit caused by
- * a guest IRET fault.
- * SDM 3: 23.2.2 (September 2008)
- * Bit 12 is undefined in any of the following cases:
- * If the VM exit sets the valid bit in the IDT-vectoring
- * information field.
- * If the VM exit is due to a double fault.
- */
- if ((exit_intr_info & INTR_INFO_VALID_MASK) && unblock_nmi &&
- vector != DF_VECTOR && !idtv_info_valid)
- vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
- GUEST_INTR_STATE_NMI);
- else
- vmx->loaded_vmcs->nmi_known_unmasked =
- !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO)
- & GUEST_INTR_STATE_NMI);
+ if (enable_vnmi) {
+ if (vmx->loaded_vmcs->nmi_known_unmasked)
+ return;
+ /*
+ * Can't use vmx->exit_intr_info since we're not sure what
+ * the exit reason is.
+ */
+ exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
+ unblock_nmi = (exit_intr_info & INTR_INFO_UNBLOCK_NMI) != 0;
+ vector = exit_intr_info & INTR_INFO_VECTOR_MASK;
+ /*
+ * SDM 3: 27.7.1.2 (September 2008)
+ * Re-set bit "block by NMI" before VM entry if vmexit caused by
+ * a guest IRET fault.
+ * SDM 3: 23.2.2 (September 2008)
+ * Bit 12 is undefined in any of the following cases:
+ * If the VM exit sets the valid bit in the IDT-vectoring
+ * information field.
+ * If the VM exit is due to a double fault.
+ */
+ if ((exit_intr_info & INTR_INFO_VALID_MASK) && unblock_nmi &&
+ vector != DF_VECTOR && !idtv_info_valid)
+ vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
+ GUEST_INTR_STATE_NMI);
+ else
+ vmx->loaded_vmcs->nmi_known_unmasked =
+ !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO)
+ & GUEST_INTR_STATE_NMI);
+ } else if (unlikely(vmx->loaded_vmcs->soft_vnmi_blocked))
+ vmx->loaded_vmcs->vnmi_blocked_time +=
+ ktime_to_ns(ktime_sub(ktime_get(),
+ vmx->loaded_vmcs->entry_time));
}
static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu,
@@ -9248,6 +9316,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned long debugctlmsr, cr3, cr4;
+ /* Record the guest's net vcpu time for enforced NMI injections. */
+ if (unlikely(!enable_vnmi &&
+ vmx->loaded_vmcs->soft_vnmi_blocked))
+ vmx->loaded_vmcs->entry_time = ktime_get();
+
/* Don't enter VMX if guest state is invalid, let the exit handler
start emulation until we arrive back to a valid state */
if (vmx->emulation_required)
diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c
index 35625d279458..9119d8e41f1f 100644
--- a/arch/x86/lib/insn-eval.c
+++ b/arch/x86/lib/insn-eval.c
@@ -733,11 +733,11 @@ static unsigned long get_seg_limit(struct pt_regs *regs, int seg_reg_idx)
*
* Returns:
*
- * A signed 8-bit value containing the default parameters on success.
+ * An int containing ORed-in default parameters on success.
*
* -EINVAL on error.
*/
-char insn_get_code_seg_params(struct pt_regs *regs)
+int insn_get_code_seg_params(struct pt_regs *regs)
{
struct desc_struct *desc;
short sel;
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index 12e377184ee4..c4d55919fac1 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -896,7 +896,7 @@ EndTable
GrpTable: Grp3_1
0: TEST Eb,Ib
-1:
+1: TEST Eb,Ib
2: NOT Eb
3: NEG Eb
4: MUL AL,Eb
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 8ae0000cbdb3..00b296617ca4 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -158,6 +158,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
if (len > TASK_SIZE)
return -ENOMEM;
+ /* No address checking. See comment at mmap_address_hint_valid() */
if (flags & MAP_FIXED) {
if (prepare_hugepage_range(file, addr, len))
return -EINVAL;
@@ -165,12 +166,16 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
}
if (addr) {
- addr = ALIGN(addr, huge_page_size(h));
+ addr &= huge_page_mask(h);
+ if (!mmap_address_hint_valid(addr, len))
+ goto get_unmapped_area;
+
vma = find_vma(mm, addr);
- if (TASK_SIZE - len >= addr &&
- (!vma || addr + len <= vm_start_gap(vma)))
+ if (!vma || addr + len <= vm_start_gap(vma))
return addr;
}
+
+get_unmapped_area:
if (mm->get_unmapped_area == arch_get_unmapped_area)
return hugetlb_get_unmapped_area_bottomup(file, addr, len,
pgoff, flags);
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index a99679826846..155ecbac9e28 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -33,6 +33,8 @@
#include <linux/compat.h>
#include <asm/elf.h>
+#include "physaddr.h"
+
struct va_alignment __read_mostly va_align = {
.flags = -1,
};
@@ -174,3 +176,63 @@ const char *arch_vma_name(struct vm_area_struct *vma)
return "[mpx]";
return NULL;
}
+
+/**
+ * mmap_address_hint_valid - Validate the address hint of mmap
+ * @addr: Address hint
+ * @len: Mapping length
+ *
+ * Check whether @addr and @addr + @len result in a valid mapping.
+ *
+ * On 32bit this only checks whether @addr + @len is <= TASK_SIZE.
+ *
+ * On 64bit with 5-level page tables another sanity check is required
+ * because mappings requested by mmap(@addr, 0) which cross the 47-bit
+ * virtual address boundary can cause the following theoretical issue:
+ *
+ * An application calls mmap(addr, 0), i.e. without MAP_FIXED, where @addr
+ * is below the border of the 47-bit address space and @addr + @len is
+ * above the border.
+ *
+ * With 4-level paging this request succeeds, but the resulting mapping
+ * address will always be within the 47-bit virtual address space, because
+ * the hint address does not result in a valid mapping and is
+ * ignored. Hence applications which are not prepared to handle virtual
+ * addresses above 47-bit work correctly.
+ *
+ * With 5-level paging this request would be granted and result in a
+ * mapping which crosses the border of the 47-bit virtual address
+ * space. If the application cannot handle addresses above 47-bit this
+ * will lead to misbehaviour and hard to diagnose failures.
+ *
+ * Therefore ignore address hints which would result in a mapping crossing
+ * the 47-bit virtual address boundary.
+ *
+ * Note, that in the same scenario with MAP_FIXED the behaviour is
+ * different. The request with @addr < 47-bit and @addr + @len > 47-bit
+ * fails on a 4-level paging machine but succeeds on a 5-level paging
+ * machine. It is reasonable to expect that an application does not rely on
+ * the failure of such a fixed mapping request, so the restriction is not
+ * applied.
+ */
+bool mmap_address_hint_valid(unsigned long addr, unsigned long len)
+{
+ if (TASK_SIZE - len < addr)
+ return false;
+
+ return (addr > DEFAULT_MAP_WINDOW) == (addr + len > DEFAULT_MAP_WINDOW);
+}
+
+/* Can we access it for direct reading/writing? Must be RAM: */
+int valid_phys_addr_range(phys_addr_t addr, size_t count)
+{
+ return addr + count <= __pa(high_memory);
+}
+
+/* Can we access it through mmap? Must be a valid physical address: */
+int valid_mmap_phys_addr_range(unsigned long pfn, size_t count)
+{
+ phys_addr_t addr = (phys_addr_t)pfn << PAGE_SHIFT;
+
+ return phys_addr_valid(addr + count - 1);
+}