5 files changed, 62 insertions, 25 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 0925676266bd..fedf32a8c3ec 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -11,6 +11,8 @@ ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_tsc.o = -pg
 CFLAGS_REMOVE_rtc.o = -pg
 CFLAGS_REMOVE_paravirt-spinlocks.o = -pg
+CFLAGS_REMOVE_pvclock.o = -pg
+CFLAGS_REMOVE_kvmclock.o = -pg
 CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_early_printk.o = -pg
 endif
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index fb7a5f052e2b..fb16f17e59be 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -61,7 +61,7 @@ struct cstate_entry {
 		unsigned int ecx;
 	} states[ACPI_PROCESSOR_MAX_POWER];
 };
-static struct cstate_entry *cpu_cstate_entry;	/* per CPU ptr */
+static struct cstate_entry __percpu *cpu_cstate_entry;	/* per CPU ptr */
 
 static short mwait_supported[ACPI_PROCESSOR_MAX_POWER];
 
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index fa044e1e30a2..679b6450382b 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -1953,6 +1953,7 @@ static void __unmap_single(struct dma_ops_domain *dma_dom,
 			   size_t size,
 			   int dir)
 {
+	dma_addr_t flush_addr;
 	dma_addr_t i, start;
 	unsigned int pages;
 
@@ -1960,6 +1961,7 @@ static void __unmap_single(struct dma_ops_domain *dma_dom,
 	    (dma_addr + size > dma_dom->aperture_size))
 		return;
 
+	flush_addr = dma_addr;
 	pages = iommu_num_pages(dma_addr, size, PAGE_SIZE);
 	dma_addr &= PAGE_MASK;
 	start = dma_addr;
@@ -1974,7 +1976,7 @@ static void __unmap_single(struct dma_ops_domain *dma_dom,
 	dma_ops_free_addresses(dma_dom, dma_addr, pages);
 
 	if (amd_iommu_unmap_flush || dma_dom->need_flush) {
-		iommu_flush_pages(&dma_dom->domain, dma_addr, size);
+		iommu_flush_pages(&dma_dom->domain, flush_addr, size);
 		dma_dom->need_flush = false;
 	}
 }
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 3cc63e2b8dd4..5a170cbbbed8 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -632,6 +632,13 @@ static void __init init_iommu_from_pci(struct amd_iommu *iommu)
 	iommu->last_device = calc_devid(MMIO_GET_BUS(range),
 					MMIO_GET_LD(range));
 	iommu->evt_msi_num = MMIO_MSI_NUM(misc);
+
+	if (is_rd890_iommu(iommu->dev)) {
+		pci_read_config_dword(iommu->dev, 0xf0, &iommu->cache_cfg[0]);
+		pci_read_config_dword(iommu->dev, 0xf4, &iommu->cache_cfg[1]);
+		pci_read_config_dword(iommu->dev, 0xf8, &iommu->cache_cfg[2]);
+		pci_read_config_dword(iommu->dev, 0xfc, &iommu->cache_cfg[3]);
+	}
 }
 
 /*
@@ -649,29 +656,9 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu,
 	struct ivhd_entry *e;
 
 	/*
-	 * First set the recommended feature enable bits from ACPI
-	 * into the IOMMU control registers
+	 * First save the recommended feature enable bits from ACPI
 	 */
-	h->flags & IVHD_FLAG_HT_TUN_EN_MASK ?
-		iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) :
-		iommu_feature_disable(iommu, CONTROL_HT_TUN_EN);
-
-	h->flags & IVHD_FLAG_PASSPW_EN_MASK ?
-		iommu_feature_enable(iommu, CONTROL_PASSPW_EN) :
-		iommu_feature_disable(iommu, CONTROL_PASSPW_EN);
-
-	h->flags & IVHD_FLAG_RESPASSPW_EN_MASK ?
-		iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) :
-		iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN);
-
-	h->flags & IVHD_FLAG_ISOC_EN_MASK ?
-		iommu_feature_enable(iommu, CONTROL_ISOC_EN) :
-		iommu_feature_disable(iommu, CONTROL_ISOC_EN);
-
-	/*
-	 * make IOMMU memory accesses cache coherent
-	 */
-	iommu_feature_enable(iommu, CONTROL_COHERENT_EN);
+	iommu->acpi_flags = h->flags;
 
 	/*
 	 * Done. Now parse the device entries
@@ -1116,6 +1103,40 @@ static void init_device_table(void)
 	}
 }
 
+static void iommu_init_flags(struct amd_iommu *iommu)
+{
+	iommu->acpi_flags & IVHD_FLAG_HT_TUN_EN_MASK ?
+		iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) :
+		iommu_feature_disable(iommu, CONTROL_HT_TUN_EN);
+
+	iommu->acpi_flags & IVHD_FLAG_PASSPW_EN_MASK ?
+		iommu_feature_enable(iommu, CONTROL_PASSPW_EN) :
+		iommu_feature_disable(iommu, CONTROL_PASSPW_EN);
+
+	iommu->acpi_flags & IVHD_FLAG_RESPASSPW_EN_MASK ?
+		iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) :
+		iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN);
+
+	iommu->acpi_flags & IVHD_FLAG_ISOC_EN_MASK ?
+		iommu_feature_enable(iommu, CONTROL_ISOC_EN) :
+		iommu_feature_disable(iommu, CONTROL_ISOC_EN);
+
+	/*
+	 * make IOMMU memory accesses cache coherent
+	 */
+	iommu_feature_enable(iommu, CONTROL_COHERENT_EN);
+}
+
+static void iommu_apply_quirks(struct amd_iommu *iommu)
+{
+	if (is_rd890_iommu(iommu->dev)) {
+		pci_write_config_dword(iommu->dev, 0xf0, iommu->cache_cfg[0]);
+		pci_write_config_dword(iommu->dev, 0xf4, iommu->cache_cfg[1]);
+		pci_write_config_dword(iommu->dev, 0xf8, iommu->cache_cfg[2]);
+		pci_write_config_dword(iommu->dev, 0xfc, iommu->cache_cfg[3]);
+	}
+}
+
 /*
  * This function finally enables all IOMMUs found in the system after
  * they have been initialized
@@ -1126,6 +1147,8 @@ static void enable_iommus(void)
 
 	for_each_iommu(iommu) {
 		iommu_disable(iommu);
+		iommu_apply_quirks(iommu);
+		iommu_init_flags(iommu);
 		iommu_set_device_table(iommu);
 		iommu_enable_command_buffer(iommu);
 		iommu_enable_event_buffer(iommu);
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 3efdf2870a35..03a5b0385ad6 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -102,6 +102,7 @@ struct cpu_hw_events {
 	 */
 	struct perf_event	*events[X86_PMC_IDX_MAX]; /* in counter order */
 	unsigned long		active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	unsigned long		running[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 	int			enabled;
 
 	int			n_events;
@@ -1010,6 +1011,7 @@ static int x86_pmu_start(struct perf_event *event)
 	x86_perf_event_set_period(event);
 	cpuc->events[idx] = event;
 	__set_bit(idx, cpuc->active_mask);
+	__set_bit(idx, cpuc->running);
 	x86_pmu.enable(event);
 	perf_event_update_userpage(event);
 
@@ -1141,8 +1143,16 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
-		if (!test_bit(idx, cpuc->active_mask))
+		if (!test_bit(idx, cpuc->active_mask)) {
+			/*
+			 * Though we deactivated the counter some cpus
+			 * might still deliver spurious interrupts still
+			 * in flight. Catch them:
+			 */
+			if (__test_and_clear_bit(idx, cpuc->running))
+				handled++;
 			continue;
+		}
 
 		event = cpuc->events[idx];
 		hwc = &event->hw;