8 files changed, 113 insertions, 25 deletions

diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index 8233a63..dde437f 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -167,7 +167,8 @@ static int __init ffh_cstate_init(void)
 {
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 
-	if (c->x86_vendor != X86_VENDOR_INTEL)
+	if (c->x86_vendor != X86_VENDOR_INTEL &&
+	    c->x86_vendor != X86_VENDOR_AMD)
 		return -1;
 
 	cpu_cstate_entry = alloc_percpu(struct cstate_entry);
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index 815dd63..cc0e8bc 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -704,6 +704,7 @@ static const struct dma_map_ops gart_dma_ops = {
 	.alloc				= gart_alloc_coherent,
 	.free				= gart_free_coherent,
 	.mapping_error			= gart_mapping_error,
+	.dma_supported			= x86_dma_supported,
 };
 
 static void gart_iommu_shutdown(void)
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 5200001..cdf8249 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -21,6 +21,7 @@ obj-y			+= common.o
 obj-y			+= rdrand.o
 obj-y			+= match.o
 obj-y			+= bugs.o
+obj-$(CONFIG_CPU_FREQ)	+= aperfmperf.o
 
 obj-$(CONFIG_PROC_FS)	+= proc.o
 obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
new file mode 100644
index 0000000..d869c86
--- /dev/null
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -0,0 +1,79 @@
+/*
+ * x86 APERF/MPERF KHz calculation for
+ * /sys/.../cpufreq/scaling_cur_freq
+ *
+ * Copyright (C) 2017 Intel Corp.
+ * Author: Len Brown <len.brown@intel.com>
+ *
+ * This file is licensed under GPLv2.
+ */
+
+#include <linux/jiffies.h>
+#include <linux/math64.h>
+#include <linux/percpu.h>
+#include <linux/smp.h>
+
+struct aperfmperf_sample {
+	unsigned int	khz;
+	unsigned long	jiffies;
+	u64	aperf;
+	u64	mperf;
+};
+
+static DEFINE_PER_CPU(struct aperfmperf_sample, samples);
+
+/*
+ * aperfmperf_snapshot_khz()
+ * On the current CPU, snapshot APERF, MPERF, and jiffies
+ * unless we already did it within 10ms
+ * calculate kHz, save snapshot
+ */
+static void aperfmperf_snapshot_khz(void *dummy)
+{
+	u64 aperf, aperf_delta;
+	u64 mperf, mperf_delta;
+	struct aperfmperf_sample *s = this_cpu_ptr(&samples);
+
+	/* Don't bother re-computing within 10 ms */
+	if (time_before(jiffies, s->jiffies + HZ/100))
+		return;
+
+	rdmsrl(MSR_IA32_APERF, aperf);
+	rdmsrl(MSR_IA32_MPERF, mperf);
+
+	aperf_delta = aperf - s->aperf;
+	mperf_delta = mperf - s->mperf;
+
+	/*
+	 * There is no architectural guarantee that MPERF
+	 * increments faster than we can read it.
+	 */
+	if (mperf_delta == 0)
+		return;
+
+	/*
+	 * if (cpu_khz * aperf_delta) fits into ULLONG_MAX, then
+	 *	khz = (cpu_khz * aperf_delta) / mperf_delta
+	 */
+	if (div64_u64(ULLONG_MAX, cpu_khz) > aperf_delta)
+		s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta);
+	else	/* khz = aperf_delta / (mperf_delta / cpu_khz) */
+		s->khz = div64_u64(aperf_delta,
+			div64_u64(mperf_delta, cpu_khz));
+	s->jiffies = jiffies;
+	s->aperf = aperf;
+	s->mperf = mperf;
+}
+
+unsigned int arch_freq_get_on_cpu(int cpu)
+{
+	if (!cpu_khz)
+		return 0;
+
+	if (!static_cpu_has(X86_FEATURE_APERFMPERF))
+		return 0;
+
+	smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1);
+
+	return per_cpu(samples.khz, cpu);
+}
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index 6df621a..218f798 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -2,7 +2,6 @@
 #include <linux/timex.h>
 #include <linux/string.h>
 #include <linux/seq_file.h>
-#include <linux/cpufreq.h>
 
 /*
  *	Get CPU information for use by the procfs.
@@ -76,14 +75,9 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	if (c->microcode)
 		seq_printf(m, "microcode\t: 0x%x\n", c->microcode);
 
-	if (cpu_has(c, X86_FEATURE_TSC)) {
-		unsigned int freq = cpufreq_quick_get(cpu);
-
-		if (!freq)
-			freq = cpu_khz;
+	if (cpu_has(c, X86_FEATURE_TSC))
 		seq_printf(m, "cpu MHz\t\t: %u.%03u\n",
-			   freq / 1000, (freq % 1000));
-	}
+			   cpu_khz / 1000, (cpu_khz % 1000));
 
 	/* Cache size */
 	if (c->x86_cache_size >= 0)
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index fda7867..5286a4a 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -50,6 +50,8 @@
 #include <asm/x86_init.h>
 #include <asm/iommu_table.h>
 
+#define CALGARY_MAPPING_ERROR	0
+
 #ifdef CONFIG_CALGARY_IOMMU_ENABLED_BY_DEFAULT
 int use_calgary __read_mostly = 1;
 #else
@@ -252,7 +254,7 @@ static unsigned long iommu_range_alloc(struct device *dev,
 			if (panic_on_overflow)
 				panic("Calgary: fix the allocator.\n");
 			else
-				return DMA_ERROR_CODE;
+				return CALGARY_MAPPING_ERROR;
 		}
 	}
 
@@ -272,10 +274,10 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
 
 	entry = iommu_range_alloc(dev, tbl, npages);
 
-	if (unlikely(entry == DMA_ERROR_CODE)) {
+	if (unlikely(entry == CALGARY_MAPPING_ERROR)) {
 		pr_warn("failed to allocate %u pages in iommu %p\n",
 			npages, tbl);
-		return DMA_ERROR_CODE;
+		return CALGARY_MAPPING_ERROR;
 	}
 
 	/* set the return dma address */
@@ -295,7 +297,7 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 	unsigned long flags;
 
 	/* were we called with bad_dma_address? */
-	badend = DMA_ERROR_CODE + (EMERGENCY_PAGES * PAGE_SIZE);
+	badend = CALGARY_MAPPING_ERROR + (EMERGENCY_PAGES * PAGE_SIZE);
 	if (unlikely(dma_addr < badend)) {
 		WARN(1, KERN_ERR "Calgary: driver tried unmapping bad DMA "
 		       "address 0x%Lx\n", dma_addr);
@@ -380,7 +382,7 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg,
 		npages = iommu_num_pages(vaddr, s->length, PAGE_SIZE);
 
 		entry = iommu_range_alloc(dev, tbl, npages);
-		if (entry == DMA_ERROR_CODE) {
+		if (entry == CALGARY_MAPPING_ERROR) {
 			/* makes sure unmap knows to stop */
 			s->dma_length = 0;
 			goto error;
@@ -398,7 +400,7 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg,
 error:
 	calgary_unmap_sg(dev, sg, nelems, dir, 0);
 	for_each_sg(sg, s, nelems, i) {
-		sg->dma_address = DMA_ERROR_CODE;
+		sg->dma_address = CALGARY_MAPPING_ERROR;
 		sg->dma_length = 0;
 	}
 	return 0;
@@ -453,7 +455,7 @@ static void* calgary_alloc_coherent(struct device *dev, size_t size,
 
 	/* set up tces to cover the allocated range */
 	mapping = iommu_alloc(dev, tbl, ret, npages, DMA_BIDIRECTIONAL);
-	if (mapping == DMA_ERROR_CODE)
+	if (mapping == CALGARY_MAPPING_ERROR)
 		goto free;
 	*dma_handle = mapping;
 	return ret;
@@ -478,6 +480,11 @@ static void calgary_free_coherent(struct device *dev, size_t size,
 	free_pages((unsigned long)vaddr, get_order(size));
 }
 
+static int calgary_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_addr == CALGARY_MAPPING_ERROR;
+}
+
 static const struct dma_map_ops calgary_dma_ops = {
 	.alloc = calgary_alloc_coherent,
 	.free = calgary_free_coherent,
@@ -485,6 +492,8 @@ static const struct dma_map_ops calgary_dma_ops = {
 	.unmap_sg = calgary_unmap_sg,
 	.map_page = calgary_map_page,
 	.unmap_page = calgary_unmap_page,
+	.mapping_error = calgary_mapping_error,
+	.dma_supported = x86_dma_supported,
 };
 
 static inline void __iomem * busno_to_bbar(unsigned char num)
@@ -732,7 +741,7 @@ static void __init calgary_reserve_regions(struct pci_dev *dev)
 	struct iommu_table *tbl = pci_iommu(dev->bus);
 
 	/* reserve EMERGENCY_PAGES from bad_dma_address and up */
-	iommu_range_reserve(tbl, DMA_ERROR_CODE, EMERGENCY_PAGES);
+	iommu_range_reserve(tbl, CALGARY_MAPPING_ERROR, EMERGENCY_PAGES);
 
 	/* avoid the BIOS/VGA first 640KB-1MB region */
 	/* for CalIOC2 - avoid the entire first MB */
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 3a216ec..5e16d3f 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -213,10 +213,8 @@ static __init int iommu_setup(char *p)
 }
 early_param("iommu", iommu_setup);
 
-int dma_supported(struct device *dev, u64 mask)
+int x86_dma_supported(struct device *dev, u64 mask)
 {
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
 #ifdef CONFIG_PCI
 	if (mask > 0xffffffff && forbid_dac > 0) {
 		dev_info(dev, "PCI: Disallowing DAC for device\n");
@@ -224,9 +222,6 @@ int dma_supported(struct device *dev, u64 mask)
 	}
 #endif
 
-	if (ops->dma_supported)
-		return ops->dma_supported(dev, mask);
-
 	/* Copied from i386. Doesn't make much sense, because it will
 	   only work for pci_alloc_coherent.
 	   The caller just has to use GFP_DMA in this case. */
@@ -252,7 +247,6 @@ int dma_supported(struct device *dev, u64 mask)
 
 	return 1;
 }
-EXPORT_SYMBOL(dma_supported);
 
 static int __init pci_iommu_init(void)
 {
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index a88952e..a6d4040 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -11,6 +11,8 @@
 #include <asm/iommu.h>
 #include <asm/dma.h>
 
+#define NOMMU_MAPPING_ERROR		0
+
 static int
 check_addr(char *name, struct device *hwdev, dma_addr_t bus, size_t size)
 {
@@ -33,7 +35,7 @@ static dma_addr_t nommu_map_page(struct device *dev, struct page *page,
 	dma_addr_t bus = page_to_phys(page) + offset;
 	WARN_ON(size == 0);
 	if (!check_addr("map_single", dev, bus, size))
-		return DMA_ERROR_CODE;
+		return NOMMU_MAPPING_ERROR;
 	flush_write_buffers();
 	return bus;
 }
@@ -88,6 +90,11 @@ static void nommu_sync_sg_for_device(struct device *dev,
 	flush_write_buffers();
 }
 
+static int nommu_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_addr == NOMMU_MAPPING_ERROR;
+}
+
 const struct dma_map_ops nommu_dma_ops = {
 	.alloc			= dma_generic_alloc_coherent,
 	.free			= dma_generic_free_coherent,
@@ -96,4 +103,6 @@ const struct dma_map_ops nommu_dma_ops = {
 	.sync_single_for_device = nommu_sync_single_for_device,
 	.sync_sg_for_device	= nommu_sync_sg_for_device,
 	.is_phys		= 1,
+	.mapping_error		= nommu_mapping_error,
+	.dma_supported		= x86_dma_supported,
 };