aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/Makefile3
-rw-r--r--arch/x86/kernel/amd_iommu.c54
-rw-r--r--arch/x86/kernel/amd_iommu_init.c7
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_64.c3
-rw-r--r--arch/x86/kernel/microcode_core.c19
-rw-r--r--arch/x86/kernel/microcode_intel.c6
-rw-r--r--arch/x86/kernel/mpparse.c3
-rw-r--r--arch/x86/kernel/paravirt-spinlocks.c3
-rw-r--r--arch/x86/kernel/pci-dma.c13
-rw-r--r--arch/x86/kernel/pci-gart_64.c6
-rw-r--r--arch/x86/kernel/pci-swiotlb_64.c29
-rw-r--r--arch/x86/kernel/setup.c12
-rw-r--r--arch/x86/kernel/smpboot.c2
-rw-r--r--arch/x86/kernel/vmi_32.c16
14 files changed, 111 insertions, 65 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index b62a7667828..a9c656f2d66 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -105,6 +105,8 @@ microcode-$(CONFIG_MICROCODE_INTEL) += microcode_intel.o
microcode-$(CONFIG_MICROCODE_AMD) += microcode_amd.o
obj-$(CONFIG_MICROCODE) += microcode.o
+obj-$(CONFIG_SWIOTLB) += pci-swiotlb_64.o # NB rename without _64
+
###
# 64 bit specific files
ifeq ($(CONFIG_X86_64),y)
@@ -118,7 +120,6 @@ ifeq ($(CONFIG_X86_64),y)
obj-$(CONFIG_GART_IOMMU) += pci-gart_64.o aperture_64.o
obj-$(CONFIG_CALGARY_IOMMU) += pci-calgary_64.o tce_64.o
obj-$(CONFIG_AMD_IOMMU) += amd_iommu_init.o amd_iommu.o
- obj-$(CONFIG_SWIOTLB) += pci-swiotlb_64.o
obj-$(CONFIG_PCI_MMCONFIG) += mmconf-fam10h_64.o
endif
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index e4899e0e878..0a60d60ed03 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -187,6 +187,8 @@ static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd)
spin_lock_irqsave(&iommu->lock, flags);
ret = __iommu_queue_command(iommu, cmd);
+ if (!ret)
+ iommu->need_sync = 1;
spin_unlock_irqrestore(&iommu->lock, flags);
return ret;
@@ -210,10 +212,13 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
cmd.data[0] = CMD_COMPL_WAIT_INT_MASK;
CMD_SET_TYPE(&cmd, CMD_COMPL_WAIT);
- iommu->need_sync = 0;
-
spin_lock_irqsave(&iommu->lock, flags);
+ if (!iommu->need_sync)
+ goto out;
+
+ iommu->need_sync = 0;
+
ret = __iommu_queue_command(iommu, &cmd);
if (ret)
@@ -230,8 +235,9 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
status &= ~MMIO_STATUS_COM_WAIT_INT_MASK;
writel(status, iommu->mmio_base + MMIO_STATUS_OFFSET);
- if (unlikely((i == EXIT_LOOP_COUNT) && printk_ratelimit()))
- printk(KERN_WARNING "AMD IOMMU: Completion wait loop failed\n");
+ if (unlikely(i == EXIT_LOOP_COUNT))
+ panic("AMD IOMMU: Completion wait loop failed\n");
+
out:
spin_unlock_irqrestore(&iommu->lock, flags);
@@ -254,8 +260,6 @@ static int iommu_queue_inv_dev_entry(struct amd_iommu *iommu, u16 devid)
ret = iommu_queue_command(iommu, &cmd);
- iommu->need_sync = 1;
-
return ret;
}
@@ -281,8 +285,6 @@ static int iommu_queue_inv_iommu_pages(struct amd_iommu *iommu,
ret = iommu_queue_command(iommu, &cmd);
- iommu->need_sync = 1;
-
return ret;
}
@@ -343,7 +345,7 @@ static int iommu_map(struct protection_domain *dom,
u64 __pte, *pte, *page;
bus_addr = PAGE_ALIGN(bus_addr);
- phys_addr = PAGE_ALIGN(bus_addr);
+ phys_addr = PAGE_ALIGN(phys_addr);
/* only support 512GB address spaces for now */
if (bus_addr > IOMMU_MAP_SIZE_L3 || !(prot & IOMMU_PROT_MASK))
@@ -599,7 +601,7 @@ static void dma_ops_free_pagetable(struct dma_ops_domain *dma_dom)
continue;
p2 = IOMMU_PTE_PAGE(p1[i]);
- for (j = 0; j < 512; ++i) {
+ for (j = 0; j < 512; ++j) {
if (!IOMMU_PTE_PRESENT(p2[j]))
continue;
p3 = IOMMU_PTE_PAGE(p2[j]);
@@ -762,8 +764,6 @@ static void set_device_domain(struct amd_iommu *iommu,
write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
iommu_queue_inv_dev_entry(iommu, devid);
-
- iommu->need_sync = 1;
}
/*****************************************************************************
@@ -858,6 +858,9 @@ static int get_device_resources(struct device *dev,
print_devid(_bdf, 1);
}
+ if (domain_for_device(_bdf) == NULL)
+ set_device_domain(*iommu, *domain, _bdf);
+
return 1;
}
@@ -908,7 +911,7 @@ static void dma_ops_domain_unmap(struct amd_iommu *iommu,
if (address >= dom->aperture_size)
return;
- WARN_ON(address & 0xfffULL || address > dom->aperture_size);
+ WARN_ON(address & ~PAGE_MASK || address >= dom->aperture_size);
pte = dom->pte_pages[IOMMU_PTE_L1_INDEX(address)];
pte += IOMMU_PTE_L0_INDEX(address);
@@ -920,8 +923,8 @@ static void dma_ops_domain_unmap(struct amd_iommu *iommu,
/*
* This function contains common code for mapping of a physically
- * contiguous memory region into DMA address space. It is uses by all
- * mapping functions provided by this IOMMU driver.
+ * contiguous memory region into DMA address space. It is used by all
+ * mapping functions provided with this IOMMU driver.
* Must be called with the domain lock held.
*/
static dma_addr_t __map_single(struct device *dev,
@@ -981,7 +984,8 @@ static void __unmap_single(struct amd_iommu *iommu,
dma_addr_t i, start;
unsigned int pages;
- if ((dma_addr == 0) || (dma_addr + size > dma_dom->aperture_size))
+ if ((dma_addr == bad_dma_address) ||
+ (dma_addr + size > dma_dom->aperture_size))
return;
pages = iommu_num_pages(dma_addr, size, PAGE_SIZE);
@@ -1031,8 +1035,7 @@ static dma_addr_t map_single(struct device *dev, phys_addr_t paddr,
if (addr == bad_dma_address)
goto out;
- if (unlikely(iommu->need_sync))
- iommu_completion_wait(iommu);
+ iommu_completion_wait(iommu);
out:
spin_unlock_irqrestore(&domain->lock, flags);
@@ -1060,8 +1063,7 @@ static void unmap_single(struct device *dev, dma_addr_t dma_addr,
__unmap_single(iommu, domain->priv, dma_addr, size, dir);
- if (unlikely(iommu->need_sync))
- iommu_completion_wait(iommu);
+ iommu_completion_wait(iommu);
spin_unlock_irqrestore(&domain->lock, flags);
}
@@ -1127,8 +1129,7 @@ static int map_sg(struct device *dev, struct scatterlist *sglist,
goto unmap;
}
- if (unlikely(iommu->need_sync))
- iommu_completion_wait(iommu);
+ iommu_completion_wait(iommu);
out:
spin_unlock_irqrestore(&domain->lock, flags);
@@ -1173,8 +1174,7 @@ static void unmap_sg(struct device *dev, struct scatterlist *sglist,
s->dma_address = s->dma_length = 0;
}
- if (unlikely(iommu->need_sync))
- iommu_completion_wait(iommu);
+ iommu_completion_wait(iommu);
spin_unlock_irqrestore(&domain->lock, flags);
}
@@ -1225,8 +1225,7 @@ static void *alloc_coherent(struct device *dev, size_t size,
goto out;
}
- if (unlikely(iommu->need_sync))
- iommu_completion_wait(iommu);
+ iommu_completion_wait(iommu);
out:
spin_unlock_irqrestore(&domain->lock, flags);
@@ -1257,8 +1256,7 @@ static void free_coherent(struct device *dev, size_t size,
__unmap_single(iommu, domain->priv, dma_addr, size, DMA_BIDIRECTIONAL);
- if (unlikely(iommu->need_sync))
- iommu_completion_wait(iommu);
+ iommu_completion_wait(iommu);
spin_unlock_irqrestore(&domain->lock, flags);
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 30ae2701b3d..c6cc22815d3 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -427,6 +427,10 @@ static u8 * __init alloc_command_buffer(struct amd_iommu *iommu)
memcpy_toio(iommu->mmio_base + MMIO_CMD_BUF_OFFSET,
&entry, sizeof(entry));
+ /* set head and tail to zero manually */
+ writel(0x00, iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
+ writel(0x00, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
+
iommu_feature_enable(iommu, CONTROL_CMDBUF_EN);
return cmd_buf;
@@ -1074,7 +1078,8 @@ int __init amd_iommu_init(void)
goto free;
/* IOMMU rlookup table - find the IOMMU for a specific device */
- amd_iommu_rlookup_table = (void *)__get_free_pages(GFP_KERNEL,
+ amd_iommu_rlookup_table = (void *)__get_free_pages(
+ GFP_KERNEL | __GFP_ZERO,
get_order(rlookup_table_size));
if (amd_iommu_rlookup_table == NULL)
goto free;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index 4b031a4ac85..1c838032fd3 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -510,12 +510,9 @@ static void __cpuinit mce_cpu_features(struct cpuinfo_x86 *c)
*/
void __cpuinit mcheck_init(struct cpuinfo_x86 *c)
{
- static cpumask_t mce_cpus = CPU_MASK_NONE;
-
mce_cpu_quirks(c);
if (mce_dont_init ||
- cpu_test_and_set(smp_processor_id(), mce_cpus) ||
!mce_available(c))
return;
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 82fb2809ce3..c4b5b24e021 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -272,13 +272,18 @@ static struct attribute_group mc_attr_group = {
.name = "microcode",
};
-static void microcode_fini_cpu(int cpu)
+static void __microcode_fini_cpu(int cpu)
{
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
- mutex_lock(&microcode_mutex);
microcode_ops->microcode_fini_cpu(cpu);
uci->valid = 0;
+}
+
+static void microcode_fini_cpu(int cpu)
+{
+ mutex_lock(&microcode_mutex);
+ __microcode_fini_cpu(cpu);
mutex_unlock(&microcode_mutex);
}
@@ -306,12 +311,16 @@ static int microcode_resume_cpu(int cpu)
* to this cpu (a bit of paranoia):
*/
if (microcode_ops->collect_cpu_info(cpu, &nsig)) {
- microcode_fini_cpu(cpu);
+ __microcode_fini_cpu(cpu);
+ printk(KERN_ERR "failed to collect_cpu_info for resuming cpu #%d\n",
+ cpu);
return -1;
}
- if (memcmp(&nsig, &uci->cpu_sig, sizeof(nsig))) {
- microcode_fini_cpu(cpu);
+ if ((nsig.sig != uci->cpu_sig.sig) || (nsig.pf != uci->cpu_sig.pf)) {
+ __microcode_fini_cpu(cpu);
+ printk(KERN_ERR "cached ucode doesn't match the resuming cpu #%d\n",
+ cpu);
/* Should we look for a new ucode here? */
return 1;
}
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index 622dc4a2178..a8e62792d17 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -155,6 +155,7 @@ static DEFINE_SPINLOCK(microcode_update_lock);
static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
{
struct cpuinfo_x86 *c = &cpu_data(cpu_num);
+ unsigned long flags;
unsigned int val[2];
memset(csig, 0, sizeof(*csig));
@@ -174,11 +175,16 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
csig->pf = 1 << ((val[1] >> 18) & 7);
}
+ /* serialize access to the physical write to MSR 0x79 */
+ spin_lock_irqsave(&microcode_update_lock, flags);
+
wrmsr(MSR_IA32_UCODE_REV, 0, 0);
/* see notes above for revision 1.07. Apparent chip bug */
sync_core();
/* get the current revision from MSR 0x8B */
rdmsr(MSR_IA32_UCODE_REV, val[0], csig->rev);
+ spin_unlock_irqrestore(&microcode_update_lock, flags);
+
pr_debug("microcode: collect_cpu_info : sig=0x%x, pf=0x%x, rev=0x%x\n",
csig->sig, csig->pf, csig->rev);
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index f98f4e1dba0..0f4c1fd5a1f 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -604,6 +604,9 @@ static void __init __get_smp_config(unsigned int early)
printk(KERN_INFO "Using ACPI for processor (LAPIC) "
"configuration information\n");
+ if (!mpf)
+ return;
+
printk(KERN_INFO "Intel MultiProcessor Specification v1.%d\n",
mpf->mpf_specification);
#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32)
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 0e9f1982b1d..95777b0faa7 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -7,7 +7,8 @@
#include <asm/paravirt.h>
-static void default_spin_lock_flags(struct raw_spinlock *lock, unsigned long flags)
+static inline void
+default_spin_lock_flags(raw_spinlock_t *lock, unsigned long flags)
{
__raw_spin_lock(lock);
}
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 19262482021..00e07447a5b 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -105,11 +105,15 @@ static void __init dma32_free_bootmem(void)
dma32_bootmem_ptr = NULL;
dma32_bootmem_size = 0;
}
+#endif
void __init pci_iommu_alloc(void)
{
+#ifdef CONFIG_X86_64
/* free the range so iommu could get some range less than 4G */
dma32_free_bootmem();
+#endif
+
/*
* The order of these functions is important for
* fall-back/fail-over reasons
@@ -125,15 +129,6 @@ void __init pci_iommu_alloc(void)
pci_swiotlb_init();
}
-unsigned long iommu_nr_pages(unsigned long addr, unsigned long len)
-{
- unsigned long size = roundup((addr & ~PAGE_MASK) + len, PAGE_SIZE);
-
- return size >> PAGE_SHIFT;
-}
-EXPORT_SYMBOL(iommu_nr_pages);
-#endif
-
void *dma_generic_alloc_coherent(struct device *dev, size_t size,
dma_addr_t *dma_addr, gfp_t flag)
{
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index a42b02b4df6..a35eaa379ff 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -123,6 +123,8 @@ static void free_iommu(unsigned long offset, int size)
spin_lock_irqsave(&iommu_bitmap_lock, flags);
iommu_area_free(iommu_gart_bitmap, offset, size);
+ if (offset >= next_bit)
+ next_bit = offset + size;
spin_unlock_irqrestore(&iommu_bitmap_lock, flags);
}
@@ -743,10 +745,8 @@ void __init gart_iommu_init(void)
unsigned long scratch;
long i;
- if (cache_k8_northbridges() < 0 || num_k8_northbridges == 0) {
- printk(KERN_INFO "PCI-GART: No AMD GART found.\n");
+ if (cache_k8_northbridges() < 0 || num_k8_northbridges == 0)
return;
- }
#ifndef CONFIG_AGP_AMD64
no_agp = 1;
diff --git a/arch/x86/kernel/pci-swiotlb_64.c b/arch/x86/kernel/pci-swiotlb_64.c
index 3c539d111ab..242c3440687 100644
--- a/arch/x86/kernel/pci-swiotlb_64.c
+++ b/arch/x86/kernel/pci-swiotlb_64.c
@@ -3,6 +3,8 @@
#include <linux/pci.h>
#include <linux/cache.h>
#include <linux/module.h>
+#include <linux/swiotlb.h>
+#include <linux/bootmem.h>
#include <linux/dma-mapping.h>
#include <asm/iommu.h>
@@ -11,6 +13,31 @@
int swiotlb __read_mostly;
+void *swiotlb_alloc_boot(size_t size, unsigned long nslabs)
+{
+ return alloc_bootmem_low_pages(size);
+}
+
+void *swiotlb_alloc(unsigned order, unsigned long nslabs)
+{
+ return (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, order);
+}
+
+dma_addr_t swiotlb_phys_to_bus(phys_addr_t paddr)
+{
+ return paddr;
+}
+
+phys_addr_t swiotlb_bus_to_phys(dma_addr_t baddr)
+{
+ return baddr;
+}
+
+int __weak swiotlb_arch_range_needs_mapping(void *ptr, size_t size)
+{
+ return 0;
+}
+
static dma_addr_t
swiotlb_map_single_phys(struct device *hwdev, phys_addr_t paddr, size_t size,
int direction)
@@ -50,8 +77,10 @@ struct dma_mapping_ops swiotlb_dma_ops = {
void __init pci_swiotlb_init(void)
{
/* don't initialize swiotlb if iommu=off (no_iommu=1) */
+#ifdef CONFIG_X86_64
if (!iommu_detected && !no_iommu && max_pfn > MAX_DMA32_PFN)
swiotlb = 1;
+#endif
if (swiotlb_force)
swiotlb = 1;
if (swiotlb) {
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 9d5674f7b6c..bdec76e5559 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -794,6 +794,9 @@ void __init setup_arch(char **cmdline_p)
printk(KERN_INFO "Command line: %s\n", boot_command_line);
#endif
+ /* VMI may relocate the fixmap; do this before touching ioremap area */
+ vmi_init();
+
early_cpu_init();
early_ioremap_init();
@@ -880,13 +883,8 @@ void __init setup_arch(char **cmdline_p)
check_efer();
#endif
-#if defined(CONFIG_VMI) && defined(CONFIG_X86_32)
- /*
- * Must be before kernel pagetables are setup
- * or fixmap area is touched.
- */
- vmi_init();
-#endif
+ /* Must be before kernel pagetables are setup */
+ vmi_activate();
/* after early param, so could get panic from serial */
reserve_early_setup_data();
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 7b109339731..f71f96fc9e6 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -294,9 +294,7 @@ static void __cpuinit start_secondary(void *unused)
* fragile that we want to limit the things done here to the
* most necessary things.
*/
-#ifdef CONFIG_VMI
vmi_bringup();
-#endif
cpu_init();
preempt_disable();
smp_callin();
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 8b6c393ab9f..22fd6577156 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -960,8 +960,6 @@ static inline int __init activate_vmi(void)
void __init vmi_init(void)
{
- unsigned long flags;
-
if (!vmi_rom)
probe_vmi_rom();
else
@@ -973,13 +971,21 @@ void __init vmi_init(void)
reserve_top_address(-vmi_rom->virtual_top);
- local_irq_save(flags);
- activate_vmi();
-
#ifdef CONFIG_X86_IO_APIC
/* This is virtual hardware; timer routing is wired correctly */
no_timer_check = 1;
#endif
+}
+
+void vmi_activate(void)
+{
+ unsigned long flags;
+
+ if (!vmi_rom)
+ return;
+
+ local_irq_save(flags);
+ activate_vmi();
local_irq_restore(flags & X86_EFLAGS_IF);
}
generated by cgit v1.2.3 (git 2.25.1) at 2025-01-07 22:46:33 +0000