aboutsummaryrefslogtreecommitdiff
path: root/drivers/pci
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/pci')
-rw-r--r--drivers/pci/dmar.c296
-rw-r--r--drivers/pci/intel-iommu.c270
-rw-r--r--drivers/pci/intr_remapping.c110
-rw-r--r--drivers/pci/pci-driver.c177
-rw-r--r--drivers/pci/pci.c142
-rw-r--r--drivers/pci/pci.h1
6 files changed, 614 insertions, 382 deletions
diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c
index 5f333403c2e..d313039e2fd 100644
--- a/drivers/pci/dmar.c
+++ b/drivers/pci/dmar.c
@@ -31,6 +31,8 @@
#include <linux/iova.h>
#include <linux/intel-iommu.h>
#include <linux/timer.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
#undef PREFIX
#define PREFIX "DMAR:"
@@ -509,6 +511,7 @@ int alloc_iommu(struct dmar_drhd_unit *drhd)
return -ENOMEM;
iommu->seq_id = iommu_allocated++;
+ sprintf (iommu->name, "dmar%d", iommu->seq_id);
iommu->reg = ioremap(drhd->reg_base_addr, VTD_PAGE_SIZE);
if (!iommu->reg) {
@@ -751,6 +754,42 @@ int qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
}
/*
+ * Disable Queued Invalidation interface.
+ */
+void dmar_disable_qi(struct intel_iommu *iommu)
+{
+ unsigned long flags;
+ u32 sts;
+ cycles_t start_time = get_cycles();
+
+ if (!ecap_qis(iommu->ecap))
+ return;
+
+ spin_lock_irqsave(&iommu->register_lock, flags);
+
+ sts = dmar_readq(iommu->reg + DMAR_GSTS_REG);
+ if (!(sts & DMA_GSTS_QIES))
+ goto end;
+
+ /*
+ * Give a chance to HW to complete the pending invalidation requests.
+ */
+ while ((readl(iommu->reg + DMAR_IQT_REG) !=
+ readl(iommu->reg + DMAR_IQH_REG)) &&
+ (DMAR_OPERATION_TIMEOUT > (get_cycles() - start_time)))
+ cpu_relax();
+
+ iommu->gcmd &= ~DMA_GCMD_QIE;
+
+ writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+
+ IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG, readl,
+ !(sts & DMA_GSTS_QIES), sts);
+end:
+ spin_unlock_irqrestore(&iommu->register_lock, flags);
+}
+
+/*
* Enable Queued Invalidation interface. This is a must to support
* interrupt-remapping. Also used by DMA-remapping, which replaces
* register based IOTLB invalidation.
@@ -770,20 +809,20 @@ int dmar_enable_qi(struct intel_iommu *iommu)
if (iommu->qi)
return 0;
- iommu->qi = kmalloc(sizeof(*qi), GFP_KERNEL);
+ iommu->qi = kmalloc(sizeof(*qi), GFP_ATOMIC);
if (!iommu->qi)
return -ENOMEM;
qi = iommu->qi;
- qi->desc = (void *)(get_zeroed_page(GFP_KERNEL));
+ qi->desc = (void *)(get_zeroed_page(GFP_ATOMIC));
if (!qi->desc) {
kfree(qi);
iommu->qi = 0;
return -ENOMEM;
}
- qi->desc_status = kmalloc(QI_LENGTH * sizeof(int), GFP_KERNEL);
+ qi->desc_status = kmalloc(QI_LENGTH * sizeof(int), GFP_ATOMIC);
if (!qi->desc_status) {
free_page((unsigned long) qi->desc);
kfree(qi);
@@ -812,3 +851,254 @@ int dmar_enable_qi(struct intel_iommu *iommu)
return 0;
}
+
+/* iommu interrupt handling. Most stuff are MSI-like. */
+
+enum faulttype {
+ DMA_REMAP,
+ INTR_REMAP,
+ UNKNOWN,
+};
+
+static const char *dma_remap_fault_reasons[] =
+{
+ "Software",
+ "Present bit in root entry is clear",
+ "Present bit in context entry is clear",
+ "Invalid context entry",
+ "Access beyond MGAW",
+ "PTE Write access is not set",
+ "PTE Read access is not set",
+ "Next page table ptr is invalid",
+ "Root table address invalid",
+ "Context table ptr is invalid",
+ "non-zero reserved fields in RTP",
+ "non-zero reserved fields in CTP",
+ "non-zero reserved fields in PTE",
+};
+
+static const char *intr_remap_fault_reasons[] =
+{
+ "Detected reserved fields in the decoded interrupt-remapped request",
+ "Interrupt index exceeded the interrupt-remapping table size",
+ "Present field in the IRTE entry is clear",
+ "Error accessing interrupt-remapping table pointed by IRTA_REG",
+ "Detected reserved fields in the IRTE entry",
+ "Blocked a compatibility format interrupt request",
+ "Blocked an interrupt request due to source-id verification failure",
+};
+
+#define MAX_FAULT_REASON_IDX (ARRAY_SIZE(fault_reason_strings) - 1)
+
+const char *dmar_get_fault_reason(u8 fault_reason, int *fault_type)
+{
+ if (fault_reason >= 0x20 && (fault_reason <= 0x20 +
+ ARRAY_SIZE(intr_remap_fault_reasons))) {
+ *fault_type = INTR_REMAP;
+ return intr_remap_fault_reasons[fault_reason - 0x20];
+ } else if (fault_reason < ARRAY_SIZE(dma_remap_fault_reasons)) {
+ *fault_type = DMA_REMAP;
+ return dma_remap_fault_reasons[fault_reason];
+ } else {
+ *fault_type = UNKNOWN;
+ return "Unknown";
+ }
+}
+
+void dmar_msi_unmask(unsigned int irq)
+{
+ struct intel_iommu *iommu = get_irq_data(irq);
+ unsigned long flag;
+
+ /* unmask it */
+ spin_lock_irqsave(&iommu->register_lock, flag);
+ writel(0, iommu->reg + DMAR_FECTL_REG);
+ /* Read a reg to force flush the post write */
+ readl(iommu->reg + DMAR_FECTL_REG);
+ spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+void dmar_msi_mask(unsigned int irq)
+{
+ unsigned long flag;
+ struct intel_iommu *iommu = get_irq_data(irq);
+
+ /* mask it */
+ spin_lock_irqsave(&iommu->register_lock, flag);
+ writel(DMA_FECTL_IM, iommu->reg + DMAR_FECTL_REG);
+ /* Read a reg to force flush the post write */
+ readl(iommu->reg + DMAR_FECTL_REG);
+ spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+void dmar_msi_write(int irq, struct msi_msg *msg)
+{
+ struct intel_iommu *iommu = get_irq_data(irq);
+ unsigned long flag;
+
+ spin_lock_irqsave(&iommu->register_lock, flag);
+ writel(msg->data, iommu->reg + DMAR_FEDATA_REG);
+ writel(msg->address_lo, iommu->reg + DMAR_FEADDR_REG);
+ writel(msg->address_hi, iommu->reg + DMAR_FEUADDR_REG);
+ spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+void dmar_msi_read(int irq, struct msi_msg *msg)
+{
+ struct intel_iommu *iommu = get_irq_data(irq);
+ unsigned long flag;
+
+ spin_lock_irqsave(&iommu->register_lock, flag);
+ msg->data = readl(iommu->reg + DMAR_FEDATA_REG);
+ msg->address_lo = readl(iommu->reg + DMAR_FEADDR_REG);
+ msg->address_hi = readl(iommu->reg + DMAR_FEUADDR_REG);
+ spin_unlock_irqrestore(&iommu->register_lock, flag);
+}
+
+static int dmar_fault_do_one(struct intel_iommu *iommu, int type,
+ u8 fault_reason, u16 source_id, unsigned long long addr)
+{
+ const char *reason;
+ int fault_type;
+
+ reason = dmar_get_fault_reason(fault_reason, &fault_type);
+
+ if (fault_type == INTR_REMAP)
+ printk(KERN_ERR "INTR-REMAP: Request device [[%02x:%02x.%d] "
+ "fault index %llx\n"
+ "INTR-REMAP:[fault reason %02d] %s\n",
+ (source_id >> 8), PCI_SLOT(source_id & 0xFF),
+ PCI_FUNC(source_id & 0xFF), addr >> 48,
+ fault_reason, reason);
+ else
+ printk(KERN_ERR
+ "DMAR:[%s] Request device [%02x:%02x.%d] "
+ "fault addr %llx \n"
+ "DMAR:[fault reason %02d] %s\n",
+ (type ? "DMA Read" : "DMA Write"),
+ (source_id >> 8), PCI_SLOT(source_id & 0xFF),
+ PCI_FUNC(source_id & 0xFF), addr, fault_reason, reason);
+ return 0;
+}
+
+#define PRIMARY_FAULT_REG_LEN (16)
+irqreturn_t dmar_fault(int irq, void *dev_id)
+{
+ struct intel_iommu *iommu = dev_id;
+ int reg, fault_index;
+ u32 fault_status;
+ unsigned long flag;
+
+ spin_lock_irqsave(&iommu->register_lock, flag);
+ fault_status = readl(iommu->reg + DMAR_FSTS_REG);
+ if (fault_status)
+ printk(KERN_ERR "DRHD: handling fault status reg %x\n",
+ fault_status);
+
+ /* TBD: ignore advanced fault log currently */
+ if (!(fault_status & DMA_FSTS_PPF))
+ goto clear_rest;
+
+ fault_index = dma_fsts_fault_record_index(fault_status);
+ reg = cap_fault_reg_offset(iommu->cap);
+ while (1) {
+ u8 fault_reason;
+ u16 source_id;
+ u64 guest_addr;
+ int type;
+ u32 data;
+
+ /* highest 32 bits */
+ data = readl(iommu->reg + reg +
+ fault_index * PRIMARY_FAULT_REG_LEN + 12);
+ if (!(data & DMA_FRCD_F))
+ break;
+
+ fault_reason = dma_frcd_fault_reason(data);
+ type = dma_frcd_type(data);
+
+ data = readl(iommu->reg + reg +
+ fault_index * PRIMARY_FAULT_REG_LEN + 8);
+ source_id = dma_frcd_source_id(data);
+
+ guest_addr = dmar_readq(iommu->reg + reg +
+ fault_index * PRIMARY_FAULT_REG_LEN);
+ guest_addr = dma_frcd_page_addr(guest_addr);
+ /* clear the fault */
+ writel(DMA_FRCD_F, iommu->reg + reg +
+ fault_index * PRIMARY_FAULT_REG_LEN + 12);
+
+ spin_unlock_irqrestore(&iommu->register_lock, flag);
+
+ dmar_fault_do_one(iommu, type, fault_reason,
+ source_id, guest_addr);
+
+ fault_index++;
+ if (fault_index > cap_num_fault_regs(iommu->cap))
+ fault_index = 0;
+ spin_lock_irqsave(&iommu->register_lock, flag);
+ }
+clear_rest:
+ /* clear all the other faults */
+ fault_status = readl(iommu->reg + DMAR_FSTS_REG);
+ writel(fault_status, iommu->reg + DMAR_FSTS_REG);
+
+ spin_unlock_irqrestore(&iommu->register_lock, flag);
+ return IRQ_HANDLED;
+}
+
+int dmar_set_interrupt(struct intel_iommu *iommu)
+{
+ int irq, ret;
+
+ /*
+ * Check if the fault interrupt is already initialized.
+ */
+ if (iommu->irq)
+ return 0;
+
+ irq = create_irq();
+ if (!irq) {
+ printk(KERN_ERR "IOMMU: no free vectors\n");
+ return -EINVAL;
+ }
+
+ set_irq_data(irq, iommu);
+ iommu->irq = irq;
+
+ ret = arch_setup_dmar_msi(irq);
+ if (ret) {
+ set_irq_data(irq, NULL);
+ iommu->irq = 0;
+ destroy_irq(irq);
+ return 0;
+ }
+
+ ret = request_irq(irq, dmar_fault, 0, iommu->name, iommu);
+ if (ret)
+ printk(KERN_ERR "IOMMU: can't request irq\n");
+ return ret;
+}
+
+int __init enable_drhd_fault_handling(void)
+{
+ struct dmar_drhd_unit *drhd;
+
+ /*
+ * Enable fault control interrupt.
+ */
+ for_each_drhd_unit(drhd) {
+ int ret;
+ struct intel_iommu *iommu = drhd->iommu;
+ ret = dmar_set_interrupt(iommu);
+
+ if (ret) {
+ printk(KERN_ERR "DRHD %Lx: failed to enable fault, "
+ " interrupt, ret %d\n",
+ (unsigned long long)drhd->reg_base_addr, ret);
+ return -1;
+ }
+ }
+
+ return 0;
+}
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index f3f686581a9..49402c39923 100644
--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -1004,194 +1004,6 @@ static int iommu_disable_translation(struct intel_iommu *iommu)
return 0;
}
-/* iommu interrupt handling. Most stuff are MSI-like. */
-
-static const char *fault_reason_strings[] =
-{
- "Software",
- "Present bit in root entry is clear",
- "Present bit in context entry is clear",
- "Invalid context entry",
- "Access beyond MGAW",
- "PTE Write access is not set",
- "PTE Read access is not set",
- "Next page table ptr is invalid",
- "Root table address invalid",
- "Context table ptr is invalid",
- "non-zero reserved fields in RTP",
- "non-zero reserved fields in CTP",
- "non-zero reserved fields in PTE",
-};
-#define MAX_FAULT_REASON_IDX (ARRAY_SIZE(fault_reason_strings) - 1)
-
-const char *dmar_get_fault_reason(u8 fault_reason)
-{
- if (fault_reason > MAX_FAULT_REASON_IDX)
- return "Unknown";
- else
- return fault_reason_strings[fault_reason];
-}
-
-void dmar_msi_unmask(unsigned int irq)
-{
- struct intel_iommu *iommu = get_irq_data(irq);
- unsigned long flag;
-
- /* unmask it */
- spin_lock_irqsave(&iommu->register_lock, flag);
- writel(0, iommu->reg + DMAR_FECTL_REG);
- /* Read a reg to force flush the post write */
- readl(iommu->reg + DMAR_FECTL_REG);
- spin_unlock_irqrestore(&iommu->register_lock, flag);
-}
-
-void dmar_msi_mask(unsigned int irq)
-{
- unsigned long flag;
- struct intel_iommu *iommu = get_irq_data(irq);
-
- /* mask it */
- spin_lock_irqsave(&iommu->register_lock, flag);
- writel(DMA_FECTL_IM, iommu->reg + DMAR_FECTL_REG);
- /* Read a reg to force flush the post write */
- readl(iommu->reg + DMAR_FECTL_REG);
- spin_unlock_irqrestore(&iommu->register_lock, flag);
-}
-
-void dmar_msi_write(int irq, struct msi_msg *msg)
-{
- struct intel_iommu *iommu = get_irq_data(irq);
- unsigned long flag;
-
- spin_lock_irqsave(&iommu->register_lock, flag);
- writel(msg->data, iommu->reg + DMAR_FEDATA_REG);
- writel(msg->address_lo, iommu->reg + DMAR_FEADDR_REG);
- writel(msg->address_hi, iommu->reg + DMAR_FEUADDR_REG);
- spin_unlock_irqrestore(&iommu->register_lock, flag);
-}
-
-void dmar_msi_read(int irq, struct msi_msg *msg)
-{
- struct intel_iommu *iommu = get_irq_data(irq);
- unsigned long flag;
-
- spin_lock_irqsave(&iommu->register_lock, flag);
- msg->data = readl(iommu->reg + DMAR_FEDATA_REG);
- msg->address_lo = readl(iommu->reg + DMAR_FEADDR_REG);
- msg->address_hi = readl(iommu->reg + DMAR_FEUADDR_REG);
- spin_unlock_irqrestore(&iommu->register_lock, flag);
-}
-
-static int iommu_page_fault_do_one(struct intel_iommu *iommu, int type,
- u8 fault_reason, u16 source_id, unsigned long long addr)
-{
- const char *reason;
-
- reason = dmar_get_fault_reason(fault_reason);
-
- printk(KERN_ERR
- "DMAR:[%s] Request device [%02x:%02x.%d] "
- "fault addr %llx \n"
- "DMAR:[fault reason %02d] %s\n",
- (type ? "DMA Read" : "DMA Write"),
- (source_id >> 8), PCI_SLOT(source_id & 0xFF),
- PCI_FUNC(source_id & 0xFF), addr, fault_reason, reason);
- return 0;
-}
-
-#define PRIMARY_FAULT_REG_LEN (16)
-static irqreturn_t iommu_page_fault(int irq, void *dev_id)
-{
- struct intel_iommu *iommu = dev_id;
- int reg, fault_index;
- u32 fault_status;
- unsigned long flag;
-
- spin_lock_irqsave(&iommu->register_lock, flag);
- fault_status = readl(iommu->reg + DMAR_FSTS_REG);
-
- /* TBD: ignore advanced fault log currently */
- if (!(fault_status & DMA_FSTS_PPF))
- goto clear_overflow;
-
- fault_index = dma_fsts_fault_record_index(fault_status);
- reg = cap_fault_reg_offset(iommu->cap);
- while (1) {
- u8 fault_reason;
- u16 source_id;
- u64 guest_addr;
- int type;
- u32 data;
-
- /* highest 32 bits */
- data = readl(iommu->reg + reg +
- fault_index * PRIMARY_FAULT_REG_LEN + 12);
- if (!(data & DMA_FRCD_F))
- break;
-
- fault_reason = dma_frcd_fault_reason(data);
- type = dma_frcd_type(data);
-
- data = readl(iommu->reg + reg +
- fault_index * PRIMARY_FAULT_REG_LEN + 8);
- source_id = dma_frcd_source_id(data);
-
- guest_addr = dmar_readq(iommu->reg + reg +
- fault_index * PRIMARY_FAULT_REG_LEN);
- guest_addr = dma_frcd_page_addr(guest_addr);
- /* clear the fault */
- writel(DMA_FRCD_F, iommu->reg + reg +
- fault_index * PRIMARY_FAULT_REG_LEN + 12);
-
- spin_unlock_irqrestore(&iommu->register_lock, flag);
-
- iommu_page_fault_do_one(iommu, type, fault_reason,
- source_id, guest_addr);
-
- fault_index++;
- if (fault_index > cap_num_fault_regs(iommu->cap))
- fault_index = 0;
- spin_lock_irqsave(&iommu->register_lock, flag);
- }
-clear_overflow:
- /* clear primary fault overflow */
- fault_status = readl(iommu->reg + DMAR_FSTS_REG);
- if (fault_status & DMA_FSTS_PFO)
- writel(DMA_FSTS_PFO, iommu->reg + DMAR_FSTS_REG);
-
- spin_unlock_irqrestore(&iommu->register_lock, flag);
- return IRQ_HANDLED;
-}
-
-int dmar_set_interrupt(struct intel_iommu *iommu)
-{
- int irq, ret;
-
- irq = create_irq();
- if (!irq) {
- printk(KERN_ERR "IOMMU: no free vectors\n");
- return -EINVAL;
- }
-
- set_irq_data(irq, iommu);
- iommu->irq = irq;
-
- ret = arch_setup_dmar_msi(irq);
- if (ret) {
- set_irq_data(irq, NULL);
- iommu->irq = 0;
- destroy_irq(irq);
- return 0;
- }
-
- /* Force fault register is cleared */
- iommu_page_fault(irq, iommu);
-
- ret = request_irq(irq, iommu_page_fault, 0, iommu->name, iommu);
- if (ret)
- printk(KERN_ERR "IOMMU: can't request irq\n");
- return ret;
-}
static int iommu_init_domains(struct intel_iommu *iommu)
{
@@ -1987,7 +1799,7 @@ static int __init init_dmars(void)
struct dmar_rmrr_unit *rmrr;
struct pci_dev *pdev;
struct intel_iommu *iommu;
- int i, ret, unit = 0;
+ int i, ret;
/*
* for each drhd
@@ -2043,11 +1855,40 @@ static int __init init_dmars(void)
}
}
+ /*
+ * Start from the sane iommu hardware state.
+ */
for_each_drhd_unit(drhd) {
if (drhd->ignored)
continue;
iommu = drhd->iommu;
+
+ /*
+ * If the queued invalidation is already initialized by us
+ * (for example, while enabling interrupt-remapping) then
+ * we got the things already rolling from a sane state.
+ */
+ if (iommu->qi)
+ continue;
+
+ /*
+ * Clear any previous faults.
+ */
+ dmar_fault(-1, iommu);
+ /*
+ * Disable queued invalidation if supported and already enabled
+ * before OS handover.
+ */
+ dmar_disable_qi(iommu);
+ }
+
+ for_each_drhd_unit(drhd) {
+ if (drhd->ignored)
+ continue;
+
+ iommu = drhd->iommu;
+
if (dmar_enable_qi(iommu)) {
/*
* Queued Invalidate not enabled, use Register Based
@@ -2109,7 +1950,6 @@ static int __init init_dmars(void)
if (drhd->ignored)
continue;
iommu = drhd->iommu;
- sprintf (iommu->name, "dmar%d", unit++);
iommu_flush_write_buffer(iommu);
@@ -2284,11 +2124,13 @@ error:
return 0;
}
-dma_addr_t intel_map_single(struct device *hwdev, phys_addr_t paddr,
- size_t size, int dir)
+static dma_addr_t intel_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir,
+ struct dma_attrs *attrs)
{
- return __intel_map_single(hwdev, paddr, size, dir,
- to_pci_dev(hwdev)->dma_mask);
+ return __intel_map_single(dev, page_to_phys(page) + offset, size,
+ dir, to_pci_dev(dev)->dma_mask);
}
static void flush_unmaps(void)
@@ -2352,8 +2194,9 @@ static void add_unmap(struct dmar_domain *dom, struct iova *iova)
spin_unlock_irqrestore(&async_umap_flush_lock, flags);
}
-void intel_unmap_single(struct device *dev, dma_addr_t dev_addr, size_t size,
- int dir)
+static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr,
+ size_t size, enum dma_data_direction dir,
+ struct dma_attrs *attrs)
{
struct pci_dev *pdev = to_pci_dev(dev);
struct dmar_domain *domain;
@@ -2397,8 +2240,14 @@ void intel_unmap_single(struct device *dev, dma_addr_t dev_addr, size_t size,
}
}
-void *intel_alloc_coherent(struct device *hwdev, size_t size,
- dma_addr_t *dma_handle, gfp_t flags)
+static void intel_unmap_single(struct device *dev, dma_addr_t dev_addr, size_t size,
+ int dir)
+{
+ intel_unmap_page(dev, dev_addr, size, dir, NULL);
+}
+
+static void *intel_alloc_coherent(struct device *hwdev, size_t size,
+ dma_addr_t *dma_handle, gfp_t flags)
{
void *vaddr;
int order;
@@ -2421,8 +2270,8 @@ void *intel_alloc_coherent(struct device *hwdev, size_t size,
return NULL;
}
-void intel_free_coherent(struct device *hwdev, size_t size, void *vaddr,
- dma_addr_t dma_handle)
+static void intel_free_coherent(struct device *hwdev, size_t size, void *vaddr,
+ dma_addr_t dma_handle)
{
int order;
@@ -2435,8 +2284,9 @@ void intel_free_coherent(struct device *hwdev, size_t size, void *vaddr,
#define SG_ENT_VIRT_ADDRESS(sg) (sg_virt((sg)))
-void intel_unmap_sg(struct device *hwdev, struct scatterlist *sglist,
- int nelems, int dir)
+static void intel_unmap_sg(struct device *hwdev, struct scatterlist *sglist,
+ int nelems, enum dma_data_direction dir,
+ struct dma_attrs *attrs)
{
int i;
struct pci_dev *pdev = to_pci_dev(hwdev);
@@ -2493,8 +2343,8 @@ static int intel_nontranslate_map_sg(struct device *hddev,
return nelems;
}
-int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int nelems,
- int dir)
+static int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int nelems,
+ enum dma_data_direction dir, struct dma_attrs *attrs)
{
void *addr;
int i;
@@ -2574,13 +2424,19 @@ int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int nelems,
return nelems;
}
-static struct dma_mapping_ops intel_dma_ops = {
+static int intel_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+ return !dma_addr;
+}
+
+struct dma_map_ops intel_dma_ops = {
.alloc_coherent = intel_alloc_coherent,
.free_coherent = intel_free_coherent,
- .map_single = intel_map_single,
- .unmap_single = intel_unmap_single,
.map_sg = intel_map_sg,
.unmap_sg = intel_unmap_sg,
+ .map_page = intel_map_page,
+ .unmap_page = intel_unmap_page,
+ .mapping_error = intel_mapping_error,
};
static inline int iommu_domain_cache_init(void)
diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c
index 9d07a05d26f..b041a409f4a 100644
--- a/drivers/pci/intr_remapping.c
+++ b/drivers/pci/intr_remapping.c
@@ -117,21 +117,22 @@ int get_irte(int irq, struct irte *entry)
{
int index;
struct irq_2_iommu *irq_iommu;
+ unsigned long flags;
if (!entry)
return -1;
- spin_lock(&irq_2_ir_lock);
+ spin_lock_irqsave(&irq_2_ir_lock, flags);
irq_iommu = valid_irq_2_iommu(irq);
if (!irq_iommu) {
- spin_unlock(&irq_2_ir_lock);
+ spin_unlock_irqrestore(&irq_2_ir_lock, flags);
return -1;
}
index = irq_iommu->irte_index + irq_iommu->sub_handle;
*entry = *(irq_iommu->iommu->ir_table->base + index);
- spin_unlock(&irq_2_ir_lock);
+ spin_unlock_irqrestore(&irq_2_ir_lock, flags);
return 0;
}
@@ -141,6 +142,7 @@ int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
struct irq_2_iommu *irq_iommu;
u16 index, start_index;
unsigned int mask = 0;
+ unsigned long flags;
int i;
if (!count)
@@ -170,7 +172,7 @@ int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
return -1;
}
- spin_lock(&irq_2_ir_lock);
+ spin_lock_irqsave(&irq_2_ir_lock, flags);
do {
for (i = index; i < index + count; i++)
if (table->base[i].present)
@@ -182,7 +184,7 @@ int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
index = (index + count) % INTR_REMAP_TABLE_ENTRIES;
if (index == start_index) {
- spin_unlock(&irq_2_ir_lock);
+ spin_unlock_irqrestore(&irq_2_ir_lock, flags);
printk(KERN_ERR "can't allocate an IRTE\n");
return -1;
}
@@ -193,7 +195,7 @@ int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
irq_iommu = irq_2_iommu_alloc(irq);
if (!irq_iommu) {
- spin_unlock(&irq_2_ir_lock);
+ spin_unlock_irqrestore(&irq_2_ir_lock, flags);
printk(KERN_ERR "can't allocate irq_2_iommu\n");
return -1;
}
@@ -203,7 +205,7 @@ int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
irq_iommu->sub_handle = 0;
irq_iommu->irte_mask = mask;
- spin_unlock(&irq_2_ir_lock);
+ spin_unlock_irqrestore(&irq_2_ir_lock, flags);
return index;
}
@@ -223,30 +225,32 @@ int map_irq_to_irte_handle(int irq, u16 *sub_handle)
{
int index;
struct irq_2_iommu *irq_iommu;
+ unsigned long flags;
- spin_lock(&irq_2_ir_lock);
+ spin_lock_irqsave(&irq_2_ir_lock, flags);
irq_iommu = valid_irq_2_iommu(irq);
if (!irq_iommu) {
- spin_unlock(&irq_2_ir_lock);
+ spin_unlock_irqrestore(&irq_2_ir_lock, flags);
return -1;
}
*sub_handle = irq_iommu->sub_handle;
index = irq_iommu->irte_index;
- spin_unlock(&irq_2_ir_lock);
+ spin_unlock_irqrestore(&irq_2_ir_lock, flags);
return index;
}
int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
{
struct irq_2_iommu *irq_iommu;
+ unsigned long flags;
- spin_lock(&irq_2_ir_lock);
+ spin_lock_irqsave(&irq_2_ir_lock, flags);
irq_iommu = irq_2_iommu_alloc(irq);
if (!irq_iommu) {
- spin_unlock(&irq_2_ir_lock);
+ spin_unlock_irqrestore(&irq_2_ir_lock, flags);
printk(KERN_ERR "can't allocate irq_2_iommu\n");
return -1;
}
@@ -256,7 +260,7 @@ int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
irq_iommu->sub_handle = subhandle;
irq_iommu->irte_mask = 0;
- spin_unlock(&irq_2_ir_lock);
+ spin_unlock_irqrestore(&irq_2_ir_lock, flags);
return 0;
}
@@ -264,11 +268,12 @@ int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
int clear_irte_irq(int irq, struct intel_iommu *iommu, u16 index)
{
struct irq_2_iommu *irq_iommu;
+ unsigned long flags;
- spin_lock(&irq_2_ir_lock);
+ spin_lock_irqsave(&irq_2_ir_lock, flags);
irq_iommu = valid_irq_2_iommu(irq);
if (!irq_iommu) {
- spin_unlock(&irq_2_ir_lock);
+ spin_unlock_irqrestore(&irq_2_ir_lock, flags);
return -1;
}
@@ -277,7 +282,7 @@ int clear_irte_irq(int irq, struct intel_iommu *iommu, u16 index)
irq_iommu->sub_handle = 0;
irq_2_iommu(irq)->irte_mask = 0;
- spin_unlock(&irq_2_ir_lock);
+ spin_unlock_irqrestore(&irq_2_ir_lock, flags);
return 0;
}
@@ -289,11 +294,12 @@ int modify_irte(int irq, struct irte *irte_modified)
struct irte *irte;
struct intel_iommu *iommu;
struct irq_2_iommu *irq_iommu;
+ unsigned long flags;
- spin_lock(&irq_2_ir_lock);
+ spin_lock_irqsave(&irq_2_ir_lock, flags);
irq_iommu = valid_irq_2_iommu(irq);
if (!irq_iommu) {
- spin_unlock(&irq_2_ir_lock);
+ spin_unlock_irqrestore(&irq_2_ir_lock, flags);
return -1;
}
@@ -302,11 +308,11 @@ int modify_irte(int irq, struct irte *irte_modified)
index = irq_iommu->irte_index + irq_iommu->sub_handle;
irte = &iommu->ir_table->base[index];
- set_64bit((unsigned long *)irte, irte_modified->low | (1 << 1));
+ set_64bit((unsigned long *)irte, irte_modified->low);
__iommu_flush_cache(iommu, irte, sizeof(*irte));
rc = qi_flush_iec(iommu, index, 0);
- spin_unlock(&irq_2_ir_lock);
+ spin_unlock_irqrestore(&irq_2_ir_lock, flags);
return rc;
}
@@ -317,11 +323,12 @@ int flush_irte(int irq)
int index;
struct intel_iommu *iommu;
struct irq_2_iommu *irq_iommu;
+ unsigned long flags;
- spin_lock(&irq_2_ir_lock);
+ spin_lock_irqsave(&irq_2_ir_lock, flags);
irq_iommu = valid_irq_2_iommu(irq);
if (!irq_iommu) {
- spin_unlock(&irq_2_ir_lock);
+ spin_unlock_irqrestore(&irq_2_ir_lock, flags);
return -1;
}
@@ -330,7 +337,7 @@ int flush_irte(int irq)
index = irq_iommu->irte_index + irq_iommu->sub_handle;
rc = qi_flush_iec(iommu, index, irq_iommu->irte_mask);
- spin_unlock(&irq_2_ir_lock);
+ spin_unlock_irqrestore(&irq_2_ir_lock, flags);
return rc;
}
@@ -363,11 +370,12 @@ int free_irte(int irq)
struct irte *irte;
struct intel_iommu *iommu;
struct irq_2_iommu *irq_iommu;
+ unsigned long flags;
- spin_lock(&irq_2_ir_lock);
+ spin_lock_irqsave(&irq_2_ir_lock, flags);
irq_iommu = valid_irq_2_iommu(irq);
if (!irq_iommu) {
- spin_unlock(&irq_2_ir_lock);
+ spin_unlock_irqrestore(&irq_2_ir_lock, flags);
return -1;
}
@@ -378,7 +386,7 @@ int free_irte(int irq)
if (!irq_iommu->sub_handle) {
for (i = 0; i < (1 << irq_iommu->irte_mask); i++)
- set_64bit((unsigned long *)irte, 0);
+ set_64bit((unsigned long *)(irte + i), 0);
rc = qi_flush_iec(iommu, index, irq_iommu->irte_mask);
}
@@ -387,7 +395,7 @@ int free_irte(int irq)
irq_iommu->sub_handle = 0;
irq_iommu->irte_mask = 0;
- spin_unlock(&irq_2_ir_lock);
+ spin_unlock_irqrestore(&irq_2_ir_lock, flags);
return rc;
}
@@ -439,12 +447,12 @@ static int setup_intr_remapping(struct intel_iommu *iommu, int mode)
struct page *pages;
ir_table = iommu->ir_table = kzalloc(sizeof(struct ir_table),
- GFP_KERNEL);
+ GFP_ATOMIC);
if (!iommu->ir_table)
return -ENOMEM;
- pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, INTR_REMAP_PAGE_ORDER);
+ pages = alloc_pages(GFP_ATOMIC | __GFP_ZERO, INTR_REMAP_PAGE_ORDER);
if (!pages) {
printk(KERN_ERR "failed to allocate pages of order %d\n",
@@ -459,11 +467,55 @@ static int setup_intr_remapping(struct intel_iommu *iommu, int mode)
return 0;
}
+/*
+ * Disable Interrupt Remapping.
+ */
+static void disable_intr_remapping(struct intel_iommu *iommu)
+{
+ unsigned long flags;
+ u32 sts;
+
+ if (!ecap_ir_support(iommu->ecap))
+ return;
+
+ spin_lock_irqsave(&iommu->register_lock, flags);
+
+ sts = dmar_readq(iommu->reg + DMAR_GSTS_REG);
+ if (!(sts & DMA_GSTS_IRES))
+ goto end;
+
+ iommu->gcmd &= ~DMA_GCMD_IRE;
+ writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+
+ IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
+ readl, !(sts & DMA_GSTS_IRES), sts);
+
+end:
+ spin_unlock_irqrestore(&iommu->register_lock, flags);
+}
+
int __init enable_intr_remapping(int eim)
{
struct dmar_drhd_unit *drhd;
int setup = 0;
+ for_each_drhd_unit(drhd) {
+ struct intel_iommu *iommu = drhd->iommu;
+
+ /*
+ * Clear previous faults.
+ */
+ dmar_fault(-1, iommu);
+
+ /*
+ * Disable intr remapping and queued invalidation, if already
+ * enabled prior to OS handover.
+ */
+ disable_intr_remapping(iommu);
+
+ dmar_disable_qi(iommu);
+ }
+
/*
* check for the Interrupt-remapping support
*/
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 93eac142358..267de88551c 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -352,53 +352,60 @@ static int pci_legacy_suspend(struct device *dev, pm_message_t state)
{
struct pci_dev * pci_dev = to_pci_dev(dev);
struct pci_driver * drv = pci_dev->driver;
- int i = 0;
+
+ pci_dev->state_saved = false;
if (drv && drv->suspend) {
pci_power_t prev = pci_dev->current_state;
+ int error;
- pci_dev->state_saved = false;
-
- i = drv->suspend(pci_dev, state);
- suspend_report_result(drv->suspend, i);
- if (i)
- return i;
-
- if (pci_dev->state_saved)
- goto Fixup;
+ error = drv->suspend(pci_dev, state);
+ suspend_report_result(drv->suspend, error);
+ if (error)
+ return error;
- if (pci_dev->current_state != PCI_D0
+ if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0
&& pci_dev->current_state != PCI_UNKNOWN) {
WARN_ONCE(pci_dev->current_state != prev,
"PCI PM: Device state not saved by %pF\n",
drv->suspend);
- goto Fixup;
}
}
- pci_save_state(pci_dev);
- /*
- * This is for compatibility with existing code with legacy PM support.
- */
- pci_pm_set_unknown_state(pci_dev);
-
- Fixup:
pci_fixup_device(pci_fixup_suspend, pci_dev);
- return i;
+ return 0;
}
static int pci_legacy_suspend_late(struct device *dev, pm_message_t state)
{
struct pci_dev * pci_dev = to_pci_dev(dev);
struct pci_driver * drv = pci_dev->driver;
- int i = 0;
if (drv && drv->suspend_late) {
- i = drv->suspend_late(pci_dev, state);
- suspend_report_result(drv->suspend_late, i);
+ pci_power_t prev = pci_dev->current_state;
+ int error;
+
+ error = drv->suspend_late(pci_dev, state);
+ suspend_report_result(drv->suspend_late, error);
+ if (error)
+ return error;
+
+ if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0
+ && pci_dev->current_state != PCI_UNKNOWN) {
+ WARN_ONCE(pci_dev->current_state != prev,
+ "PCI PM: Device state not saved by %pF\n",
+ drv->suspend_late);
+ return 0;
+ }
}
- return i;
+
+ if (!pci_dev->state_saved)
+ pci_save_state(pci_dev);
+
+ pci_pm_set_unknown_state(pci_dev);
+
+ return 0;
}
static int pci_legacy_resume_early(struct device *dev)
@@ -423,6 +430,23 @@ static int pci_legacy_resume(struct device *dev)
/* Auxiliary functions used by the new power management framework */
+/**
+ * pci_restore_standard_config - restore standard config registers of PCI device
+ * @pci_dev: PCI device to handle
+ */
+static int pci_restore_standard_config(struct pci_dev *pci_dev)
+{
+ pci_update_current_state(pci_dev, PCI_UNKNOWN);
+
+ if (pci_dev->current_state != PCI_D0) {
+ int error = pci_set_power_state(pci_dev, PCI_D0);
+ if (error)
+ return error;
+ }
+
+ return pci_dev->state_saved ? pci_restore_state(pci_dev) : 0;
+}
+
static void pci_pm_default_resume_noirq(struct pci_dev *pci_dev)
{
pci_restore_standard_config(pci_dev);
@@ -443,7 +467,6 @@ static void pci_pm_default_suspend(struct pci_dev *pci_dev)
/* Disable non-bridge devices without PM support */
if (!pci_is_bridge(pci_dev))
pci_disable_enabled_device(pci_dev);
- pci_save_state(pci_dev);
}
static bool pci_has_legacy_pm_support(struct pci_dev *pci_dev)
@@ -493,13 +516,13 @@ static int pci_pm_suspend(struct device *dev)
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_suspend(dev, PMSG_SUSPEND);
+ pci_dev->state_saved = false;
+
if (!pm) {
pci_pm_default_suspend(pci_dev);
goto Fixup;
}
- pci_dev->state_saved = false;
-
if (pm->suspend) {
pci_power_t prev = pci_dev->current_state;
int error;
@@ -509,24 +532,14 @@ static int pci_pm_suspend(struct device *dev)
if (error)
return error;
- if (pci_dev->state_saved)
- goto Fixup;
-
- if (pci_dev->current_state != PCI_D0
+ if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0
&& pci_dev->current_state != PCI_UNKNOWN) {
WARN_ONCE(pci_dev->current_state != prev,
"PCI PM: State of device not saved by %pF\n",
pm->suspend);
- goto Fixup;
}
}
- if (!pci_dev->state_saved) {
- pci_save_state(pci_dev);
- if (!pci_is_bridge(pci_dev))
- pci_prepare_to_sleep(pci_dev);
- }
-
Fixup:
pci_fixup_device(pci_fixup_suspend, pci_dev);
@@ -536,21 +549,43 @@ static int pci_pm_suspend(struct device *dev)
static int pci_pm_suspend_noirq(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
- struct device_driver *drv = dev->driver;
- int error = 0;
+ struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_suspend_late(dev, PMSG_SUSPEND);
- if (drv && drv->pm && drv->pm->suspend_noirq) {
- error = drv->pm->suspend_noirq(dev);
- suspend_report_result(drv->pm->suspend_noirq, error);
+ if (!pm) {
+ pci_save_state(pci_dev);
+ return 0;
}
- if (!error)
- pci_pm_set_unknown_state(pci_dev);
+ if (pm->suspend_noirq) {
+ pci_power_t prev = pci_dev->current_state;
+ int error;
- return error;
+ error = pm->suspend_noirq(dev);
+ suspend_report_result(pm->suspend_noirq, error);
+ if (error)
+ return error;
+
+ if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0
+ && pci_dev->current_state != PCI_UNKNOWN) {
+ WARN_ONCE(pci_dev->current_state != prev,
+ "PCI PM: State of device not saved by %pF\n",
+ pm->suspend_noirq);
+ return 0;
+ }
+ }
+
+ if (!pci_dev->state_saved) {
+ pci_save_state(pci_dev);
+ if (!pci_is_bridge(pci_dev))
+ pci_prepare_to_sleep(pci_dev);
+ }
+
+ pci_pm_set_unknown_state(pci_dev);
+
+ return 0;
}
static int pci_pm_resume_noirq(struct device *dev)
@@ -617,13 +652,13 @@ static int pci_pm_freeze(struct device *dev)
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_suspend(dev, PMSG_FREEZE);
+ pci_dev->state_saved = false;
+
if (!pm) {
pci_pm_default_suspend(pci_dev);
return 0;
}
- pci_dev->state_saved = false;
-
if (pm->freeze) {
int error;
@@ -633,9 +668,6 @@ static int pci_pm_freeze(struct device *dev)
return error;
}
- if (!pci_dev->state_saved)
- pci_save_state(pci_dev);
-
return 0;
}
@@ -643,20 +675,25 @@ static int pci_pm_freeze_noirq(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
struct device_driver *drv = dev->driver;
- int error = 0;
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_suspend_late(dev, PMSG_FREEZE);
if (drv && drv->pm && drv->pm->freeze_noirq) {
+ int error;
+
error = drv->pm->freeze_noirq(dev);
suspend_report_result(drv->pm->freeze_noirq, error);
+ if (error)
+ return error;
}
- if (!error)
- pci_pm_set_unknown_state(pci_dev);
+ if (!pci_dev->state_saved)
+ pci_save_state(pci_dev);
- return error;
+ pci_pm_set_unknown_state(pci_dev);
+
+ return 0;
}
static int pci_pm_thaw_noirq(struct device *dev)
@@ -699,46 +736,56 @@ static int pci_pm_poweroff(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
- int error = 0;
if (pci_has_legacy_pm_support(pci_dev))
return pci_legacy_suspend(dev, PMSG_HIBERNATE);
+ pci_dev->state_saved = false;
+
if (!pm) {
pci_pm_default_suspend(pci_dev);
goto Fixup;
}
- pci_dev->state_saved = false;
-
if (pm->poweroff) {
+ int error;
+
error = pm->poweroff(dev);
suspend_report_result(pm->poweroff, error);
+ if (error)
+ return error;
}
- if (!pci_dev->state_saved && !pci_is_bridge(pci_dev))
- pci_prepare_to_sleep(pci_dev);
-
Fixup:
pci_fixup_device(pci_fixup_suspend, pci_dev);
- return error;
+ return 0;
}
static int pci_pm_poweroff_noirq(struct device *dev)
{
+ struct pci_dev *pci_dev = to_pci_dev(dev);
struct device_driver *drv = dev->driver;
- int error = 0;
if (pci_has_legacy_pm_support(to_pci_dev(dev)))
return pci_legacy_suspend_late(dev, PMSG_HIBERNATE);
- if (drv && drv->pm && drv->pm->poweroff_noirq) {
+ if (!drv || !drv->pm)
+ return 0;
+
+ if (drv->pm->poweroff_noirq) {
+ int error;
+
error = drv->pm->poweroff_noirq(dev);
suspend_report_result(drv->pm->poweroff_noirq, error);
+ if (error)
+ return error;
}
- return error;
+ if (!pci_dev->state_saved && !pci_is_bridge(pci_dev))
+ pci_prepare_to_sleep(pci_dev);
+
+ return 0;
}
static int pci_pm_restore_noirq(struct device *dev)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 6d6120007af..0195066251e 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -426,7 +426,6 @@ static inline int platform_pci_sleep_wake(struct pci_dev *dev, bool enable)
* given PCI device
* @dev: PCI device to handle.
* @state: PCI power state (D0, D1, D2, D3hot) to put the device into.
- * @wait: If 'true', wait for the device to change its power state
*
* RETURN VALUE:
* -EINVAL if the requested state is invalid.
@@ -435,12 +434,15 @@ static inline int platform_pci_sleep_wake(struct pci_dev *dev, bool enable)
* 0 if device already is in the requested state.
* 0 if device's power state has been successfully changed.
*/
-static int
-pci_raw_set_power_state(struct pci_dev *dev, pci_power_t state, bool wait)
+static int pci_raw_set_power_state(struct pci_dev *dev, pci_power_t state)
{
u16 pmcsr;
bool need_restore = false;
+ /* Check if we're already there */
+ if (dev->current_state == state)
+ return 0;
+
if (!dev->pm_cap)
return -EIO;
@@ -451,10 +453,7 @@ pci_raw_set_power_state(struct pci_dev *dev, pci_power_t state, bool wait)
* Can enter D0 from any state, but if we can only go deeper
* to sleep if we're already in a low power state
*/
- if (dev->current_state == state) {
- /* we're already there */
- return 0;
- } else if (state != PCI_D0 && dev->current_state <= PCI_D3cold
+ if (state != PCI_D0 && dev->current_state <= PCI_D3cold
&& dev->current_state > state) {
dev_err(&dev->dev, "invalid power transition "
"(from state %d to %d)\n", dev->current_state, state);
@@ -481,10 +480,8 @@ pci_raw_set_power_state(struct pci_dev *dev, pci_power_t state, bool wait)
break;
case PCI_UNKNOWN: /* Boot-up */
if ((pmcsr & PCI_PM_CTRL_STATE_MASK) == PCI_D3hot
- && !(pmcsr & PCI_PM_CTRL_NO_SOFT_RESET)) {
+ && !(pmcsr & PCI_PM_CTRL_NO_SOFT_RESET))
need_restore = true;
- wait = true;
- }
/* Fall-through: force to D0 */
default:
pmcsr = 0;
@@ -494,9 +491,6 @@ pci_raw_set_power_state(struct pci_dev *dev, pci_power_t state, bool wait)
/* enter specified state */
pci_write_config_word(dev, dev->pm_cap + PCI_PM_CTRL, pmcsr);
- if (!wait)
- return 0;
-
/* Mandatory power management transition delays */
/* see PCI PM 1.1 5.6.1 table 18 */
if (state == PCI_D3hot || dev->current_state == PCI_D3hot)
@@ -521,7 +515,7 @@ pci_raw_set_power_state(struct pci_dev *dev, pci_power_t state, bool wait)
if (need_restore)
pci_restore_bars(dev);
- if (wait && dev->bus->self)
+ if (dev->bus->self)
pcie_aspm_pm_state_change(dev->bus->self);
return 0;
@@ -546,6 +540,53 @@ void pci_update_current_state(struct pci_dev *dev, pci_power_t state)
}
/**
+ * pci_platform_power_transition - Use platform to change device power state
+ * @dev: PCI device to handle.
+ * @state: State to put the device into.
+ */
+static int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state)
+{
+ int error;
+
+ if (platform_pci_power_manageable(dev)) {
+ error = platform_pci_set_power_state(dev, state);
+ if (!error)
+ pci_update_current_state(dev, state);
+ } else {
+ error = -ENODEV;
+ /* Fall back to PCI_D0 if native PM is not supported */
+ pci_update_current_state(dev, PCI_D0);
+ }
+
+ return error;
+}
+
+/**
+ * __pci_start_power_transition - Start power transition of a PCI device
+ * @dev: PCI device to handle.
+ * @state: State to put the device into.
+ */
+static void __pci_start_power_transition(struct pci_dev *dev, pci_power_t state)
+{
+ if (state == PCI_D0)
+ pci_platform_power_transition(dev, PCI_D0);
+}
+
+/**
+ * __pci_complete_power_transition - Complete power transition of a PCI device
+ * @dev: PCI device to handle.
+ * @state: State to put the device into.
+ *
+ * This function should not be called directly by device drivers.
+ */
+int __pci_complete_power_transition(struct pci_dev *dev, pci_power_t state)
+{
+ return state > PCI_D0 ?
+ pci_platform_power_transition(dev, state) : -EINVAL;
+}
+EXPORT_SYMBOL_GPL(__pci_complete_power_transition);
+
+/**
* pci_set_power_state - Set the power state of a PCI device
* @dev: PCI device to handle.
* @state: PCI power state (D0, D1, D2, D3hot) to put the device into.
@@ -577,30 +618,21 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
*/
return 0;
- if (state == PCI_D0 && platform_pci_power_manageable(dev)) {
- /*
- * Allow the platform to change the state, for example via ACPI
- * _PR0, _PS0 and some such, but do not trust it.
- */
- int ret = platform_pci_set_power_state(dev, PCI_D0);
- if (!ret)
- pci_update_current_state(dev, PCI_D0);
- }
+ /* Check if we're already there */
+ if (dev->current_state == state)
+ return 0;
+
+ __pci_start_power_transition(dev, state);
+
/* This device is quirked not to be put into D3, so
don't put it in D3 */
if (state == PCI_D3hot && (dev->dev_flags & PCI_DEV_FLAGS_NO_D3))
return 0;
- error = pci_raw_set_power_state(dev, state, true);
+ error = pci_raw_set_power_state(dev, state);
- if (state > PCI_D0 && platform_pci_power_manageable(dev)) {
- /* Allow the platform to finalize the transition */
- int ret = platform_pci_set_power_state(dev, state);
- if (!ret) {
- pci_update_current_state(dev, state);
- error = 0;
- }
- }
+ if (!__pci_complete_power_transition(dev, state))
+ error = 0;
return error;
}
@@ -1231,7 +1263,7 @@ int pci_prepare_to_sleep(struct pci_dev *dev)
if (target_state == PCI_POWER_ERROR)
return -EIO;
- pci_enable_wake(dev, target_state, true);
+ pci_enable_wake(dev, target_state, device_may_wakeup(&dev->dev));
error = pci_set_power_state(dev, target_state);
@@ -1381,50 +1413,6 @@ void pci_allocate_cap_save_buffers(struct pci_dev *dev)
}
/**
- * pci_restore_standard_config - restore standard config registers of PCI device
- * @dev: PCI device to handle
- *
- * This function assumes that the device's configuration space is accessible.
- * If the device needs to be powered up, the function will wait for it to
- * change the state.
- */
-int pci_restore_standard_config(struct pci_dev *dev)
-{
- pci_power_t prev_state;
- int error;
-
- pci_update_current_state(dev, PCI_D0);
-
- prev_state = dev->current_state;
- if (prev_state == PCI_D0)
- goto Restore;
-
- error = pci_raw_set_power_state(dev, PCI_D0, false);
- if (error)
- return error;
-
- /*
- * This assumes that we won't get a bus in B2 or B3 from the BIOS, but
- * we've made this assumption forever and it appears to be universally
- * satisfied.
- */
- switch(prev_state) {
- case PCI_D3cold:
- case PCI_D3hot:
- mdelay(pci_pm_d3_delay);
- break;
- case PCI_D2:
- udelay(PCI_PM_D2_DELAY);
- break;
- }
-
- pci_update_current_state(dev, PCI_D0);
-
- Restore:
- return dev->state_saved ? pci_restore_state(dev) : 0;
-}
-
-/**
* pci_enable_ari - enable ARI forwarding if hardware support it
* @dev: the PCI device
*/
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 07c0aa5275e..149fff65891 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -49,7 +49,6 @@ extern void pci_disable_enabled_device(struct pci_dev *dev);
extern void pci_pm_init(struct pci_dev *dev);
extern void platform_pci_wakeup_init(struct pci_dev *dev);
extern void pci_allocate_cap_save_buffers(struct pci_dev *dev);
-extern int pci_restore_standard_config(struct pci_dev *dev);
static inline bool pci_is_bridge(struct pci_dev *pci_dev)
{