s390/pci: Use dma-iommu layer

While s390 already has a standard IOMMU driver and previous changes have added I/O TLB flushing operations this driver is currently only used for user-space PCI access such as vfio-pci. For the DMA API s390 instead utilizes its own implementation in arch/s390/pci/pci_dma.c which drives the same hardware and shares some code but requires a complex and fragile hand over between DMA API and IOMMU API use of a device and despite code sharing still leads to significant duplication and maintenance effort. Let's utilize the common code DMAP API implementation from drivers/iommu/dma-iommu.c instead allowing us to get rid of arch/s390/pci/pci_dma.c. Reviewed-by: Matthew Rosato <[email protected]> Signed-off-by: Niklas Schnelle <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Joerg Roedel <[email protected]>
torvalds · Oct 2, 2023 · c76c067 · c76c067
1 parent b6f8887
commit c76c067
Show file tree

Hide file tree

Showing 13 changed files with 402 additions and 939 deletions.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
@@ -2220,7 +2220,7 @@
  forcing Dual Address Cycle for PCI cards supporting
  greater than 32-bit addressing.
 
- iommu.strict= [ARM64, X86] Configure TLB invalidation behaviour
+ iommu.strict= [ARM64, X86, S390] Configure TLB invalidation behaviour
  Format: { "0" | "1" }
  0 - Lazy mode.
  Request that DMA unmap operations use deferred
@@ -5611,9 +5611,10 @@
  s390_iommu= [HW,S390]
  Set s390 IOTLB flushing mode
  strict
- With strict flushing every unmap operation will result in
- an IOTLB flush. Default is lazy flushing before reuse,
- which is faster.
+ With strict flushing every unmap operation will result
+ in an IOTLB flush. Default is lazy flushing before
+ reuse, which is faster. Deprecated, equivalent to
+ iommu.strict=1.
 
  s390_iommu_aperture= [KNL,S390]
  Specifies the size of the per device DMA address space

diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
@@ -159,13 +159,6 @@ struct zpci_dev {
  unsigned long *dma_table;
  int tlb_refresh;
 
- spinlock_t iommu_bitmap_lock;
- unsigned long *iommu_bitmap;
- unsigned long *lazy_bitmap;
- unsigned long iommu_size;
- unsigned long iommu_pages;
- unsigned int next_bit;
-
  struct iommu_device iommu_dev; /* IOMMU core handle */
 
  char res_name[16];

diff --git a/arch/s390/include/asm/pci_clp.h b/arch/s390/include/asm/pci_clp.h
@@ -50,6 +50,9 @@ struct clp_fh_list_entry {
 #define CLP_UTIL_STR_LEN 64
 #define CLP_PFIP_NR_SEGMENTS 4
 
+/* PCI function type numbers */
+#define PCI_FUNC_TYPE_ISM 0x5 /* ISM device */
+
 extern bool zpci_unique_uid;
 
 struct clp_rsp_slpc_pci {

diff --git a/arch/s390/include/asm/pci_dma.h b/arch/s390/include/asm/pci_dma.h
@@ -82,117 +82,16 @@ enum zpci_ioat_dtype {
 #define ZPCI_TABLE_VALID_MASK 0x20
 #define ZPCI_TABLE_PROT_MASK 0x200
 
-static inline unsigned int calc_rtx(dma_addr_t ptr)
-{
- return ((unsigned long) ptr >> ZPCI_RT_SHIFT) & ZPCI_INDEX_MASK;
-}
-
-static inline unsigned int calc_sx(dma_addr_t ptr)
-{
- return ((unsigned long) ptr >> ZPCI_ST_SHIFT) & ZPCI_INDEX_MASK;
-}
-
-static inline unsigned int calc_px(dma_addr_t ptr)
-{
- return ((unsigned long) ptr >> PAGE_SHIFT) & ZPCI_PT_MASK;
-}
-
-static inline void set_pt_pfaa(unsigned long *entry, phys_addr_t pfaa)
-{
- *entry &= ZPCI_PTE_FLAG_MASK;
- *entry |= (pfaa & ZPCI_PTE_ADDR_MASK);
-}
-
-static inline void set_rt_sto(unsigned long *entry, phys_addr_t sto)
-{
- *entry &= ZPCI_RTE_FLAG_MASK;
- *entry |= (sto & ZPCI_RTE_ADDR_MASK);
- *entry |= ZPCI_TABLE_TYPE_RTX;
-}
-
-static inline void set_st_pto(unsigned long *entry, phys_addr_t pto)
-{
- *entry &= ZPCI_STE_FLAG_MASK;
- *entry |= (pto & ZPCI_STE_ADDR_MASK);
- *entry |= ZPCI_TABLE_TYPE_SX;
-}
-
-static inline void validate_rt_entry(unsigned long *entry)
-{
- *entry &= ~ZPCI_TABLE_VALID_MASK;
- *entry &= ~ZPCI_TABLE_OFFSET_MASK;
- *entry |= ZPCI_TABLE_VALID;
- *entry |= ZPCI_TABLE_LEN_RTX;
-}
-
-static inline void validate_st_entry(unsigned long *entry)
-{
- *entry &= ~ZPCI_TABLE_VALID_MASK;
- *entry |= ZPCI_TABLE_VALID;
-}
-
-static inline void invalidate_pt_entry(unsigned long *entry)
-{
- WARN_ON_ONCE((*entry & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_INVALID);
- *entry &= ~ZPCI_PTE_VALID_MASK;
- *entry |= ZPCI_PTE_INVALID;
-}
-
-static inline void validate_pt_entry(unsigned long *entry)
-{
- WARN_ON_ONCE((*entry & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID);
- *entry &= ~ZPCI_PTE_VALID_MASK;
- *entry |= ZPCI_PTE_VALID;
-}
-
-static inline void entry_set_protected(unsigned long *entry)
-{
- *entry &= ~ZPCI_TABLE_PROT_MASK;
- *entry |= ZPCI_TABLE_PROTECTED;
-}
-
-static inline void entry_clr_protected(unsigned long *entry)
-{
- *entry &= ~ZPCI_TABLE_PROT_MASK;
- *entry |= ZPCI_TABLE_UNPROTECTED;
-}
-
-static inline int reg_entry_isvalid(unsigned long entry)
-{
- return (entry & ZPCI_TABLE_VALID_MASK) == ZPCI_TABLE_VALID;
-}
-
-static inline int pt_entry_isvalid(unsigned long entry)
-{
- return (entry & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID;
-}
-
-static inline unsigned long *get_rt_sto(unsigned long entry)
-{
- if ((entry & ZPCI_TABLE_TYPE_MASK) == ZPCI_TABLE_TYPE_RTX)
- return phys_to_virt(entry & ZPCI_RTE_ADDR_MASK);
- else
- return NULL;
-
-}
-
-static inline unsigned long *get_st_pto(unsigned long entry)
-{
- if ((entry & ZPCI_TABLE_TYPE_MASK) == ZPCI_TABLE_TYPE_SX)
- return phys_to_virt(entry & ZPCI_STE_ADDR_MASK);
- else
- return NULL;
-}
-
-/* Prototypes */
-void dma_free_seg_table(unsigned long);
-unsigned long *dma_alloc_cpu_table(gfp_t gfp);
-void dma_cleanup_tables(unsigned long *);
-unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr,
- gfp_t gfp);
-void dma_update_cpu_trans(unsigned long *entry, phys_addr_t page_addr, int flags);
-
-extern const struct dma_map_ops s390_pci_dma_ops;
+struct zpci_iommu_ctrs {
+ atomic64_t mapped_pages;
+ atomic64_t unmapped_pages;
+ atomic64_t global_rpcits;
+ atomic64_t sync_map_rpcits;
+ atomic64_t sync_rpcits;
+};
+
+struct zpci_dev;
 
+struct zpci_iommu_ctrs *zpci_get_iommu_ctrs(struct zpci_dev *zdev);
 
 #endif
diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile
@@ -3,7 +3,7 @@
 # Makefile for the s390 PCI subsystem.
 #
 
-obj-$(CONFIG_PCI) += pci.o pci_irq.o pci_dma.o pci_clp.o pci_sysfs.o \
+obj-$(CONFIG_PCI) += pci.o pci_irq.o pci_clp.o pci_sysfs.o \
  pci_event.o pci_debug.o pci_insn.o pci_mmio.o \
  pci_bus.o pci_kvm_hook.o
 obj-$(CONFIG_PCI_IOV) += pci_iov.o
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
@@ -124,7 +124,11 @@ int zpci_register_ioat(struct zpci_dev *zdev, u8 dmaas,
 
  WARN_ON_ONCE(iota & 0x3fff);
  fib.pba = base;
- fib.pal = limit;
+ /* Work around off by one in ISM virt device */
+ if (zdev->pft == PCI_FUNC_TYPE_ISM && limit > base)
+ fib.pal = limit + (1 << 12);
+ else
+ fib.pal = limit;
  fib.iota = iota | ZPCI_IOTA_RTTO_FLAG;
  fib.gd = zdev->gisa;
  cc = zpci_mod_fc(req, &fib, status);
@@ -582,7 +586,6 @@ int pcibios_device_add(struct pci_dev *pdev)
  pdev->no_vf_scan = 1;
 
  pdev->dev.groups = zpci_attr_groups;
- pdev->dev.dma_ops = &s390_pci_dma_ops;
  zpci_map_resources(pdev);
 
  for (i = 0; i < PCI_STD_NUM_BARS; i++) {
@@ -756,8 +759,6 @@ int zpci_hot_reset_device(struct zpci_dev *zdev)
  if (zdev->dma_table)
  rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
  virt_to_phys(zdev->dma_table), &status);
- else
- rc = zpci_dma_init_device(zdev);
  if (rc) {
  zpci_disable_device(zdev);
  return rc;
@@ -865,11 +866,6 @@ int zpci_deconfigure_device(struct zpci_dev *zdev)
  if (zdev->zbus->bus)
  zpci_bus_remove_device(zdev, false);
 
- if (zdev->dma_table) {
- rc = zpci_dma_exit_device(zdev);
- if (rc)
- return rc;
- }
  if (zdev_enabled(zdev)) {
  rc = zpci_disable_device(zdev);
  if (rc)
@@ -918,8 +914,6 @@ void zpci_release_device(struct kref *kref)
  if (zdev->zbus->bus)
  zpci_bus_remove_device(zdev, false);
 
- if (zdev->dma_table)
- zpci_dma_exit_device(zdev);
  if (zdev_enabled(zdev))
  zpci_disable_device(zdev);
 
@@ -1109,10 +1103,6 @@ static int __init pci_base_init(void)
  if (rc)
  goto out_irq;
 
- rc = zpci_dma_init();
- if (rc)
- goto out_dma;
-
  rc = clp_scan_pci_devices();
  if (rc)
  goto out_find;
@@ -1122,8 +1112,6 @@ static int __init pci_base_init(void)
  return 0;
 
 out_find:
- zpci_dma_exit();
-out_dma:
  zpci_irq_exit();
 out_irq:
  zpci_mem_exit();

diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c
@@ -47,11 +47,6 @@ static int zpci_bus_prepare_device(struct zpci_dev *zdev)
  rc = zpci_enable_device(zdev);
  if (rc)
  return rc;
- rc = zpci_dma_init_device(zdev);
- if (rc) {
- zpci_disable_device(zdev);
- return rc;
- }
  }
 
  if (!zdev->has_resources) {

diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c
@@ -53,9 +53,11 @@ static char *pci_fmt3_names[] = {
 };
 
 static char *pci_sw_names[] = {
- "Allocated pages",
  "Mapped pages",
  "Unmapped pages",
+ "Global RPCITs",
+ "Sync Map RPCITs",
+ "Sync RPCITs",
 };
 
 static void pci_fmb_show(struct seq_file *m, char *name[], int length,
@@ -69,10 +71,14 @@ static void pci_fmb_show(struct seq_file *m, char *name[], int length,
 
 static void pci_sw_counter_show(struct seq_file *m)
 {
- struct zpci_dev *zdev = m->private;
- atomic64_t *counter = &zdev->allocated_pages;
+ struct zpci_iommu_ctrs *ctrs = zpci_get_iommu_ctrs(m->private);
+ atomic64_t *counter;
  int i;
 
+ if (!ctrs)
+ return;
+
+ counter = &ctrs->mapped_pages;
  for (i = 0; i < ARRAY_SIZE(pci_sw_names); i++, counter++)
  seq_printf(m, "%26s:\t%llu\n", pci_sw_names[i],
  atomic64_read(counter));