s390/pci: Implement ioremap_wc/prot() with MIO

With our current support for the new MIO PCI instructions, write
combining/write back MMIO memory can be obtained via the pci_iomap_wc()
and pci_iomap_wc_range() functions.
This is achieved by using the write back address for a specific bar
as provided in clp_store_query_pci_fn()

These functions are however not widely used and instead drivers often
rely on ioremap_wc() and ioremap_prot(), which on other platforms enable
write combining using a PTE flag set through the pgrprot value.

While we do not have a write combining flag in the low order flag bits
of the PTE like x86_64 does, with MIO support, there is a write back bit
in the physical address (bit 1 on z15) and thus also the PTE.
Which bit is used to toggle write back and whether it is available at
all, is however not fixed in the architecture. Instead we get this
information from the CLP Store Logical Processor Characteristics for PCI
command. When the write back bit is not provided we fall back to the
existing behavior.

Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com>
Reviewed-by: Pierre Morel <pmorel@linux.ibm.com>
Reviewed-by: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>

2 files changed, 63 insertions, 3 deletions

diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 4b62d6b55024..fdbb99c4569d 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -226,7 +226,7 @@ void __iowrite64_copy(void __iomem *to, const void *from, size_t count)
        zpci_memcpy_toio(to, from, count);
 }
 
-void __iomem *ioremap(phys_addr_t addr, size_t size)
+static void __iomem *__ioremap(phys_addr_t addr, size_t size, pgprot_t prot)
 {
 	unsigned long offset, vaddr;
 	struct vm_struct *area;
@@ -247,14 +247,37 @@ void __iomem *ioremap(phys_addr_t addr, size_t size)
 		return NULL;
 
 	vaddr = (unsigned long) area->addr;
-	if (ioremap_page_range(vaddr, vaddr + size, addr, PAGE_KERNEL)) {
+	if (ioremap_page_range(vaddr, vaddr + size, addr, prot)) {
 		free_vm_area(area);
 		return NULL;
 	}
 	return (void __iomem *) ((unsigned long) area->addr + offset);
 }
+
+void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long prot)
+{
+	return __ioremap(addr, size, __pgprot(prot));
+}
+EXPORT_SYMBOL(ioremap_prot);
+
+void __iomem *ioremap(phys_addr_t addr, size_t size)
+{
+	return __ioremap(addr, size, PAGE_KERNEL);
+}
 EXPORT_SYMBOL(ioremap);
 
+void __iomem *ioremap_wc(phys_addr_t addr, size_t size)
+{
+	return __ioremap(addr, size, pgprot_writecombine(PAGE_KERNEL));
+}
+EXPORT_SYMBOL(ioremap_wc);
+
+void __iomem *ioremap_wt(phys_addr_t addr, size_t size)
+{
+	return __ioremap(addr, size, pgprot_writethrough(PAGE_KERNEL));
+}
+EXPORT_SYMBOL(ioremap_wt);
+
 void iounmap(volatile void __iomem *addr)
 {
 	if (static_branch_likely(&have_mio))
@@ -784,6 +807,9 @@ static int zpci_mem_init(void)
 	if (!zpci_iomap_bitmap)
 		goto error_iomap_bitmap;
 
+	if (static_branch_likely(&have_mio))
+		clp_setup_writeback_mio();
+
 	return 0;
 error_iomap_bitmap:
 	kfree(zpci_iomap_start);
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index 7e735f41a0a6..51807945ca00 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -292,6 +292,40 @@ static int clp_set_pci_fn(struct zpci_dev *zdev, u8 nr_dma_as, u8 command)
 	return rc;
 }
 
+int clp_setup_writeback_mio(void)
+{
+	struct clp_req_rsp_slpc_pci *rrb;
+	u8  wb_bit_pos;
+	int rc;
+
+	rrb = clp_alloc_block(GFP_KERNEL);
+	if (!rrb)
+		return -ENOMEM;
+
+	memset(rrb, 0, sizeof(*rrb));
+	rrb->request.hdr.len = sizeof(rrb->request);
+	rrb->request.hdr.cmd = CLP_SLPC;
+	rrb->response.hdr.len = sizeof(rrb->response);
+
+	rc = clp_req(rrb, CLP_LPS_PCI);
+	if (!rc && rrb->response.hdr.rsp == CLP_RC_OK) {
+		if (rrb->response.vwb) {
+			wb_bit_pos = rrb->response.mio_wb;
+			set_bit_inv(wb_bit_pos, &mio_wb_bit_mask);
+			zpci_dbg(3, "wb bit: %d\n", wb_bit_pos);
+		} else {
+			zpci_dbg(3, "wb bit: n.a.\n");
+		}
+
+	} else {
+		zpci_err("SLPC PCI:\n");
+		zpci_err_clp(rrb->response.hdr.rsp, rc);
+		rc = -EIO;
+	}
+	clp_free_block(rrb);
+	return rc;
+}
+
 int clp_enable_fh(struct zpci_dev *zdev, u8 nr_dma_as)
 {
 	int rc;
@@ -495,7 +529,7 @@ static int clp_base_command(struct clp_req *req, struct clp_req_hdr *lpcb)
 	}
 }
 
-static int clp_pci_slpc(struct clp_req *req, struct clp_req_rsp_slpc *lpcb)
+static int clp_pci_slpc(struct clp_req *req, struct clp_req_rsp_slpc_pci *lpcb)
 {
 	unsigned long limit = PAGE_SIZE - sizeof(lpcb->request);