/*
* Copyright 2010
* by Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
*
* This code provides a IOMMU for Xen PV guests with PCI passthrough.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License v2.0 as published by
* the Free Software Foundation
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* PV guests under Xen are running in an non-contiguous memory architecture.
*
* When PCI pass-through is utilized, this necessitates an IOMMU for
* translating bus (DMA) to virtual and vice-versa and also providing a
* mechanism to have contiguous pages for device drivers operations (say DMA
* operations).
*
* Specifically, under Xen the Linux idea of pages is an illusion. It
* assumes that pages start at zero and go up to the available memory. To
* help with that, the Linux Xen MMU provides a lookup mechanism to
* translate the page frame numbers (PFN) to machine frame numbers (MFN)
* and vice-versa. The MFN are the "real" frame numbers. Furthermore
* memory is not contiguous. Xen hypervisor stitches memory for guests
* from different pools, which means there is no guarantee that PFN==MFN
* and PFN+1==MFN+1. Lastly with Xen 4.0, pages (in debug mode) are
* allocated in descending order (high to low), meaning the guest might
* never get any MFN's under the 4GB mark.
*
*/
#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
#include <linux/bootmem.h>
#include <linux/dma-mapping.h>
#include <linux/export.h>
#include <xen/swiotlb-xen.h>
#include <xen/page.h>
#include <xen/xen-ops.h>
#include <xen/hvc-console.h>
#include <asm/dma-mapping.h>
#include <asm/xen/page-coherent.h>
#include <trace/events/swiotlb.h>
/*
* Used to do a quick range check in swiotlb_tbl_unmap_single and
* swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this
* API.
*/
#ifndef CONFIG_X86
static unsigned long dma_alloc_coherent_mask(struct device *dev,
gfp_t gfp)
{
unsigned long dma_mask = 0;
dma_mask = dev->coherent_dma_mask;
if (!dma_mask)
dma_mask = (gfp & GFP_DMA) ? DMA_BIT_MASK(24) : DMA_BIT_MASK(32);
return dma_mask;
}
#endif
static char *xen_io_tlb_start, *xen_io_tlb_end;
static unsigned long xen_io_tlb_nslabs;
/*
* Quick lookup value of the bus address of the IOTLB.
*/
static u64 start_dma_addr;
/*
* Both of these functions should avoid PFN_PHYS because phys_addr_t
* can be 32bit when dma_addr_t is 64bit leading to a loss in
* information if the shift is done before casting to 64bit.
*/
static inline dma_addr_t xen_phys_to_bus(phys_addr_t paddr)
{
unsigned long mfn = pfn_to_mfn(PFN_DOWN(paddr));
dma_addr_t dma = (dma_addr_t)mfn << PAGE_SHIFT;
dma |= paddr & ~PAGE_MASK;
return dma;
}
static inline phys_addr_t xen_bus_to_phys(dma_addr_t baddr)
{
unsigned long pfn = mfn_to_pfn(PFN_DOWN(baddr));
dma_addr_t dma = (dma_addr_t)pfn << PAGE_SHIFT;
phys_addr_t paddr = dma;
paddr |= baddr & ~PAGE_MASK;
return paddr;
}
static inline dma_addr_t xen_virt_to_bus(void *address)
{
return xen_phys_to_bus(virt_to_phys(address));
}
static int check_pages_physically_contiguous(unsigned long pfn,
unsigned int offset,
size_t length)
{
unsigned long next_mfn;
int i;
int nr_pages;
next_mfn = pfn_to_mfn(pfn);
nr_pages = (offset + length + PAGE_SIZE-1) >> PAGE_SHIFT;
for (i = 1; i < nr_pages; i++) {
if (pfn_to_mfn(++pfn) != ++next_mfn)
return 0;
}
return 1;
}
static inline int range_straddles_page_boundary(phys_addr_t p, size_t size)
{
unsigned long pfn = PFN_DOWN(p);
unsigned int offset = p & ~PAGE_MASK;
if (offset + size <= PAGE_SIZE)
return 0;
if (check_pages_physically_contiguous(pfn, offset, size))
return 0;
return 1;
}
static int is_xen_swiotlb_buffer(dma_addr_t dma_addr)
{
unsigned long mfn = PFN_DOWN(dma_addr);
unsigned long pfn = mfn_to_local_pfn(mfn);
phys_addr_t paddr;
/* If the address is outside our domain, it CAN
* have the same virtual address as another address
* in our domain. Therefore _only_ check address within our domain.
*/
if (pfn_valid(pfn)) {
paddr = PFN_PHYS(pfn);
return paddr >= virt_to_phys(xen_io_tlb_start) &&
paddr < virt_to_phys(xen_io_tlb_end);
}
return 0;
}
static int max_dma_bits = 32;
static int
xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs)
{
int i, rc;
int dma_bits;
dma_addr_t dma_handle;
phys_addr_t p = virt_to_phys(buf);
dma_bits = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT) + PAGE_SHIFT;
i = 0;
do {
int slabs = min(nslabs - i, (unsigned long)IO_TLB_SEGSIZE);
do {
rc = xen_create_contiguous_region(
p + (i << IO_TLB_SHIFT),
get_order(slabs << IO_TLB_SHIFT),
dma_bits, &dma_handle);
} while (rc && dma_bits++ < max_dma_bits);
if (rc)
return rc;
i += slabs;
} while (i < nslabs);
return 0;
}
static unsigned long xen_set_nslabs(unsigned long nr_tbl)
{
if (!nr_tbl) {
xen_io_tlb_nslabs = (64 * 1024 * 1024 >> IO_TLB_SHIFT);
xen_io_tlb_nslabs = ALIGN(xen_io_tlb_nslabs, IO_TLB_SEGSIZE);
} else
xen_io_tlb_nslabs = nr_tbl;
return xen_io_tlb_nslabs << IO_TLB_SHIFT;
}
enum xen_swiotlb_err {
XEN_SWIOTLB_UNKNOWN = 0,
XEN_SWIOTLB_ENOMEM,
XEN_SWIOTLB_EFIXUP
};
static const char *xen_swiotlb_error(enum xen_swiotlb_err err)
{
switch (err) {
case XEN_SWIOTLB_ENOMEM:
return "Cannot allocate Xen-SWIOTLB buffer\n";
case XEN_SWIOTLB_EFIXUP:
return "Failed to get contiguous memory for DMA from Xen!\n"\
"You either: don't have the permissions, do not have"\
" enough free memory under 4GB, or the hypervisor memory"\
" is too fragmented!";
default:
break;
}
return "";
}
int __ref xen_swiotlb_init(int verbose, bool early)
{
unsigned long bytes, order;
int rc = -ENOMEM;
enum xen_swiotlb_err m_ret = XEN_SWIOTLB_UNKNOWN;
unsigned int repeat = 3;
xen_io_tlb_nslabs = swiotlb_nr_tbl();
retry:
bytes = xen_set_nslabs(xen_io_tlb_nslabs);
order = get_order(xen_io_tlb_nslabs << IO_TLB_SHIFT);
/*
* Get IO TLB memory from any location.
*/
if (early)
xen_io_tlb_start = alloc_bootmem_pages(PAGE_ALIGN(bytes));
else {
#define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT))
#define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT)
while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
xen_io_tlb_start = (void *)__get_free_pages(__GFP_NOWARN, order);
if (xen_io_tlb_start)
break;
order--;
}
if (order != get_order(bytes)) {
pr_warn("Warning: only able to allocate %ld MB for software IO TLB\n",
(PAGE_SIZE << order) >> 20);
xen_io_tlb_nslabs = SLABS_PER_PAGE << order;
bytes = xen_io_tlb_nslabs << IO_TLB_SHIFT;
}
}
if (!xen_io_tlb_start) {
m_ret = XEN_SWIOTLB_ENOMEM;
goto error;
}
xen_io_tlb_end = xen_io_tlb_start + bytes;
/*
* And replace that memory with pages under 4GB.
*/
rc = xen_swiotlb_fixup(xen_io_tlb_start,
bytes,
xen_io_tlb_nslabs);
if (rc) {
if (early)
free_bootmem(__pa(xen_io_tlb_start), PAGE_ALIGN(bytes));
else {
free_pages((unsigned long)xen_io_tlb_start, order);
xen_io_tlb_start = NULL;
}
m_ret = XEN_SWIOTLB_EFIXUP;
goto error;
}
start_dma_addr = xen_virt_to_bus(xen_io_tlb_start);
if (early) {
if (swiotlb_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs,
verbose))
panic("Cannot allocate SWIOTLB buffer");
rc = 0;
} else
rc = swiotlb_late_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs);
return rc;
error:
if (repeat--) {
xen_io_tlb_nslabs = max(1024UL, /* Min is 2MB */
(xen_io_tlb_nslabs >> 1));
pr_info("Lowering to %luMB\n",
(xen_io_tlb_nslabs << IO_TLB_SHIFT) >> 20);
goto retry;
}
pr_err("%s (rc:%d)\n", xen_swiotlb_error(m_ret), rc);
if (early)
panic("%s (rc:%d)", xen_swiotlb_error(m_ret), rc);
else
free_pages((unsigned long