![Linus Torvalds](/assets/img/avatar_default.png)
Bart Van Assche noted that the ib DMA mapping code was significantly similar enough to the core DMA mapping code that with a few changes it was possible to remove the IB DMA mapping code entirely and switch the RDMA stack to use the core DMA mapping code. This resulted in a nice set of cleanups, but touched the entire tree. This branch will be submitted separately to Linus at the end of the merge window as per normal practice for tree wide changes like this. -----BEGIN PGP SIGNATURE----- iQIcBAABAgAGBQJYo06oAAoJELgmozMOVy/d9Z8QALedWHdu98St1L0u2c8sxnR9 2zo/4sF5Vb9u7FpmdIX32L4SQ9s9KhPE8Qp8NtZLf9v10zlDebIRJDpXknXtKooV CAXxX4sxBXV27/UrhbZEfXiPrmm6ccJFyIfRnMU6NlMqh2AtAsRa5AC2/RMp8oUD Med97PFiF0o6TD22/UH1VFbRpX1zjaKyqm7a3as5sJfzNA+UGIZAQ7Euz8000DKZ xCgVLTEwS0FmOujtBkCst7xa9TjuqR1HLOB4DdGvAhP6BHdz2yamM7Qmh9NN+NEX 0BtjsuXomtn6j6AszGC+bpipCZh3NUigcwoFAARXCYFHibBvo4DPdFeGsraFgXdy 1+KyR8CCeQG3Aly5Vwr264RFPGkGpwMj8PsBlXgQVtrlg4rriaCzOJNmIIbfdADw ftqhxBOzReZw77aH2s+9p2ILRfcAmPqhynLvFGFo9LBvsik8LVso7YgZN0xGxwcI IjI/XGC8UskPVsIZBIYA6sl2bYzgOjtBIHiXjRrPlW3uhduIXLrvKFfLPP/5XLAG ehLXK+J0bfsyY9ClmlNS8oH/WdLhXAyy/KNmnj5bRRm9qg6BRJR3bsOBhZJODuoC XgEXFfF6/7roNESWxowff7pK0rTkRg/m/Pa4VQpeO+6NWHE7kgZhL6kyIp5nKcwS 3e7mgpcwC+3XfA/6vU3F =e0Si -----END PGP SIGNATURE----- Merge tag 'for-next-dma_ops' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma Pull rdma DMA mapping updates from Doug Ledford: "Drop IB DMA mapping code and use core DMA code instead. Bart Van Assche noted that the ib DMA mapping code was significantly similar enough to the core DMA mapping code that with a few changes it was possible to remove the IB DMA mapping code entirely and switch the RDMA stack to use the core DMA mapping code. This resulted in a nice set of cleanups, but touched the entire tree and has been kept separate for that reason." * tag 'for-next-dma_ops' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (37 commits) IB/rxe, IB/rdmavt: Use dma_virt_ops instead of duplicating it IB/core: Remove ib_device.dma_device nvme-rdma: Switch from dma_device to dev.parent RDS: net: Switch from dma_device to dev.parent IB/srpt: Modify a debug statement IB/srp: Switch from dma_device to dev.parent IB/iser: Switch from dma_device to dev.parent IB/IPoIB: Switch from dma_device to dev.parent IB/rxe: Switch from dma_device to dev.parent IB/vmw_pvrdma: Switch from dma_device to dev.parent IB/usnic: Switch from dma_device to dev.parent IB/qib: Switch from dma_device to dev.parent IB/qedr: Switch from dma_device to dev.parent IB/ocrdma: Switch from dma_device to dev.parent IB/nes: Remove a superfluous assignment statement IB/mthca: Switch from dma_device to dev.parent IB/mlx5: Switch from dma_device to dev.parent IB/mlx4: Switch from dma_device to dev.parent IB/i40iw: Remove a superfluous assignment statement IB/hns: Switch from dma_device to dev.parent ...
290 lines
7.1 KiB
C
290 lines
7.1 KiB
C
#include <linux/dma-mapping.h>
|
|
#include <linux/dma-debug.h>
|
|
#include <linux/dmar.h>
|
|
#include <linux/export.h>
|
|
#include <linux/bootmem.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/pci.h>
|
|
#include <linux/kmemleak.h>
|
|
|
|
#include <asm/proto.h>
|
|
#include <asm/dma.h>
|
|
#include <asm/iommu.h>
|
|
#include <asm/gart.h>
|
|
#include <asm/calgary.h>
|
|
#include <asm/x86_init.h>
|
|
#include <asm/iommu_table.h>
|
|
|
|
static int forbid_dac __read_mostly;
|
|
|
|
const struct dma_map_ops *dma_ops = &nommu_dma_ops;
|
|
EXPORT_SYMBOL(dma_ops);
|
|
|
|
static int iommu_sac_force __read_mostly;
|
|
|
|
#ifdef CONFIG_IOMMU_DEBUG
|
|
int panic_on_overflow __read_mostly = 1;
|
|
int force_iommu __read_mostly = 1;
|
|
#else
|
|
int panic_on_overflow __read_mostly = 0;
|
|
int force_iommu __read_mostly = 0;
|
|
#endif
|
|
|
|
int iommu_merge __read_mostly = 0;
|
|
|
|
int no_iommu __read_mostly;
|
|
/* Set this to 1 if there is a HW IOMMU in the system */
|
|
int iommu_detected __read_mostly = 0;
|
|
|
|
/*
|
|
* This variable becomes 1 if iommu=pt is passed on the kernel command line.
|
|
* If this variable is 1, IOMMU implementations do no DMA translation for
|
|
* devices and allow every device to access to whole physical memory. This is
|
|
* useful if a user wants to use an IOMMU only for KVM device assignment to
|
|
* guests and not for driver dma translation.
|
|
*/
|
|
int iommu_pass_through __read_mostly;
|
|
|
|
extern struct iommu_table_entry __iommu_table[], __iommu_table_end[];
|
|
|
|
/* Dummy device used for NULL arguments (normally ISA). */
|
|
struct device x86_dma_fallback_dev = {
|
|
.init_name = "fallback device",
|
|
.coherent_dma_mask = ISA_DMA_BIT_MASK,
|
|
.dma_mask = &x86_dma_fallback_dev.coherent_dma_mask,
|
|
};
|
|
EXPORT_SYMBOL(x86_dma_fallback_dev);
|
|
|
|
/* Number of entries preallocated for DMA-API debugging */
|
|
#define PREALLOC_DMA_DEBUG_ENTRIES 65536
|
|
|
|
void __init pci_iommu_alloc(void)
|
|
{
|
|
struct iommu_table_entry *p;
|
|
|
|
sort_iommu_table(__iommu_table, __iommu_table_end);
|
|
check_iommu_entries(__iommu_table, __iommu_table_end);
|
|
|
|
for (p = __iommu_table; p < __iommu_table_end; p++) {
|
|
if (p && p->detect && p->detect() > 0) {
|
|
p->flags |= IOMMU_DETECTED;
|
|
if (p->early_init)
|
|
p->early_init();
|
|
if (p->flags & IOMMU_FINISH_IF_DETECTED)
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
void *dma_generic_alloc_coherent(struct device *dev, size_t size,
|
|
dma_addr_t *dma_addr, gfp_t flag,
|
|
unsigned long attrs)
|
|
{
|
|
unsigned long dma_mask;
|
|
struct page *page;
|
|
unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
|
|
dma_addr_t addr;
|
|
|
|
dma_mask = dma_alloc_coherent_mask(dev, flag);
|
|
|
|
flag &= ~__GFP_ZERO;
|
|
again:
|
|
page = NULL;
|
|
/* CMA can be used only in the context which permits sleeping */
|
|
if (gfpflags_allow_blocking(flag)) {
|
|
page = dma_alloc_from_contiguous(dev, count, get_order(size),
|
|
flag);
|
|
if (page && page_to_phys(page) + size > dma_mask) {
|
|
dma_release_from_contiguous(dev, page, count);
|
|
page = NULL;
|
|
}
|
|
}
|
|
/* fallback */
|
|
if (!page)
|
|
page = alloc_pages_node(dev_to_node(dev), flag, get_order(size));
|
|
if (!page)
|
|
return NULL;
|
|
|
|
addr = page_to_phys(page);
|
|
if (addr + size > dma_mask) {
|
|
__free_pages(page, get_order(size));
|
|
|
|
if (dma_mask < DMA_BIT_MASK(32) && !(flag & GFP_DMA)) {
|
|
flag = (flag & ~GFP_DMA32) | GFP_DMA;
|
|
goto again;
|
|
}
|
|
|
|
return NULL;
|
|
}
|
|
memset(page_address(page), 0, size);
|
|
*dma_addr = addr;
|
|
return page_address(page);
|
|
}
|
|
|
|
void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr,
|
|
dma_addr_t dma_addr, unsigned long attrs)
|
|
{
|
|
unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
|
|
struct page *page = virt_to_page(vaddr);
|
|
|
|
if (!dma_release_from_contiguous(dev, page, count))
|
|
free_pages((unsigned long)vaddr, get_order(size));
|
|
}
|
|
|
|
bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp)
|
|
{
|
|
if (!*dev)
|
|
*dev = &x86_dma_fallback_dev;
|
|
|
|
*gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
|
|
*gfp = dma_alloc_coherent_gfp_flags(*dev, *gfp);
|
|
|
|
if (!is_device_dma_capable(*dev))
|
|
return false;
|
|
return true;
|
|
|
|
}
|
|
EXPORT_SYMBOL(arch_dma_alloc_attrs);
|
|
|
|
/*
|
|
* See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel
|
|
* parameter documentation.
|
|
*/
|
|
static __init int iommu_setup(char *p)
|
|
{
|
|
iommu_merge = 1;
|
|
|
|
if (!p)
|
|
return -EINVAL;
|
|
|
|
while (*p) {
|
|
if (!strncmp(p, "off", 3))
|
|
no_iommu = 1;
|
|
/* gart_parse_options has more force support */
|
|
if (!strncmp(p, "force", 5))
|
|
force_iommu = 1;
|
|
if (!strncmp(p, "noforce", 7)) {
|
|
iommu_merge = 0;
|
|
force_iommu = 0;
|
|
}
|
|
|
|
if (!strncmp(p, "biomerge", 8)) {
|
|
iommu_merge = 1;
|
|
force_iommu = 1;
|
|
}
|
|
if (!strncmp(p, "panic", 5))
|
|
panic_on_overflow = 1;
|
|
if (!strncmp(p, "nopanic", 7))
|
|
panic_on_overflow = 0;
|
|
if (!strncmp(p, "merge", 5)) {
|
|
iommu_merge = 1;
|
|
force_iommu = 1;
|
|
}
|
|
if (!strncmp(p, "nomerge", 7))
|
|
iommu_merge = 0;
|
|
if (!strncmp(p, "forcesac", 8))
|
|
iommu_sac_force = 1;
|
|
if (!strncmp(p, "allowdac", 8))
|
|
forbid_dac = 0;
|
|
if (!strncmp(p, "nodac", 5))
|
|
forbid_dac = 1;
|
|
if (!strncmp(p, "usedac", 6)) {
|
|
forbid_dac = -1;
|
|
return 1;
|
|
}
|
|
#ifdef CONFIG_SWIOTLB
|
|
if (!strncmp(p, "soft", 4))
|
|
swiotlb = 1;
|
|
#endif
|
|
if (!strncmp(p, "pt", 2))
|
|
iommu_pass_through = 1;
|
|
|
|
gart_parse_options(p);
|
|
|
|
#ifdef CONFIG_CALGARY_IOMMU
|
|
if (!strncmp(p, "calgary", 7))
|
|
use_calgary = 1;
|
|
#endif /* CONFIG_CALGARY_IOMMU */
|
|
|
|
p += strcspn(p, ",");
|
|
if (*p == ',')
|
|
++p;
|
|
}
|
|
return 0;
|
|
}
|
|
early_param("iommu", iommu_setup);
|
|
|
|
int dma_supported(struct device *dev, u64 mask)
|
|
{
|
|
const struct dma_map_ops *ops = get_dma_ops(dev);
|
|
|
|
#ifdef CONFIG_PCI
|
|
if (mask > 0xffffffff && forbid_dac > 0) {
|
|
dev_info(dev, "PCI: Disallowing DAC for device\n");
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
if (ops->dma_supported)
|
|
return ops->dma_supported(dev, mask);
|
|
|
|
/* Copied from i386. Doesn't make much sense, because it will
|
|
only work for pci_alloc_coherent.
|
|
The caller just has to use GFP_DMA in this case. */
|
|
if (mask < DMA_BIT_MASK(24))
|
|
return 0;
|
|
|
|
/* Tell the device to use SAC when IOMMU force is on. This
|
|
allows the driver to use cheaper accesses in some cases.
|
|
|
|
Problem with this is that if we overflow the IOMMU area and
|
|
return DAC as fallback address the device may not handle it
|
|
correctly.
|
|
|
|
As a special case some controllers have a 39bit address
|
|
mode that is as efficient as 32bit (aic79xx). Don't force
|
|
SAC for these. Assume all masks <= 40 bits are of this
|
|
type. Normally this doesn't make any difference, but gives
|
|
more gentle handling of IOMMU overflow. */
|
|
if (iommu_sac_force && (mask >= DMA_BIT_MASK(40))) {
|
|
dev_info(dev, "Force SAC with mask %Lx\n", mask);
|
|
return 0;
|
|
}
|
|
|
|
return 1;
|
|
}
|
|
EXPORT_SYMBOL(dma_supported);
|
|
|
|
static int __init pci_iommu_init(void)
|
|
{
|
|
struct iommu_table_entry *p;
|
|
dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
|
|
|
|
#ifdef CONFIG_PCI
|
|
dma_debug_add_bus(&pci_bus_type);
|
|
#endif
|
|
x86_init.iommu.iommu_init();
|
|
|
|
for (p = __iommu_table; p < __iommu_table_end; p++) {
|
|
if (p && (p->flags & IOMMU_DETECTED) && p->late_init)
|
|
p->late_init();
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
/* Must execute after PCI subsystem */
|
|
rootfs_initcall(pci_iommu_init);
|
|
|
|
#ifdef CONFIG_PCI
|
|
/* Many VIA bridges seem to corrupt data for DAC. Disable it here */
|
|
|
|
static void via_no_dac(struct pci_dev *dev)
|
|
{
|
|
if (forbid_dac == 0) {
|
|
dev_info(&dev->dev, "disabling DAC on VIA PCI bridge\n");
|
|
forbid_dac = 1;
|
|
}
|
|
}
|
|
DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID,
|
|
PCI_CLASS_BRIDGE_PCI, 8, via_no_dac);
|
|
#endif
|