* [PATCH kernel 1/2] Revert "dma-mapping: move large parts of <linux/dma-direct.h> to kernel/dma"
2020-10-21 3:20 [PATCH kernel 0/2] powerpc/dma: Fallback to dma_ops when persistent memory present Alexey Kardashevskiy
@ 2020-10-21 3:20 ` Alexey Kardashevskiy
2020-10-21 3:20 ` [PATCH kernel 2/2] powerpc/dma: Fallback to dma_ops when persistent memory present Alexey Kardashevskiy
2020-10-27 8:36 ` [PATCH kernel 0/2] " Christoph Hellwig
2 siblings, 0 replies; 4+ messages in thread
From: Alexey Kardashevskiy @ 2020-10-21 3:20 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Alexey Kardashevskiy, Christoph Hellwig, linux-kernel
This reverts commit 19c65c3d30bb5a97170e425979d2e44ab2096c7d which
was a right move but sadly there is a POWERPC/pseries hardware config
which uses a mixture of direct and IOMMU DMA but bringing this
logic to the generic code won't benefit anybody else. The user of
this revert comes in the next patch.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
include/linux/dma-direct.h | 106 +++++++++++++++++++++++++++++++++
kernel/dma/direct.h | 119 -------------------------------------
kernel/dma/direct.c | 2 +-
kernel/dma/mapping.c | 2 +-
4 files changed, 108 insertions(+), 121 deletions(-)
delete mode 100644 kernel/dma/direct.h
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 18aade195884..e388b77e0048 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -120,8 +120,114 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
void dma_direct_free_pages(struct device *dev, size_t size,
struct page *page, dma_addr_t dma_addr,
enum dma_data_direction dir);
+int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ unsigned long attrs);
+bool dma_direct_can_mmap(struct device *dev);
+int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ unsigned long attrs);
int dma_direct_supported(struct device *dev, u64 mask);
+bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr);
+int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
+ enum dma_data_direction dir, unsigned long attrs);
dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
size_t size, enum dma_data_direction dir, unsigned long attrs);
+size_t dma_direct_max_mapping_size(struct device *dev);
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
+ defined(CONFIG_SWIOTLB)
+void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
+ int nents, enum dma_data_direction dir);
+#else
+static inline void dma_direct_sync_sg_for_device(struct device *dev,
+ struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+}
+#endif
+
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
+ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
+ defined(CONFIG_SWIOTLB)
+void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
+ int nents, enum dma_data_direction dir, unsigned long attrs);
+void dma_direct_sync_sg_for_cpu(struct device *dev,
+ struct scatterlist *sgl, int nents, enum dma_data_direction dir);
+#else
+static inline void dma_direct_unmap_sg(struct device *dev,
+ struct scatterlist *sgl, int nents, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+}
+static inline void dma_direct_sync_sg_for_cpu(struct device *dev,
+ struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+}
+#endif
+
+static inline void dma_direct_sync_single_for_device(struct device *dev,
+ dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+ phys_addr_t paddr = dma_to_phys(dev, addr);
+
+ if (unlikely(is_swiotlb_buffer(paddr)))
+ swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);
+
+ if (!dev_is_dma_coherent(dev))
+ arch_sync_dma_for_device(paddr, size, dir);
+}
+
+static inline void dma_direct_sync_single_for_cpu(struct device *dev,
+ dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+ phys_addr_t paddr = dma_to_phys(dev, addr);
+
+ if (!dev_is_dma_coherent(dev)) {
+ arch_sync_dma_for_cpu(paddr, size, dir);
+ arch_sync_dma_for_cpu_all();
+ }
+
+ if (unlikely(is_swiotlb_buffer(paddr)))
+ swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
+
+ if (dir == DMA_FROM_DEVICE)
+ arch_dma_mark_clean(paddr, size);
+}
+
+static inline dma_addr_t dma_direct_map_page(struct device *dev,
+ struct page *page, unsigned long offset, size_t size,
+ enum dma_data_direction dir, unsigned long attrs)
+{
+ phys_addr_t phys = page_to_phys(page) + offset;
+ dma_addr_t dma_addr = phys_to_dma(dev, phys);
+
+ if (unlikely(swiotlb_force == SWIOTLB_FORCE))
+ return swiotlb_map(dev, phys, size, dir, attrs);
+
+ if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+ if (swiotlb_force != SWIOTLB_NO_FORCE)
+ return swiotlb_map(dev, phys, size, dir, attrs);
+
+ dev_WARN_ONCE(dev, 1,
+ "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+ &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
+ return DMA_MAPPING_ERROR;
+ }
+
+ if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+ arch_sync_dma_for_device(phys, size, dir);
+ return dma_addr;
+}
+
+static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
+ size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+ phys_addr_t phys = dma_to_phys(dev, addr);
+
+ if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+ dma_direct_sync_single_for_cpu(dev, addr, size, dir);
+
+ if (unlikely(is_swiotlb_buffer(phys)))
+ swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs);
+}
#endif /* _LINUX_DMA_DIRECT_H */
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
deleted file mode 100644
index b98615578737..000000000000
--- a/kernel/dma/direct.h
+++ /dev/null
@@ -1,119 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2018 Christoph Hellwig.
- *
- * DMA operations that map physical memory directly without using an IOMMU.
- */
-#ifndef _KERNEL_DMA_DIRECT_H
-#define _KERNEL_DMA_DIRECT_H
-
-#include <linux/dma-direct.h>
-
-int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
- void *cpu_addr, dma_addr_t dma_addr, size_t size,
- unsigned long attrs);
-bool dma_direct_can_mmap(struct device *dev);
-int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
- void *cpu_addr, dma_addr_t dma_addr, size_t size,
- unsigned long attrs);
-bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr);
-int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
- enum dma_data_direction dir, unsigned long attrs);
-size_t dma_direct_max_mapping_size(struct device *dev);
-
-#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
- defined(CONFIG_SWIOTLB)
-void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
- int nents, enum dma_data_direction dir);
-#else
-static inline void dma_direct_sync_sg_for_device(struct device *dev,
- struct scatterlist *sgl, int nents, enum dma_data_direction dir)
-{
-}
-#endif
-
-#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
- defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
- defined(CONFIG_SWIOTLB)
-void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
- int nents, enum dma_data_direction dir, unsigned long attrs);
-void dma_direct_sync_sg_for_cpu(struct device *dev,
- struct scatterlist *sgl, int nents, enum dma_data_direction dir);
-#else
-static inline void dma_direct_unmap_sg(struct device *dev,
- struct scatterlist *sgl, int nents, enum dma_data_direction dir,
- unsigned long attrs)
-{
-}
-static inline void dma_direct_sync_sg_for_cpu(struct device *dev,
- struct scatterlist *sgl, int nents, enum dma_data_direction dir)
-{
-}
-#endif
-
-static inline void dma_direct_sync_single_for_device(struct device *dev,
- dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
- phys_addr_t paddr = dma_to_phys(dev, addr);
-
- if (unlikely(is_swiotlb_buffer(paddr)))
- swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);
-
- if (!dev_is_dma_coherent(dev))
- arch_sync_dma_for_device(paddr, size, dir);
-}
-
-static inline void dma_direct_sync_single_for_cpu(struct device *dev,
- dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
- phys_addr_t paddr = dma_to_phys(dev, addr);
-
- if (!dev_is_dma_coherent(dev)) {
- arch_sync_dma_for_cpu(paddr, size, dir);
- arch_sync_dma_for_cpu_all();
- }
-
- if (unlikely(is_swiotlb_buffer(paddr)))
- swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
-
- if (dir == DMA_FROM_DEVICE)
- arch_dma_mark_clean(paddr, size);
-}
-
-static inline dma_addr_t dma_direct_map_page(struct device *dev,
- struct page *page, unsigned long offset, size_t size,
- enum dma_data_direction dir, unsigned long attrs)
-{
- phys_addr_t phys = page_to_phys(page) + offset;
- dma_addr_t dma_addr = phys_to_dma(dev, phys);
-
- if (unlikely(swiotlb_force == SWIOTLB_FORCE))
- return swiotlb_map(dev, phys, size, dir, attrs);
-
- if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
- if (swiotlb_force != SWIOTLB_NO_FORCE)
- return swiotlb_map(dev, phys, size, dir, attrs);
-
- dev_WARN_ONCE(dev, 1,
- "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
- &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
- return DMA_MAPPING_ERROR;
- }
-
- if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
- arch_sync_dma_for_device(phys, size, dir);
- return dma_addr;
-}
-
-static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
- size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
- phys_addr_t phys = dma_to_phys(dev, addr);
-
- if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
- dma_direct_sync_single_for_cpu(dev, addr, size, dir);
-
- if (unlikely(is_swiotlb_buffer(phys)))
- swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs);
-}
-#endif /* _KERNEL_DMA_DIRECT_H */
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 06c111544f61..cf281589cdc6 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -7,13 +7,13 @@
#include <linux/memblock.h> /* for max_pfn */
#include <linux/export.h>
#include <linux/mm.h>
+#include <linux/dma-direct.h>
#include <linux/dma-map-ops.h>
#include <linux/scatterlist.h>
#include <linux/pfn.h>
#include <linux/vmalloc.h>
#include <linux/set_memory.h>
#include <linux/slab.h>
-#include "direct.h"
/*
* Most architectures use ZONE_DMA for the first 16 Megabytes, but some use
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 51bb8fa8eb89..335ba183e095 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -7,6 +7,7 @@
*/
#include <linux/memblock.h> /* for max_pfn */
#include <linux/acpi.h>
+#include <linux/dma-direct.h>
#include <linux/dma-map-ops.h>
#include <linux/export.h>
#include <linux/gfp.h>
@@ -14,7 +15,6 @@
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include "debug.h"
-#include "direct.h"
/*
* Managed DMA API
--
2.17.1
^ permalink raw reply related [flat|nested] 4+ messages in thread* [PATCH kernel 2/2] powerpc/dma: Fallback to dma_ops when persistent memory present
2020-10-21 3:20 [PATCH kernel 0/2] powerpc/dma: Fallback to dma_ops when persistent memory present Alexey Kardashevskiy
2020-10-21 3:20 ` [PATCH kernel 1/2] Revert "dma-mapping: move large parts of <linux/dma-direct.h> to kernel/dma" Alexey Kardashevskiy
@ 2020-10-21 3:20 ` Alexey Kardashevskiy
2020-10-27 8:36 ` [PATCH kernel 0/2] " Christoph Hellwig
2 siblings, 0 replies; 4+ messages in thread
From: Alexey Kardashevskiy @ 2020-10-21 3:20 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Alexey Kardashevskiy, Christoph Hellwig, linux-kernel
So far we have been using huge DMA windows to map all the RAM available.
The RAM is normally mapped to the VM address space contiguously, and
there is always a reasonable upper limit for possible future hot plugged
RAM which makes it easy to map all RAM via IOMMU.
Now there is persistent memory ("ibm,pmemory" in the FDT) which (unlike
normal RAM) can map anywhere in the VM space beyond the maximum RAM size
and since it can be used for DMA, it requires extending the huge window
up to MAX_PHYSMEM_BITS which requires hypervisor support for:
1. huge TCE tables;
2. multilevel TCE tables;
3. huge IOMMU pages.
Certain hypervisors cannot do either so the only option left is
restricting the huge DMA window to include only RAM and fallback to
the default DMA window for persistent memory.
This checks if the system has persistent memory. If it does not,
the DMA bypass mode is selected, i.e.
* dev->bus_dma_limit = 0
* dev->dma_ops_bypass = true <- this avoid calling dma_ops for mapping.
If there is such memory, this creates identity mapping only for RAM and
disables the DMA bypass mode which makes generic DMA code use indirect
dma_ops which may have performance impact:
* dev->bus_dma_limit = bus_offset + max_ram_size
for example 0x0800.0000.8000.0000 for a 2GB VM
* dev->dma_ops_bypass = false <- this forces indirect calls to dma_ops for
every mapping which then directs these to small or huge window.
This should not change the existing behaviour when no persistent memory.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
Without reverting 19c65c3d30bb5a97170, I could have added
I can repost if this is preferrable. Thanks.
---
Changelog:
v2:
* rebased on current upstream with the device::bypass added and DMA
direct code movement reverted
---
arch/powerpc/kernel/dma-iommu.c | 68 +++++++++++++++++++++++++-
arch/powerpc/platforms/pseries/iommu.c | 41 +++++++++++++---
2 files changed, 99 insertions(+), 10 deletions(-)
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index a1c744194018..9a2a3b95f72d 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -10,6 +10,16 @@
#include <linux/pci.h>
#include <asm/iommu.h>
+static inline bool can_map_direct(struct device *dev, phys_addr_t addr)
+{
+ return dev->bus_dma_limit >= phys_to_dma(dev, addr);
+}
+
+static inline bool dma_handle_direct(struct device *dev, dma_addr_t dma_handle)
+{
+ return dma_handle >= dev->archdata.dma_offset;
+}
+
/*
* Generic iommu implementation
*/
@@ -44,6 +54,12 @@ static dma_addr_t dma_iommu_map_page(struct device *dev, struct page *page,
enum dma_data_direction direction,
unsigned long attrs)
{
+ if (dev->bus_dma_limit &&
+ can_map_direct(dev, (phys_addr_t) page_to_phys(page) +
+ offset + size))
+ return dma_direct_map_page(dev, page, offset, size, direction,
+ attrs);
+
return iommu_map_page(dev, get_iommu_table_base(dev), page, offset,
size, dma_get_mask(dev), direction, attrs);
}
@@ -53,6 +69,12 @@ static void dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle,
size_t size, enum dma_data_direction direction,
unsigned long attrs)
{
+ if (dev->bus_dma_limit &&
+ dma_handle_direct(dev, dma_handle + size)) {
+ dma_direct_unmap_page(dev, dma_handle, size, direction, attrs);
+ return;
+ }
+
iommu_unmap_page(get_iommu_table_base(dev), dma_handle, size, direction,
attrs);
}
@@ -62,6 +84,22 @@ static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
int nelems, enum dma_data_direction direction,
unsigned long attrs)
{
+ if (dev->bus_dma_limit) {
+ struct scatterlist *s;
+ bool direct = true;
+ int i;
+
+ for_each_sg(sglist, s, nelems, i) {
+ direct = can_map_direct(dev,
+ sg_phys(s) + s->offset + s->length);
+ if (!direct)
+ break;
+ }
+ if (direct)
+ return dma_direct_map_sg(dev, sglist, nelems, direction,
+ attrs);
+ }
+
return ppc_iommu_map_sg(dev, get_iommu_table_base(dev), sglist, nelems,
dma_get_mask(dev), direction, attrs);
}
@@ -70,6 +108,24 @@ static void dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist,
int nelems, enum dma_data_direction direction,
unsigned long attrs)
{
+ if (dev->bus_dma_limit) {
+ struct scatterlist *s;
+ bool direct = true;
+ int i;
+
+ for_each_sg(sglist, s, nelems, i) {
+ direct = dma_handle_direct(dev,
+ s->dma_address + s->length);
+ if (!direct)
+ break;
+ }
+ if (direct) {
+ dma_direct_unmap_sg(dev, sglist, nelems, direction,
+ attrs);
+ return;
+ }
+ }
+
ppc_iommu_unmap_sg(get_iommu_table_base(dev), sglist, nelems,
direction, attrs);
}
@@ -90,8 +146,16 @@ int dma_iommu_dma_supported(struct device *dev, u64 mask)
struct iommu_table *tbl = get_iommu_table_base(dev);
if (dev_is_pci(dev) && dma_iommu_bypass_supported(dev, mask)) {
- dev->dma_ops_bypass = true;
- dev_dbg(dev, "iommu: 64-bit OK, using fixed ops\n");
+ /*
+ * dma_iommu_bypass_supported() sets dma_max when there is
+ * 1:1 mapping but it is somehow limited.
+ * ibm,pmemory is one example.
+ */
+ dev->dma_ops_bypass = dev->bus_dma_limit == 0;
+ if (!dev->dma_ops_bypass)
+ dev_warn(dev, "iommu: 64-bit OK but using default ops\n");
+ else
+ dev_dbg(dev, "iommu: 64-bit OK, using fixed ops\n");
return 1;
}
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index e4198700ed1a..e6aa6c923666 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -839,7 +839,7 @@ static void remove_ddw(struct device_node *np, bool remove_prop)
np, ret);
}
-static u64 find_existing_ddw(struct device_node *pdn)
+static u64 find_existing_ddw(struct device_node *pdn, int *window_shift)
{
struct direct_window *window;
const struct dynamic_dma_window_prop *direct64;
@@ -851,6 +851,7 @@ static u64 find_existing_ddw(struct device_node *pdn)
if (window->device == pdn) {
direct64 = window->prop;
dma_addr = be64_to_cpu(direct64->dma_base);
+ *window_shift = be32_to_cpu(direct64->window_shift);
break;
}
}
@@ -1111,11 +1112,13 @@ static void reset_dma_window(struct pci_dev *dev, struct device_node *par_dn)
*/
static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
{
- int len, ret;
+ int len = 0, ret;
+ bool pmem_present = of_find_node_by_type(NULL, "ibm,pmemory") != NULL;
+ int max_ram_len = order_base_2(ddw_memory_hotplug_max());
struct ddw_query_response query;
struct ddw_create_response create;
int page_shift;
- u64 dma_addr, max_addr;
+ u64 dma_addr;
struct device_node *dn;
u32 ddw_avail[DDW_APPLICABLE_SIZE];
struct direct_window *window;
@@ -1126,7 +1129,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
mutex_lock(&direct_window_init_mutex);
- dma_addr = find_existing_ddw(pdn);
+ dma_addr = find_existing_ddw(pdn, &len);
if (dma_addr != 0)
goto out_unlock;
@@ -1212,14 +1215,27 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
}
/* verify the window * number of ptes will map the partition */
/* check largest block * page size > max memory hotplug addr */
- max_addr = ddw_memory_hotplug_max();
- if (query.largest_available_block < (max_addr >> page_shift)) {
+ /*
+ * The "ibm,pmemory" can appear anywhere in the address space.
+ * Assuming it is still backed by page structs, try MAX_PHYSMEM_BITS
+ * for the upper limit and fallback to max RAM otherwise but this
+ * disables device::dma_ops_bypass.
+ */
+ len = max_ram_len;
+ if (pmem_present) {
+ if (query.largest_available_block >=
+ (1ULL << (MAX_PHYSMEM_BITS - page_shift)))
+ len = MAX_PHYSMEM_BITS - page_shift;
+ else
+ dev_info(&dev->dev, "Skipping ibm,pmemory");
+ }
+
+ if (query.largest_available_block < (1ULL << (len - page_shift))) {
dev_dbg(&dev->dev, "can't map partition max 0x%llx with %llu "
- "%llu-sized pages\n", max_addr, query.largest_available_block,
+ "%llu-sized pages\n", 1ULL << len, query.largest_available_block,
1ULL << page_shift);
goto out_failed;
}
- len = order_base_2(max_addr);
win64 = kzalloc(sizeof(struct property), GFP_KERNEL);
if (!win64) {
dev_info(&dev->dev,
@@ -1299,6 +1315,15 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
out_unlock:
mutex_unlock(&direct_window_init_mutex);
+
+ /*
+ * If we have persistent memory and the window size is only as big
+ * as RAM, then we failed to create a window to cover persistent
+ * memory and need to set the DMA limit.
+ */
+ if (pmem_present && dma_addr && (len == max_ram_len))
+ dev->dev.bus_dma_limit = dma_addr + (1ULL << len);
+
return dma_addr;
}
--
2.17.1
^ permalink raw reply related [flat|nested] 4+ messages in thread