In powerPC, if Dynamic DMA Window is big enough, RAM is pre-mapped. To
determine the size of RAM, a PAPR+ property "ibm,lrdr-capacity" is used.
This OF property dictates what is the max size of RAM an LPAR can have,
including DR added memory.
In PowerPC, 16GB pages can be allocated at machine level and then
assigned to LPARs. These 16GB pages are added to LPAR memory at the time
of boot. The address range for these 16GB pages is above MAX RAM an LPAR
can have (ibm,lrdr-capacity). In the current implementation, these 16GB
pages are being excluded from pre-mapped TCEs. A driver can have DMA
buffers allocated from 16GB pages. This results in platform to raise an
EEH when DMA is attempted on buffers in 16GB memory range.
commit 6aa989ab2bd0 ("powerpc/pseries/iommu: memory notifier incorrectly
adds TCEs for pmemory")
Prior to the above patch, memblock_end_of_DRAM() was being used to
determine the MAX memory of an LPAR. This included 16GB pages as well.
The issue with using memblock_end_of_DRAM() is that when pmemory is
converted to RAM via daxctl command, the DDW engine will incorrectly try
to add TCEs for pmemory as well.
Below is the address distribution of RAM, 16GB pages and pmemory for an
LPAR with max memory of 256GB, memory allocated 64GB, 2 16GB pages and
assigned pmemory of 8GB.
RANGE SIZE STATE REMOVABLE BLOCK
0x0000000000000000-0x0000000fffffffff 64G online yes 0-255
0x0000004000000000-0x00000047ffffffff 32G online yes 1024-1151
cat /sys/bus/nd/devices/region0/resource
0x40100000000
cat /sys/bus/nd/devices/region0/size
8589934592
The approach to fix this problem is to revert back the code changes
introduced by the above patch and to stash away the MAX memory of an
LPAR, including 16GB pages, at the LPAR boot time. This value is then
used whenever TCEs are needed to be pre-mapped - enable_DDW() or,
iommu_mem_notifier()
Fixes: 6aa989ab2bd0 ("powerpc/pseries/iommu: memory notifier incorrectly adds
TCEs for pmemory")
Signed-off-by: Gaurav Batra <[email protected]>
---
arch/powerpc/platforms/pseries/iommu.c | 38 ++++++++++++++++++--------
1 file changed, 26 insertions(+), 12 deletions(-)
diff --git a/arch/powerpc/platforms/pseries/iommu.c
b/arch/powerpc/platforms/pseries/iommu.c
index 3e1f915fe4f6..e74954b7add6 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -69,6 +69,8 @@ static struct iommu_table *iommu_pseries_alloc_table(int node)
return tbl;
}
+static phys_addr_t pseries_ddw_max_ram;
+
#ifdef CONFIG_IOMMU_API
static struct iommu_table_group_ops spapr_tce_table_group_ops;
#endif
@@ -1285,15 +1287,19 @@ static LIST_HEAD(failed_ddw_pdn_list);
static phys_addr_t ddw_memory_hotplug_max(void)
{
- resource_size_t max_addr;
+ resource_size_t max_addr = memory_hotplug_max();
+ struct device_node *memory;
-#if defined(CONFIG_NUMA) && defined(CONFIG_MEMORY_HOTPLUG)
- max_addr = hot_add_drconf_memory_max();
-#else
- max_addr = memblock_end_of_DRAM();
-#endif
+ for_each_node_by_type(memory, "memory") {
+ struct resource res;
+
+ if (of_address_to_resource(memory, 0, &res))
+ continue;
- return max_addr;
+ max_addr = max_t(resource_size_t, max_addr, res.end + 1);
+ }
+
+ return max_addr;
}
/*
@@ -1446,7 +1452,7 @@ static struct property *ddw_property_create(const char
*propname, u32 liobn, u64
static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn, u64
dma_mask)
{
int len = 0, ret;
- int max_ram_len = order_base_2(ddw_memory_hotplug_max());
+ int max_ram_len = order_base_2(pseries_ddw_max_ram);
struct ddw_query_response query;
struct ddw_create_response create;
int page_shift;
@@ -1668,7 +1674,7 @@ static bool enable_ddw(struct pci_dev *dev, struct
device_node *pdn, u64 dma_mas
if (direct_mapping) {
/* DDW maps the whole partition, so enable direct DMA mapping */
- ret = walk_system_ram_range(0, ddw_memory_hotplug_max() >>
PAGE_SHIFT,
+ ret = walk_system_ram_range(0, pseries_ddw_max_ram >>
PAGE_SHIFT,
win64->value,
tce_setrange_multi_pSeriesLP_walk);
if (ret) {
dev_info(&dev->dev, "failed to map DMA window for %pOF:
%d\n",
@@ -2423,7 +2429,7 @@ static int iommu_mem_notifier(struct notifier_block *nb,
unsigned long action,
/* This notifier can get called when onlining persistent memory as well.
* TCEs are not pre-mapped for persistent memory. Persistent memory will
- * always be above ddw_memory_hotplug_max()
+ * always be above pseries_ddw_max_ram
*/
switch (action) {
@@ -2431,7 +2437,7 @@ static int iommu_mem_notifier(struct notifier_block *nb,
unsigned long action,
spin_lock(&dma_win_list_lock);
list_for_each_entry(window, &dma_win_list, list) {
if (window->direct && (arg->start_pfn << PAGE_SHIFT) <
- ddw_memory_hotplug_max()) {
+ pseries_ddw_max_ram) {
ret |=
tce_setrange_multi_pSeriesLP(arg->start_pfn,
arg->nr_pages, window->prop);
}
@@ -2444,7 +2450,7 @@ static int iommu_mem_notifier(struct notifier_block *nb,
unsigned long action,
spin_lock(&dma_win_list_lock);
list_for_each_entry(window, &dma_win_list, list) {
if (window->direct && (arg->start_pfn << PAGE_SHIFT) <
- ddw_memory_hotplug_max()) {
+ pseries_ddw_max_ram) {
ret |=
tce_clearrange_multi_pSeriesLP(arg->start_pfn,
arg->nr_pages, window->prop);
}
@@ -2532,6 +2538,14 @@ void __init iommu_init_early_pSeries(void)
register_memory_notifier(&iommu_mem_nb);
set_pci_dma_ops(&dma_iommu_ops);
+
+ /* During init determine the max memory an LPAR can have and set it.
This
+ * will be used for pre-mapping RAM in DDW. memblock_end_of_DRAM() can
+ * change during the running of LPAR - daxctl can add pmemory as
+ * "system-ram". This memory range should not be pre-mapped in DDW since
+ * the address of pmemory can be much higher than the DDW size.
+ */
+ pseries_ddw_max_ram = ddw_memory_hotplug_max();
}
static int __init disable_multitce(char *str)
base-commit: 6d35786de28116ecf78797a62b84e6bf3c45aa5a
--
2.39.3
