linux_dsm_epyc7002/arch/powerpc/platforms/pseries/papr_scm.c

525 lines
12 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
#define pr_fmt(fmt) "papr-scm: " fmt
#include <linux/of.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/ioport.h>
#include <linux/slab.h>
#include <linux/ndctl.h>
#include <linux/sched.h>
#include <linux/libnvdimm.h>
#include <linux/platform_device.h>
#include <linux/delay.h>
#include <asm/plpar_wrappers.h>
#define BIND_ANY_ADDR (~0ul)
#define PAPR_SCM_DIMM_CMD_MASK \
((1ul << ND_CMD_GET_CONFIG_SIZE) | \
(1ul << ND_CMD_GET_CONFIG_DATA) | \
(1ul << ND_CMD_SET_CONFIG_DATA))
struct papr_scm_priv {
struct platform_device *pdev;
struct device_node *dn;
uint32_t drc_index;
uint64_t blocks;
uint64_t block_size;
int metadata_size;
bool is_volatile;
uint64_t bound_addr;
struct nvdimm_bus_descriptor bus_desc;
struct nvdimm_bus *bus;
struct nvdimm *nvdimm;
struct resource res;
struct nd_region *region;
struct nd_interleave_set nd_set;
};
static int drc_pmem_bind(struct papr_scm_priv *p)
{
unsigned long ret[PLPAR_HCALL_BUFSIZE];
uint64_t saved = 0;
uint64_t token;
int64_t rc;
/*
* When the hypervisor cannot map all the requested memory in a single
* hcall it returns H_BUSY and we call again with the token until
* we get H_SUCCESS. Aborting the retry loop before getting H_SUCCESS
* leave the system in an undefined state, so we wait.
*/
token = 0;
do {
rc = plpar_hcall(H_SCM_BIND_MEM, ret, p->drc_index, 0,
p->blocks, BIND_ANY_ADDR, token);
token = ret[0];
if (!saved)
saved = ret[1];
cond_resched();
} while (rc == H_BUSY);
if (rc)
return rc;
p->bound_addr = saved;
dev_dbg(&p->pdev->dev, "bound drc 0x%x to %pR\n", p->drc_index, &p->res);
return rc;
}
static void drc_pmem_unbind(struct papr_scm_priv *p)
{
unsigned long ret[PLPAR_HCALL_BUFSIZE];
uint64_t token = 0;
int64_t rc;
dev_dbg(&p->pdev->dev, "unbind drc 0x%x\n", p->drc_index);
/* NB: unbind has the same retry requirements as drc_pmem_bind() */
do {
/* Unbind of all SCM resources associated with drcIndex */
rc = plpar_hcall(H_SCM_UNBIND_ALL, ret, H_UNBIND_SCOPE_DRC,
p->drc_index, token);
token = ret[0];
/* Check if we are stalled for some time */
if (H_IS_LONG_BUSY(rc)) {
msleep(get_longbusy_msecs(rc));
rc = H_BUSY;
} else if (rc == H_BUSY) {
cond_resched();
}
} while (rc == H_BUSY);
if (rc)
dev_err(&p->pdev->dev, "unbind error: %lld\n", rc);
else
dev_dbg(&p->pdev->dev, "unbind drc 0x%x complete\n",
p->drc_index);
return;
}
static int drc_pmem_query_n_bind(struct papr_scm_priv *p)
{
unsigned long start_addr;
unsigned long end_addr;
unsigned long ret[PLPAR_HCALL_BUFSIZE];
int64_t rc;
rc = plpar_hcall(H_SCM_QUERY_BLOCK_MEM_BINDING, ret,
p->drc_index, 0);
if (rc)
goto err_out;
start_addr = ret[0];
/* Make sure the full region is bound. */
rc = plpar_hcall(H_SCM_QUERY_BLOCK_MEM_BINDING, ret,
p->drc_index, p->blocks - 1);
if (rc)
goto err_out;
end_addr = ret[0];
if ((end_addr - start_addr) != ((p->blocks - 1) * p->block_size))
goto err_out;
p->bound_addr = start_addr;
dev_dbg(&p->pdev->dev, "bound drc 0x%x to %pR\n", p->drc_index, &p->res);
return rc;
err_out:
dev_info(&p->pdev->dev,
"Failed to query, trying an unbind followed by bind");
drc_pmem_unbind(p);
return drc_pmem_bind(p);
}
static int papr_scm_meta_get(struct papr_scm_priv *p,
struct nd_cmd_get_config_data_hdr *hdr)
{
unsigned long data[PLPAR_HCALL_BUFSIZE];
unsigned long offset, data_offset;
int len, read;
int64_t ret;
if ((hdr->in_offset + hdr->in_length) >= p->metadata_size)
return -EINVAL;
for (len = hdr->in_length; len; len -= read) {
data_offset = hdr->in_length - len;
offset = hdr->in_offset + data_offset;
if (len >= 8)
read = 8;
else if (len >= 4)
read = 4;
else if (len >= 2)
read = 2;
else
read = 1;
ret = plpar_hcall(H_SCM_READ_METADATA, data, p->drc_index,
offset, read);
if (ret == H_PARAMETER) /* bad DRC index */
return -ENODEV;
if (ret)
return -EINVAL; /* other invalid parameter */
switch (read) {
case 8:
*(uint64_t *)(hdr->out_buf + data_offset) = be64_to_cpu(data[0]);
break;
case 4:
*(uint32_t *)(hdr->out_buf + data_offset) = be32_to_cpu(data[0] & 0xffffffff);
break;
case 2:
*(uint16_t *)(hdr->out_buf + data_offset) = be16_to_cpu(data[0] & 0xffff);
break;
case 1:
*(uint8_t *)(hdr->out_buf + data_offset) = (data[0] & 0xff);
break;
}
}
return 0;
}
static int papr_scm_meta_set(struct papr_scm_priv *p,
struct nd_cmd_set_config_hdr *hdr)
{
unsigned long offset, data_offset;
int len, wrote;
unsigned long data;
__be64 data_be;
int64_t ret;
if ((hdr->in_offset + hdr->in_length) >= p->metadata_size)
return -EINVAL;
for (len = hdr->in_length; len; len -= wrote) {
data_offset = hdr->in_length - len;
offset = hdr->in_offset + data_offset;
if (len >= 8) {
data = *(uint64_t *)(hdr->in_buf + data_offset);
data_be = cpu_to_be64(data);
wrote = 8;
} else if (len >= 4) {
data = *(uint32_t *)(hdr->in_buf + data_offset);
data &= 0xffffffff;
data_be = cpu_to_be32(data);
wrote = 4;
} else if (len >= 2) {
data = *(uint16_t *)(hdr->in_buf + data_offset);
data &= 0xffff;
data_be = cpu_to_be16(data);
wrote = 2;
} else {
data_be = *(uint8_t *)(hdr->in_buf + data_offset);
data_be &= 0xff;
wrote = 1;
}
ret = plpar_hcall_norets(H_SCM_WRITE_METADATA, p->drc_index,
offset, data_be, wrote);
if (ret == H_PARAMETER) /* bad DRC index */
return -ENODEV;
if (ret)
return -EINVAL; /* other invalid parameter */
}
return 0;
}
int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
unsigned int cmd, void *buf, unsigned int buf_len, int *cmd_rc)
{
struct nd_cmd_get_config_size *get_size_hdr;
struct papr_scm_priv *p;
/* Only dimm-specific calls are supported atm */
if (!nvdimm)
return -EINVAL;
p = nvdimm_provider_data(nvdimm);
switch (cmd) {
case ND_CMD_GET_CONFIG_SIZE:
get_size_hdr = buf;
get_size_hdr->status = 0;
get_size_hdr->max_xfer = 8;
get_size_hdr->config_size = p->metadata_size;
*cmd_rc = 0;
break;
case ND_CMD_GET_CONFIG_DATA:
*cmd_rc = papr_scm_meta_get(p, buf);
break;
case ND_CMD_SET_CONFIG_DATA:
*cmd_rc = papr_scm_meta_set(p, buf);
break;
default:
return -EINVAL;
}
dev_dbg(&p->pdev->dev, "returned with cmd_rc = %d\n", *cmd_rc);
return 0;
}
static const struct attribute_group *region_attr_groups[] = {
&nd_region_attribute_group,
&nd_device_attribute_group,
&nd_mapping_attribute_group,
&nd_numa_attribute_group,
NULL,
};
static const struct attribute_group *bus_attr_groups[] = {
&nvdimm_bus_attribute_group,
NULL,
};
static const struct attribute_group *papr_scm_dimm_groups[] = {
&nvdimm_attribute_group,
&nd_device_attribute_group,
NULL,
};
powerpc/nvdimm: Pick nearby online node if the device node is not online Currently, nvdimm subsystem expects the device numa node for SCM device to be an online node. It also doesn't try to bring the device numa node online. Hence if we use a non-online numa node as device node we hit crashes like below. This is because we try to access uninitialized NODE_DATA in different code paths. cpu 0x0: Vector: 300 (Data Access) at [c0000000fac53170] pc: c0000000004bbc50: ___slab_alloc+0x120/0xca0 lr: c0000000004bc834: __slab_alloc+0x64/0xc0 sp: c0000000fac53400 msr: 8000000002009033 dar: 73e8 dsisr: 80000 current = 0xc0000000fabb6d80 paca = 0xc000000003870000 irqmask: 0x03 irq_happened: 0x01 pid = 7, comm = kworker/u16:0 Linux version 5.2.0-06234-g76bd729b2644 (kvaneesh@ltc-boston123) (gcc version 7.4.0 (Ubuntu 7.4.0-1ubuntu1~18.04.1)) #135 SMP Thu Jul 11 05:36:30 CDT 2019 enter ? for help [link register ] c0000000004bc834 __slab_alloc+0x64/0xc0 [c0000000fac53400] c0000000fac53480 (unreliable) [c0000000fac53500] c0000000004bc818 __slab_alloc+0x48/0xc0 [c0000000fac53560] c0000000004c30a0 __kmalloc_node_track_caller+0x3c0/0x6b0 [c0000000fac535d0] c000000000cfafe4 devm_kmalloc+0x74/0xc0 [c0000000fac53600] c000000000d69434 nd_region_activate+0x144/0x560 [c0000000fac536d0] c000000000d6b19c nd_region_probe+0x17c/0x370 [c0000000fac537b0] c000000000d6349c nvdimm_bus_probe+0x10c/0x230 [c0000000fac53840] c000000000cf3cc4 really_probe+0x254/0x4e0 [c0000000fac538d0] c000000000cf429c driver_probe_device+0x16c/0x1e0 [c0000000fac53950] c000000000cf0b44 bus_for_each_drv+0x94/0x130 [c0000000fac539b0] c000000000cf392c __device_attach+0xdc/0x200 [c0000000fac53a50] c000000000cf231c bus_probe_device+0x4c/0xf0 [c0000000fac53a90] c000000000ced268 device_add+0x528/0x810 [c0000000fac53b60] c000000000d62a58 nd_async_device_register+0x28/0xa0 [c0000000fac53bd0] c0000000001ccb8c async_run_entry_fn+0xcc/0x1f0 [c0000000fac53c50] c0000000001bcd9c process_one_work+0x46c/0x860 [c0000000fac53d20] c0000000001bd4f4 worker_thread+0x364/0x5f0 [c0000000fac53db0] c0000000001c7260 kthread+0x1b0/0x1c0 [c0000000fac53e20] c00000000000b954 ret_from_kernel_thread+0x5c/0x68 The patch tries to fix this by picking the nearest online node as the SCM node. This does have a problem of us losing the information that SCM node is equidistant from two other online nodes. If applications need to understand these fine-grained details we should express then like x86 does via /sys/devices/system/node/nodeX/accessY/initiators/ With the patch we get # numactl -H available: 2 nodes (0-1) node 0 cpus: node 0 size: 0 MB node 0 free: 0 MB node 1 cpus: 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 node 1 size: 130865 MB node 1 free: 129130 MB node distances: node 0 1 0: 10 20 1: 20 10 # cat /sys/bus/nd/devices/region0/numa_node 0 # dmesg | grep papr_scm [ 91.332305] papr_scm ibm,persistent-memory:ibm,pmemory@44104001: Region registered with target node 2 and online node 0 Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20190729095128.23707-1-aneesh.kumar@linux.ibm.com
2019-07-29 16:51:28 +07:00
static inline int papr_scm_node(int node)
{
int min_dist = INT_MAX, dist;
int nid, min_node;
if ((node == NUMA_NO_NODE) || node_online(node))
return node;
min_node = first_online_node;
for_each_online_node(nid) {
dist = node_distance(node, nid);
if (dist < min_dist) {
min_dist = dist;
min_node = nid;
}
}
return min_node;
}
static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
{
struct device *dev = &p->pdev->dev;
struct nd_mapping_desc mapping;
struct nd_region_desc ndr_desc;
unsigned long dimm_flags;
powerpc/nvdimm: Pick nearby online node if the device node is not online Currently, nvdimm subsystem expects the device numa node for SCM device to be an online node. It also doesn't try to bring the device numa node online. Hence if we use a non-online numa node as device node we hit crashes like below. This is because we try to access uninitialized NODE_DATA in different code paths. cpu 0x0: Vector: 300 (Data Access) at [c0000000fac53170] pc: c0000000004bbc50: ___slab_alloc+0x120/0xca0 lr: c0000000004bc834: __slab_alloc+0x64/0xc0 sp: c0000000fac53400 msr: 8000000002009033 dar: 73e8 dsisr: 80000 current = 0xc0000000fabb6d80 paca = 0xc000000003870000 irqmask: 0x03 irq_happened: 0x01 pid = 7, comm = kworker/u16:0 Linux version 5.2.0-06234-g76bd729b2644 (kvaneesh@ltc-boston123) (gcc version 7.4.0 (Ubuntu 7.4.0-1ubuntu1~18.04.1)) #135 SMP Thu Jul 11 05:36:30 CDT 2019 enter ? for help [link register ] c0000000004bc834 __slab_alloc+0x64/0xc0 [c0000000fac53400] c0000000fac53480 (unreliable) [c0000000fac53500] c0000000004bc818 __slab_alloc+0x48/0xc0 [c0000000fac53560] c0000000004c30a0 __kmalloc_node_track_caller+0x3c0/0x6b0 [c0000000fac535d0] c000000000cfafe4 devm_kmalloc+0x74/0xc0 [c0000000fac53600] c000000000d69434 nd_region_activate+0x144/0x560 [c0000000fac536d0] c000000000d6b19c nd_region_probe+0x17c/0x370 [c0000000fac537b0] c000000000d6349c nvdimm_bus_probe+0x10c/0x230 [c0000000fac53840] c000000000cf3cc4 really_probe+0x254/0x4e0 [c0000000fac538d0] c000000000cf429c driver_probe_device+0x16c/0x1e0 [c0000000fac53950] c000000000cf0b44 bus_for_each_drv+0x94/0x130 [c0000000fac539b0] c000000000cf392c __device_attach+0xdc/0x200 [c0000000fac53a50] c000000000cf231c bus_probe_device+0x4c/0xf0 [c0000000fac53a90] c000000000ced268 device_add+0x528/0x810 [c0000000fac53b60] c000000000d62a58 nd_async_device_register+0x28/0xa0 [c0000000fac53bd0] c0000000001ccb8c async_run_entry_fn+0xcc/0x1f0 [c0000000fac53c50] c0000000001bcd9c process_one_work+0x46c/0x860 [c0000000fac53d20] c0000000001bd4f4 worker_thread+0x364/0x5f0 [c0000000fac53db0] c0000000001c7260 kthread+0x1b0/0x1c0 [c0000000fac53e20] c00000000000b954 ret_from_kernel_thread+0x5c/0x68 The patch tries to fix this by picking the nearest online node as the SCM node. This does have a problem of us losing the information that SCM node is equidistant from two other online nodes. If applications need to understand these fine-grained details we should express then like x86 does via /sys/devices/system/node/nodeX/accessY/initiators/ With the patch we get # numactl -H available: 2 nodes (0-1) node 0 cpus: node 0 size: 0 MB node 0 free: 0 MB node 1 cpus: 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 node 1 size: 130865 MB node 1 free: 129130 MB node distances: node 0 1 0: 10 20 1: 20 10 # cat /sys/bus/nd/devices/region0/numa_node 0 # dmesg | grep papr_scm [ 91.332305] papr_scm ibm,persistent-memory:ibm,pmemory@44104001: Region registered with target node 2 and online node 0 Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20190729095128.23707-1-aneesh.kumar@linux.ibm.com
2019-07-29 16:51:28 +07:00
int target_nid, online_nid;
p->bus_desc.ndctl = papr_scm_ndctl;
p->bus_desc.module = THIS_MODULE;
p->bus_desc.of_node = p->pdev->dev.of_node;
p->bus_desc.attr_groups = bus_attr_groups;
p->bus_desc.provider_name = kstrdup(p->pdev->name, GFP_KERNEL);
if (!p->bus_desc.provider_name)
return -ENOMEM;
p->bus = nvdimm_bus_register(NULL, &p->bus_desc);
if (!p->bus) {
dev_err(dev, "Error creating nvdimm bus %pOF\n", p->dn);
return -ENXIO;
}
dimm_flags = 0;
set_bit(NDD_ALIASING, &dimm_flags);
p->nvdimm = nvdimm_create(p->bus, p, papr_scm_dimm_groups,
dimm_flags, PAPR_SCM_DIMM_CMD_MASK, 0, NULL);
if (!p->nvdimm) {
dev_err(dev, "Error creating DIMM object for %pOF\n", p->dn);
goto err;
}
if (nvdimm_bus_check_dimm_count(p->bus, 1))
goto err;
/* now add the region */
memset(&mapping, 0, sizeof(mapping));
mapping.nvdimm = p->nvdimm;
mapping.start = 0;
mapping.size = p->blocks * p->block_size; // XXX: potential overflow?
memset(&ndr_desc, 0, sizeof(ndr_desc));
ndr_desc.attr_groups = region_attr_groups;
powerpc/nvdimm: Pick nearby online node if the device node is not online Currently, nvdimm subsystem expects the device numa node for SCM device to be an online node. It also doesn't try to bring the device numa node online. Hence if we use a non-online numa node as device node we hit crashes like below. This is because we try to access uninitialized NODE_DATA in different code paths. cpu 0x0: Vector: 300 (Data Access) at [c0000000fac53170] pc: c0000000004bbc50: ___slab_alloc+0x120/0xca0 lr: c0000000004bc834: __slab_alloc+0x64/0xc0 sp: c0000000fac53400 msr: 8000000002009033 dar: 73e8 dsisr: 80000 current = 0xc0000000fabb6d80 paca = 0xc000000003870000 irqmask: 0x03 irq_happened: 0x01 pid = 7, comm = kworker/u16:0 Linux version 5.2.0-06234-g76bd729b2644 (kvaneesh@ltc-boston123) (gcc version 7.4.0 (Ubuntu 7.4.0-1ubuntu1~18.04.1)) #135 SMP Thu Jul 11 05:36:30 CDT 2019 enter ? for help [link register ] c0000000004bc834 __slab_alloc+0x64/0xc0 [c0000000fac53400] c0000000fac53480 (unreliable) [c0000000fac53500] c0000000004bc818 __slab_alloc+0x48/0xc0 [c0000000fac53560] c0000000004c30a0 __kmalloc_node_track_caller+0x3c0/0x6b0 [c0000000fac535d0] c000000000cfafe4 devm_kmalloc+0x74/0xc0 [c0000000fac53600] c000000000d69434 nd_region_activate+0x144/0x560 [c0000000fac536d0] c000000000d6b19c nd_region_probe+0x17c/0x370 [c0000000fac537b0] c000000000d6349c nvdimm_bus_probe+0x10c/0x230 [c0000000fac53840] c000000000cf3cc4 really_probe+0x254/0x4e0 [c0000000fac538d0] c000000000cf429c driver_probe_device+0x16c/0x1e0 [c0000000fac53950] c000000000cf0b44 bus_for_each_drv+0x94/0x130 [c0000000fac539b0] c000000000cf392c __device_attach+0xdc/0x200 [c0000000fac53a50] c000000000cf231c bus_probe_device+0x4c/0xf0 [c0000000fac53a90] c000000000ced268 device_add+0x528/0x810 [c0000000fac53b60] c000000000d62a58 nd_async_device_register+0x28/0xa0 [c0000000fac53bd0] c0000000001ccb8c async_run_entry_fn+0xcc/0x1f0 [c0000000fac53c50] c0000000001bcd9c process_one_work+0x46c/0x860 [c0000000fac53d20] c0000000001bd4f4 worker_thread+0x364/0x5f0 [c0000000fac53db0] c0000000001c7260 kthread+0x1b0/0x1c0 [c0000000fac53e20] c00000000000b954 ret_from_kernel_thread+0x5c/0x68 The patch tries to fix this by picking the nearest online node as the SCM node. This does have a problem of us losing the information that SCM node is equidistant from two other online nodes. If applications need to understand these fine-grained details we should express then like x86 does via /sys/devices/system/node/nodeX/accessY/initiators/ With the patch we get # numactl -H available: 2 nodes (0-1) node 0 cpus: node 0 size: 0 MB node 0 free: 0 MB node 1 cpus: 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 node 1 size: 130865 MB node 1 free: 129130 MB node distances: node 0 1 0: 10 20 1: 20 10 # cat /sys/bus/nd/devices/region0/numa_node 0 # dmesg | grep papr_scm [ 91.332305] papr_scm ibm,persistent-memory:ibm,pmemory@44104001: Region registered with target node 2 and online node 0 Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20190729095128.23707-1-aneesh.kumar@linux.ibm.com
2019-07-29 16:51:28 +07:00
target_nid = dev_to_node(&p->pdev->dev);
online_nid = papr_scm_node(target_nid);
ndr_desc.numa_node = online_nid;
ndr_desc.target_node = target_nid;
ndr_desc.res = &p->res;
ndr_desc.of_node = p->dn;
ndr_desc.provider_data = p;
ndr_desc.mapping = &mapping;
ndr_desc.num_mappings = 1;
ndr_desc.nd_set = &p->nd_set;
set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags);
if (p->is_volatile)
p->region = nvdimm_volatile_region_create(p->bus, &ndr_desc);
else
p->region = nvdimm_pmem_region_create(p->bus, &ndr_desc);
if (!p->region) {
dev_err(dev, "Error registering region %pR from %pOF\n",
ndr_desc.res, p->dn);
goto err;
}
powerpc/nvdimm: Pick nearby online node if the device node is not online Currently, nvdimm subsystem expects the device numa node for SCM device to be an online node. It also doesn't try to bring the device numa node online. Hence if we use a non-online numa node as device node we hit crashes like below. This is because we try to access uninitialized NODE_DATA in different code paths. cpu 0x0: Vector: 300 (Data Access) at [c0000000fac53170] pc: c0000000004bbc50: ___slab_alloc+0x120/0xca0 lr: c0000000004bc834: __slab_alloc+0x64/0xc0 sp: c0000000fac53400 msr: 8000000002009033 dar: 73e8 dsisr: 80000 current = 0xc0000000fabb6d80 paca = 0xc000000003870000 irqmask: 0x03 irq_happened: 0x01 pid = 7, comm = kworker/u16:0 Linux version 5.2.0-06234-g76bd729b2644 (kvaneesh@ltc-boston123) (gcc version 7.4.0 (Ubuntu 7.4.0-1ubuntu1~18.04.1)) #135 SMP Thu Jul 11 05:36:30 CDT 2019 enter ? for help [link register ] c0000000004bc834 __slab_alloc+0x64/0xc0 [c0000000fac53400] c0000000fac53480 (unreliable) [c0000000fac53500] c0000000004bc818 __slab_alloc+0x48/0xc0 [c0000000fac53560] c0000000004c30a0 __kmalloc_node_track_caller+0x3c0/0x6b0 [c0000000fac535d0] c000000000cfafe4 devm_kmalloc+0x74/0xc0 [c0000000fac53600] c000000000d69434 nd_region_activate+0x144/0x560 [c0000000fac536d0] c000000000d6b19c nd_region_probe+0x17c/0x370 [c0000000fac537b0] c000000000d6349c nvdimm_bus_probe+0x10c/0x230 [c0000000fac53840] c000000000cf3cc4 really_probe+0x254/0x4e0 [c0000000fac538d0] c000000000cf429c driver_probe_device+0x16c/0x1e0 [c0000000fac53950] c000000000cf0b44 bus_for_each_drv+0x94/0x130 [c0000000fac539b0] c000000000cf392c __device_attach+0xdc/0x200 [c0000000fac53a50] c000000000cf231c bus_probe_device+0x4c/0xf0 [c0000000fac53a90] c000000000ced268 device_add+0x528/0x810 [c0000000fac53b60] c000000000d62a58 nd_async_device_register+0x28/0xa0 [c0000000fac53bd0] c0000000001ccb8c async_run_entry_fn+0xcc/0x1f0 [c0000000fac53c50] c0000000001bcd9c process_one_work+0x46c/0x860 [c0000000fac53d20] c0000000001bd4f4 worker_thread+0x364/0x5f0 [c0000000fac53db0] c0000000001c7260 kthread+0x1b0/0x1c0 [c0000000fac53e20] c00000000000b954 ret_from_kernel_thread+0x5c/0x68 The patch tries to fix this by picking the nearest online node as the SCM node. This does have a problem of us losing the information that SCM node is equidistant from two other online nodes. If applications need to understand these fine-grained details we should express then like x86 does via /sys/devices/system/node/nodeX/accessY/initiators/ With the patch we get # numactl -H available: 2 nodes (0-1) node 0 cpus: node 0 size: 0 MB node 0 free: 0 MB node 1 cpus: 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 node 1 size: 130865 MB node 1 free: 129130 MB node distances: node 0 1 0: 10 20 1: 20 10 # cat /sys/bus/nd/devices/region0/numa_node 0 # dmesg | grep papr_scm [ 91.332305] papr_scm ibm,persistent-memory:ibm,pmemory@44104001: Region registered with target node 2 and online node 0 Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20190729095128.23707-1-aneesh.kumar@linux.ibm.com
2019-07-29 16:51:28 +07:00
if (target_nid != online_nid)
dev_info(dev, "Region registered with target node %d and online node %d",
target_nid, online_nid);
return 0;
err: nvdimm_bus_unregister(p->bus);
kfree(p->bus_desc.provider_name);
return -ENXIO;
}
static int papr_scm_probe(struct platform_device *pdev)
{
struct device_node *dn = pdev->dev.of_node;
u32 drc_index, metadata_size;
u64 blocks, block_size;
struct papr_scm_priv *p;
const char *uuid_str;
u64 uuid[2];
int rc;
/* check we have all the required DT properties */
if (of_property_read_u32(dn, "ibm,my-drc-index", &drc_index)) {
dev_err(&pdev->dev, "%pOF: missing drc-index!\n", dn);
return -ENODEV;
}
if (of_property_read_u64(dn, "ibm,block-size", &block_size)) {
dev_err(&pdev->dev, "%pOF: missing block-size!\n", dn);
return -ENODEV;
}
if (of_property_read_u64(dn, "ibm,number-of-blocks", &blocks)) {
dev_err(&pdev->dev, "%pOF: missing number-of-blocks!\n", dn);
return -ENODEV;
}
if (of_property_read_string(dn, "ibm,unit-guid", &uuid_str)) {
dev_err(&pdev->dev, "%pOF: missing unit-guid!\n", dn);
return -ENODEV;
}
p = kzalloc(sizeof(*p), GFP_KERNEL);
if (!p)
return -ENOMEM;
/* optional DT properties */
of_property_read_u32(dn, "ibm,metadata-size", &metadata_size);
p->dn = dn;
p->drc_index = drc_index;
p->block_size = block_size;
p->blocks = blocks;
p->is_volatile = !of_property_read_bool(dn, "ibm,cache-flush-required");
/* We just need to ensure that set cookies are unique across */
uuid_parse(uuid_str, (uuid_t *) uuid);
/*
* cookie1 and cookie2 are not really little endian
* we store a little endian representation of the
* uuid str so that we can compare this with the label
* area cookie irrespective of the endian config with which
* the kernel is built.
*/
p->nd_set.cookie1 = cpu_to_le64(uuid[0]);
p->nd_set.cookie2 = cpu_to_le64(uuid[1]);
/* might be zero */
p->metadata_size = metadata_size;
p->pdev = pdev;
/* request the hypervisor to bind this region to somewhere in memory */
rc = drc_pmem_bind(p);
/* If phyp says drc memory still bound then force unbound and retry */
if (rc == H_OVERLAP)
rc = drc_pmem_query_n_bind(p);
if (rc != H_SUCCESS) {
dev_err(&p->pdev->dev, "bind err: %d\n", rc);
rc = -ENXIO;
goto err;
}
/* setup the resource for the newly bound range */
p->res.start = p->bound_addr;
p->res.end = p->bound_addr + p->blocks * p->block_size - 1;
p->res.name = pdev->name;
p->res.flags = IORESOURCE_MEM;
rc = papr_scm_nvdimm_init(p);
if (rc)
goto err2;
platform_set_drvdata(pdev, p);
return 0;
err2: drc_pmem_unbind(p);
err: kfree(p);
return rc;
}
static int papr_scm_remove(struct platform_device *pdev)
{
struct papr_scm_priv *p = platform_get_drvdata(pdev);
nvdimm_bus_unregister(p->bus);
drc_pmem_unbind(p);
kfree(p);
return 0;
}
static const struct of_device_id papr_scm_match[] = {
{ .compatible = "ibm,pmemory" },
{ },
};
static struct platform_driver papr_scm_driver = {
.probe = papr_scm_probe,
.remove = papr_scm_remove,
.driver = {
.name = "papr_scm",
.owner = THIS_MODULE,
.of_match_table = papr_scm_match,
},
};
module_platform_driver(papr_scm_driver);
MODULE_DEVICE_TABLE(of, papr_scm_match);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("IBM Corporation");