On 10/09/2018 03:37 PM, Michael Bringmann wrote:
> migration/memory: This patch adds code that recognizes changes to
> the associativity of memory blocks described by the device-tree
> properties in order to drive equivalent 'hotplug' operations to
> update local and general kernel data structures to reflect those
> changes. These differences may include:
>
> * Evaluate 'ibm,dynamic-memory' properties when processing the
> updated device-tree properties of the system during Post Migration
> events (migration_store). The new functionality looks for changes
> to the aa_index values for each drc_index/LMB to identify any memory
> blocks that should be readded.
>
> * In an LPAR migration scenario, the "ibm,associativity-lookup-arrays"
> property may change. In the event that a row of the array differs,
> locate all assigned memory blocks with that 'aa_index' and 're-add'
> them to the system memory block data structures. In the process of
> the 're-add', the system routines will update the corresponding entry
> for the memory in the LMB structures and any other relevant kernel
> data structures.
>
> A number of previous extensions made to the DRMEM code for scanning
> device-tree properties and creating LMB arrays are used here to
> ensure that the resulting code is simpler and more usable:
>
> * Use new paired list iterator for the DRMEM LMB info arrays to find
> differences in old and new versions of properties.
> * Use new iterator for copies of the DRMEM info arrays to evaluate
> completely new structures.
> * Combine common code for parsing and evaluating memory description
> properties based on the DRMEM LMB array model to greatly simplify
> extension from the older property 'ibm,dynamic-memory' to the new
> property model of 'ibm,dynamic-memory-v2'.
>
> For support, add a new pseries hotplug action for DLPAR operations,
> PSERIES_HP_ELOG_ACTION_READD_MULTIPLE. It is a variant of the READD
> operation which performs the action upon multiple instances of the
> resource at one time. The operation is to be triggered by device-tree
> analysis of updates by RTAS events analyzed by 'migation_store' during
> post-migration processing. It will be used for memory updates,
> initially.
>
> Signed-off-by: Michael Bringmann <m...@linux.vnet.ibm.com>
> ---
> Changes in v04:
> -- Move dlpar_memory_readd_multiple() function definition and use
> into previous patch along with action constant definition.
> -- Correct spacing in patch
> Changes in v03:
> -- Modify the code that parses the memory affinity attributes to
> mark relevant DRMEM LMB array entries using the internal_flags
> mechanism instead of generate unique hotplug actions for each
> memory block to be readded. The change is intended to both
> simplify the code, and to require fewer resources on systems
> with huge amounts of memory.
> -- Save up notice about any all LMB entries until the end of the
> 'migration_store' operation at which point a single action is
> queued to scan the entire DRMEM array.
> -- Add READD_MULTIPLE function for memory that scans the DRMEM
> array to identify multiple entries that were marked previously.
> The corresponding memory blocks are to be readded to the system
> to update relevant data structures outside of the powerpc-
> specific code.
> -- Change dlpar_memory_pmt_changes_action to directly queue worker
> to pseries work queue.
> ---
> arch/powerpc/platforms/pseries/hotplug-memory.c | 189
> +++++++++++++++++++----
> arch/powerpc/platforms/pseries/mobility.c | 4
> arch/powerpc/platforms/pseries/pseries.h | 4
> 3 files changed, 163 insertions(+), 34 deletions(-)
>
> diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c
> b/arch/powerpc/platforms/pseries/hotplug-memory.c
> index bf2420a..a7ca22e 100644
> --- a/arch/powerpc/platforms/pseries/hotplug-memory.c
> +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
> @@ -534,8 +534,11 @@ static int dlpar_memory_readd_by_index(u32 drc_index)
> }
> }
>
> - if (!lmb_found)
> - rc = -EINVAL;
> + if (!lmb_found) {
> + pr_info("Failed to update memory for drc index %lx\n",
> + (unsigned long) drc_index);
> + return -EINVAL;
> + }
>
> if (rc)
> pr_info("Failed to update memory at %llx\n",
> @@ -1002,13 +1005,43 @@ static int pseries_add_mem_node(struct device_node
> *np)
> return (ret < 0) ? -EINVAL : 0;
> }
>
> -static int pseries_update_drconf_memory(struct of_reconfig_data *pr)
> +static int pmt_changes = 0;
> +
> +void dlpar_memory_pmt_changes_set(void)
> +{
> + pmt_changes = 1;
> +}
> +
> +void dlpar_memory_pmt_changes_clear(void)
> +{
> + pmt_changes = 0;
> +}
> +
> +int dlpar_memory_pmt_changes(void)
> +{
> + return pmt_changes;
> +}
> +
> +void dlpar_memory_pmt_changes_action(void)
> +{
> + if (dlpar_memory_pmt_changes()) {
> + struct pseries_hp_errorlog hp_errlog;
> +
> + hp_errlog.resource = PSERIES_HP_ELOG_RESOURCE_MEM;
> + hp_errlog.action = PSERIES_HP_ELOG_ACTION_READD_MULTIPLE;
> + hp_errlog.id_type = 0;
> +
> + queue_hotplug_event(&hp_errlog, NULL, NULL);
> +
> + dlpar_memory_pmt_changes_clear();
> + }
> +}
> +
> +static int pseries_update_drconf_memory(struct drmem_lmb_info *new_dinfo)
> {
> - struct of_drconf_cell_v1 *new_drmem, *old_drmem;
> + struct drmem_lmb *old_lmb, *new_lmb;
> unsigned long memblock_size;
> - u32 entries;
> - __be32 *p;
> - int i, rc = -EINVAL;
> + int rc = 0;
>
> if (rtas_hp_event)
> return 0;
> @@ -1017,42 +1050,122 @@ static int pseries_update_drconf_memory(struct
> of_reconfig_data *pr)
> if (!memblock_size)
> return -EINVAL;
>
> - p = (__be32 *) pr->old_prop->value;
> - if (!p)
> - return -EINVAL;
> -
> - /* The first int of the property is the number of lmb's described
> - * by the property. This is followed by an array of of_drconf_cell
> - * entries. Get the number of entries and skip to the array of
> - * of_drconf_cell's.
> - */
> - entries = be32_to_cpu(*p++);
> - old_drmem = (struct of_drconf_cell_v1 *)p;
> + /* Arrays should have the same size and DRC indexes */
> + for_each_pair_dinfo_lmb(drmem_info, old_lmb, new_dinfo, new_lmb) {
>
> - p = (__be32 *)pr->prop->value;
> - p++;
> - new_drmem = (struct of_drconf_cell_v1 *)p;
> + if (new_lmb->drc_index != old_lmb->drc_index)
> + continue;
>
> - for (i = 0; i < entries; i++) {
> - if ((be32_to_cpu(old_drmem[i].flags) & DRCONF_MEM_ASSIGNED) &&
> - (!(be32_to_cpu(new_drmem[i].flags) & DRCONF_MEM_ASSIGNED)))
> {
> + if ((old_lmb->flags & DRCONF_MEM_ASSIGNED) &&
> + (!(new_lmb->flags & DRCONF_MEM_ASSIGNED))) {
> rc = pseries_remove_memblock(
> - be64_to_cpu(old_drmem[i].base_addr),
> - memblock_size);
> + old_lmb->base_addr, memblock_size);
> break;
> - } else if ((!(be32_to_cpu(old_drmem[i].flags) &
> - DRCONF_MEM_ASSIGNED)) &&
> - (be32_to_cpu(new_drmem[i].flags) &
> - DRCONF_MEM_ASSIGNED)) {
> - rc = memblock_add(be64_to_cpu(old_drmem[i].base_addr),
> - memblock_size);
> + } else if ((!(old_lmb->flags & DRCONF_MEM_ASSIGNED)) &&
> + (new_lmb->flags & DRCONF_MEM_ASSIGNED)) {
> + rc = memblock_add(old_lmb->base_addr,
> + memblock_size);
> rc = (rc < 0) ? -EINVAL : 0;
> break;
> + } else if ((old_lmb->aa_index != new_lmb->aa_index) &&
> + (new_lmb->flags & DRCONF_MEM_ASSIGNED)) {
> + drmem_mark_lmb_update(old_lmb);
> + dlpar_memory_pmt_changes_set();
> }
> }
> return rc;
> }
>
> +static void pseries_update_ala_memory_aai(int aa_index)
> +{
> + struct drmem_lmb *lmb;
> +
> + /* Readd all LMBs which were previously using the
> + * specified aa_index value.
> + */
> + for_each_drmem_lmb(lmb) {
> + if ((lmb->aa_index == aa_index) &&
> + (lmb->flags & DRCONF_MEM_ASSIGNED)) {
> + drmem_mark_lmb_update(lmb);
> + dlpar_memory_pmt_changes_set();
> + }
> + }
> +}
> +
> +struct assoc_arrays {
> + u32 n_arrays;
> + u32 array_sz;
> + const __be32 *arrays;
> +};
This struct is also defined in arch/powerpc/mm/numa.c. May be a good idea to
move the
definition to common place.
> +
> +static int pseries_update_ala_memory(struct of_reconfig_data *pr)
> +{
> + struct assoc_arrays new_ala, old_ala;
> + __be32 *p;
> + int i, lim;
> +
> + if (rtas_hp_event)
> + return 0;
> +
> + /*
> + * The layout of the ibm,associativity-lookup-arrays
> + * property is a number N indicating the number of
> + * associativity arrays, followed by a number M
> + * indicating the size of each associativity array,
> + * followed by a list of N associativity arrays.
> + */
> +
> + p = (__be32 *) pr->old_prop->value;
> + if (!p)
> + return -EINVAL;
> + old_ala.n_arrays = of_read_number(p++, 1);
> + old_ala.array_sz = of_read_number(p++, 1);
> + old_ala.arrays = p;
> +
> + p = (__be32 *) pr->prop->value;
> + if (!p)
> + return -EINVAL;
> + new_ala.n_arrays = of_read_number(p++, 1);
> + new_ala.array_sz = of_read_number(p++, 1);
> + new_ala.arrays = p;
> +
> + lim = (new_ala.n_arrays > old_ala.n_arrays) ? old_ala.n_arrays :
> + new_ala.n_arrays;
> +
> + if (old_ala.array_sz == new_ala.array_sz) {
> +
> + /* Reset any entries where the old and new rows
> + * the array have changed.
Small nit, the wording in that comment could be clearer.
-Nathan
> + */
> + for (i = 0; i < lim; i++) {
> + int index = (i * new_ala.array_sz);
> +
> + if (!memcmp(&old_ala.arrays[index],
> + &new_ala.arrays[index],
> + new_ala.array_sz))
> + continue;
> +
> + pseries_update_ala_memory_aai(i);
> + }
> +
> + /* Reset any entries representing the extra rows.
> + * There shouldn't be any, but just in case ...
> + */
> + for (i = lim; i < new_ala.n_arrays; i++)
> + pseries_update_ala_memory_aai(i);
> +
> + } else {
> + /* Update all entries representing these rows;
> + * as all rows have different sizes, none can
> + * have equivalent values.
> + */
> + for (i = 0; i < lim; i++)
> + pseries_update_ala_memory_aai(i);
> + }
> +
> + return 0;
> +}
> +
> static int pseries_memory_notifier(struct notifier_block *nb,
> unsigned long action, void *data)
> {
> @@ -1067,8 +1180,16 @@ static int pseries_memory_notifier(struct
> notifier_block *nb,
> err = pseries_remove_mem_node(rd->dn);
> break;
> case OF_RECONFIG_UPDATE_PROPERTY:
> - if (!strcmp(rd->prop->name, "ibm,dynamic-memory"))
> - err = pseries_update_drconf_memory(rd);
> + if (!strcmp(rd->prop->name, "ibm,dynamic-memory")) {
> + struct drmem_lmb_info *dinfo =
> + drmem_lmbs_init(rd->prop);
> + if (!dinfo)
> + return -EINVAL;
> + err = pseries_update_drconf_memory(dinfo);
> + drmem_lmbs_free(dinfo);
> + } else if (!strcmp(rd->prop->name,
> + "ibm,associativity-lookup-arrays"))
> + err = pseries_update_ala_memory(rd);
> break;
> }
> return notifier_from_errno(err);
> diff --git a/arch/powerpc/platforms/pseries/mobility.c
> b/arch/powerpc/platforms/pseries/mobility.c
> index eba7ef7..c9d3d80 100644
> --- a/arch/powerpc/platforms/pseries/mobility.c
> +++ b/arch/powerpc/platforms/pseries/mobility.c
> @@ -373,6 +373,10 @@ static ssize_t migration_store(struct class *class,
> return rc;
>
> post_mobility_fixup();
> +
> + /* Apply any necessary changes identified during fixup */
> + dlpar_memory_pmt_changes_action();
> +
> return count;
> }
>
> diff --git a/arch/powerpc/platforms/pseries/pseries.h
> b/arch/powerpc/platforms/pseries/pseries.h
> index 72c0b89..3352f90 100644
> --- a/arch/powerpc/platforms/pseries/pseries.h
> +++ b/arch/powerpc/platforms/pseries/pseries.h
> @@ -71,6 +71,10 @@ static inline int dlpar_memory(struct pseries_hp_errorlog
> *hp_elog)
> return -EOPNOTSUPP;
> }
> #endif
> +void dlpar_memory_pmt_changes_set(void);
> +void dlpar_memory_pmt_changes_clear(void);
> +int dlpar_memory_pmt_changes(void);
> +void dlpar_memory_pmt_changes_action(void);
>
> #ifdef CONFIG_HOTPLUG_CPU
> int dlpar_cpu(struct pseries_hp_errorlog *hp_elog);
>
