@@ -3575,6 +3575,49 @@ static SpaprDimmState *spapr_recover_pending_dimm_state(SpaprMachineState *ms,
return spapr_pending_dimm_unplugs_add(ms, avail_lmbs, dimm);
}
+void spapr_clear_pending_dimm_unplug_state(SpaprMachineState *spapr,
+ DeviceState *dev)
+{
+ SpaprDimmState *ds;
+ PCDIMMDevice *dimm;
+ SpaprDrc *drc;
+ uint32_t nr_lmbs;
+ uint64_t size, addr_start, addr;
+ int i;
+
+ if (!dev) {
+ return;
+ }
+
+ dimm = PC_DIMM(dev);
+ ds = spapr_pending_dimm_unplugs_find(spapr, dimm);
+
+ /*
+ * 'ds == NULL' would mean that the DIMM doesn't have a pending
+ * unplug state, but one of its DRC is marked as unplug_requested.
+ * This is bad and weird enough to g_assert() out.
+ */
+ g_assert(ds);
+
+ spapr_pending_dimm_unplugs_remove(spapr, ds);
+
+ size = memory_device_get_region_size(MEMORY_DEVICE(dimm), &error_abort);
+ nr_lmbs = size / SPAPR_MEMORY_BLOCK_SIZE;
+
+ addr_start = object_property_get_uint(OBJECT(dimm), PC_DIMM_ADDR_PROP,
+ &error_abort);
+
+ addr = addr_start;
+ for (i = 0; i < nr_lmbs; i++) {
+ drc = spapr_drc_by_id(TYPE_SPAPR_DRC_LMB,
+ addr / SPAPR_MEMORY_BLOCK_SIZE);
+ g_assert(drc);
+
+ drc->unplug_requested = false;
+ addr += SPAPR_MEMORY_BLOCK_SIZE;
+ }
+}
+
/* Callback to be called during DRC release. */
void spapr_lmb_release(DeviceState *dev)
{
@@ -1230,6 +1230,16 @@ static void rtas_ibm_configure_connector(PowerPCCPU *cpu,
drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc);
+ /*
+ * This indicates that the kernel is reconfiguring a LMB due to
+ * a failed hotunplug. Clear the pending unplug state for the whole
+ * DIMM.
+ */
+ if (spapr_drc_type(drc) == SPAPR_DR_CONNECTOR_TYPE_LMB &&
+ drc->unplug_requested) {
+ spapr_clear_pending_dimm_unplug_state(spapr, drc->dev);
+ }
+
if (!drc->fdt) {
void *fdt;
int fdt_size;
@@ -847,6 +847,8 @@ int spapr_hpt_shift_for_ramsize(uint64_t ramsize);
int spapr_reallocate_hpt(SpaprMachineState *spapr, int shift, Error **errp);
void spapr_clear_pending_events(SpaprMachineState *spapr);
void spapr_clear_pending_hotplug_events(SpaprMachineState *spapr);
+void spapr_clear_pending_dimm_unplug_state(SpaprMachineState *spapr,
+ DeviceState *dev);
int spapr_max_server_number(SpaprMachineState *spapr);
void spapr_store_hpte(PowerPCCPU *cpu, hwaddr ptex,
uint64_t pte0, uint64_t pte1);
Handling errors in memory hotunplug in the pSeries machine is more complex than any other device type, because there are all the complications that other devices has, and more. For instance, determining a timeout for a DIMM hotunplug must consider if it's a Hash-MMU or a Radix-MMU guest, because Hash guests takes longer to hotunplug DIMMs. The size of the DIMM is also a factor, given that longer DIMMs naturally takes longer to be hotunplugged from the kernel. And there's also the guest memory usage to be considered: if there's a process that is consuming memory that would be lost by the DIMM unplug, the kernel will postpone the unplug process until the process finishes, and then initiate the regular hotunplug process. The first two considerations are manageable, but the last one is a deal breaker. There is no sane way for the pSeries machine to determine the memory load in the guest when attempting a DIMM hotunplug - and even if there was a way, the guest can start using all the RAM in the middle of the unplug process and invalidate our previous assumptions - and in result we can't even begin to calculate a timeout for the operation. This means that we can't implement a viable timeout mechanism for memory unplug in pSeries. Going back to why we would consider an unplug timeout, the reason is that we can't know if the kernel is giving up the unplug. Turns out that, sometimes, we can. Consider a failed memory hotunplug attempt where the kernel will error out with the following message: 'pseries-hotplug-mem: Memory indexed-count-remove failed, adding any removed LMBs' This happens when there is a LMB that the kernel gave up in removing, and the LMBs previously marked for removal are now being added back. This happens in the pseries kernel in [1], dlpar_memory_remove_by_ic() into dlpar_add_lmb(), and after that update_lmb_associativity_index(). In this function, the kernel is configuring the LMB DRC connector again. Note that this is a valid usage in LOPAR, as stated in section "ibm,configure-connector RTAS Call": 'A subsequent sequence of calls to ibm,configure-connector with the same entry from the “ibm,drc-indexes” or “ibm,drc-info” property will restart the configuration of devices which were not completely configured.' We can use this kernel behavior in our favor. If a DRC connector reconfiguration for a LMB that we marked as unplug pending happens, this indicates that the kernel changed its mind about the unplug and is reasserting that it will keep using all the LMBs of the DIMM. In this case, it's safe to assume that the whole DIMM device unplug was cancelled. This patch hops into rtas_ibm_configure_connector() and, in the scenario described above, clear the unplug state for the DIMM device. This will not solve all the problems we still have with memory unplug, but it will cover this case where the kernel reconfigures LMBs after a failed unplug. We are a bit more resilient, without using an unreliable timeout, and we didn't make the remaining error cases any worse. [1] arch/powerpc/platforms/pseries/hotplug-memory.c Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com> --- hw/ppc/spapr.c | 43 ++++++++++++++++++++++++++++++++++++++++++ hw/ppc/spapr_drc.c | 10 ++++++++++ include/hw/ppc/spapr.h | 2 ++ 3 files changed, 55 insertions(+)