Merge: Updates for iommu TCEs for pmemory

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/6830

Description: Updates for iommu TCEs for pmemory

JIRA: https://issues.redhat.com/browse/RHEL-88421

Build Info: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=67511443

Tested: Verified Brew build test kernel RPMs

Signed-off-by: Mamatha Inamdar <minamdar@redhat.com>

commit 6aa989a
Author: Gaurav Batra <gbatra@linux.ibm.com>
Date:   Thu Jan 30 12:38:54 2025 -0600

    powerpc/pseries/iommu: memory notifier incorrectly adds TCEs for pmemory

    iommu_mem_notifier() is invoked when RAM is dynamically added/removed. This
    notifier call is responsible to add/remove TCEs from the Dynamic DMA Window
    (DDW) when TCEs are pre-mapped. TCEs are pre-mapped only for RAM and not
    for persistent memory (pmemory). For DMA buffers in pmemory, TCEs are
    dynamically mapped when the device driver instructs to do so.

    The issue is 'daxctl' command is capable of adding pmemory as "System RAM"
    after LPAR boot. The command to do so is -

    daxctl reconfigure-device --mode=system-ram dax0.0 --force

    This will dynamically add pmemory range to LPAR RAM eventually invoking
    iommu_mem_notifier(). The address range of pmemory is way beyond the Max
    RAM that the LPAR can have. Which means, this range is beyond the DDW
    created for the device, at device initialization time.

    As a result when TCEs are pre-mapped for the pmemory range, by
    iommu_mem_notifier(), PHYP HCALL returns H_PARAMETER. This failed the
    command, daxctl, to add pmemory as RAM.

    The solution is to not pre-map TCEs for pmemory.

    Signed-off-by: Gaurav Batra <gbatra@linux.ibm.com>
    Tested-by: Donet Tom <donettom@linux.ibm.com>
    Reviewed-by: Donet Tom <donettom@linux.ibm.com>
    Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
    Link: https://patch.msgid.link/20250130183854.92258-1-gbatra@linux.ibm.com

Signed-off-by: Mamatha Inamdar <minamdar@redhat.com>

Approved-by: Steve Best <sbest@redhat.com>
Approved-by: Rafael Aquini <raquini@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Augusto Caringi <acaringi@redhat.com>

Author: caringi

arch/powerpc/include/asm/mmzone.h

@@ -35,6 +35,7 @@ extern cpumask_var_t node_to_cpumask_map[];
 #ifdef CONFIG_MEMORY_HOTPLUG
 extern unsigned long max_pfn;
 u64 memory_hotplug_max(void);
+u64 hot_add_drconf_memory_max(void);
 #else
 #define memory_hotplug_max() memblock_end_of_DRAM()
 #endif

arch/powerpc/mm/numa.c

@@ -1354,7 +1354,7 @@ int hot_add_scn_to_nid(unsigned long scn_addr)
 	return nid;
 }
 
-static u64 hot_add_drconf_memory_max(void)
+u64 hot_add_drconf_memory_max(void)
 {
 	struct device_node *memory = NULL;
 	struct device_node *dn = NULL;

arch/powerpc/platforms/pseries/iommu.c

@@ -1287,17 +1287,13 @@ static LIST_HEAD(failed_ddw_pdn_list);
 
 static phys_addr_t ddw_memory_hotplug_max(void)
 {
-	resource_size_t max_addr = memory_hotplug_max();
-	struct device_node *memory;
+	resource_size_t max_addr;
 
-	for_each_node_by_type(memory, "memory") {
-		struct resource res;
-
-		if (of_address_to_resource(memory, 0, &res))
-			continue;
-
-		max_addr = max_t(resource_size_t, max_addr, res.end + 1);
-	}
+#if defined(CONFIG_NUMA) && defined(CONFIG_MEMORY_HOTPLUG)
+	max_addr = hot_add_drconf_memory_max();
+#else
+	max_addr = memblock_end_of_DRAM();
+#endif
 
 	return max_addr;
 }
@@ -1603,7 +1599,7 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 
 	if (direct_mapping) {
 		/* DDW maps the whole partition, so enable direct DMA mapping */
-		ret = walk_system_ram_range(0, memblock_end_of_DRAM() >> PAGE_SHIFT,
+		ret = walk_system_ram_range(0, ddw_memory_hotplug_max() >> PAGE_SHIFT,
 					    win64->value, tce_setrange_multi_pSeriesLP_walk);
 		if (ret) {
 			dev_info(&dev->dev, "failed to map DMA window for %pOF: %d\n",
@@ -2352,11 +2348,17 @@ static int iommu_mem_notifier(struct notifier_block *nb, unsigned long action,
 	struct memory_notify *arg = data;
 	int ret = 0;
 
+	/* 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()
+	 */
+
 	switch (action) {
 	case MEM_GOING_ONLINE:
 		spin_lock(&dma_win_list_lock);
 		list_for_each_entry(window, &dma_win_list, list) {
-			if (window->direct) {
+			if (window->direct && (arg->start_pfn << PAGE_SHIFT) <
+				ddw_memory_hotplug_max()) {
 				ret |= tce_setrange_multi_pSeriesLP(arg->start_pfn,
 						arg->nr_pages, window->prop);
 			}
@@ -2368,7 +2370,8 @@ static int iommu_mem_notifier(struct notifier_block *nb, unsigned long action,
 	case MEM_OFFLINE:
 		spin_lock(&dma_win_list_lock);
 		list_for_each_entry(window, &dma_win_list, list) {
-			if (window->direct) {
+			if (window->direct && (arg->start_pfn << PAGE_SHIFT) <
+				ddw_memory_hotplug_max()) {
 				ret |= tce_clearrange_multi_pSeriesLP(arg->start_pfn,
 						arg->nr_pages, window->prop);
 			}