From fa5d374f6bacbaa081b271ae0a74ea0b38cc8b06 Mon Sep 17 00:00:00 2001 From: Gaurav Batra Date: Thu, 30 Jan 2025 12:38:54 -0600 Subject: [PATCH] powerpc/pseries/iommu: memory notifier incorrectly adds TCEs for pmemory [ Upstream commit 6aa989ab2bd0d37540c812b4270006ff794662e7 ] 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 Tested-by: Donet Tom Reviewed-by: Donet Tom Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20250130183854.92258-1-gbatra@linux.ibm.com Signed-off-by: Sasha Levin --- arch/powerpc/include/asm/mmzone.h | 1 + arch/powerpc/mm/numa.c | 2 +- arch/powerpc/platforms/pseries/iommu.c | 29 ++++++++++++++------------ 3 files changed, 18 insertions(+), 14 deletions(-) diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h index da827d2d0866..f2c4457c94c3 100644 --- a/arch/powerpc/include/asm/mmzone.h +++ b/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 diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index f6c4ace3b221..65a9df0b9e5a 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1342,7 +1342,7 @@ 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; diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index b1e6d275cda9..bf02f94a973d 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -1183,17 +1183,13 @@ 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; } @@ -1471,7 +1467,7 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn) window->direct = true; /* 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", @@ -1658,11 +1654,17 @@ 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); } @@ -1674,7 +1676,8 @@ 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); }