From d15e59260f62bd5e0f625cf5f5240f6ffac78ab6 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 30 Oct 2018 15:10:18 -0700 Subject: mm/memory_hotplug: make remove_memory() take the device_hotplug_lock Patch series "mm: online/offline_pages called w.o. mem_hotplug_lock", v3. Reading through the code and studying how mem_hotplug_lock is to be used, I noticed that there are two places where we can end up calling device_online()/device_offline() - online_pages()/offline_pages() without the mem_hotplug_lock. And there are other places where we call device_online()/device_offline() without the device_hotplug_lock. While e.g. echo "online" > /sys/devices/system/memory/memory9/state is fine, e.g. echo 1 > /sys/devices/system/memory/memory9/online Will not take the mem_hotplug_lock. However the device_lock() and device_hotplug_lock. E.g. via memory_probe_store(), we can end up calling add_memory()->online_pages() without the device_hotplug_lock. So we can have concurrent callers in online_pages(). We e.g. touch in online_pages() basically unprotected zone->present_pages then. Looks like there is a longer history to that (see Patch #2 for details), and fixing it to work the way it was intended is not really possible. We would e.g. have to take the mem_hotplug_lock in device/base/core.c, which sounds wrong. Summary: We had a lock inversion on mem_hotplug_lock and device_lock(). More details can be found in patch 3 and patch 6. I propose the general rules (documentation added in patch 6): 1. add_memory/add_memory_resource() must only be called with device_hotplug_lock. 2. remove_memory() must only be called with device_hotplug_lock. This is already documented and holds for all callers. 3. device_online()/device_offline() must only be called with device_hotplug_lock. This is already documented and true for now in core code. Other callers (related to memory hotplug) have to be fixed up. 4. mem_hotplug_lock is taken inside of add_memory/remove_memory/ online_pages/offline_pages. To me, this looks way cleaner than what we have right now (and easier to verify). And looking at the documentation of remove_memory, using lock_device_hotplug also for add_memory() feels natural. This patch (of 6): remove_memory() is exported right now but requires the device_hotplug_lock, which is not exported. So let's provide a variant that takes the lock and only export that one. The lock is already held in arch/powerpc/platforms/pseries/hotplug-memory.c drivers/acpi/acpi_memhotplug.c arch/powerpc/platforms/powernv/memtrace.c Apart from that, there are not other users in the tree. Link: http://lkml.kernel.org/r/20180925091457.28651-2-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Pavel Tatashin Reviewed-by: Rafael J. Wysocki Reviewed-by: Rashmica Gupta Reviewed-by: Oscar Salvador Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Rashmica Gupta Cc: Michael Neuling Cc: Balbir Singh Cc: Nathan Fontenot Cc: John Allen Cc: Michal Hocko Cc: Dan Williams Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: Greg Kroah-Hartman Cc: YASUAKI ISHIMATSU Cc: Mathieu Malaterre Cc: Boris Ostrovsky Cc: Haiyang Zhang Cc: Heiko Carstens Cc: Jonathan Corbet Cc: Juergen Gross Cc: Kate Stewart Cc: "K. Y. Srinivasan" Cc: Martin Schwidefsky Cc: Philippe Ombredanne Cc: Stephen Hemminger Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/platforms/powernv/memtrace.c | 2 +- arch/powerpc/platforms/pseries/hotplug-memory.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c index a29fdf8a2e56..773623f6bfb1 100644 --- a/arch/powerpc/platforms/powernv/memtrace.c +++ b/arch/powerpc/platforms/powernv/memtrace.c @@ -121,7 +121,7 @@ static u64 memtrace_alloc_node(u32 nid, u64 size) lock_device_hotplug(); end_pfn = base_pfn + nr_pages; for (pfn = base_pfn; pfn < end_pfn; pfn += bytes>> PAGE_SHIFT) { - remove_memory(nid, pfn << PAGE_SHIFT, bytes); + __remove_memory(nid, pfn << PAGE_SHIFT, bytes); } unlock_device_hotplug(); return base_pfn << PAGE_SHIFT; diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 2b796da822c2..d79b31e7a6cf 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -300,7 +300,7 @@ static int pseries_remove_memblock(unsigned long base, unsigned int memblock_siz nid = memory_add_physaddr_to_nid(base); for (i = 0; i < sections_per_block; i++) { - remove_memory(nid, base, MIN_MEMORY_BLOCK_SIZE); + __remove_memory(nid, base, MIN_MEMORY_BLOCK_SIZE); base += MIN_MEMORY_BLOCK_SIZE; } @@ -389,7 +389,7 @@ static int dlpar_remove_lmb(struct drmem_lmb *lmb) block_sz = pseries_memory_block_size(); nid = memory_add_physaddr_to_nid(lmb->base_addr); - remove_memory(nid, lmb->base_addr, block_sz); + __remove_memory(nid, lmb->base_addr, block_sz); /* Update memory regions for memory remove */ memblock_remove(lmb->base_addr, block_sz); @@ -676,7 +676,7 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb) rc = dlpar_online_lmb(lmb); if (rc) { - remove_memory(nid, lmb->base_addr, block_sz); + __remove_memory(nid, lmb->base_addr, block_sz); invalidate_lmb_associativity_index(lmb); } else { lmb->flags |= DRCONF_MEM_ASSIGNED; -- cgit v1.2.3