| Message ID | 20190408101226.20976-4-david@redhat.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | mm/memory_hotplug: Factor out memory block device handling | expand |
On Mon, Apr 08, 2019 at 12:12:26PM +0200, David Hildenbrand wrote: > Let's factor out removing of memory block devices, which is only > necessary for memory added via add_memory() and friends that created > memory block devices. Remove the devices before calling > arch_remove_memory(). > > TODO: We should try to get rid of the errors that could be reported by > unregister_memory_block_under_nodes(). Ignoring failures is not that > nice. Hi David, I am sorry but I will not have to look into this until next week as I am up to my ears with work plus I am in the middle of a move. I remember I was once trying to simplify unregister_mem_sect_under_nodes (your new unregister_memory_block_under_nodes), and I checked whether we could get rid of the NODEMASK_ALLOC there, something like: diff --git a/drivers/base/node.c b/drivers/base/node.c index 8598fcbd2a17..f4294a2928dd 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -805,16 +805,10 @@ int register_mem_sect_under_node(struct memory_block *mem_blk, void *arg) int unregister_mem_sect_under_nodes(struct memory_block *mem_blk, unsigned long phys_index) { - NODEMASK_ALLOC(nodemask_t, unlinked_nodes, GFP_KERNEL); + nodemask_t unlinked_nodes; unsigned long pfn, sect_start_pfn, sect_end_pfn; - if (!mem_blk) { - NODEMASK_FREE(unlinked_nodes); - return -EFAULT; - } - if (!unlinked_nodes) - return -ENOMEM; - nodes_clear(*unlinked_nodes); + nodes_clear(unlinked_nodes); sect_start_pfn = section_nr_to_pfn(phys_index); sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1; @@ -826,14 +820,13 @@ int unregister_mem_sect_under_nodes(struct memory_block *mem_blk, continue; if (!node_online(nid)) continue; - if (node_test_and_set(nid, *unlinked_nodes)) + if (node_test_and_set(nid, unlinked_nodes)) continue; sysfs_remove_link(&node_devices[nid]->dev.kobj, kobject_name(&mem_blk->dev.kobj)); sysfs_remove_link(&mem_blk->dev.kobj, kobject_name(&node_devices[nid]->dev.kobj)); } - NODEMASK_FREE(unlinked_nodes); return 0; } nodemask_t is 128bytes when CONFIG_NODES_SHIFT is 10 , which is the maximum value. We just need to check whether we can overflow the stack or not. AFAICS, it is not really a shore stack but it might not be that deep either. > > Signed-off-by: David Hildenbrand <david@redhat.com> > --- > drivers/base/memory.c | 41 +++++++++++++++-------------------------- > drivers/base/node.c | 7 +++---- > include/linux/memory.h | 2 +- > include/linux/node.h | 6 ++---- > mm/memory_hotplug.c | 10 ++++------ > 5 files changed, 25 insertions(+), 41 deletions(-) > > diff --git a/drivers/base/memory.c b/drivers/base/memory.c > index 847b33061e2e..fd8940c37129 100644 > --- a/drivers/base/memory.c > +++ b/drivers/base/memory.c > @@ -752,40 +752,29 @@ int hotplug_memory_register(unsigned long start, unsigned long size) > } > > #ifdef CONFIG_MEMORY_HOTREMOVE > -static int remove_memory_section(struct mem_section *section) > +void hotplug_memory_unregister(unsigned long start, unsigned long size) > { > + unsigned long block_nr_pages = memory_block_size_bytes() >> PAGE_SHIFT; > + unsigned long start_pfn = PFN_DOWN(start); > + unsigned long end_pfn = start_pfn + (size >> PAGE_SHIFT); > struct memory_block *mem; > + unsigned long pfn; > > - mutex_lock(&mem_sysfs_mutex); > - > - /* > - * Some users of the memory hotplug do not want/need memblock to > - * track all sections. Skip over those. > - */ > - mem = find_memory_block(section); > - if (!mem) > - goto out_unlock; > - > - unregister_mem_sect_under_nodes(mem, __section_nr(section)); > + BUG_ON(!IS_ALIGNED(start, memory_block_size_bytes())); > + BUG_ON(!IS_ALIGNED(size, memory_block_size_bytes())); > > - mem->section_count--; > - if (mem->section_count == 0) > + mutex_lock(&mem_sysfs_mutex); > + for (pfn = start_pfn; pfn != end_pfn; pfn += block_nr_pages) { > + mem = find_memory_block(__pfn_to_section(pfn)); > + if (!mem) > + continue; > + mem->section_count = 0; > + unregister_memory_block_under_nodes(mem); > unregister_memory(mem); > - else > - put_device(&mem->dev); > - > -out_unlock: > + } > mutex_unlock(&mem_sysfs_mutex); > - return 0; > } > > -int unregister_memory_section(struct mem_section *section) > -{ > - if (!present_section(section)) > - return -EINVAL; > - > - return remove_memory_section(section); > -} > #endif /* CONFIG_MEMORY_HOTREMOVE */ > > /* return true if the memory block is offlined, otherwise, return false */ > diff --git a/drivers/base/node.c b/drivers/base/node.c > index 8598fcbd2a17..f9997770ac15 100644 > --- a/drivers/base/node.c > +++ b/drivers/base/node.c > @@ -802,8 +802,7 @@ int register_mem_sect_under_node(struct memory_block *mem_blk, void *arg) > } > > /* unregister memory section under all nodes that it spans */ > -int unregister_mem_sect_under_nodes(struct memory_block *mem_blk, > - unsigned long phys_index) > +int unregister_memory_block_under_nodes(struct memory_block *mem_blk) > { > NODEMASK_ALLOC(nodemask_t, unlinked_nodes, GFP_KERNEL); > unsigned long pfn, sect_start_pfn, sect_end_pfn; > @@ -816,8 +815,8 @@ int unregister_mem_sect_under_nodes(struct memory_block *mem_blk, > return -ENOMEM; > nodes_clear(*unlinked_nodes); > > - sect_start_pfn = section_nr_to_pfn(phys_index); > - sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1; > + sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr); > + sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr); > for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) { > int nid; > > diff --git a/include/linux/memory.h b/include/linux/memory.h > index e275dc775834..414e43ab0881 100644 > --- a/include/linux/memory.h > +++ b/include/linux/memory.h > @@ -113,7 +113,7 @@ extern int register_memory_isolate_notifier(struct notifier_block *nb); > extern void unregister_memory_isolate_notifier(struct notifier_block *nb); > int hotplug_memory_register(unsigned long start, unsigned long size); > #ifdef CONFIG_MEMORY_HOTREMOVE > -extern int unregister_memory_section(struct mem_section *); > +void hotplug_memory_unregister(unsigned long start, unsigned long size); > #endif > extern int memory_dev_init(void); > extern int memory_notify(unsigned long val, void *v); > diff --git a/include/linux/node.h b/include/linux/node.h > index 1a557c589ecb..02a29e71b175 100644 > --- a/include/linux/node.h > +++ b/include/linux/node.h > @@ -139,8 +139,7 @@ extern int register_cpu_under_node(unsigned int cpu, unsigned int nid); > extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid); > extern int register_mem_sect_under_node(struct memory_block *mem_blk, > void *arg); > -extern int unregister_mem_sect_under_nodes(struct memory_block *mem_blk, > - unsigned long phys_index); > +extern int unregister_memory_block_under_nodes(struct memory_block *mem_blk); > > extern int register_memory_node_under_compute_node(unsigned int mem_nid, > unsigned int cpu_nid, > @@ -176,8 +175,7 @@ static inline int register_mem_sect_under_node(struct memory_block *mem_blk, > { > return 0; > } > -static inline int unregister_mem_sect_under_nodes(struct memory_block *mem_blk, > - unsigned long phys_index) > +static inline int unregister_memory_block_under_nodes(struct memory_block *mem_blk) > { > return 0; > } > diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c > index 13ee0a26e034..041b93c5eede 100644 > --- a/mm/memory_hotplug.c > +++ b/mm/memory_hotplug.c > @@ -518,14 +518,9 @@ static int __remove_section(struct zone *zone, struct mem_section *ms, > { > unsigned long start_pfn; > int scn_nr; > - int ret = -EINVAL; > > if (!valid_section(ms)) > - return ret; > - > - ret = unregister_memory_section(ms); > - if (ret) > - return ret; > + return -EINVAL; > > scn_nr = __section_nr(ms); > start_pfn = section_nr_to_pfn((unsigned long)scn_nr); > @@ -1875,6 +1870,9 @@ void __ref __remove_memory(int nid, u64 start, u64 size) > memblock_free(start, size); > memblock_remove(start, size); > > + /* remove memory block devices before removing memory */ > + hotplug_memory_unregister(start, size); > + > arch_remove_memory(nid, start, size, NULL); > > try_offline_node(nid); > -- > 2.17.2 >
On 09.04.19 11:18, Oscar Salvador wrote: > On Mon, Apr 08, 2019 at 12:12:26PM +0200, David Hildenbrand wrote: >> Let's factor out removing of memory block devices, which is only >> necessary for memory added via add_memory() and friends that created >> memory block devices. Remove the devices before calling >> arch_remove_memory(). >> >> TODO: We should try to get rid of the errors that could be reported by >> unregister_memory_block_under_nodes(). Ignoring failures is not that >> nice. > > Hi David, > > I am sorry but I will not have to look into this until next week as I am > up to my ears with work plus I am in the middle of a move. No worries, I have plenty of other stuff to do as well and this is only an RFC that will require other refactorings and maybe discussions first - one of these, I will send out shortly so we can discuss. Happy moving :) > > I remember I was once trying to simplify unregister_mem_sect_under_nodes (your > new unregister_memory_block_under_nodes), and I checked whether we could get > rid of the NODEMASK_ALLOC there, something like: Yeah, something like that makes perfect sense. Thanks! > > diff --git a/drivers/base/node.c b/drivers/base/node.c > index 8598fcbd2a17..f4294a2928dd 100644 > --- a/drivers/base/node.c > +++ b/drivers/base/node.c > @@ -805,16 +805,10 @@ int register_mem_sect_under_node(struct memory_block *mem_blk, void *arg) > int unregister_mem_sect_under_nodes(struct memory_block *mem_blk, > unsigned long phys_index) > { > - NODEMASK_ALLOC(nodemask_t, unlinked_nodes, GFP_KERNEL); > + nodemask_t unlinked_nodes; > unsigned long pfn, sect_start_pfn, sect_end_pfn; > > - if (!mem_blk) { > - NODEMASK_FREE(unlinked_nodes); > - return -EFAULT; > - } > - if (!unlinked_nodes) > - return -ENOMEM; > - nodes_clear(*unlinked_nodes); > + nodes_clear(unlinked_nodes); > > sect_start_pfn = section_nr_to_pfn(phys_index); > sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1; > @@ -826,14 +820,13 @@ int unregister_mem_sect_under_nodes(struct memory_block *mem_blk, > continue; > if (!node_online(nid)) > continue; > - if (node_test_and_set(nid, *unlinked_nodes)) > + if (node_test_and_set(nid, unlinked_nodes)) > continue; > sysfs_remove_link(&node_devices[nid]->dev.kobj, > kobject_name(&mem_blk->dev.kobj)); > sysfs_remove_link(&mem_blk->dev.kobj, > kobject_name(&node_devices[nid]->dev.kobj)); > } > - NODEMASK_FREE(unlinked_nodes); > return 0; > } > > > nodemask_t is 128bytes when CONFIG_NODES_SHIFT is 10 , which is the maximum value. > We just need to check whether we can overflow the stack or not. > > AFAICS, it is not really a shore stack but it might not be that deep either.
diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 847b33061e2e..fd8940c37129 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -752,40 +752,29 @@ int hotplug_memory_register(unsigned long start, unsigned long size) } #ifdef CONFIG_MEMORY_HOTREMOVE -static int remove_memory_section(struct mem_section *section) +void hotplug_memory_unregister(unsigned long start, unsigned long size) { + unsigned long block_nr_pages = memory_block_size_bytes() >> PAGE_SHIFT; + unsigned long start_pfn = PFN_DOWN(start); + unsigned long end_pfn = start_pfn + (size >> PAGE_SHIFT); struct memory_block *mem; + unsigned long pfn; - mutex_lock(&mem_sysfs_mutex); - - /* - * Some users of the memory hotplug do not want/need memblock to - * track all sections. Skip over those. - */ - mem = find_memory_block(section); - if (!mem) - goto out_unlock; - - unregister_mem_sect_under_nodes(mem, __section_nr(section)); + BUG_ON(!IS_ALIGNED(start, memory_block_size_bytes())); + BUG_ON(!IS_ALIGNED(size, memory_block_size_bytes())); - mem->section_count--; - if (mem->section_count == 0) + mutex_lock(&mem_sysfs_mutex); + for (pfn = start_pfn; pfn != end_pfn; pfn += block_nr_pages) { + mem = find_memory_block(__pfn_to_section(pfn)); + if (!mem) + continue; + mem->section_count = 0; + unregister_memory_block_under_nodes(mem); unregister_memory(mem); - else - put_device(&mem->dev); - -out_unlock: + } mutex_unlock(&mem_sysfs_mutex); - return 0; } -int unregister_memory_section(struct mem_section *section) -{ - if (!present_section(section)) - return -EINVAL; - - return remove_memory_section(section); -} #endif /* CONFIG_MEMORY_HOTREMOVE */ /* return true if the memory block is offlined, otherwise, return false */ diff --git a/drivers/base/node.c b/drivers/base/node.c index 8598fcbd2a17..f9997770ac15 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -802,8 +802,7 @@ int register_mem_sect_under_node(struct memory_block *mem_blk, void *arg) } /* unregister memory section under all nodes that it spans */ -int unregister_mem_sect_under_nodes(struct memory_block *mem_blk, - unsigned long phys_index) +int unregister_memory_block_under_nodes(struct memory_block *mem_blk) { NODEMASK_ALLOC(nodemask_t, unlinked_nodes, GFP_KERNEL); unsigned long pfn, sect_start_pfn, sect_end_pfn; @@ -816,8 +815,8 @@ int unregister_mem_sect_under_nodes(struct memory_block *mem_blk, return -ENOMEM; nodes_clear(*unlinked_nodes); - sect_start_pfn = section_nr_to_pfn(phys_index); - sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1; + sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr); + sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr); for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) { int nid; diff --git a/include/linux/memory.h b/include/linux/memory.h index e275dc775834..414e43ab0881 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -113,7 +113,7 @@ extern int register_memory_isolate_notifier(struct notifier_block *nb); extern void unregister_memory_isolate_notifier(struct notifier_block *nb); int hotplug_memory_register(unsigned long start, unsigned long size); #ifdef CONFIG_MEMORY_HOTREMOVE -extern int unregister_memory_section(struct mem_section *); +void hotplug_memory_unregister(unsigned long start, unsigned long size); #endif extern int memory_dev_init(void); extern int memory_notify(unsigned long val, void *v); diff --git a/include/linux/node.h b/include/linux/node.h index 1a557c589ecb..02a29e71b175 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -139,8 +139,7 @@ extern int register_cpu_under_node(unsigned int cpu, unsigned int nid); extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid); extern int register_mem_sect_under_node(struct memory_block *mem_blk, void *arg); -extern int unregister_mem_sect_under_nodes(struct memory_block *mem_blk, - unsigned long phys_index); +extern int unregister_memory_block_under_nodes(struct memory_block *mem_blk); extern int register_memory_node_under_compute_node(unsigned int mem_nid, unsigned int cpu_nid, @@ -176,8 +175,7 @@ static inline int register_mem_sect_under_node(struct memory_block *mem_blk, { return 0; } -static inline int unregister_mem_sect_under_nodes(struct memory_block *mem_blk, - unsigned long phys_index) +static inline int unregister_memory_block_under_nodes(struct memory_block *mem_blk) { return 0; } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 13ee0a26e034..041b93c5eede 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -518,14 +518,9 @@ static int __remove_section(struct zone *zone, struct mem_section *ms, { unsigned long start_pfn; int scn_nr; - int ret = -EINVAL; if (!valid_section(ms)) - return ret; - - ret = unregister_memory_section(ms); - if (ret) - return ret; + return -EINVAL; scn_nr = __section_nr(ms); start_pfn = section_nr_to_pfn((unsigned long)scn_nr); @@ -1875,6 +1870,9 @@ void __ref __remove_memory(int nid, u64 start, u64 size) memblock_free(start, size); memblock_remove(start, size); + /* remove memory block devices before removing memory */ + hotplug_memory_unregister(start, size); + arch_remove_memory(nid, start, size, NULL); try_offline_node(nid);
Let's factor out removing of memory block devices, which is only necessary for memory added via add_memory() and friends that created memory block devices. Remove the devices before calling arch_remove_memory(). TODO: We should try to get rid of the errors that could be reported by unregister_memory_block_under_nodes(). Ignoring failures is not that nice. Signed-off-by: David Hildenbrand <david@redhat.com> --- drivers/base/memory.c | 41 +++++++++++++++-------------------------- drivers/base/node.c | 7 +++---- include/linux/memory.h | 2 +- include/linux/node.h | 6 ++---- mm/memory_hotplug.c | 10 ++++------ 5 files changed, 25 insertions(+), 41 deletions(-)