summaryrefslogtreecommitdiff
path: root/arch/powerpc/platforms/pseries
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/platforms/pseries')
-rw-r--r--arch/powerpc/platforms/pseries/Kconfig1
-rw-r--r--arch/powerpc/platforms/pseries/cmm.c431
-rw-r--r--arch/powerpc/platforms/pseries/hotplug-cpu.c244
-rw-r--r--arch/powerpc/platforms/pseries/hotplug-memory.c6
-rw-r--r--arch/powerpc/platforms/pseries/lpar.c18
-rw-r--r--arch/powerpc/platforms/pseries/of_helpers.c8
-rw-r--r--arch/powerpc/platforms/pseries/papr_scm.c5
-rw-r--r--arch/powerpc/platforms/pseries/pci_dlpar.c18
-rw-r--r--arch/powerpc/platforms/pseries/pseries_energy.c23
-rw-r--r--arch/powerpc/platforms/pseries/ras.c2
10 files changed, 396 insertions, 360 deletions
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 9e35cddddf73..595e9f8a6539 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -108,6 +108,7 @@ config PPC_SMLPAR
config CMM
tristate "Collaborative memory management"
depends on PPC_SMLPAR
+ select MEMORY_BALLOON
default y
help
Select this option, if you want to enable the kernel interface
diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c
index b33251d75927..91571841df8a 100644
--- a/arch/powerpc/platforms/pseries/cmm.c
+++ b/arch/powerpc/platforms/pseries/cmm.c
@@ -19,6 +19,10 @@
#include <linux/stringify.h>
#include <linux/swap.h>
#include <linux/device.h>
+#include <linux/mount.h>
+#include <linux/pseudo_fs.h>
+#include <linux/magic.h>
+#include <linux/balloon_compaction.h>
#include <asm/firmware.h>
#include <asm/hvcall.h>
#include <asm/mmu.h>
@@ -38,12 +42,8 @@
#define CMM_MIN_MEM_MB 256
#define KB2PAGES(_p) ((_p)>>(PAGE_SHIFT-10))
#define PAGES2KB(_p) ((_p)<<(PAGE_SHIFT-10))
-/*
- * The priority level tries to ensure that this notifier is called as
- * late as possible to reduce thrashing in the shared memory pool.
- */
+
#define CMM_MEM_HOTPLUG_PRI 1
-#define CMM_MEM_ISOLATE_PRI 15
static unsigned int delay = CMM_DEFAULT_DELAY;
static unsigned int hotplug_delay = CMM_HOTPLUG_DELAY;
@@ -51,6 +51,8 @@ static unsigned int oom_kb = CMM_OOM_KB;
static unsigned int cmm_debug = CMM_DEBUG;
static unsigned int cmm_disabled = CMM_DISABLE;
static unsigned long min_mem_mb = CMM_MIN_MEM_MB;
+static bool __read_mostly simulate;
+static unsigned long simulate_loan_target_kb;
static struct device cmm_dev;
MODULE_AUTHOR("Brian King <brking@linux.vnet.ibm.com>");
@@ -74,35 +76,31 @@ MODULE_PARM_DESC(min_mem_mb, "Minimum amount of memory (in MB) to not balloon. "
module_param_named(debug, cmm_debug, uint, 0644);
MODULE_PARM_DESC(debug, "Enable module debugging logging. Set to 1 to enable. "
"[Default=" __stringify(CMM_DEBUG) "]");
-
-#define CMM_NR_PAGES ((PAGE_SIZE - sizeof(void *) - sizeof(unsigned long)) / sizeof(unsigned long))
+module_param_named(simulate, simulate, bool, 0444);
+MODULE_PARM_DESC(simulate, "Enable simulation mode (no communication with hw).");
#define cmm_dbg(...) if (cmm_debug) { printk(KERN_INFO "cmm: "__VA_ARGS__); }
-struct cmm_page_array {
- struct cmm_page_array *next;
- unsigned long index;
- unsigned long page[CMM_NR_PAGES];
-};
-
-static unsigned long loaned_pages;
+static atomic_long_t loaned_pages;
static unsigned long loaned_pages_target;
static unsigned long oom_freed_pages;
-static struct cmm_page_array *cmm_page_list;
-static DEFINE_SPINLOCK(cmm_lock);
-
static DEFINE_MUTEX(hotplug_mutex);
static int hotplug_occurred; /* protected by the hotplug mutex */
static struct task_struct *cmm_thread_ptr;
+static struct balloon_dev_info b_dev_info;
-static long plpar_page_set_loaned(unsigned long vpa)
+static long plpar_page_set_loaned(struct page *page)
{
+ const unsigned long vpa = page_to_phys(page);
unsigned long cmo_page_sz = cmo_get_page_size();
long rc = 0;
int i;
+ if (unlikely(simulate))
+ return 0;
+
for (i = 0; !rc && i < PAGE_SIZE; i += cmo_page_sz)
rc = plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_LOANED, vpa + i, 0);
@@ -113,12 +111,16 @@ static long plpar_page_set_loaned(unsigned long vpa)
return rc;
}
-static long plpar_page_set_active(unsigned long vpa)
+static long plpar_page_set_active(struct page *page)
{
+ const unsigned long vpa = page_to_phys(page);
unsigned long cmo_page_sz = cmo_get_page_size();
long rc = 0;
int i;
+ if (unlikely(simulate))
+ return 0;
+
for (i = 0; !rc && i < PAGE_SIZE; i += cmo_page_sz)
rc = plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_ACTIVE, vpa + i, 0);
@@ -138,8 +140,7 @@ static long plpar_page_set_active(unsigned long vpa)
**/
static long cmm_alloc_pages(long nr)
{
- struct cmm_page_array *pa, *npa;
- unsigned long addr;
+ struct page *page;
long rc;
cmm_dbg("Begin request for %ld pages\n", nr);
@@ -156,46 +157,19 @@ static long cmm_alloc_pages(long nr)
break;
}
- addr = __get_free_page(GFP_NOIO | __GFP_NOWARN |
- __GFP_NORETRY | __GFP_NOMEMALLOC);
- if (!addr)
+ page = balloon_page_alloc();
+ if (!page)
break;
- spin_lock(&cmm_lock);
- pa = cmm_page_list;
- if (!pa || pa->index >= CMM_NR_PAGES) {
- /* Need a new page for the page list. */
- spin_unlock(&cmm_lock);
- npa = (struct cmm_page_array *)__get_free_page(
- GFP_NOIO | __GFP_NOWARN |
- __GFP_NORETRY | __GFP_NOMEMALLOC);
- if (!npa) {
- pr_info("%s: Can not allocate new page list\n", __func__);
- free_page(addr);
- break;
- }
- spin_lock(&cmm_lock);
- pa = cmm_page_list;
-
- if (!pa || pa->index >= CMM_NR_PAGES) {
- npa->next = pa;
- npa->index = 0;
- pa = npa;
- cmm_page_list = pa;
- } else
- free_page((unsigned long) npa);
- }
-
- if ((rc = plpar_page_set_loaned(__pa(addr)))) {
+ rc = plpar_page_set_loaned(page);
+ if (rc) {
pr_err("%s: Can not set page to loaned. rc=%ld\n", __func__, rc);
- spin_unlock(&cmm_lock);
- free_page(addr);
+ __free_page(page);
break;
}
- pa->page[pa->index++] = addr;
- loaned_pages++;
- totalram_pages_dec();
- spin_unlock(&cmm_lock);
+ balloon_page_enqueue(&b_dev_info, page);
+ atomic_long_inc(&loaned_pages);
+ adjust_managed_page_count(page, -1);
nr--;
}
@@ -212,30 +186,19 @@ static long cmm_alloc_pages(long nr)
**/
static long cmm_free_pages(long nr)
{
- struct cmm_page_array *pa;
- unsigned long addr;
+ struct page *page;
cmm_dbg("Begin free of %ld pages.\n", nr);
- spin_lock(&cmm_lock);
- pa = cmm_page_list;
while (nr) {
- if (!pa || pa->index <= 0)
+ page = balloon_page_dequeue(&b_dev_info);
+ if (!page)
break;
- addr = pa->page[--pa->index];
-
- if (pa->index == 0) {
- pa = pa->next;
- free_page((unsigned long) cmm_page_list);
- cmm_page_list = pa;
- }
-
- plpar_page_set_active(__pa(addr));
- free_page(addr);
- loaned_pages--;
+ plpar_page_set_active(page);
+ adjust_managed_page_count(page, 1);
+ __free_page(page);
+ atomic_long_dec(&loaned_pages);
nr--;
- totalram_pages_inc();
}
- spin_unlock(&cmm_lock);
cmm_dbg("End request with %ld pages unfulfilled\n", nr);
return nr;
}
@@ -257,7 +220,7 @@ static int cmm_oom_notify(struct notifier_block *self,
cmm_dbg("OOM processing started\n");
nr = cmm_free_pages(nr);
- loaned_pages_target = loaned_pages;
+ loaned_pages_target = atomic_long_read(&loaned_pages);
*freed += KB2PAGES(oom_kb) - nr;
oom_freed_pages += KB2PAGES(oom_kb) - nr;
cmm_dbg("OOM processing complete\n");
@@ -274,19 +237,24 @@ static int cmm_oom_notify(struct notifier_block *self,
**/
static void cmm_get_mpp(void)
{
+ const long __loaned_pages = atomic_long_read(&loaned_pages);
+ const long total_pages = totalram_pages() + __loaned_pages;
int rc;
struct hvcall_mpp_data mpp_data;
signed long active_pages_target, page_loan_request, target;
- signed long total_pages = totalram_pages() + loaned_pages;
signed long min_mem_pages = (min_mem_mb * 1024 * 1024) / PAGE_SIZE;
- rc = h_get_mpp(&mpp_data);
-
- if (rc != H_SUCCESS)
- return;
-
- page_loan_request = div_s64((s64)mpp_data.loan_request, PAGE_SIZE);
- target = page_loan_request + (signed long)loaned_pages;
+ if (likely(!simulate)) {
+ rc = h_get_mpp(&mpp_data);
+ if (rc != H_SUCCESS)
+ return;
+ page_loan_request = div_s64((s64)mpp_data.loan_request,
+ PAGE_SIZE);
+ target = page_loan_request + __loaned_pages;
+ } else {
+ target = KB2PAGES(simulate_loan_target_kb);
+ page_loan_request = target - __loaned_pages;
+ }
if (target < 0 || total_pages < min_mem_pages)
target = 0;
@@ -307,7 +275,7 @@ static void cmm_get_mpp(void)
loaned_pages_target = target;
cmm_dbg("delta = %ld, loaned = %lu, target = %lu, oom = %lu, totalram = %lu\n",
- page_loan_request, loaned_pages, loaned_pages_target,
+ page_loan_request, __loaned_pages, loaned_pages_target,
oom_freed_pages, totalram_pages());
}
@@ -325,6 +293,7 @@ static struct notifier_block cmm_oom_nb = {
static int cmm_thread(void *dummy)
{
unsigned long timeleft;
+ long __loaned_pages;
while (1) {
timeleft = msleep_interruptible(delay * 1000);
@@ -355,11 +324,12 @@ static int cmm_thread(void *dummy)
cmm_get_mpp();
- if (loaned_pages_target > loaned_pages) {
- if (cmm_alloc_pages(loaned_pages_target - loaned_pages))
- loaned_pages_target = loaned_pages;
- } else if (loaned_pages_target < loaned_pages)
- cmm_free_pages(loaned_pages - loaned_pages_target);
+ __loaned_pages = atomic_long_read(&loaned_pages);
+ if (loaned_pages_target > __loaned_pages) {
+ if (cmm_alloc_pages(loaned_pages_target - __loaned_pages))
+ loaned_pages_target = __loaned_pages;
+ } else if (loaned_pages_target < __loaned_pages)
+ cmm_free_pages(__loaned_pages - loaned_pages_target);
}
return 0;
}
@@ -373,7 +343,7 @@ static int cmm_thread(void *dummy)
} \
static DEVICE_ATTR(name, 0444, show_##name, NULL)
-CMM_SHOW(loaned_kb, "%lu\n", PAGES2KB(loaned_pages));
+CMM_SHOW(loaned_kb, "%lu\n", PAGES2KB(atomic_long_read(&loaned_pages)));
CMM_SHOW(loaned_target_kb, "%lu\n", PAGES2KB(loaned_pages_target));
static ssize_t show_oom_pages(struct device *dev,
@@ -406,11 +376,18 @@ static struct device_attribute *cmm_attrs[] = {
&dev_attr_oom_freed_kb,
};
+static DEVICE_ULONG_ATTR(simulate_loan_target_kb, 0644,
+ simulate_loan_target_kb);
+
static struct bus_type cmm_subsys = {
.name = "cmm",
.dev_name = "cmm",
};
+static void cmm_release_device(struct device *dev)
+{
+}
+
/**
* cmm_sysfs_register - Register with sysfs
*
@@ -426,6 +403,7 @@ static int cmm_sysfs_register(struct device *dev)
dev->id = 0;
dev->bus = &cmm_subsys;
+ dev->release = cmm_release_device;
if ((rc = device_register(dev)))
goto subsys_unregister;
@@ -435,6 +413,11 @@ static int cmm_sysfs_register(struct device *dev)
goto fail;
}
+ if (!simulate)
+ return 0;
+ rc = device_create_file(dev, &dev_attr_simulate_loan_target_kb.attr);
+ if (rc)
+ goto fail;
return 0;
fail:
@@ -471,7 +454,7 @@ static int cmm_reboot_notifier(struct notifier_block *nb,
if (cmm_thread_ptr)
kthread_stop(cmm_thread_ptr);
cmm_thread_ptr = NULL;
- cmm_free_pages(loaned_pages);
+ cmm_free_pages(atomic_long_read(&loaned_pages));
}
return NOTIFY_DONE;
}
@@ -481,142 +464,6 @@ static struct notifier_block cmm_reboot_nb = {
};
/**
- * cmm_count_pages - Count the number of pages loaned in a particular range.
- *
- * @arg: memory_isolate_notify structure with address range and count
- *
- * Return value:
- * 0 on success
- **/
-static unsigned long cmm_count_pages(void *arg)
-{
- struct memory_isolate_notify *marg = arg;
- struct cmm_page_array *pa;
- unsigned long start = (unsigned long)pfn_to_kaddr(marg->start_pfn);
- unsigned long end = start + (marg->nr_pages << PAGE_SHIFT);
- unsigned long idx;
-
- spin_lock(&cmm_lock);
- pa = cmm_page_list;
- while (pa) {
- if ((unsigned long)pa >= start && (unsigned long)pa < end)
- marg->pages_found++;
- for (idx = 0; idx < pa->index; idx++)
- if (pa->page[idx] >= start && pa->page[idx] < end)
- marg->pages_found++;
- pa = pa->next;
- }
- spin_unlock(&cmm_lock);
- return 0;
-}
-
-/**
- * cmm_memory_isolate_cb - Handle memory isolation notifier calls
- * @self: notifier block struct
- * @action: action to take
- * @arg: struct memory_isolate_notify data for handler
- *
- * Return value:
- * NOTIFY_OK or notifier error based on subfunction return value
- **/
-static int cmm_memory_isolate_cb(struct notifier_block *self,
- unsigned long action, void *arg)
-{
- int ret = 0;
-
- if (action == MEM_ISOLATE_COUNT)
- ret = cmm_count_pages(arg);
-
- return notifier_from_errno(ret);
-}
-
-static struct notifier_block cmm_mem_isolate_nb = {
- .notifier_call = cmm_memory_isolate_cb,
- .priority = CMM_MEM_ISOLATE_PRI
-};
-
-/**
- * cmm_mem_going_offline - Unloan pages where memory is to be removed
- * @arg: memory_notify structure with page range to be offlined
- *
- * Return value:
- * 0 on success
- **/
-static int cmm_mem_going_offline(void *arg)
-{
- struct memory_notify *marg = arg;
- unsigned long start_page = (unsigned long)pfn_to_kaddr(marg->start_pfn);
- unsigned long end_page = start_page + (marg->nr_pages << PAGE_SHIFT);
- struct cmm_page_array *pa_curr, *pa_last, *npa;
- unsigned long idx;
- unsigned long freed = 0;
-
- cmm_dbg("Memory going offline, searching 0x%lx (%ld pages).\n",
- start_page, marg->nr_pages);
- spin_lock(&cmm_lock);
-
- /* Search the page list for pages in the range to be offlined */
- pa_last = pa_curr = cmm_page_list;
- while (pa_curr) {
- for (idx = (pa_curr->index - 1); (idx + 1) > 0; idx--) {
- if ((pa_curr->page[idx] < start_page) ||
- (pa_curr->page[idx] >= end_page))
- continue;
-
- plpar_page_set_active(__pa(pa_curr->page[idx]));
- free_page(pa_curr->page[idx]);
- freed++;
- loaned_pages--;
- totalram_pages_inc();
- pa_curr->page[idx] = pa_last->page[--pa_last->index];
- if (pa_last->index == 0) {
- if (pa_curr == pa_last)
- pa_curr = pa_last->next;
- pa_last = pa_last->next;
- free_page((unsigned long)cmm_page_list);
- cmm_page_list = pa_last;
- }
- }
- pa_curr = pa_curr->next;
- }
-
- /* Search for page list structures in the range to be offlined */
- pa_last = NULL;
- pa_curr = cmm_page_list;
- while (pa_curr) {
- if (((unsigned long)pa_curr >= start_page) &&
- ((unsigned long)pa_curr < end_page)) {
- npa = (struct cmm_page_array *)__get_free_page(
- GFP_NOIO | __GFP_NOWARN |
- __GFP_NORETRY | __GFP_NOMEMALLOC);
- if (!npa) {
- spin_unlock(&cmm_lock);
- cmm_dbg("Failed to allocate memory for list "
- "management. Memory hotplug "
- "failed.\n");
- return -ENOMEM;
- }
- memcpy(npa, pa_curr, PAGE_SIZE);
- if (pa_curr == cmm_page_list)
- cmm_page_list = npa;
- if (pa_last)
- pa_last->next = npa;
- free_page((unsigned long) pa_curr);
- freed++;
- pa_curr = npa;
- }
-
- pa_last = pa_curr;
- pa_curr = pa_curr->next;
- }
-
- spin_unlock(&cmm_lock);
- cmm_dbg("Released %ld pages in the search range.\n", freed);
-
- return 0;
-}
-
-/**
* cmm_memory_cb - Handle memory hotplug notifier calls
* @self: notifier block struct
* @action: action to take
@@ -635,7 +482,6 @@ static int cmm_memory_cb(struct notifier_block *self,
case MEM_GOING_OFFLINE:
mutex_lock(&hotplug_mutex);
hotplug_occurred = 1;
- ret = cmm_mem_going_offline(arg);
break;
case MEM_OFFLINE:
case MEM_CANCEL_OFFLINE:
@@ -656,6 +502,106 @@ static struct notifier_block cmm_mem_nb = {
.priority = CMM_MEM_HOTPLUG_PRI
};
+#ifdef CONFIG_BALLOON_COMPACTION
+static struct vfsmount *balloon_mnt;
+
+static int cmm_init_fs_context(struct fs_context *fc)
+{
+ return init_pseudo(fc, PPC_CMM_MAGIC) ? 0 : -ENOMEM;
+}
+
+static struct file_system_type balloon_fs = {
+ .name = "ppc-cmm",
+ .init_fs_context = cmm_init_fs_context,
+ .kill_sb = kill_anon_super,
+};
+
+static int cmm_migratepage(struct balloon_dev_info *b_dev_info,
+ struct page *newpage, struct page *page,
+ enum migrate_mode mode)
+{
+ unsigned long flags;
+
+ /*
+ * loan/"inflate" the newpage first.
+ *
+ * We might race against the cmm_thread who might discover after our
+ * loan request that another page is to be unloaned. However, once
+ * the cmm_thread runs again later, this error will automatically
+ * be corrected.
+ */
+ if (plpar_page_set_loaned(newpage)) {
+ /* Unlikely, but possible. Tell the caller not to retry now. */
+ pr_err_ratelimited("%s: Cannot set page to loaned.", __func__);
+ return -EBUSY;
+ }
+
+ /* balloon page list reference */
+ get_page(newpage);
+
+ spin_lock_irqsave(&b_dev_info->pages_lock, flags);
+ balloon_page_insert(b_dev_info, newpage);
+ balloon_page_delete(page);
+ b_dev_info->isolated_pages--;
+ spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
+
+ /*
+ * activate/"deflate" the old page. We ignore any errors just like the
+ * other callers.
+ */
+ plpar_page_set_active(page);
+
+ /* balloon page list reference */
+ put_page(page);
+
+ return MIGRATEPAGE_SUCCESS;
+}
+
+static int cmm_balloon_compaction_init(void)
+{
+ int rc;
+
+ balloon_devinfo_init(&b_dev_info);
+ b_dev_info.migratepage = cmm_migratepage;
+
+ balloon_mnt = kern_mount(&balloon_fs);
+ if (IS_ERR(balloon_mnt)) {
+ rc = PTR_ERR(balloon_mnt);
+ balloon_mnt = NULL;
+ return rc;
+ }
+
+ b_dev_info.inode = alloc_anon_inode(balloon_mnt->mnt_sb);
+ if (IS_ERR(b_dev_info.inode)) {
+ rc = PTR_ERR(b_dev_info.inode);
+ b_dev_info.inode = NULL;
+ kern_unmount(balloon_mnt);
+ balloon_mnt = NULL;
+ return rc;
+ }
+
+ b_dev_info.inode->i_mapping->a_ops = &balloon_aops;
+ return 0;
+}
+static void cmm_balloon_compaction_deinit(void)
+{
+ if (b_dev_info.inode)
+ iput(b_dev_info.inode);
+ b_dev_info.inode = NULL;
+ kern_unmount(balloon_mnt);
+ balloon_mnt = NULL;
+}
+#else /* CONFIG_BALLOON_COMPACTION */
+static int cmm_balloon_compaction_init(void)
+{
+ return 0;
+}
+
+static void cmm_balloon_compaction_deinit(void)
+{
+}
+#endif /* CONFIG_BALLOON_COMPACTION */
+
/**
* cmm_init - Module initialization
*
@@ -664,26 +610,31 @@ static struct notifier_block cmm_mem_nb = {
**/
static int cmm_init(void)
{
- int rc = -ENOMEM;
+ int rc;
- if (!firmware_has_feature(FW_FEATURE_CMO))
+ if (!firmware_has_feature(FW_FEATURE_CMO) && !simulate)
return -EOPNOTSUPP;
- if ((rc = register_oom_notifier(&cmm_oom_nb)) < 0)
+ rc = cmm_balloon_compaction_init();
+ if (rc)
return rc;
+ rc = register_oom_notifier(&cmm_oom_nb);
+ if (rc < 0)
+ goto out_balloon_compaction;
+
if ((rc = register_reboot_notifier(&cmm_reboot_nb)))
goto out_oom_notifier;
if ((rc = cmm_sysfs_register(&cmm_dev)))
goto out_reboot_notifier;
- if (register_memory_notifier(&cmm_mem_nb) ||
- register_memory_isolate_notifier(&cmm_mem_isolate_nb))
+ rc = register_memory_notifier(&cmm_mem_nb);
+ if (rc)
goto out_unregister_notifier;
if (cmm_disabled)
- return rc;
+ return 0;
cmm_thread_ptr = kthread_run(cmm_thread, NULL, "cmmthread");
if (IS_ERR(cmm_thread_ptr)) {
@@ -691,16 +642,16 @@ static int cmm_init(void)
goto out_unregister_notifier;
}
- return rc;
-
+ return 0;
out_unregister_notifier:
unregister_memory_notifier(&cmm_mem_nb);
- unregister_memory_isolate_notifier(&cmm_mem_isolate_nb);
cmm_unregister_sysfs(&cmm_dev);
out_reboot_notifier:
unregister_reboot_notifier(&cmm_reboot_nb);
out_oom_notifier:
unregister_oom_notifier(&cmm_oom_nb);
+out_balloon_compaction:
+ cmm_balloon_compaction_deinit();
return rc;
}
@@ -717,9 +668,9 @@ static void cmm_exit(void)
unregister_oom_notifier(&cmm_oom_nb);
unregister_reboot_notifier(&cmm_reboot_nb);
unregister_memory_notifier(&cmm_mem_nb);
- unregister_memory_isolate_notifier(&cmm_mem_isolate_nb);
- cmm_free_pages(loaned_pages);
+ cmm_free_pages(atomic_long_read(&loaned_pages));
cmm_unregister_sysfs(&cmm_dev);
+ cmm_balloon_compaction_deinit();
}
/**
@@ -739,7 +690,7 @@ static int cmm_set_disable(const char *val, const struct kernel_param *kp)
if (cmm_thread_ptr)
kthread_stop(cmm_thread_ptr);
cmm_thread_ptr = NULL;
- cmm_free_pages(loaned_pages);
+ cmm_free_pages(atomic_long_read(&loaned_pages));
} else if (!disable && cmm_disabled) {
cmm_thread_ptr = kthread_run(cmm_thread, NULL, "cmmthread");
if (IS_ERR(cmm_thread_ptr))
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index bbda646b63b5..3e8cbfe7a80f 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -338,6 +338,62 @@ static void pseries_remove_processor(struct device_node *np)
cpu_maps_update_done();
}
+static int dlpar_offline_cpu(struct device_node *dn)
+{
+ int rc = 0;
+ unsigned int cpu;
+ int len, nthreads, i;
+ const __be32 *intserv;
+ u32 thread;
+
+ intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len);
+ if (!intserv)
+ return -EINVAL;
+
+ nthreads = len / sizeof(u32);
+
+ cpu_maps_update_begin();
+ for (i = 0; i < nthreads; i++) {
+ thread = be32_to_cpu(intserv[i]);
+ for_each_present_cpu(cpu) {
+ if (get_hard_smp_processor_id(cpu) != thread)
+ continue;
+
+ if (get_cpu_current_state(cpu) == CPU_STATE_OFFLINE)
+ break;
+
+ if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) {
+ set_preferred_offline_state(cpu,
+ CPU_STATE_OFFLINE);
+ cpu_maps_update_done();
+ timed_topology_update(1);
+ rc = device_offline(get_cpu_device(cpu));
+ if (rc)
+ goto out;
+ cpu_maps_update_begin();
+ break;
+ }
+
+ /*
+ * The cpu is in CPU_STATE_INACTIVE.
+ * Upgrade it's state to CPU_STATE_OFFLINE.
+ */
+ set_preferred_offline_state(cpu, CPU_STATE_OFFLINE);
+ WARN_ON(plpar_hcall_norets(H_PROD, thread) != H_SUCCESS);
+ __cpu_die(cpu);
+ break;
+ }
+ if (cpu == num_possible_cpus()) {
+ pr_warn("Could not find cpu to offline with physical id 0x%x\n",
+ thread);
+ }
+ }
+ cpu_maps_update_done();
+
+out:
+ return rc;
+}
+
static int dlpar_online_cpu(struct device_node *dn)
{
int rc = 0;
@@ -364,8 +420,10 @@ static int dlpar_online_cpu(struct device_node *dn)
timed_topology_update(1);
find_and_online_cpu_nid(cpu);
rc = device_online(get_cpu_device(cpu));
- if (rc)
+ if (rc) {
+ dlpar_offline_cpu(dn);
goto out;
+ }
cpu_maps_update_begin();
break;
@@ -407,17 +465,67 @@ static bool dlpar_cpu_exists(struct device_node *parent, u32 drc_index)
return found;
}
+static bool drc_info_valid_index(struct device_node *parent, u32 drc_index)
+{
+ struct property *info;
+ struct of_drc_info drc;
+ const __be32 *value;
+ u32 index;
+ int count, i, j;
+
+ info = of_find_property(parent, "ibm,drc-info", NULL);
+ if (!info)
+ return false;
+
+ value = of_prop_next_u32(info, NULL, &count);
+
+ /* First value of ibm,drc-info is number of drc-info records */
+ if (value)
+ value++;
+ else
+ return false;
+
+ for (i = 0; i < count; i++) {
+ if (of_read_drc_info_cell(&info, &value, &drc))
+ return false;
+
+ if (strncmp(drc.drc_type, "CPU", 3))
+ break;
+
+ if (drc_index > drc.last_drc_index)
+ continue;
+
+ index = drc.drc_index_start;
+ for (j = 0; j < drc.num_sequential_elems; j++) {
+ if (drc_index == index)
+ return true;
+
+ index += drc.sequential_inc;
+ }
+ }
+
+ return false;
+}
+
static bool valid_cpu_drc_index(struct device_node *parent, u32 drc_index)
{
bool found = false;
int rc, index;
- index = 0;
+ if (of_find_property(parent, "ibm,drc-info", NULL))
+ return drc_info_valid_index(parent, drc_index);
+
+ /* Note that the format of the ibm,drc-indexes array is
+ * the number of entries in the array followed by the array
+ * of drc values so we start looking at index = 1.
+ */
+ index = 1;
while (!found) {
u32 drc;
rc = of_property_read_u32_index(parent, "ibm,drc-indexes",
index++, &drc);
+
if (rc)
break;
@@ -505,63 +613,6 @@ static ssize_t dlpar_cpu_add(u32 drc_index)
return rc;
}
-static int dlpar_offline_cpu(struct device_node *dn)
-{
- int rc = 0;
- unsigned int cpu;
- int len, nthreads, i;
- const __be32 *intserv;
- u32 thread;
-
- intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len);
- if (!intserv)
- return -EINVAL;
-
- nthreads = len / sizeof(u32);
-
- cpu_maps_update_begin();
- for (i = 0; i < nthreads; i++) {
- thread = be32_to_cpu(intserv[i]);
- for_each_present_cpu(cpu) {
- if (get_hard_smp_processor_id(cpu) != thread)
- continue;
-
- if (get_cpu_current_state(cpu) == CPU_STATE_OFFLINE)
- break;
-
- if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) {
- set_preferred_offline_state(cpu,
- CPU_STATE_OFFLINE);
- cpu_maps_update_done();
- timed_topology_update(1);
- rc = device_offline(get_cpu_device(cpu));
- if (rc)
- goto out;
- cpu_maps_update_begin();
- break;
-
- }
-
- /*
- * The cpu is in CPU_STATE_INACTIVE.
- * Upgrade it's state to CPU_STATE_OFFLINE.
- */
- set_preferred_offline_state(cpu, CPU_STATE_OFFLINE);
- BUG_ON(plpar_hcall_norets(H_PROD, thread)
- != H_SUCCESS);
- __cpu_die(cpu);
- break;
- }
- if (cpu == num_possible_cpus())
- printk(KERN_WARNING "Could not find cpu to offline with physical id 0x%x\n", thread);
- }
- cpu_maps_update_done();
-
-out:
- return rc;
-
-}
-
static ssize_t dlpar_cpu_remove(struct device_node *dn, u32 drc_index)
{
int rc;
@@ -717,19 +768,52 @@ static int dlpar_cpu_remove_by_count(u32 cpus_to_remove)
return rc;
}
-static int find_dlpar_cpus_to_add(u32 *cpu_drcs, u32 cpus_to_add)
+static int find_drc_info_cpus_to_add(struct device_node *cpus,
+ struct property *info,
+ u32 *cpu_drcs, u32 cpus_to_add)
{
- struct device_node *parent;
+ struct of_drc_info drc;
+ const __be32 *value;
+ u32 count, drc_index;
int cpus_found = 0;
- int index, rc;
+ int i, j;
- parent = of_find_node_by_path("/cpus");
- if (!parent) {
- pr_warn("Could not find CPU root node in device tree\n");
- kfree(cpu_drcs);
+ if (!info)
return -1;
+
+ value = of_prop_next_u32(info, NULL, &count);
+ if (value)
+ value++;
+
+ for (i = 0; i < count; i++) {
+ of_read_drc_info_cell(&info, &value, &drc);
+ if (strncmp(drc.drc_type, "CPU", 3))
+ break;
+
+ drc_index = drc.drc_index_start;
+ for (j = 0; j < drc.num_sequential_elems; j++) {
+ if (dlpar_cpu_exists(cpus, drc_index))
+ continue;
+
+ cpu_drcs[cpus_found++] = drc_index;
+
+ if (cpus_found == cpus_to_add)
+ return cpus_found;
+
+ drc_index += drc.sequential_inc;
+ }
}
+ return cpus_found;
+}
+
+static int find_drc_index_cpus_to_add(struct device_node *cpus,
+ u32 *cpu_drcs, u32 cpus_to_add)
+{
+ int cpus_found = 0;
+ int index, rc;
+ u32 drc_index;
+
/* Search the ibm,drc-indexes array for possible CPU drcs to
* add. Note that the format of the ibm,drc-indexes array is
* the number of entries in the array followed by the array
@@ -737,25 +821,25 @@ static int find_dlpar_cpus_to_add(u32 *cpu_drcs, u32 cpus_to_add)
*/
index = 1;
while (cpus_found < cpus_to_add) {
- u32 drc;
+ rc = of_property_read_u32_index(cpus, "ibm,drc-indexes",
+ index++, &drc_index);
- rc = of_property_read_u32_index(parent, "ibm,drc-indexes",
- index++, &drc);
if (rc)
break;
- if (dlpar_cpu_exists(parent, drc))
+ if (dlpar_cpu_exists(cpus, drc_index))
continue;
- cpu_drcs[cpus_found++] = drc;
+ cpu_drcs[cpus_found++] = drc_index;
}
- of_node_put(parent);
return cpus_found;
}
static int dlpar_cpu_add_by_count(u32 cpus_to_add)
{
+ struct device_node *parent;
+ struct property *info;
u32 *cpu_drcs;
int cpus_added = 0;
int cpus_found;
@@ -767,7 +851,21 @@ static int dlpar_cpu_add_by_count(u32 cpus_to_add)
if (!cpu_drcs)
return -EINVAL;
- cpus_found = find_dlpar_cpus_to_add(cpu_drcs, cpus_to_add);
+ parent = of_find_node_by_path("/cpus");
+ if (!parent) {
+ pr_warn("Could not find CPU root node in device tree\n");
+ kfree(cpu_drcs);
+ return -1;
+ }
+
+ info = of_find_property(parent, "ibm,drc-info", NULL);
+ if (info)
+ cpus_found = find_drc_info_cpus_to_add(parent, info, cpu_drcs, cpus_to_add);
+ else
+ cpus_found = find_drc_index_cpus_to_add(parent, cpu_drcs, cpus_to_add);
+
+ of_node_put(parent);
+
if (cpus_found < cpus_to_add) {
pr_warn("Failed to find enough CPUs (%d of %d) to add\n",
cpus_found, cpus_to_add);
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 8e700390f3d6..c126b94d1943 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -338,7 +338,7 @@ static int pseries_remove_mem_node(struct device_node *np)
static bool lmb_is_removable(struct drmem_lmb *lmb)
{
int i, scns_per_block;
- int rc = 1;
+ bool rc = true;
unsigned long pfn, block_sz;
u64 phys_addr;
@@ -363,11 +363,11 @@ static bool lmb_is_removable(struct drmem_lmb *lmb)
if (!pfn_present(pfn))
continue;
- rc &= is_mem_section_removable(pfn, PAGES_PER_SECTION);
+ rc = rc && is_mem_section_removable(pfn, PAGES_PER_SECTION);
phys_addr += MIN_MEMORY_BLOCK_SIZE;
}
- return rc ? true : false;
+ return rc;
}
static int dlpar_add_lmb(struct drmem_lmb *);
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index f9f57c55655e..60cb29ae4739 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -774,7 +774,7 @@ static long pSeries_lpar_hpte_remove(unsigned long hpte_group)
/* don't remove a bolted entry */
lpar_rc = plpar_pte_remove(H_ANDCOND, hpte_group + slot_offset,
- (0x1UL << 4), &dummy1, &dummy2);
+ HPTE_V_BOLTED, &dummy1, &dummy2);
if (lpar_rc == H_SUCCESS)
return i;
@@ -938,11 +938,19 @@ static long pSeries_lpar_hpte_find(unsigned long vpn, int psize, int ssize)
hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, ssize);
want_v = hpte_encode_avpn(vpn, psize, ssize);
- /* Bolted entries are always in the primary group */
+ /*
+ * We try to keep bolted entries always in primary hash
+ * But in some case we can find them in secondary too.
+ */
hpte_group = (hash & htab_hash_mask) * HPTES_PER_GROUP;
slot = __pSeries_lpar_hpte_find(want_v, hpte_group);
- if (slot < 0)
- return -1;
+ if (slot < 0) {
+ /* Try in secondary */
+ hpte_group = (~hash & htab_hash_mask) * HPTES_PER_GROUP;
+ slot = __pSeries_lpar_hpte_find(want_v, hpte_group);
+ if (slot < 0)
+ return -1;
+ }
return hpte_group + slot;
}
@@ -1992,7 +2000,7 @@ static int __init vpa_debugfs_init(void)
{
char name[16];
long i;
- static struct dentry *vpa_dir;
+ struct dentry *vpa_dir;
if (!firmware_has_feature(FW_FEATURE_SPLPAR))
return 0;
diff --git a/arch/powerpc/platforms/pseries/of_helpers.c b/arch/powerpc/platforms/pseries/of_helpers.c
index 6df192f38f80..66dfd8256712 100644
--- a/arch/powerpc/platforms/pseries/of_helpers.c
+++ b/arch/powerpc/platforms/pseries/of_helpers.c
@@ -45,14 +45,14 @@ struct device_node *pseries_of_derive_parent(const char *path)
int of_read_drc_info_cell(struct property **prop, const __be32 **curval,
struct of_drc_info *data)
{
- const char *p;
+ const char *p = (char *)(*curval);
const __be32 *p2;
if (!data)
return -EINVAL;
/* Get drc-type:encode-string */
- p = data->drc_type = (char*) (*curval);
+ data->drc_type = (char *)p;
p = of_prop_next_string(*prop, p);
if (!p)
return -EINVAL;
@@ -65,9 +65,7 @@ int of_read_drc_info_cell(struct property **prop, const __be32 **curval,
/* Get drc-index-start:encode-int */
p2 = (const __be32 *)p;
- p2 = of_prop_next_u32(*prop, p2, &data->drc_index_start);
- if (!p2)
- return -EINVAL;
+ data->drc_index_start = be32_to_cpu(*p2);
/* Get drc-name-suffix-start:encode-int */
p2 = of_prop_next_u32(*prop, p2, &data->drc_name_suffix_start);
diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
index 61883291defc..f87b474d25a7 100644
--- a/arch/powerpc/platforms/pseries/papr_scm.c
+++ b/arch/powerpc/platforms/pseries/papr_scm.c
@@ -152,7 +152,7 @@ static int papr_scm_meta_get(struct papr_scm_priv *p,
int len, read;
int64_t ret;
- if ((hdr->in_offset + hdr->in_length) >= p->metadata_size)
+ if ((hdr->in_offset + hdr->in_length) > p->metadata_size)
return -EINVAL;
for (len = hdr->in_length; len; len -= read) {
@@ -206,7 +206,7 @@ static int papr_scm_meta_set(struct papr_scm_priv *p,
__be64 data_be;
int64_t ret;
- if ((hdr->in_offset + hdr->in_length) >= p->metadata_size)
+ if ((hdr->in_offset + hdr->in_length) > p->metadata_size)
return -EINVAL;
for (len = hdr->in_length; len; len -= wrote) {
@@ -513,7 +513,6 @@ static struct platform_driver papr_scm_driver = {
.remove = papr_scm_remove,
.driver = {
.name = "papr_scm",
- .owner = THIS_MODULE,
.of_match_table = papr_scm_match,
},
};
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 561917fa54a8..361986e4354e 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* PCI Dynamic LPAR, PCI Hot Plug and PCI EEH recovery code
* for RPA-compliant PPC64 platform.
@@ -6,23 +7,6 @@
*
* Updates, 2005, John Rose <johnrose@austin.ibm.com>
* Updates, 2005, Linas Vepstas <linas@austin.ibm.com>
- *
- * All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or (at
- * your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT. See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <linux/pci.h>
diff --git a/arch/powerpc/platforms/pseries/pseries_energy.c b/arch/powerpc/platforms/pseries/pseries_energy.c
index a96874f9492f..09e98d301db0 100644
--- a/arch/powerpc/platforms/pseries/pseries_energy.c
+++ b/arch/powerpc/platforms/pseries/pseries_energy.c
@@ -36,6 +36,7 @@ static int sysfs_entries;
static u32 cpu_to_drc_index(int cpu)
{
struct device_node *dn = NULL;
+ struct property *info;
int thread_index;
int rc = 1;
u32 ret = 0;
@@ -47,20 +48,18 @@ static u32 cpu_to_drc_index(int cpu)
/* Convert logical cpu number to core number */
thread_index = cpu_core_index_of_thread(cpu);
- if (firmware_has_feature(FW_FEATURE_DRC_INFO)) {
- struct property *info = NULL;
+ info = of_find_property(dn, "ibm,drc-info", NULL);
+ if (info) {
struct of_drc_info drc;
int j;
u32 num_set_entries;
const __be32 *value;
- info = of_find_property(dn, "ibm,drc-info", NULL);
- if (info == NULL)
- goto err_of_node_put;
-
value = of_prop_next_u32(info, NULL, &num_set_entries);
if (!value)
goto err_of_node_put;
+ else
+ value++;
for (j = 0; j < num_set_entries; j++) {
@@ -110,6 +109,7 @@ err:
static int drc_index_to_cpu(u32 drc_index)
{
struct device_node *dn = NULL;
+ struct property *info;
const int *indexes;
int thread_index = 0, cpu = 0;
int rc = 1;
@@ -117,21 +117,18 @@ static int drc_index_to_cpu(u32 drc_index)
dn = of_find_node_by_path("/cpus");
if (dn == NULL)
goto err;
-
- if (firmware_has_feature(FW_FEATURE_DRC_INFO)) {
- struct property *info = NULL;
+ info = of_find_property(dn, "ibm,drc-info", NULL);
+ if (info) {
struct of_drc_info drc;
int j;
u32 num_set_entries;
const __be32 *value;
- info = of_find_property(dn, "ibm,drc-info", NULL);
- if (info == NULL)
- goto err_of_node_put;
-
value = of_prop_next_u32(info, NULL, &num_set_entries);
if (!value)
goto err_of_node_put;
+ else
+ value++;
for (j = 0; j < num_set_entries; j++) {
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index 3acdcc3bb908..1d7f973c647b 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -255,7 +255,7 @@ static void rtas_parse_epow_errlog(struct rtas_error_log *log)
break;
case EPOW_SYSTEM_SHUTDOWN:
- handle_system_shutdown(epow_log->event_modifier);
+ handle_system_shutdown(modifier);
break;
case EPOW_SYSTEM_HALT: