powerpc/pseries: CMO unused page hinting

Adds support for the "unused" page hint which can be used in shared
memory partitions to flag pages not in use, which will then be stolen
before active pages by the hypervisor when memory needs to be moved to
LPARs in need of additional memory.  Failure to mark pages as 'unused'
makes the LPAR slower to give up unused memory to other partitions.

This adds the kernel parameter 'cmo_free_hint' to disable this
functionality.

Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: Robert Jennings <rcj@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

3 files changed, 64 insertions, 0 deletions

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index e87bdbf..844e9a6 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -497,6 +497,13 @@ and is between 256 and 4096 characters. It is defined in the file
 			Also note the kernel might malfunction if you disable
 			some critical bits.
 
+	cmo_free_hint=	[PPC] Format: { yes | no }
+			Specify whether pages are marked as being inactive
+			when they are freed.  This is used in CMO environments
+			to determine OS memory pressure for page stealing by
+			a hypervisor.
+			Default: yes
+
 	code_bytes	[X86] How many bytes of object code to print
 			in an oops report.
 			Range: 0 - 8192
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 32cbf16..4940662 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -231,6 +231,11 @@ extern void copy_user_page(void *to, void *from, unsigned long vaddr,
 		struct page *p);
 extern int page_is_ram(unsigned long pfn);
 
+#ifdef CONFIG_PPC_SMLPAR
+void arch_free_page(struct page *page, int order);
+#define HAVE_ARCH_FREE_PAGE
+#endif
+
 struct vm_area_struct;
 
 typedef struct page *pgtable_t;
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 52a80e5..e3139fa 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -609,3 +609,55 @@ void __init hpte_init_lpar(void)
 	ppc_md.flush_hash_range	= pSeries_lpar_flush_hash_range;
 	ppc_md.hpte_clear_all   = pSeries_lpar_hptab_clear;
 }
+
+#ifdef CONFIG_PPC_SMLPAR
+#define CMO_FREE_HINT_DEFAULT 1
+static int cmo_free_hint_flag = CMO_FREE_HINT_DEFAULT;
+
+static int __init cmo_free_hint(char *str)
+{
+	char *parm;
+	parm = strstrip(str);
+
+	if (strcasecmp(parm, "no") == 0 || strcasecmp(parm, "off") == 0) {
+		printk(KERN_INFO "cmo_free_hint: CMO free page hinting is not active.\n");
+		cmo_free_hint_flag = 0;
+		return 1;
+	}
+
+	cmo_free_hint_flag = 1;
+	printk(KERN_INFO "cmo_free_hint: CMO free page hinting is active.\n");
+
+	if (strcasecmp(parm, "yes") == 0 || strcasecmp(parm, "on") == 0)
+		return 1;
+
+	return 0;
+}
+
+__setup("cmo_free_hint=", cmo_free_hint);
+
+static void pSeries_set_page_state(struct page *page, int order,
+				   unsigned long state)
+{
+	int i, j;
+	unsigned long cmo_page_sz, addr;
+
+	cmo_page_sz = cmo_get_page_size();
+	addr = __pa((unsigned long)page_address(page));
+
+	for (i = 0; i < (1 << order); i++, addr += PAGE_SIZE) {
+		for (j = 0; j < PAGE_SIZE; j += cmo_page_sz)
+			plpar_hcall_norets(H_PAGE_INIT, state, addr + j, 0);
+	}
+}
+
+void arch_free_page(struct page *page, int order)
+{
+	if (!cmo_free_hint_flag || !firmware_has_feature(FW_FEATURE_CMO))
+		return;
+
+	pSeries_set_page_state(page, order, H_PAGE_SET_UNUSED);
+}
+EXPORT_SYMBOL(arch_free_page);
+
+#endif