After the page ranges in the pagetable have been reserved the pagetable
is no longer needed. Rather than free it during early boot by unreserving
page-sized blocks which can be inefficient when dealing with a large number
of blocks, wait until the page structs have been initialized and free them
as pages.
Signed-off-by: Anthony Yznaga <anthony.yznaga@xxxxxxxxxx>
---
arch/x86/mm/init_64.c | 1 +
include/linux/pkram.h | 3 ++
mm/pkram.c | 11 +++++++
mm/pkram_pagetable.c | 82 +++++++++++++++++++++++++++++++++++++++++++++++++++
4 files changed, 97 insertions(+)
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index ae569ef6bd7d..72662615977b 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1245,6 +1245,7 @@ void __init mem_init(void)
after_bootmem = 1;
x86_init.hyper.init_after_bootmem();
+ pkram_free_pgt();
totalram_pages_add(pkram_reserved_pages);
/*
* Must be done after boot memory is put on freelist, because here we
diff --git a/include/linux/pkram.h b/include/linux/pkram.h
index 1b475f6e1598..edc5d8bef9d3 100644
--- a/include/linux/pkram.h
+++ b/include/linux/pkram.h
@@ -39,6 +39,7 @@ struct pkram_pg_state {
};
void pkram_walk_pgt_rev(struct pkram_pg_state *st, pgd_t *pgd);
+void pkram_free_pgt_walk_pgd(pgd_t *pgd);
int pkram_prepare_save(struct pkram_stream *ps, const char *name,
gfp_t gfp_mask);
@@ -64,9 +65,11 @@ size_t pkram_read(struct pkram_stream *ps, void *buf, size_t count);
#ifdef CONFIG_PKRAM
extern unsigned long pkram_reserved_pages;
void pkram_reserve(void);
+void pkram_free_pgt(void);
#else
#define pkram_reserved_pages 0UL
static inline void pkram_reserve(void) { }
+static inline void pkram_free_pgt(void) { }
#endif
#endif /* _LINUX_PKRAM_H */
diff --git a/mm/pkram.c b/mm/pkram.c
index 2c323154df76..dd3c89614010 100644
--- a/mm/pkram.c
+++ b/mm/pkram.c
@@ -1227,3 +1227,14 @@ static int __init pkram_reserve_page_ranges(pgd_t *pgd)
return err;
}
+
+void pkram_free_pgt(void)
+{
+ if (!pkram_pgd)
+ return;
+
+ pkram_free_pgt_walk_pgd(pkram_pgd);
+
+ __free_pages_core(virt_to_page(pkram_pgd), 0);
+ pkram_pgd = NULL;
+}
diff --git a/mm/pkram_pagetable.c b/mm/pkram_pagetable.c
index d31aa36207ba..7033e9b1c47f 100644
--- a/mm/pkram_pagetable.c
+++ b/mm/pkram_pagetable.c
@@ -3,6 +3,8 @@
#include <asm/pgtable.h>
#include <linux/pkram.h>
+#include "internal.h"
+
#define pgd_none(a) (pgtable_l5_enabled() ? pgd_none(a) : p4d_none(__p4d(pgd_val(a))))
static int note_page_rev(struct pkram_pg_state *st, unsigned long curr_size, bool present)
@@ -167,3 +169,83 @@ void pkram_walk_pgt_rev(struct pkram_pg_state *st, pgd_t *pgd)
break;
}
}
+
+static void pkram_free_pgt_walk_pmd(pud_t addr)
+{
+ unsigned long bitmap_pa;
+ struct page *page;
+ pmd_t *start;
+ int i;
+
+ start = (pmd_t *)pud_page_vaddr(addr);
+ for (i = 0; i < PTRS_PER_PMD; i++, start++) {
+ if (!pmd_none(*start)) {
+ bitmap_pa = pte_val(pte_clrhuge(*(pte_t *)start));
+ if (pmd_large(*start) && !bitmap_pa)
+ continue;
+ page = virt_to_page(__va(bitmap_pa));
+ __free_pages_core(page, 0);
+ }
+ }
+}
+
+static void pkram_free_pgt_walk_pud(p4d_t addr)
+{
+ struct page *page;
+ pud_t *start;
+ int i;
+
+ start = (pud_t *)p4d_page_vaddr(addr);
+ for (i = 0; i < PTRS_PER_PUD; i++, start++) {
+ if (!pud_none(*start)) {
+ if (pud_large(*start)) {
+ WARN_ONCE(1, "PKRAM: unexpected pud hugepage\n");
+ continue;
+ }
+ pkram_free_pgt_walk_pmd(*start);
+ page = virt_to_page(__va(pud_val(*start)));
+ __free_pages_core(page, 0);
+ }
+ }
+}
+
+static void pkram_free_pgt_walk_p4d(pgd_t addr)
+{
+ struct page *page;
+ p4d_t *start;
+ int i;
+
+ if (PTRS_PER_P4D == 1)
+ return pkram_free_pgt_walk_pud(__p4d(pgd_val(addr)));
+
+ start = (p4d_t *)pgd_page_vaddr(addr);
+ for (i = 0; i < PTRS_PER_P4D; i++, start++) {
+ if (!p4d_none(*start)) {
+ if (p4d_large(*start)) {
+ WARN_ONCE(1, "PKRAM: unexpected p4d hugepage\n");
+ continue;
+ }
+ pkram_free_pgt_walk_pud(*start);
+ page = virt_to_page(__va(p4d_val(*start)));
+ __free_pages_core(page, 0);
+ }
+ }
+}
+
+/*
+ * Free the pagetable passed from the previous boot.
+ */
+void pkram_free_pgt_walk_pgd(pgd_t *pgd)
+{
+ pgd_t *start = pgd;
+ struct page *page;
+ int i;
+
+ for (i = 0; i < PTRS_PER_PGD; i++, start++) {
+ if (!pgd_none(*start)) {
+ pkram_free_pgt_walk_p4d(*start);
+ page = virt_to_page(__va(pgd_val(*start)));
+ __free_pages_core(page, 0);
+ }
+ }
+}
--
2.13.3
_______________________________________________
kexec mailing list
kexec@xxxxxxxxxxxxxxxxxxx
http://lists.infradead.org/mailman/listinfo/kexec
