From: Martin Schwidefsky [EMAIL PROTECTED]
The SIE instruction on s390 uses the 2nd half of the page table page to
virtualize the storage keys of a guest. This patch offers the s390_enable_sie
function, which reorganizes the page tables of a single-threaded process to
reserve space in the page table:
s390_enable_sie makes sure that the process is single threaded and then uses
dup_mm to create a new mm with reorganized page tables. The old mm is freed
and the process has now a page status extended field after every page table.
Code that wants to exploit pgstes should SELECT CONFIG_PGSTE.
This patch has a small common code hit, namely making dup_mm non-static.
Edit (Carsten): I've modified Martin's patch, following Jeremy Fitzhardinge's
review feedback. Now we do have the prototype for dup_mm in
include/linux/sched.h.
Signed-off-by: Martin Schwidefsky [EMAIL PROTECTED]
Signed-off-by: Carsten Otte [EMAIL PROTECTED]
---
arch/s390/Kconfig |4 +++
arch/s390/kernel/setup.c |4 +++
arch/s390/mm/pgtable.c | 53 ++---
include/asm-s390/mmu.h |1
include/asm-s390/mmu_context.h |8 +-
include/asm-s390/pgtable.h |1
include/linux/sched.h |2 +
kernel/fork.c |2 -
8 files changed, 70 insertions(+), 5 deletions(-)
Index: linux-host/arch/s390/Kconfig
===
--- linux-host.orig/arch/s390/Kconfig
+++ linux-host/arch/s390/Kconfig
@@ -55,6 +55,10 @@ config GENERIC_LOCKBREAK
default y
depends on SMP PREEMPT
+config PGSTE
+ bool
+ default y if KVM
+
mainmenu Linux Kernel Configuration
config S390
Index: linux-host/arch/s390/kernel/setup.c
===
--- linux-host.orig/arch/s390/kernel/setup.c
+++ linux-host/arch/s390/kernel/setup.c
@@ -315,7 +315,11 @@ static int __init early_parse_ipldelay(c
early_param(ipldelay, early_parse_ipldelay);
#ifdef CONFIG_S390_SWITCH_AMODE
+#ifdef CONFIG_PGSTE
+unsigned int switch_amode = 1;
+#else
unsigned int switch_amode = 0;
+#endif
EXPORT_SYMBOL_GPL(switch_amode);
static void set_amode_and_uaccess(unsigned long user_amode,
Index: linux-host/arch/s390/mm/pgtable.c
===
--- linux-host.orig/arch/s390/mm/pgtable.c
+++ linux-host/arch/s390/mm/pgtable.c
@@ -30,11 +30,27 @@
#define TABLES_PER_PAGE4
#define FRAG_MASK 15UL
#define SECOND_HALVES 10UL
+
+void clear_table_pgstes(unsigned long *table)
+{
+ clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE/4);
+ memset(table + 256, 0, PAGE_SIZE/4);
+ clear_table(table + 512, _PAGE_TYPE_EMPTY, PAGE_SIZE/4);
+ memset(table + 768, 0, PAGE_SIZE/4);
+}
+
#else
#define ALLOC_ORDER2
#define TABLES_PER_PAGE2
#define FRAG_MASK 3UL
#define SECOND_HALVES 2UL
+
+void clear_table_pgstes(unsigned long *table)
+{
+ clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE/2);
+ memset(table + 256, 0, PAGE_SIZE/2);
+}
+
#endif
unsigned long *crst_table_alloc(struct mm_struct *mm, int noexec)
@@ -153,7 +169,7 @@ unsigned long *page_table_alloc(struct m
unsigned long *table;
unsigned long bits;
- bits = mm-context.noexec ? 3UL : 1UL;
+ bits = (mm-context.noexec || mm-context.pgstes) ? 3UL : 1UL;
spin_lock(mm-page_table_lock);
page = NULL;
if (!list_empty(mm-context.pgtable_list)) {
@@ -170,7 +186,10 @@ unsigned long *page_table_alloc(struct m
pgtable_page_ctor(page);
page-flags = ~FRAG_MASK;
table = (unsigned long *) page_to_phys(page);
- clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE);
+ if (mm-context.pgstes)
+ clear_table_pgstes(table);
+ else
+ clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE);
spin_lock(mm-page_table_lock);
list_add(page-lru, mm-context.pgtable_list);
}
@@ -191,7 +210,7 @@ void page_table_free(struct mm_struct *m
struct page *page;
unsigned long bits;
- bits = mm-context.noexec ? 3UL : 1UL;
+ bits = (mm-context.noexec || mm-context.pgstes) ? 3UL : 1UL;
bits = (__pa(table) (PAGE_SIZE - 1)) / 256 / sizeof(unsigned long);
page = pfn_to_page(__pa(table) PAGE_SHIFT);
spin_lock(mm-page_table_lock);
@@ -228,3 +247,31 @@ void disable_noexec(struct mm_struct *mm
mm-context.noexec = 0;
update_mm(mm, tsk);
}
+
+/*
+ * switch on pgstes for its userspace process (for kvm)
+ */
+int s390_enable_sie(void)
+{
+ struct task_struct *tsk = current;
+ struct mm_struct *mm;
+
+ if (tsk-mm-context.pgstes)
+ return 0;
+ if (!tsk-mm || atomic_read(tsk-mm-mm_users) 1 ||
+ tsk-mm != tsk-active_mm ||
