From: Claudio Imbrenda <imbrenda@linux.ibm.com>
To: kvm@vger.kernel.org
Cc: linux-s390@vger.kernel.org, frankja@linux.ibm.com,
borntraeger@de.ibm.com, schlameuss@linux.ibm.com,
david@redhat.com, willy@infradead.org, hca@linux.ibm.com,
svens@linux.ibm.com, agordeev@linux.ibm.com, gor@linux.ibm.com,
nrb@linux.ibm.com, nsg@linux.ibm.com, seanjc@google.com,
seiden@linux.ibm.com, pbonzini@redhat.com
Subject: [PATCH v4 10/15] KVM: s390: stop using page->index for non-shadow gmaps
Date: Thu, 23 Jan 2025 15:46:22 +0100 [thread overview]
Message-ID: <20250123144627.312456-11-imbrenda@linux.ibm.com> (raw)
In-Reply-To: <20250123144627.312456-1-imbrenda@linux.ibm.com>
The host_to_guest radix tree will now map userspace addresses to guest
addresses, instead of userspace addresses to segment tables.
When segment tables and page tables are needed, they are found using an
additional gmap_table_walk().
This gets rid of all usage of page->index for non-shadow gmaps.
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Reviewed-by: Janosch Frank <frankja@linux.ibm.com>
---
arch/s390/mm/gmap.c | 105 +++++++++++++++++++++++---------------------
1 file changed, 54 insertions(+), 51 deletions(-)
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index ae71b401312b..1f83262a5a55 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -24,8 +24,20 @@
#include <asm/page.h>
#include <asm/tlb.h>
+/*
+ * The address is saved in a radix tree directly; NULL would be ambiguous,
+ * since 0 is a valid address, and NULL is returned when nothing was found.
+ * The lower bits are ignored by all users of the macro, so it can be used
+ * to distinguish a valid address 0 from a NULL.
+ */
+#define VALID_GADDR_FLAG 1
+#define IS_GADDR_VALID(gaddr) ((gaddr) & VALID_GADDR_FLAG)
+#define MAKE_VALID_GADDR(gaddr) (((gaddr) & HPAGE_MASK) | VALID_GADDR_FLAG)
+
#define GMAP_SHADOW_FAKE_TABLE 1ULL
+static inline unsigned long *gmap_table_walk(struct gmap *gmap, unsigned long gaddr, int level);
+
static struct page *gmap_alloc_crst(void)
{
struct page *page;
@@ -82,7 +94,6 @@ struct gmap *gmap_alloc(unsigned long limit)
page = gmap_alloc_crst();
if (!page)
goto out_free;
- page->index = 0;
list_add(&page->lru, &gmap->crst_list);
table = page_to_virt(page);
crst_table_init(table, etype);
@@ -303,7 +314,6 @@ static int gmap_alloc_table(struct gmap *gmap, unsigned long *table,
list_add(&page->lru, &gmap->crst_list);
*table = __pa(new) | _REGION_ENTRY_LENGTH |
(*table & _REGION_ENTRY_TYPE_MASK);
- page->index = gaddr;
page = NULL;
}
spin_unlock(&gmap->guest_table_lock);
@@ -312,21 +322,23 @@ static int gmap_alloc_table(struct gmap *gmap, unsigned long *table,
return 0;
}
-/**
- * __gmap_segment_gaddr - find virtual address from segment pointer
- * @entry: pointer to a segment table entry in the guest address space
- *
- * Returns the virtual address in the guest address space for the segment
- */
-static unsigned long __gmap_segment_gaddr(unsigned long *entry)
+static unsigned long host_to_guest_lookup(struct gmap *gmap, unsigned long vmaddr)
{
- struct page *page;
- unsigned long offset;
+ return (unsigned long)radix_tree_lookup(&gmap->host_to_guest, vmaddr >> PMD_SHIFT);
+}
- offset = (unsigned long) entry / sizeof(unsigned long);
- offset = (offset & (PTRS_PER_PMD - 1)) * PMD_SIZE;
- page = pmd_pgtable_page((pmd_t *) entry);
- return page->index + offset;
+static unsigned long host_to_guest_delete(struct gmap *gmap, unsigned long vmaddr)
+{
+ return (unsigned long)radix_tree_delete(&gmap->host_to_guest, vmaddr >> PMD_SHIFT);
+}
+
+static pmd_t *host_to_guest_pmd_delete(struct gmap *gmap, unsigned long vmaddr,
+ unsigned long *gaddr)
+{
+ *gaddr = host_to_guest_delete(gmap, vmaddr);
+ if (IS_GADDR_VALID(*gaddr))
+ return (pmd_t *)gmap_table_walk(gmap, *gaddr, 1);
+ return NULL;
}
/**
@@ -338,16 +350,19 @@ static unsigned long __gmap_segment_gaddr(unsigned long *entry)
*/
static int __gmap_unlink_by_vmaddr(struct gmap *gmap, unsigned long vmaddr)
{
- unsigned long *entry;
+ unsigned long gaddr;
int flush = 0;
+ pmd_t *pmdp;
BUG_ON(gmap_is_shadow(gmap));
spin_lock(&gmap->guest_table_lock);
- entry = radix_tree_delete(&gmap->host_to_guest, vmaddr >> PMD_SHIFT);
- if (entry) {
- flush = (*entry != _SEGMENT_ENTRY_EMPTY);
- *entry = _SEGMENT_ENTRY_EMPTY;
+
+ pmdp = host_to_guest_pmd_delete(gmap, vmaddr, &gaddr);
+ if (pmdp) {
+ flush = (pmd_val(*pmdp) != _SEGMENT_ENTRY_EMPTY);
+ *pmdp = __pmd(_SEGMENT_ENTRY_EMPTY);
}
+
spin_unlock(&gmap->guest_table_lock);
return flush;
}
@@ -564,7 +579,8 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
spin_lock(&gmap->guest_table_lock);
if (*table == _SEGMENT_ENTRY_EMPTY) {
rc = radix_tree_insert(&gmap->host_to_guest,
- vmaddr >> PMD_SHIFT, table);
+ vmaddr >> PMD_SHIFT,
+ (void *)MAKE_VALID_GADDR(gaddr));
if (!rc) {
if (pmd_leaf(*pmd)) {
*table = (pmd_val(*pmd) &
@@ -1995,7 +2011,6 @@ void ptep_notify(struct mm_struct *mm, unsigned long vmaddr,
pte_t *pte, unsigned long bits)
{
unsigned long offset, gaddr = 0;
- unsigned long *table;
struct gmap *gmap, *sg, *next;
offset = ((unsigned long) pte) & (255 * sizeof(pte_t));
@@ -2003,12 +2018,9 @@ void ptep_notify(struct mm_struct *mm, unsigned long vmaddr,
rcu_read_lock();
list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
spin_lock(&gmap->guest_table_lock);
- table = radix_tree_lookup(&gmap->host_to_guest,
- vmaddr >> PMD_SHIFT);
- if (table)
- gaddr = __gmap_segment_gaddr(table) + offset;
+ gaddr = host_to_guest_lookup(gmap, vmaddr) + offset;
spin_unlock(&gmap->guest_table_lock);
- if (!table)
+ if (!IS_GADDR_VALID(gaddr))
continue;
if (!list_empty(&gmap->children) && (bits & PGSTE_VSIE_BIT)) {
@@ -2068,10 +2080,8 @@ static void gmap_pmdp_clear(struct mm_struct *mm, unsigned long vmaddr,
rcu_read_lock();
list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
spin_lock(&gmap->guest_table_lock);
- pmdp = (pmd_t *)radix_tree_delete(&gmap->host_to_guest,
- vmaddr >> PMD_SHIFT);
+ pmdp = host_to_guest_pmd_delete(gmap, vmaddr, &gaddr);
if (pmdp) {
- gaddr = __gmap_segment_gaddr((unsigned long *)pmdp);
pmdp_notify_gmap(gmap, pmdp, gaddr);
WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
_SEGMENT_ENTRY_GMAP_UC |
@@ -2115,28 +2125,25 @@ EXPORT_SYMBOL_GPL(gmap_pmdp_csp);
*/
void gmap_pmdp_idte_local(struct mm_struct *mm, unsigned long vmaddr)
{
- unsigned long *entry, gaddr;
+ unsigned long gaddr;
struct gmap *gmap;
pmd_t *pmdp;
rcu_read_lock();
list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
spin_lock(&gmap->guest_table_lock);
- entry = radix_tree_delete(&gmap->host_to_guest,
- vmaddr >> PMD_SHIFT);
- if (entry) {
- pmdp = (pmd_t *)entry;
- gaddr = __gmap_segment_gaddr(entry);
+ pmdp = host_to_guest_pmd_delete(gmap, vmaddr, &gaddr);
+ if (pmdp) {
pmdp_notify_gmap(gmap, pmdp, gaddr);
- WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
- _SEGMENT_ENTRY_GMAP_UC |
- _SEGMENT_ENTRY));
+ WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
+ _SEGMENT_ENTRY_GMAP_UC |
+ _SEGMENT_ENTRY));
if (MACHINE_HAS_TLB_GUEST)
__pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE,
gmap->asce, IDTE_LOCAL);
else if (MACHINE_HAS_IDTE)
__pmdp_idte(gaddr, pmdp, 0, 0, IDTE_LOCAL);
- *entry = _SEGMENT_ENTRY_EMPTY;
+ *pmdp = __pmd(_SEGMENT_ENTRY_EMPTY);
}
spin_unlock(&gmap->guest_table_lock);
}
@@ -2151,22 +2158,19 @@ EXPORT_SYMBOL_GPL(gmap_pmdp_idte_local);
*/
void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr)
{
- unsigned long *entry, gaddr;
+ unsigned long gaddr;
struct gmap *gmap;
pmd_t *pmdp;
rcu_read_lock();
list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
spin_lock(&gmap->guest_table_lock);
- entry = radix_tree_delete(&gmap->host_to_guest,
- vmaddr >> PMD_SHIFT);
- if (entry) {
- pmdp = (pmd_t *)entry;
- gaddr = __gmap_segment_gaddr(entry);
+ pmdp = host_to_guest_pmd_delete(gmap, vmaddr, &gaddr);
+ if (pmdp) {
pmdp_notify_gmap(gmap, pmdp, gaddr);
- WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
- _SEGMENT_ENTRY_GMAP_UC |
- _SEGMENT_ENTRY));
+ WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
+ _SEGMENT_ENTRY_GMAP_UC |
+ _SEGMENT_ENTRY));
if (MACHINE_HAS_TLB_GUEST)
__pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE,
gmap->asce, IDTE_GLOBAL);
@@ -2174,7 +2178,7 @@ void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr)
__pmdp_idte(gaddr, pmdp, 0, 0, IDTE_GLOBAL);
else
__pmdp_csp(pmdp);
- *entry = _SEGMENT_ENTRY_EMPTY;
+ *pmdp = __pmd(_SEGMENT_ENTRY_EMPTY);
}
spin_unlock(&gmap->guest_table_lock);
}
@@ -2690,7 +2694,6 @@ int s390_replace_asce(struct gmap *gmap)
page = gmap_alloc_crst();
if (!page)
return -ENOMEM;
- page->index = 0;
table = page_to_virt(page);
memcpy(table, gmap->table, 1UL << (CRST_ALLOC_ORDER + PAGE_SHIFT));
--
2.48.1
next prev parent reply other threads:[~2025-01-23 14:46 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-01-23 14:46 [PATCH v4 00/15] KVM: s390: Stop using page->index and other things Claudio Imbrenda
2025-01-23 14:46 ` [PATCH v4 01/15] KVM: Do not restrict the size of KVM-internal memory regions Claudio Imbrenda
2025-01-23 14:46 ` [PATCH v4 02/15] KVM: s390: wrapper for KVM_BUG Claudio Imbrenda
2025-01-23 14:46 ` [PATCH v4 03/15] KVM: s390: fake memslot for ucontrol VMs Claudio Imbrenda
2025-01-23 14:46 ` [PATCH v4 04/15] KVM: s390: selftests: fix ucontrol memory region test Claudio Imbrenda
2025-01-24 14:34 ` Christoph Schlameuss
2025-01-23 14:46 ` [PATCH v4 05/15] KVM: s390: move pv gmap functions into kvm Claudio Imbrenda
2025-01-27 8:06 ` Christoph Schlameuss
2025-01-23 14:46 ` [PATCH v4 06/15] KVM: s390: use __kvm_faultin_pfn() Claudio Imbrenda
2025-01-23 14:46 ` [PATCH v4 07/15] KVM: s390: get rid of gmap_fault() Claudio Imbrenda
2025-01-23 14:46 ` [PATCH v4 08/15] KVM: s390: get rid of gmap_translate() Claudio Imbrenda
2025-01-23 14:46 ` [PATCH v4 09/15] KVM: s390: move some gmap shadowing functions away from mm/gmap.c Claudio Imbrenda
2025-01-27 9:16 ` Christoph Schlameuss
2025-01-23 14:46 ` Claudio Imbrenda [this message]
2025-01-27 9:26 ` [PATCH v4 10/15] KVM: s390: stop using page->index for non-shadow gmaps Christoph Schlameuss
2025-01-23 14:46 ` [PATCH v4 11/15] KVM: s390: stop using lists to keep track of used dat tables Claudio Imbrenda
2025-01-23 14:46 ` [PATCH v4 12/15] KVM: s390: move gmap_shadow_pgt_lookup() into kvm Claudio Imbrenda
2025-01-27 9:33 ` Christoph Schlameuss
2025-01-23 14:46 ` [PATCH v4 13/15] KVM: s390: remove useless page->index usage Claudio Imbrenda
2025-01-27 9:34 ` Christoph Schlameuss
2025-01-23 14:46 ` [PATCH v4 14/15] KVM: s390: move PGSTE softbits Claudio Imbrenda
2025-01-27 9:35 ` Christoph Schlameuss
2025-01-23 14:46 ` [PATCH v4 15/15] KVM: s390: remove the last user of page->index Claudio Imbrenda
2025-01-27 9:36 ` Christoph Schlameuss
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250123144627.312456-11-imbrenda@linux.ibm.com \
--to=imbrenda@linux.ibm.com \
--cc=agordeev@linux.ibm.com \
--cc=borntraeger@de.ibm.com \
--cc=david@redhat.com \
--cc=frankja@linux.ibm.com \
--cc=gor@linux.ibm.com \
--cc=hca@linux.ibm.com \
--cc=kvm@vger.kernel.org \
--cc=linux-s390@vger.kernel.org \
--cc=nrb@linux.ibm.com \
--cc=nsg@linux.ibm.com \
--cc=pbonzini@redhat.com \
--cc=schlameuss@linux.ibm.com \
--cc=seanjc@google.com \
--cc=seiden@linux.ibm.com \
--cc=svens@linux.ibm.com \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox