xen-devel.lists.xenproject.org archive mirror
 help / color / mirror / Atom feed
From: Jan Beulich <jbeulich@suse.com>
To: "xen-devel@lists.xenproject.org" <xen-devel@lists.xenproject.org>
Cc: "Andrew Cooper" <andrew.cooper3@citrix.com>,
	"George Dunlap" <george.dunlap@citrix.com>,
	"Ian Jackson" <iwj@xenproject.org>,
	"Julien Grall" <julien@xen.org>,
	"Stefano Stabellini" <sstabellini@kernel.org>,
	"Wei Liu" <wl@xen.org>, "Roger Pau Monné" <roger.pau@citrix.com>
Subject: [PATCH v3 01/22] mm: introduce xvmalloc() et al and use for grant table allocations
Date: Thu, 22 Apr 2021 16:43:39 +0200	[thread overview]
Message-ID: <69778de6-3b94-64d1-99d9-1a0fcfa503fd@suse.com> (raw)
In-Reply-To: <322de6db-e01f-0b57-5777-5d94a13c441a@suse.com>

All of the array allocations in grant_table_init() can exceed a page's
worth of memory, which xmalloc()-based interfaces aren't really suitable
for after boot. We also don't need any of these allocations to be
physically contiguous.. Introduce interfaces dynamically switching
between xmalloc() et al and vmalloc() et al, based on requested size,
and use them instead.

All the wrappers in the new header get cloned mostly verbatim from
xmalloc.h, with the sole adjustment to switch unsigned long to size_t
for sizes and to unsigned int for alignments.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
---
v2: Actually edit a copy-and-pasted comment in xvmalloc.h which was
    meant to be edited from the beginning.
---
I'm unconvinced of the mentioning of "physically contiguous" in the
comment at the top of the new header: I don't think xmalloc() provides
such a guarantee. Any use assuming so would look (latently) broken to
me.

--- a/xen/common/grant_table.c
+++ b/xen/common/grant_table.c
@@ -37,7 +37,7 @@
 #include <xen/iommu.h>
 #include <xen/paging.h>
 #include <xen/keyhandler.h>
-#include <xen/vmap.h>
+#include <xen/xvmalloc.h>
 #include <xen/nospec.h>
 #include <xsm/xsm.h>
 #include <asm/flushtlb.h>
@@ -1749,8 +1749,8 @@ gnttab_populate_status_frames(struct dom
 
     if ( gt->status == ZERO_BLOCK_PTR )
     {
-        gt->status = xzalloc_array(grant_status_t *,
-                                   grant_to_status_frames(gt->max_grant_frames));
+        gt->status = xvzalloc_array(grant_status_t *,
+                                    grant_to_status_frames(gt->max_grant_frames));
         if ( !gt->status )
         {
             gt->status = ZERO_BLOCK_PTR;
@@ -1780,7 +1780,7 @@ status_alloc_failed:
     }
     if ( !nr_status_frames(gt) )
     {
-        xfree(gt->status);
+        xvfree(gt->status);
         gt->status = ZERO_BLOCK_PTR;
     }
     return -ENOMEM;
@@ -1852,7 +1852,7 @@ gnttab_unpopulate_status_frames(struct d
     gt->nr_status_frames = 0;
     for ( i = 0; i < n; i++ )
         free_xenheap_page(gt->status[i]);
-    xfree(gt->status);
+    xvfree(gt->status);
     gt->status = ZERO_BLOCK_PTR;
 
     return 0;
@@ -1966,21 +1966,22 @@ int grant_table_init(struct domain *d, i
     d->grant_table = gt;
 
     /* Active grant table. */
-    gt->active = xzalloc_array(struct active_grant_entry *,
-                               max_nr_active_grant_frames(gt));
+    gt->active = xvzalloc_array(struct active_grant_entry *,
+                                max_nr_active_grant_frames(gt));
     if ( gt->active == NULL )
         goto out;
 
     /* Tracking of mapped foreign frames table */
     if ( gt->max_maptrack_frames )
     {
-        gt->maptrack = vzalloc(gt->max_maptrack_frames * sizeof(*gt->maptrack));
+        gt->maptrack = xvzalloc_array(struct grant_mapping *,
+                                      gt->max_maptrack_frames);
         if ( gt->maptrack == NULL )
             goto out;
     }
 
     /* Shared grant table. */
-    gt->shared_raw = xzalloc_array(void *, gt->max_grant_frames);
+    gt->shared_raw = xvzalloc_array(void *, gt->max_grant_frames);
     if ( gt->shared_raw == NULL )
         goto out;
 
@@ -3868,19 +3869,19 @@ grant_table_destroy(
 
     for ( i = 0; i < nr_grant_frames(t); i++ )
         free_xenheap_page(t->shared_raw[i]);
-    xfree(t->shared_raw);
+    xvfree(t->shared_raw);
 
     for ( i = 0; i < nr_maptrack_frames(t); i++ )
         free_xenheap_page(t->maptrack[i]);
-    vfree(t->maptrack);
+    xvfree(t->maptrack);
 
     for ( i = 0; i < nr_active_grant_frames(t); i++ )
         free_xenheap_page(t->active[i]);
-    xfree(t->active);
+    xvfree(t->active);
 
     for ( i = 0; i < nr_status_frames(t); i++ )
         free_xenheap_page(t->status[i]);
-    xfree(t->status);
+    xvfree(t->status);
 
     xfree(t);
     d->grant_table = NULL;
--- a/xen/common/vmap.c
+++ b/xen/common/vmap.c
@@ -7,6 +7,7 @@
 #include <xen/spinlock.h>
 #include <xen/types.h>
 #include <xen/vmap.h>
+#include <xen/xvmalloc.h>
 #include <asm/page.h>
 
 static DEFINE_SPINLOCK(vm_lock);
@@ -301,11 +302,29 @@ void *vzalloc(size_t size)
     return p;
 }
 
-void vfree(void *va)
+static void _vfree(const void *va, unsigned int pages, enum vmap_region type)
 {
-    unsigned int i, pages;
+    unsigned int i;
     struct page_info *pg;
     PAGE_LIST_HEAD(pg_list);
+
+    ASSERT(pages);
+
+    for ( i = 0; i < pages; i++ )
+    {
+        pg = vmap_to_page(va + i * PAGE_SIZE);
+        ASSERT(pg);
+        page_list_add(pg, &pg_list);
+    }
+    vunmap(va);
+
+    while ( (pg = page_list_remove_head(&pg_list)) != NULL )
+        free_domheap_page(pg);
+}
+
+void vfree(void *va)
+{
+    unsigned int pages;
     enum vmap_region type = VMAP_DEFAULT;
 
     if ( !va )
@@ -317,18 +336,71 @@ void vfree(void *va)
         type = VMAP_XEN;
         pages = vm_size(va, type);
     }
-    ASSERT(pages);
 
-    for ( i = 0; i < pages; i++ )
+    _vfree(va, pages, type);
+}
+
+void xvfree(void *va)
+{
+    unsigned int pages = vm_size(va, VMAP_DEFAULT);
+
+    if ( pages )
+        _vfree(va, pages, VMAP_DEFAULT);
+    else
+        xfree(va);
+}
+
+void *_xvmalloc(size_t size, unsigned int align)
+{
+    ASSERT(align <= PAGE_SIZE);
+    return size <= PAGE_SIZE ? _xmalloc(size, align) : vmalloc(size);
+}
+
+void *_xvzalloc(size_t size, unsigned int align)
+{
+    ASSERT(align <= PAGE_SIZE);
+    return size <= PAGE_SIZE ? _xzalloc(size, align) : vzalloc(size);
+}
+
+void *_xvrealloc(void *va, size_t size, unsigned int align)
+{
+    size_t pages = vm_size(va, VMAP_DEFAULT);
+    void *ptr;
+
+    ASSERT(align <= PAGE_SIZE);
+
+    if ( !pages )
     {
-        struct page_info *page = vmap_to_page(va + i * PAGE_SIZE);
+        if ( size <= PAGE_SIZE )
+            return _xrealloc(va, size, align);
 
-        ASSERT(page);
-        page_list_add(page, &pg_list);
+        ptr = vmalloc(size);
+        if ( ptr && va && va != ZERO_BLOCK_PTR )
+        {
+            /*
+             * xmalloc-based allocations up to PAGE_SIZE don't cross page
+             * boundaries. Therefore, without needing to know the exact
+             * prior allocation size, simply copy the entire tail of the
+             * page containing the earlier allocation.
+             */
+            memcpy(ptr, va, PAGE_SIZE - PAGE_OFFSET(va));
+            xfree(va);
+        }
+    }
+    else if ( pages == PFN_UP(size) )
+        ptr = va;
+    else
+    {
+        ptr = _xvmalloc(size, align);
+        if ( ptr )
+        {
+            memcpy(ptr, va, min(size, pages << PAGE_SHIFT));
+            vfree(va);
+        }
+        else if ( pages > PFN_UP(size) )
+            ptr = va;
     }
-    vunmap(va);
 
-    while ( (pg = page_list_remove_head(&pg_list)) != NULL )
-        free_domheap_page(pg);
+    return ptr;
 }
 #endif
--- /dev/null
+++ b/xen/include/xen/xvmalloc.h
@@ -0,0 +1,73 @@
+
+#ifndef __XVMALLOC_H__
+#define __XVMALLOC_H__
+
+#include <xen/cache.h>
+#include <xen/types.h>
+
+/*
+ * Xen malloc/free-style interface for allocations possibly exceeding a page's
+ * worth of memory, as long as there's no need to have physically contiguous
+ * memory allocated.  These should be used in preference to xmalloc() et al
+ * whenever the size is not known to be constrained to at most a single page.
+ */
+
+/* Allocate space for typed object. */
+#define xvmalloc(_type) ((_type *)_xvmalloc(sizeof(_type), __alignof__(_type)))
+#define xvzalloc(_type) ((_type *)_xvzalloc(sizeof(_type), __alignof__(_type)))
+
+/* Allocate space for array of typed objects. */
+#define xvmalloc_array(_type, _num) \
+    ((_type *)_xvmalloc_array(sizeof(_type), __alignof__(_type), _num))
+#define xvzalloc_array(_type, _num) \
+    ((_type *)_xvzalloc_array(sizeof(_type), __alignof__(_type), _num))
+
+/* Allocate space for a structure with a flexible array of typed objects. */
+#define xvzalloc_flex_struct(type, field, nr) \
+    ((type *)_xvzalloc(offsetof(type, field[nr]), __alignof__(type)))
+
+#define xvmalloc_flex_struct(type, field, nr) \
+    ((type *)_xvmalloc(offsetof(type, field[nr]), __alignof__(type)))
+
+/* Re-allocate space for a structure with a flexible array of typed objects. */
+#define xvrealloc_flex_struct(ptr, field, nr)                          \
+    ((typeof(ptr))_xvrealloc(ptr, offsetof(typeof(*(ptr)), field[nr]), \
+                             __alignof__(typeof(*(ptr)))))
+
+/* Allocate untyped storage. */
+#define xvmalloc_bytes(_bytes) _xvmalloc(_bytes, SMP_CACHE_BYTES)
+#define xvzalloc_bytes(_bytes) _xvzalloc(_bytes, SMP_CACHE_BYTES)
+
+/* Free any of the above. */
+extern void xvfree(void *);
+
+/* Free an allocation, and zero the pointer to it. */
+#define XVFREE(p) do { \
+    xvfree(p);         \
+    (p) = NULL;        \
+} while ( false )
+
+/* Underlying functions */
+extern void *_xvmalloc(size_t size, unsigned int align);
+extern void *_xvzalloc(size_t size, unsigned int align);
+extern void *_xvrealloc(void *ptr, size_t size, unsigned int align);
+
+static inline void *_xvmalloc_array(
+    size_t size, unsigned int align, unsigned long num)
+{
+    /* Check for overflow. */
+    if ( size && num > UINT_MAX / size )
+        return NULL;
+    return _xvmalloc(size * num, align);
+}
+
+static inline void *_xvzalloc_array(
+    size_t size, unsigned int align, unsigned long num)
+{
+    /* Check for overflow. */
+    if ( size && num > UINT_MAX / size )
+        return NULL;
+    return _xvzalloc(size * num, align);
+}
+
+#endif /* __XVMALLOC_H__ */



  reply	other threads:[~2021-04-22 14:43 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-22 14:38 [PATCH v3 00/22] xvmalloc() / x86 xstate area / x86 CPUID / AMX+XFD Jan Beulich
2021-04-22 14:43 ` Jan Beulich [this message]
2021-05-03 11:31   ` [PATCH v3 01/22] mm: introduce xvmalloc() et al and use for grant table allocations Roger Pau Monné
2021-05-03 13:50     ` Jan Beulich
2021-05-03 14:54       ` Roger Pau Monné
2021-05-03 15:21         ` Jan Beulich
2021-05-03 16:39           ` Roger Pau Monné
2021-04-22 14:44 ` [PATCH v3 02/22] x86/xstate: use xvzalloc() for save area allocation Jan Beulich
2021-05-05 13:29   ` Roger Pau Monné
2021-04-22 14:44 ` [PATCH v3 03/22] x86/xstate: re-size save area when CPUID policy changes Jan Beulich
2021-05-03 13:57   ` Andrew Cooper
2021-05-03 14:22     ` Jan Beulich
2021-05-11 16:41       ` Andrew Cooper
2021-05-17  7:33         ` Jan Beulich
2021-04-22 14:45 ` [PATCH v3 04/22] x86/xstate: re-use valid_xcr0() for boot-time checks Jan Beulich
2021-05-03 11:53   ` Andrew Cooper
2021-04-22 14:45 ` [PATCH v3 05/22] x86/xstate: drop xstate_offsets[] and xstate_sizes[] Jan Beulich
2021-05-03 16:10   ` Andrew Cooper
2021-05-04  7:57     ` Jan Beulich
2021-04-22 14:46 ` [PATCH v3 06/22] x86/xstate: replace xsave_cntxt_size and drop XCNTXT_MASK Jan Beulich
2021-04-22 14:47 ` [PATCH v3 07/22] x86/xstate: avoid accounting for unsupported components Jan Beulich
2021-04-22 14:47 ` [PATCH v3 08/22] x86: use xvmalloc() for extended context buffer allocations Jan Beulich
2021-04-22 14:48 ` [PATCH v3 09/22] x86/xstate: enable AMX components Jan Beulich
2021-04-22 14:50 ` [PATCH v3 10/22] x86/CPUID: adjust extended leaves out of range clearing Jan Beulich
2021-04-22 14:50 ` [PATCH v3 11/22] x86/CPUID: move bounding of max_{,sub}leaf fields to library code Jan Beulich
2021-04-22 14:51 ` [PATCH v3 12/22] x86/CPUID: enable AMX leaves Jan Beulich
2021-04-22 14:52 ` [PATCH v3 13/22] x86: XFD enabling Jan Beulich
2021-04-22 14:53 ` [PATCH v3 14/22] x86emul: introduce X86EMUL_FPU_{tilecfg,tile} Jan Beulich
2021-04-22 14:53 ` [PATCH v3 15/22] x86emul: support TILERELEASE Jan Beulich
2021-04-22 14:53 ` [PATCH v3 16/22] x86: introduce struct for TILECFG register Jan Beulich
2021-04-22 14:54 ` [PATCH v3 17/22] x86emul: support {LD,ST}TILECFG Jan Beulich
2021-04-22 14:55 ` [PATCH v3 18/22] x86emul: support TILEZERO Jan Beulich
2021-04-22 14:55 ` [PATCH v3 19/22] x86emul: support TILELOADD{,T1} and TILESTORE Jan Beulich
2021-04-22 15:06   ` Jan Beulich
2021-04-22 15:11     ` Jan Beulich
2021-04-26  7:12       ` Paul Durrant
2021-04-29  9:40         ` Jan Beulich
2021-04-22 14:56 ` [PATCH v3 20/22] x86emul: support tile multiplication insns Jan Beulich
2021-04-22 14:57 ` [PATCH v3 21/22] x86emul: test AMX insns Jan Beulich
2021-04-22 14:57 ` [PATCH v3 22/22] x86: permit guests to use AMX and XFD Jan Beulich

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=69778de6-3b94-64d1-99d9-1a0fcfa503fd@suse.com \
    --to=jbeulich@suse.com \
    --cc=andrew.cooper3@citrix.com \
    --cc=george.dunlap@citrix.com \
    --cc=iwj@xenproject.org \
    --cc=julien@xen.org \
    --cc=roger.pau@citrix.com \
    --cc=sstabellini@kernel.org \
    --cc=wl@xen.org \
    --cc=xen-devel@lists.xenproject.org \
    --subject='Re: [PATCH v3 01/22] mm: introduce xvmalloc() et al and use for grant table allocations' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).