@@ -13,6 +13,9 @@ To compile LLC coloring support set ``CONFIG_LLC_COLORING=y``.
If needed, change the maximum number of colors with
``CONFIG_LLC_COLORS_ORDER=<n>``.
+If needed, change the buddy allocator reserved size with
+``CONFIG_BUDDY_ALLOCATOR_SIZE=<n>``.
+
Runtime configuration is done via `Command line parameters`_.
For DomUs follow `DomUs configuration`_.
@@ -110,6 +113,8 @@ Specific documentation is available at `docs/misc/xen-command-line.pandoc`.
+----------------------+-------------------------------+
| ``dom0-llc-colors`` | Dom0 color configuration |
+----------------------+-------------------------------+
+| ``buddy-alloc-size`` | Buddy allocator reserved size |
++----------------------+-------------------------------+
Colors selection format
***********************
@@ -197,6 +202,17 @@ For example:
**Note:** If no color configuration is provided for a domain, the default one,
which corresponds to all available colors is used instead.
+Colored allocator and buddy allocator
+*************************************
+
+The colored allocator distributes pages based on color configurations of
+domains so that each domains only gets pages of its own colors.
+The colored allocator is meant as an alternative to the buddy allocator because
+its allocation policy is by definition incompatible with the generic one. Since
+the Xen heap is not colored yet, we need to support the coexistence of the two
+allocators and some memory must be left for the buddy one. Buddy memory
+reservation is configured via Kconfig or via command-line.
+
Known issues and limitations
****************************
@@ -207,3 +223,24 @@ In the domain configuration, "xen,static-mem" allows memory to be statically
allocated to the domain. This isn't possible when LLC coloring is enabled,
because that memory can't be guaranteed to use only colors assigned to the
domain.
+
+Cache coloring is intended only for embedded systems
+####################################################
+
+The current implementation aims to satisfy the need of predictability in
+embedded systems with small amount of memory to be managed in a colored way.
+Given that, some shortcuts are taken in the development. Expect worse
+performances on larger systems.
+
+Colored allocator can only make use of order-0 pages
+####################################################
+
+The cache coloring technique relies on memory mappings and on the smallest
+mapping granularity to achieve the maximum number of colors (cache partitions)
+possible. This granularity is what is normally called a page and, in Xen
+terminology, the order-0 page is the smallest one. The fairly simple
+colored allocator currently implemented, makes use only of such pages.
+It must be said that a more complex one could, in theory, adopt higher order
+pages if the colors selection contained adjacent colors. Two subsequent colors,
+for example, can be represented by an order-1 page, four colors correspond to
+an order-2 page, etc.
@@ -270,6 +270,20 @@ and not running softirqs. Reduce this if softirqs are not being run frequently
enough. Setting this to a high value may cause boot failure, particularly if
the NMI watchdog is also enabled.
+### buddy-alloc-size (arm64)
+> `= <size>`
+
+> Default: `64M`
+
+Amount of memory reserved for the buddy allocator when colored allocator is
+active. This option is available only when `CONFIG_LLC_COLORING` is enabled.
+The colored allocator is meant as an alternative to the buddy allocator,
+because its allocation policy is by definition incompatible with the generic
+one. Since the Xen heap systems is not colored yet, we need to support the
+coexistence of the two allocators for now. This parameter, which is optional
+and for expert only, it's used to set the amount of memory reserved to the
+buddy allocator.
+
### cet
= List of [ shstk=<bool>, ibt=<bool> ]
@@ -145,6 +145,11 @@ struct page_info
#else
#define PGC_static 0
#endif
+#ifdef CONFIG_LLC_COLORING
+/* Page is cache colored */
+#define _PGC_colored PG_shift(4)
+#define PGC_colored PG_mask(1, 4)
+#endif
/* ... */
/* Page is broken? */
#define _PGC_broken PG_shift(7)
@@ -537,4 +537,12 @@ config LLC_COLORS_ORDER
The default value corresponds to an 8 MiB 16-ways LLC, which should be
more than what's needed in the general case.
+config BUDDY_ALLOCATOR_SIZE
+ int "Buddy allocator reserved memory size (MiB)"
+ default "64"
+ depends on LLC_COLORING
+ help
+ Amount of memory reserved for the buddy allocator to serve Xen heap,
+ working alongside the colored one.
+
endmenu
@@ -32,6 +32,9 @@ static unsigned int __ro_after_init default_colors[NR_LLC_COLORS];
static unsigned int __initdata dom0_colors[NR_LLC_COLORS];
static unsigned int __initdata dom0_num_colors;
+#define mfn_color_mask (max_nr_colors - 1)
+#define mfn_to_color(mfn) (mfn_x(mfn) & mfn_color_mask)
+
/*
* Parse the coloring configuration given in the buf string, following the
* syntax below.
@@ -317,6 +320,16 @@ int __init domain_set_llc_colors_from_str(struct domain *d, const char *str)
return 0;
}
+unsigned int page_to_llc_color(const struct page_info *pg)
+{
+ return mfn_to_color(page_to_mfn(pg));
+}
+
+unsigned int get_max_nr_llc_colors(void)
+{
+ return max_nr_colors;
+}
+
/*
* Local variables:
* mode: C
@@ -139,6 +139,7 @@
#include <xen/softirq.h>
#include <xen/spinlock.h>
#include <xen/vm_event.h>
+#include <xen/xvmalloc.h>
#include <asm/flushtlb.h>
#include <asm/page.h>
@@ -160,8 +161,12 @@
#define PGC_static 0
#endif
-#define PGC_no_buddy_merge PGC_static
-#define PGC_preserved (PGC_extra | PGC_static)
+#ifndef PGC_colored
+#define PGC_colored 0
+#endif
+
+#define PGC_no_buddy_merge (PGC_static | PGC_colored)
+#define PGC_preserved (PGC_extra | PGC_static | PGC_colored)
#ifndef PGT_TYPE_INFO_INITIALIZER
#define PGT_TYPE_INFO_INITIALIZER 0
@@ -1473,6 +1478,8 @@ static bool mark_page_free(struct page_info *pg, mfn_t mfn)
return pg_offlined;
}
+static void free_color_heap_page(struct page_info *pg, bool need_scrub);
+
/* Free 2^@order set of pages. */
static void free_heap_pages(
struct page_info *pg, unsigned int order, bool need_scrub)
@@ -1497,6 +1504,15 @@ static void free_heap_pages(
pg[i].count_info |= PGC_need_scrub;
poison_one_page(&pg[i]);
}
+
+ if ( pg->count_info & PGC_colored )
+ {
+ ASSERT(order == 0);
+
+ free_color_heap_page(pg, need_scrub);
+ spin_unlock(&heap_lock);
+ return;
+ }
}
avail[node][zone] += 1 << order;
@@ -1961,6 +1977,157 @@ static unsigned long avail_heap_pages(
return free_pages;
}
+/*************************
+ * COLORED SIDE-ALLOCATOR
+ *
+ * Pages are grouped by LLC color in lists which are globally referred to as the
+ * color heap. Lists are populated in end_boot_allocator().
+ * After initialization there will be N lists where N is the number of
+ * available colors on the platform.
+ */
+static struct page_list_head *__ro_after_init _color_heap;
+#define color_heap(color) (&_color_heap[color])
+
+static unsigned long *__ro_after_init free_colored_pages;
+
+#ifdef CONFIG_LLC_COLORING
+#define domain_num_llc_colors(d) ((d)->num_llc_colors)
+#define domain_llc_color(d, i) ((d)->llc_colors[i])
+
+/* Memory required for buddy allocator to work with colored one */
+static unsigned long __initdata buddy_alloc_size =
+ MB(CONFIG_BUDDY_ALLOCATOR_SIZE);
+size_param("buddy-alloc-size", buddy_alloc_size);
+#else
+#define domain_num_llc_colors(d) 0
+#define domain_llc_color(d, i) 0
+#endif
+
+static void free_color_heap_page(struct page_info *pg, bool need_scrub)
+{
+ unsigned int color;
+
+ color = page_to_llc_color(pg);
+ free_colored_pages[color]++;
+ /*
+ * Head insertion allows re-using cache-hot pages in configurations without
+ * sharing of colors.
+ */
+ page_list_add(pg, color_heap(color));
+}
+
+static struct page_info *alloc_color_heap_page(unsigned int memflags,
+ const struct domain *d)
+{
+ struct page_info *pg = NULL;
+ unsigned int i, color = 0;
+ unsigned long max = 0;
+ bool need_tlbflush = false;
+ uint32_t tlbflush_timestamp = 0;
+ bool need_scrub;
+
+ if ( memflags & ~(MEMF_no_refcount | MEMF_no_owner | MEMF_no_tlbflush |
+ MEMF_no_icache_flush | MEMF_no_scrub) )
+ return NULL;
+
+ spin_lock(&heap_lock);
+
+ for ( i = 0; i < domain_num_llc_colors(d); i++ )
+ {
+ unsigned long free = free_colored_pages[domain_llc_color(d, i)];
+
+ if ( free > max )
+ {
+ color = domain_llc_color(d, i);
+ pg = page_list_first(color_heap(color));
+ max = free;
+ }
+ }
+
+ if ( !pg )
+ {
+ spin_unlock(&heap_lock);
+ return NULL;
+ }
+
+ need_scrub = pg->count_info & PGC_need_scrub;
+ pg->count_info = PGC_state_inuse | (pg->count_info & PGC_colored);
+ free_colored_pages[color]--;
+ page_list_del(pg, color_heap(color));
+
+ if ( !(memflags & MEMF_no_tlbflush) )
+ accumulate_tlbflush(&need_tlbflush, pg, &tlbflush_timestamp);
+
+ init_free_page_fields(pg);
+
+ spin_unlock(&heap_lock);
+
+ if ( !(memflags & MEMF_no_scrub) )
+ {
+ if ( need_scrub )
+ scrub_one_page(pg);
+ else
+ check_one_page(pg);
+ }
+
+ if ( need_tlbflush )
+ filtered_flush_tlb_mask(tlbflush_timestamp);
+
+ flush_page_to_ram(mfn_x(page_to_mfn(pg)),
+ !(memflags & MEMF_no_icache_flush));
+
+ return pg;
+}
+
+static void __init init_color_heap_pages(struct page_info *pg,
+ unsigned long nr_pages)
+{
+ unsigned long i;
+ bool need_scrub = opt_bootscrub == BOOTSCRUB_IDLE;
+
+#ifdef buddy_alloc_size
+ if ( buddy_alloc_size >= PAGE_SIZE )
+ {
+ unsigned long buddy_pages = min(PFN_DOWN(buddy_alloc_size), nr_pages);
+
+ init_heap_pages(pg, buddy_pages);
+ nr_pages -= buddy_pages;
+ buddy_alloc_size -= buddy_pages << PAGE_SHIFT;
+ pg += buddy_pages;
+ }
+#endif
+
+ if ( !_color_heap )
+ {
+ unsigned int max_nr_colors = get_max_nr_llc_colors();
+
+ _color_heap = xvmalloc_array(struct page_list_head, max_nr_colors);
+ free_colored_pages = xvzalloc_array(unsigned long, max_nr_colors);
+ if ( !_color_heap || !free_colored_pages )
+ panic("Can't allocate colored heap. Buddy reserved size is too low");
+
+ for ( i = 0; i < max_nr_colors; i++ )
+ INIT_PAGE_LIST_HEAD(color_heap(i));
+ }
+
+ for ( i = 0; i < nr_pages; i++ )
+ {
+ pg[i].count_info = PGC_colored;
+ free_color_heap_page(&pg[i], need_scrub);
+ }
+}
+
+static void dump_color_heap(void)
+{
+ unsigned int color;
+
+ printk("Dumping color heap info\n");
+ for ( color = 0; color < get_max_nr_llc_colors(); color++ )
+ if ( free_colored_pages[color] > 0 )
+ printk("Color heap[%u]: %lu pages\n",
+ color, free_colored_pages[color]);
+}
+
void __init end_boot_allocator(void)
{
unsigned int i;
@@ -1980,7 +2147,13 @@ void __init end_boot_allocator(void)
for ( i = nr_bootmem_regions; i-- > 0; )
{
struct bootmem_region *r = &bootmem_region_list[i];
- if ( r->s < r->e )
+
+ if ( r->s >= r->e )
+ continue;
+
+ if ( llc_coloring_enabled )
+ init_color_heap_pages(mfn_to_page(_mfn(r->s)), r->e - r->s);
+ else
init_heap_pages(mfn_to_page(_mfn(r->s)), r->e - r->s);
}
nr_bootmem_regions = 0;
@@ -2476,7 +2649,14 @@ struct page_info *alloc_domheap_pages(
if ( memflags & MEMF_no_owner )
memflags |= MEMF_no_refcount;
- if ( !dma_bitsize )
+ /* Only domains are supported for coloring */
+ if ( d && llc_coloring_enabled )
+ {
+ /* Colored allocation must be done on 0 order */
+ if ( order || (pg = alloc_color_heap_page(memflags, d)) == NULL )
+ return NULL;
+ }
+ else if ( !dma_bitsize )
memflags &= ~MEMF_no_dma;
else if ( (dma_zone = bits_to_zone(dma_bitsize)) < zone_hi )
pg = alloc_heap_pages(dma_zone + 1, zone_hi, order, memflags, d);
@@ -2688,6 +2868,9 @@ static void cf_check dump_heap(unsigned char key)
continue;
printk("Node %d has %lu unscrubbed pages\n", i, node_need_scrub[i]);
}
+
+ if ( llc_coloring_enabled )
+ dump_color_heap();
}
static __init int cf_check register_heap_trigger(void)
@@ -9,6 +9,7 @@
#define __XEN_LLC_COLORING_H__
struct domain;
+struct page_info;
struct xen_domctl_set_llc_colors;
#ifdef CONFIG_LLC_COLORING
@@ -33,6 +34,8 @@ int dom0_set_llc_colors(struct domain *d);
int domain_set_llc_colors(struct domain *d,
const struct xen_domctl_set_llc_colors *config);
int domain_set_llc_colors_from_str(struct domain *d, const char *str);
+unsigned int page_to_llc_color(const struct page_info *pg);
+unsigned int get_max_nr_llc_colors(void);
#endif /* __XEN_LLC_COLORING_H__ */