[xen master] xen/common: add cache coloring common code

[patchbot@xxxxxxx]

commit 44dd6d4a124a33e44eeb7157b05a3ad3d9cf46c3
Author:     Carlo Nonato <carlo.nonato@xxxxxxxxxxxxxxx>
AuthorDate: Tue Dec 17 18:06:26 2024 +0100
Commit:     Michal Orzel <michal.orzel@xxxxxxx>
CommitDate: Thu Dec 19 19:24:31 2024 +0100

    xen/common: add cache coloring common code
    
    Last Level Cache (LLC) coloring allows to partition the cache in smaller
    chunks called cache colors.
    
    Since not all architectures can actually implement it, add a 
HAS_LLC_COLORING
    Kconfig option.
    LLC_COLORS_ORDER Kconfig option has a range maximum of 10 (2^10 = 1024)
    because that's the number of colors that fit in a 4 KiB page when integers
    are 4 bytes long.
    
    LLC colors are a property of the domain, so struct domain has to be 
extended.
    
    Based on original work from: Luca Miccio <lucmiccio@xxxxxxxxx>
    
    Signed-off-by: Carlo Nonato <carlo.nonato@xxxxxxxxxxxxxxx>
    Signed-off-by: Marco Solieri <marco.solieri@xxxxxxxxxxxxxxx>
    Acked-by: Michal Orzel <michal.orzel@xxxxxxx>
---
 SUPPORT.md                        |   7 +++
 docs/index.rst                    |   1 +
 docs/misc/cache-coloring.rst      | 118 ++++++++++++++++++++++++++++++++++++
 docs/misc/xen-command-line.pandoc |  39 ++++++++++++
 xen/common/Kconfig                |  21 +++++++
 xen/common/Makefile               |   1 +
 xen/common/keyhandler.c           |   3 +
 xen/common/llc-coloring.c         | 124 ++++++++++++++++++++++++++++++++++++++
 xen/common/page_alloc.c           |   3 +
 xen/include/xen/llc-coloring.h    |  36 +++++++++++
 xen/include/xen/sched.h           |   5 ++
 11 files changed, 358 insertions(+)

diff --git a/SUPPORT.md b/SUPPORT.md
index 82239d0294..998faf5635 100644
--- a/SUPPORT.md
+++ b/SUPPORT.md
@@ -401,6 +401,13 @@ by maintaining multiple physical to machine (p2m) memory 
mappings.
     Status, x86 HVM: Tech Preview
     Status, ARM: Tech Preview
 
+### Cache coloring
+
+Allows to reserve Last Level Cache (LLC) partitions for Dom0, DomUs and Xen
+itself.
+
+    Status, Arm64: Experimental
+
 ## Resource Management
 
 ### CPU Pools
diff --git a/docs/index.rst b/docs/index.rst
index 1d44796d72..1bb8d02ea3 100644
--- a/docs/index.rst
+++ b/docs/index.rst
@@ -66,6 +66,7 @@ Documents in need of some rearranging.
    misc/xen-makefiles/makefiles
    misra/index
    fusa/index
+   misc/cache-coloring
 
 
 Miscellanea
diff --git a/docs/misc/cache-coloring.rst b/docs/misc/cache-coloring.rst
new file mode 100644
index 0000000000..371f21a0e7
--- /dev/null
+++ b/docs/misc/cache-coloring.rst
@@ -0,0 +1,118 @@
+.. SPDX-License-Identifier: CC-BY-4.0
+
+Xen cache coloring user guide
+=============================
+
+The cache coloring support in Xen allows to reserve Last Level Cache (LLC)
+partitions for Dom0, DomUs and Xen itself. Currently only ARM64 is supported.
+Cache coloring realizes per-set cache partitioning in software and is 
applicable
+to shared LLCs as implemented in Cortex-A53, Cortex-A72 and similar CPUs.
+
+To compile LLC coloring support set ``CONFIG_LLC_COLORING=y``.
+
+If needed, change the maximum number of colors with
+``CONFIG_LLC_COLORS_ORDER=<n>``.
+
+Runtime configuration is done via `Command line parameters`_.
+
+Background
+**********
+
+Cache hierarchy of a modern multi-core CPU typically has first levels dedicated
+to each core (hence using multiple cache units), while the last level is shared
+among all of them. Such configuration implies that memory operations on one
+core (e.g. running a DomU) are able to generate interference on another core
+(e.g. hosting another DomU). Cache coloring realizes per-set cache-partitioning
+in software and mitigates this, guaranteeing more predictable performances for
+memory accesses.
+Software-based cache coloring is particularly useful in those situations where
+no hardware mechanisms (e.g., DSU-based way partitioning) are available to
+partition caches. This is the case for e.g., Cortex-A53, A57 and A72 CPUs that
+feature a L2 LLC cache shared among all cores.
+
+The key concept underlying cache coloring is a fragmentation of the memory
+space into a set of sub-spaces called colors that are mapped to disjoint cache
+partitions. Technically, the whole memory space is first divided into a number
+of subsequent regions. Then each region is in turn divided into a number of
+subsequent sub-colors. The generic i-th color is then obtained by all the
+i-th sub-colors in each region.
+
+::
+
+                            Region j            Region j+1
+                .....................   ............
+                .                     . .
+                .                       .
+            _ _ _______________ _ _____________________ _ _
+                |     |     |     |     |     |     |
+                | c_0 | c_1 |     | c_n | c_0 | c_1 |
+           _ _ _|_____|_____|_ _ _|_____|_____|_____|_ _ _
+                    :                       :
+                    :                       :...         ... .
+                    :                            color 0
+                    :...........................         ... .
+                                                :
+          . . ..................................:
+
+How colors are actually defined depends on the function that maps memory to
+cache lines. In case of physically-indexed, physically-tagged caches with 
linear
+mapping, the set index is found by extracting some contiguous bits from the
+physical address. This allows colors to be defined as shown in figure: they
+appear in memory as subsequent blocks of equal size and repeats themselves 
after
+``n`` different colors, where ``n`` is the total number of colors.
+
+If some kind of bit shuffling appears in the mapping function, then colors
+assume a different layout in memory. Those kind of caches aren't supported by
+the current implementation.
+
+**Note**: Finding the exact cache mapping function can be a really difficult
+task since it's not always documented in the CPU manual. As said Cortex-A53, 
A57
+and A72 are known to work with the current implementation.
+
+How to compute the number of colors
+###################################
+
+Given the linear mapping from physical memory to cache lines for granted, the
+number of available colors for a specific platform is computed using three
+parameters:
+
+- the size of the LLC.
+- the number of the LLC ways.
+- the page size used by Xen.
+
+The first two parameters can be found in the processor manual, while the third
+one is the minimum mapping granularity. Dividing the cache size by the number 
of
+its ways we obtain the size of a way. Dividing this number by the page size,
+the number of total cache colors is found. So for example an Arm Cortex-A53
+with a 16-ways associative 1 MiB LLC can isolate up to 16 colors when pages are
+4 KiB in size.
+
+Effective colors assignment
+###########################
+
+When assigning colors, if one wants to avoid cache interference between two
+domains, different colors needs to be used for their memory.
+
+Command line parameters
+***********************
+
+Specific documentation is available at `docs/misc/xen-command-line.pandoc`.
+
++----------------------+-------------------------------+
+| **Parameter**        | **Description**               |
++----------------------+-------------------------------+
+| ``llc-coloring``     | Enable coloring at runtime    |
++----------------------+-------------------------------+
+| ``llc-size``         | Set the LLC size              |
++----------------------+-------------------------------+
+| ``llc-nr-ways``      | Set the LLC number of ways    |
++----------------------+-------------------------------+
+
+Auto-probing of LLC specs
+#########################
+
+LLC size and number of ways are probed automatically by default.
+
+LLC specs can be manually set via the above command line parameters. This
+bypasses any auto-probing and it's used to overcome failing situations, such as
+flawed probing logic, or for debugging/testing purposes.
diff --git a/docs/misc/xen-command-line.pandoc 
b/docs/misc/xen-command-line.pandoc
index 67727f15e9..d75903b84c 100644
--- a/docs/misc/xen-command-line.pandoc
+++ b/docs/misc/xen-command-line.pandoc
@@ -1710,6 +1710,45 @@ This option is intended for debugging purposes only.  
Enable MSR_DEBUGCTL.LBR
 in hypervisor context to be able to dump the Last Interrupt/Exception To/From
 record with other registers.
 
+### llc-coloring (arm64)
+> `= <boolean>`
+
+> Default: `false`
+
+Flag to enable or disable LLC coloring support at runtime. This option is
+available only when `CONFIG_LLC_COLORING` is enabled. See the general
+cache coloring documentation for more info.
+
+### llc-nr-ways (arm64)
+> `= <integer>`
+
+> Default: `Obtained from hardware`
+
+Specify the number of ways of the Last Level Cache. This option is available
+only when `CONFIG_LLC_COLORING` is enabled. LLC size and number of ways are 
used
+to find the number of supported cache colors. By default the value is
+automatically computed by probing the hardware, but in case of specific needs,
+it can be manually set. Those include failing probing and debugging/testing
+purposes so that it's possible to emulate platforms with different number of
+supported colors. If set, also "llc-size" must be set, otherwise the default
+will be used. Note that using both options implies "llc-coloring=on" unless an
+earlier "llc-coloring=off" is there.
+
+### llc-size (arm64)
+> `= <size>`
+
+> Default: `Obtained from hardware`
+
+Specify the size of the Last Level Cache. This option is available only when
+`CONFIG_LLC_COLORING` is enabled. LLC size and number of ways are used to find
+the number of supported cache colors. By default the value is automatically
+computed by probing the hardware, but in case of specific needs, it can be
+manually set. Those include failing probing and debugging/testing purposes so
+that it's possible to emulate platforms with different number of supported
+colors. If set, also "llc-nr-ways" must be set, otherwise the default will be
+used. Note that using both options implies "llc-coloring=on" unless an
+earlier "llc-coloring=off" is there.
+
 ### lock-depth-size
 > `= <integer>`
 
diff --git a/xen/common/Kconfig b/xen/common/Kconfig
index 90268d9249..b4ec6893be 100644
--- a/xen/common/Kconfig
+++ b/xen/common/Kconfig
@@ -71,6 +71,9 @@ config HAS_IOPORTS
 config HAS_KEXEC
        bool
 
+config HAS_LLC_COLORING
+       bool
+
 config HAS_PIRQ
        bool
 
@@ -516,4 +519,22 @@ config TRACEBUFFER
          to be collected at run time for debugging or performance analysis.
          Memory and execution overhead when not active is minimal.
 
+config LLC_COLORING
+       bool "Last Level Cache (LLC) coloring" if EXPERT
+       depends on HAS_LLC_COLORING
+
+config LLC_COLORS_ORDER
+       int "Maximum number of LLC colors (base-2 exponent)"
+       range 1 10
+       default 7
+       depends on LLC_COLORING
+       help
+         Controls the build-time size of various arrays associated with LLC
+         coloring. The value is a base-2 exponent. Refer to cache coloring
+         documentation for how to compute the number of colors supported by the
+         platform. This is only an upper bound. The runtime value is 
autocomputed
+         or manually set via cmdline parameters.
+         The default value corresponds to an 8 MiB 16-ways LLC, which should be
+         more than what's needed in the general case.
+
 endmenu
diff --git a/xen/common/Makefile b/xen/common/Makefile
index b279b09bfb..cba3b32733 100644
--- a/xen/common/Makefile
+++ b/xen/common/Makefile
@@ -25,6 +25,7 @@ obj-y += keyhandler.o
 obj-$(CONFIG_KEXEC) += kexec.o
 obj-$(CONFIG_KEXEC) += kimage.o
 obj-$(CONFIG_LIVEPATCH) += livepatch.o livepatch_elf.o
+obj-$(CONFIG_LLC_COLORING) += llc-coloring.o
 obj-$(CONFIG_MEM_ACCESS) += mem_access.o
 obj-y += memory.o
 obj-y += multicall.o
diff --git a/xen/common/keyhandler.c b/xen/common/keyhandler.c
index 6da291b34e..6ea54838d4 100644
--- a/xen/common/keyhandler.c
+++ b/xen/common/keyhandler.c
@@ -5,6 +5,7 @@
 #include <asm/regs.h>
 #include <xen/delay.h>
 #include <xen/keyhandler.h>
+#include <xen/llc-coloring.h>
 #include <xen/param.h>
 #include <xen/sections.h>
 #include <xen/shutdown.h>
@@ -304,6 +305,8 @@ static void cf_check dump_domains(unsigned char key)
 
         arch_dump_domain_info(d);
 
+        domain_dump_llc_colors(d);
+
         rangeset_domain_printk(d);
 
         dump_pageframe_info(d);
diff --git a/xen/common/llc-coloring.c b/xen/common/llc-coloring.c
new file mode 100644
index 0000000000..335a907296
--- /dev/null
+++ b/xen/common/llc-coloring.c
@@ -0,0 +1,124 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Last Level Cache (LLC) coloring common code
+ *
+ * Copyright (C) 2024, Advanced Micro Devices, Inc.
+ * Copyright (C) 2024, Minerva Systems SRL
+ */
+#include <xen/keyhandler.h>
+#include <xen/llc-coloring.h>
+#include <xen/param.h>
+
+#define NR_LLC_COLORS          (1U << CONFIG_LLC_COLORS_ORDER)
+
+/*
+ * -1: not specified (disabled unless llc-size and llc-nr-ways present)
+ *  0: explicitly disabled through cmdline
+ *  1: explicitly enabled through cmdline
+ */
+static int8_t __initdata opt_llc_coloring = -1;
+boolean_param("llc-coloring", opt_llc_coloring);
+
+static bool __ro_after_init llc_coloring_enabled;
+
+static unsigned int __initdata llc_size;
+size_param("llc-size", llc_size);
+static unsigned int __initdata llc_nr_ways;
+integer_param("llc-nr-ways", llc_nr_ways);
+/* Number of colors available in the LLC */
+static unsigned int __ro_after_init max_nr_colors;
+
+static void print_colors(const unsigned int colors[], unsigned int num_colors)
+{
+    unsigned int i;
+
+    printk("{ ");
+    for ( i = 0; i < num_colors; i++ )
+    {
+        unsigned int start = colors[i], end = start;
+
+        printk("%u", start);
+
+        for ( ; i < num_colors - 1 && end + 1 == colors[i + 1]; i++, end++ )
+            ;
+
+        if ( start != end )
+            printk("-%u", end);
+
+        if ( i < num_colors - 1 )
+            printk(", ");
+    }
+    printk(" }\n");
+}
+
+void __init llc_coloring_init(void)
+{
+    unsigned int way_size;
+
+    llc_coloring_enabled = (opt_llc_coloring >= 1);
+    if ( (opt_llc_coloring != 0) && llc_size && llc_nr_ways )
+    {
+        llc_coloring_enabled = true;
+        way_size = llc_size / llc_nr_ways;
+    }
+    else if ( !llc_coloring_enabled )
+        return;
+    else
+    {
+        way_size = get_llc_way_size();
+        if ( !way_size )
+            panic("LLC probing failed and 'llc-size' or 'llc-nr-ways' 
missing\n");
+    }
+
+    if ( way_size & ~PAGE_MASK )
+        panic("LLC way size must be a multiple of PAGE_SIZE\n");
+
+    /*
+     * The maximum number of colors must be a power of 2 in order to correctly
+     * map them to bits of an address.
+     */
+    max_nr_colors = way_size >> PAGE_SHIFT;
+
+    if ( max_nr_colors & (max_nr_colors - 1) )
+        panic("Number of LLC colors (%u) isn't a power of 2\n", max_nr_colors);
+
+    if ( max_nr_colors > NR_LLC_COLORS )
+    {
+        printk(XENLOG_WARNING
+               "Number of LLC colors (%u) too big. Using configured max %u\n",
+               max_nr_colors, NR_LLC_COLORS);
+        max_nr_colors = NR_LLC_COLORS;
+    }
+    else if ( max_nr_colors < 2 )
+        panic("Number of LLC colors %u < 2\n", max_nr_colors);
+
+    arch_llc_coloring_init();
+}
+
+void dump_llc_coloring_info(void)
+{
+    if ( !llc_coloring_enabled )
+        return;
+
+    printk("LLC coloring info:\n");
+    printk("    Number of LLC colors supported: %u\n", max_nr_colors);
+}
+
+void domain_dump_llc_colors(const struct domain *d)
+{
+    if ( !llc_coloring_enabled )
+        return;
+
+    printk("%u LLC colors: ", d->num_llc_colors);
+    print_colors(d->llc_colors, d->num_llc_colors);
+}
+
+/*
+ * Local variables:
+ * mode: C
+ * c-file-style: "BSD"
+ * c-basic-offset: 4
+ * tab-width: 4
+ * indent-tabs-mode: nil
+ * End:
+ */
diff --git a/xen/common/page_alloc.c b/xen/common/page_alloc.c
index b76a03fd73..6dc8e0d5c9 100644
--- a/xen/common/page_alloc.c
+++ b/xen/common/page_alloc.c
@@ -126,6 +126,7 @@
 #include <xen/irq.h>
 #include <xen/keyhandler.h>
 #include <xen/lib.h>
+#include <xen/llc-coloring.h>
 #include <xen/mm.h>
 #include <xen/nodemask.h>
 #include <xen/numa.h>
@@ -2651,6 +2652,8 @@ static void cf_check pagealloc_info(unsigned char key)
     }
 
     printk("    Dom heap: %lukB free\n", total << (PAGE_SHIFT-10));
+
+    dump_llc_coloring_info();
 }
 
 static __init int cf_check pagealloc_keyhandler_init(void)
diff --git a/xen/include/xen/llc-coloring.h b/xen/include/xen/llc-coloring.h
new file mode 100644
index 0000000000..0acd8d0ad6
--- /dev/null
+++ b/xen/include/xen/llc-coloring.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Last Level Cache (LLC) coloring common header
+ *
+ * Copyright (C) 2024, Advanced Micro Devices, Inc.
+ * Copyright (C) 2024, Minerva Systems SRL
+ */
+#ifndef __XEN_LLC_COLORING_H__
+#define __XEN_LLC_COLORING_H__
+
+struct domain;
+
+#ifdef CONFIG_LLC_COLORING
+void llc_coloring_init(void);
+void dump_llc_coloring_info(void);
+void domain_dump_llc_colors(const struct domain *d);
+#else
+static inline void llc_coloring_init(void) {}
+static inline void dump_llc_coloring_info(void) {}
+static inline void domain_dump_llc_colors(const struct domain *d) {}
+#endif
+
+unsigned int get_llc_way_size(void);
+void arch_llc_coloring_init(void);
+
+#endif /* __XEN_LLC_COLORING_H__ */
+
+/*
+ * Local variables:
+ * mode: C
+ * c-file-style: "BSD"
+ * c-basic-offset: 4
+ * tab-width: 4
+ * indent-tabs-mode: nil
+ * End:
+ */
diff --git a/xen/include/xen/sched.h b/xen/include/xen/sched.h
index 711668e028..037c83fda2 100644
--- a/xen/include/xen/sched.h
+++ b/xen/include/xen/sched.h
@@ -640,6 +640,11 @@ struct domain
 
     /* Holding CDF_* constant. Internal flags for domain creation. */
     unsigned int cdf;
+
+#ifdef CONFIG_LLC_COLORING
+    unsigned int num_llc_colors;
+    const unsigned int *llc_colors;
+#endif
 };
 
 static inline struct page_list_head *page_to_list(
--
generated by git-patchbot for /home/xen/git/xen.git#master