xen/arm: permit non direct-mapped Dom0 construction

Cache coloring requires Dom0 not to be direct-mapped because of its non
contiguous mapping nature, so allocate_memory() is needed in this case.
8d2c3ab18c ("arm/dom0less: put dom0less feature code in a separate module")
moved allocate_memory() in dom0less_build.c. In order to use it
in Dom0 construction bring it back to domain_build.c and declare it in
domain_build.h.

Adapt the implementation of allocate_memory() so that it uses the host
layout when called on the hwdom, via find_unallocated_memory().

Since gnttab information are needed in the process, move find_gnttab_region()
before allocate_memory() in construct_dom0().

Introduce add_hwdom_free_regions() callback to add hwdom banks in descending
order.

Signed-off-by: Carlo Nonato <carlo.nonato@minervasys.tech>
Reviewed-by: Michal Orzel <michal.orzel@amd.com>

xen/arch/arm/dom0less-build.c

@@ -49,50 +49,6 @@ bool __init is_dom0less_mode(void)
     return ( !dom0found && domUfound );
 }
 
-static void __init allocate_memory(struct domain *d, struct kernel_info *kinfo)
-{
-    struct membanks *mem = kernel_info_get_mem(kinfo);
-    unsigned int i;
-    paddr_t bank_size;
-
-    printk(XENLOG_INFO "Allocating mappings totalling %ldMB for %pd:\n",
-           /* Don't want format this as PRIpaddr (16 digit hex) */
-           (unsigned long)(kinfo->unassigned_mem >> 20), d);
-
-    mem->nr_banks = 0;
-    bank_size = MIN(GUEST_RAM0_SIZE, kinfo->unassigned_mem);
-    if ( !allocate_bank_memory(kinfo, gaddr_to_gfn(GUEST_RAM0_BASE),
-                               bank_size) )
-        goto fail;
-
-    bank_size = MIN(GUEST_RAM1_SIZE, kinfo->unassigned_mem);
-    if ( !allocate_bank_memory(kinfo, gaddr_to_gfn(GUEST_RAM1_BASE),
-                               bank_size) )
-        goto fail;
-
-    if ( kinfo->unassigned_mem )
-        goto fail;
-
-    for( i = 0; i < mem->nr_banks; i++ )
-    {
-        printk(XENLOG_INFO "%pd BANK[%d] %#"PRIpaddr"-%#"PRIpaddr" (%ldMB)\n",
-               d,
-               i,
-               mem->bank[i].start,
-               mem->bank[i].start + mem->bank[i].size,
-               /* Don't want format this as PRIpaddr (16 digit hex) */
-               (unsigned long)(mem->bank[i].size >> 20));
-    }
-
-    return;
-
-fail:
-    panic("Failed to allocate requested domain memory."
-          /* Don't want format this as PRIpaddr (16 digit hex) */
-          " %ldKB unallocated. Fix the VMs configurations.\n",
-          (unsigned long)kinfo->unassigned_mem >> 10);
-}
-
 #ifdef CONFIG_VGICV2
 static int __init make_gicv2_domU_node(struct kernel_info *kinfo)
 {

xen/arch/arm/domain_build.c

@@ -2,6 +2,7 @@
 #include <xen/init.h>
 #include <xen/compile.h>
 #include <xen/lib.h>
+#include <xen/llc-coloring.h>
 #include <xen/mm.h>
 #include <xen/param.h>
 #include <xen/domain_page.h>
@@ -416,7 +417,6 @@ static void __init allocate_memory_11(struct domain *d,
     }
 }
 
-#ifdef CONFIG_DOM0LESS_BOOT
 bool __init allocate_domheap_memory(struct domain *d, paddr_t tot_size,
                                     alloc_domheap_mem_cb cb, void *extra)
 {
@@ -508,7 +508,6 @@ bool __init allocate_bank_memory(struct kernel_info *kinfo, gfn_t sgfn,
 
     return true;
 }
-#endif
 
 /*
  * When PCI passthrough is available we want to keep the
@@ -900,6 +899,52 @@ int __init add_ext_regions(unsigned long s_gfn, unsigned long e_gfn,
     return 0;
 }
 
+static int __init add_hwdom_free_regions(unsigned long s_gfn,
+                                         unsigned long e_gfn, void *data)
+{
+    struct membanks *free_regions = data;
+    paddr_t start, size;
+    paddr_t s = pfn_to_paddr(s_gfn);
+    paddr_t e = pfn_to_paddr(e_gfn);
+    unsigned int i, j;
+
+    if ( free_regions->nr_banks >= free_regions->max_banks )
+        return 0;
+
+    /*
+     * Both start and size of the free region should be 2MB aligned to
+     * potentially allow superpage mapping.
+     */
+    start = (s + SZ_2M - 1) & ~(SZ_2M - 1);
+    if ( start > e )
+        return 0;
+
+    /*
+     * e is actually "end-1" because it is called by rangeset functions
+     * which are inclusive of the last address.
+     */
+    e += 1;
+    size = (e - start) & ~(SZ_2M - 1);
+
+    /* Find the insert position (descending order). */
+    for ( i = 0; i < free_regions->nr_banks ; i++ )
+        if ( size > free_regions->bank[i].size )
+            break;
+
+    /* Move the other banks to make space. */
+    for ( j = free_regions->nr_banks; j > i ; j-- )
+    {
+        free_regions->bank[j].start = free_regions->bank[j - 1].start;
+        free_regions->bank[j].size = free_regions->bank[j - 1].size;
+    }
+
+    free_regions->bank[i].start = start;
+    free_regions->bank[i].size = size;
+    free_regions->nr_banks++;
+
+    return 0;
+}
+
 /*
  * Find unused regions of Host address space which can be exposed to domain
  * using the host memory layout. In order to calculate regions we exclude every
@@ -977,6 +1022,106 @@ out:
     return res;
 }
 
+void __init allocate_memory(struct domain *d, struct kernel_info *kinfo)
+{
+    struct membanks *mem = kernel_info_get_mem(kinfo);
+    unsigned int i, nr_banks = GUEST_RAM_BANKS;
+    struct membanks *hwdom_free_mem = NULL;
+
+    printk(XENLOG_INFO "Allocating mappings totalling %ldMB for %pd:\n",
+           /* Don't want format this as PRIpaddr (16 digit hex) */
+           (unsigned long)(kinfo->unassigned_mem >> 20), d);
+
+    mem->nr_banks = 0;
+    /*
+     * Use host memory layout for hwdom. Only case for this is when LLC coloring
+     * is enabled.
+     */
+    if ( is_hardware_domain(d) )
+    {
+        struct membanks *gnttab = xzalloc_flex_struct(struct membanks, bank, 1);
+        /*
+         * Exclude the following regions:
+         * 1) Remove reserved memory
+         * 2) Grant table assigned to hwdom
+         */
+        const struct membanks *mem_banks[] = {
+            bootinfo_get_reserved_mem(),
+            gnttab,
+        };
+
+        if ( !gnttab )
+            goto fail;
+
+        gnttab->nr_banks = 1;
+        gnttab->bank[0].start = kinfo->gnttab_start;
+        gnttab->bank[0].size = kinfo->gnttab_size;
+
+        hwdom_free_mem = xzalloc_flex_struct(struct membanks, bank,
+                                             NR_MEM_BANKS);
+        if ( !hwdom_free_mem )
+            goto fail;
+
+        hwdom_free_mem->max_banks = NR_MEM_BANKS;
+
+        if ( find_unallocated_memory(kinfo, mem_banks, ARRAY_SIZE(mem_banks),
+                                     hwdom_free_mem, add_hwdom_free_regions) )
+            goto fail;
+
+        nr_banks = hwdom_free_mem->nr_banks;
+        xfree(gnttab);
+    }
+
+    for ( i = 0; kinfo->unassigned_mem > 0 && nr_banks > 0; i++, nr_banks-- )
+    {
+        paddr_t bank_start, bank_size;
+
+        if ( is_hardware_domain(d) )
+        {
+            bank_start = hwdom_free_mem->bank[i].start;
+            bank_size = hwdom_free_mem->bank[i].size;
+        }
+        else
+        {
+            const uint64_t bankbase[] = GUEST_RAM_BANK_BASES;
+            const uint64_t banksize[] = GUEST_RAM_BANK_SIZES;
+
+            if ( i >= GUEST_RAM_BANKS )
+                goto fail;
+
+            bank_start = bankbase[i];
+            bank_size = banksize[i];
+        }
+
+        bank_size = MIN(bank_size, kinfo->unassigned_mem);
+        if ( !allocate_bank_memory(kinfo, gaddr_to_gfn(bank_start), bank_size) )
+            goto fail;
+    }
+
+    if ( kinfo->unassigned_mem )
+        goto fail;
+
+    for( i = 0; i < mem->nr_banks; i++ )
+    {
+        printk(XENLOG_INFO "%pd BANK[%d] %#"PRIpaddr"-%#"PRIpaddr" (%ldMB)\n",
+               d,
+               i,
+               mem->bank[i].start,
+               mem->bank[i].start + mem->bank[i].size,
+               /* Don't want format this as PRIpaddr (16 digit hex) */
+               (unsigned long)(mem->bank[i].size >> 20));
+    }
+
+    xfree(hwdom_free_mem);
+    return;
+
+  fail:
+    panic("Failed to allocate requested domain memory."
+          /* Don't want format this as PRIpaddr (16 digit hex) */
+          " %ldKB unallocated. Fix the VMs configurations.\n",
+          (unsigned long)kinfo->unassigned_mem >> 10);
+}
+
 static int __init handle_pci_range(const struct dt_device_node *dev,
                                    uint64_t addr, uint64_t len, void *data)
 {
@@ -1235,7 +1380,7 @@ int __init make_hypervisor_node(struct domain *d,
 
         ext_regions->max_banks = NR_MEM_BANKS;
 
-        if ( is_domain_direct_mapped(d) )
+        if ( domain_use_host_layout(d) )
         {
             if ( !is_iommu_enabled(d) )
                 res = find_host_extended_regions(kinfo, ext_regions);
@@ -2164,8 +2309,11 @@ static int __init construct_dom0(struct domain *d)
     /* type must be set before allocate_memory */
     d->arch.type = kinfo.type;
 #endif
-    allocate_memory_11(d, &kinfo);
     find_gnttab_region(d, &kinfo);
+    if ( is_domain_direct_mapped(d) )
+        allocate_memory_11(d, &kinfo);
+    else
+        allocate_memory(d, &kinfo);
 
     rc = process_shm_chosen(d, &kinfo);
     if ( rc < 0 )

xen/arch/arm/include/asm/domain_build.h

@@ -11,6 +11,7 @@ bool allocate_domheap_memory(struct domain *d, paddr_t tot_size,
                              alloc_domheap_mem_cb cb, void *extra);
 bool allocate_bank_memory(struct kernel_info *kinfo, gfn_t sgfn,
                           paddr_t tot_size);
+void allocate_memory(struct domain *d, struct kernel_info *kinfo);
 int construct_domain(struct domain *d, struct kernel_info *kinfo);
 int domain_fdt_begin_node(void *fdt, const char *name, uint64_t unit);
 int make_chosen_node(const struct kernel_info *kinfo);