From 1b5faf7bd57ff3733271ec16038ddd782d9dd5ea Mon Sep 17 00:00:00 2001
From: Niklas Femerstrand <niklas.femerstrand@gmail.com>
Date: Thu, 12 Feb 2026 15:45:42 -0500
Subject: [PATCH] Fix Xen PVH boot and init_physical_heap low-memory trimming
 bug

https://github.com/nanovms/nanos/issues/2136
---
 platform/pc/service.c  | 39 ++++++++++++++++++++++++---------------
 src/x86_64/init.s      |  2 ++
 src/x86_64/interrupt.c |  9 ++++++---
 3 files changed, 32 insertions(+), 18 deletions(-)

diff --git a/platform/pc/service.c b/platform/pc/service.c
index 7c798384b..4c7950bb5 100644
--- a/platform/pc/service.c
+++ b/platform/pc/service.c
@@ -78,6 +78,7 @@ range kern_get_elf(void)
 
 BSS_RO_AFTER_INIT static boolean have_rdseed;
 BSS_RO_AFTER_INIT static boolean have_rdrand;
+BSS_RO_AFTER_INIT boolean pvh_boot;
 
 static boolean hw_seed(u64 * seed, boolean rdseed)
 {
@@ -205,8 +206,9 @@ void start_secondary_cores(kernel_heaps kh)
 
 void count_cpus_present(void)
 {
-    /* Read ACPI tables for MADT access */
-    init_acpi_tables(get_kernel_heaps());
+    /* Read ACPI tables for MADT access (not available on PVH) */
+    if (!pvh_boot)
+        init_acpi_tables(get_kernel_heaps());
 
 #ifdef SMP_ENABLE
     if (acpi_walk_madt(stack_closure_func(madt_handler, count_processors_handler))) {
@@ -265,21 +267,24 @@ static void find_initial_pages(void)
 
 void init_physical_heap(void)
 {
-    /* Carve the bootstrap heap out of a physical memory region. */
+    /* Remove low memory area from physical regions so it can be used for things
+       like starting secondary CPUs. This must be a separate pass because the
+       search below may break early, skipping remaining regions. */
     for_regions(e) {
-        if (e->type == REGION_PHYSICAL) {
-            /* Remove low memory area from physical memory regions, so that it can be used for
-             * things like starting secondary CPUs. */
-            if (e->base < MB) {
-                u64 end = e->base + e->length;
-                if (end > MB) {
-                    e->base = MB;
-                    e->length = end - MB;
-                } else {
-                    e->length = 0;
-                }
+        if (e->type == REGION_PHYSICAL && e->base < MB) {
+            u64 end = e->base + e->length;
+            if (end > MB) {
+                e->base = MB;
+                e->length = end - MB;
+            } else {
+                e->length = 0;
             }
+        }
+    }
 
+    /* Carve the bootstrap heap out of a physical memory region. */
+    for_regions(e) {
+        if (e->type == REGION_PHYSICAL) {
             u64 base = pad(e->base, PAGESIZE);
             u64 end = e->base + e->length;
             u64 length = (end & ~MASK(PAGELOG)) - base;
@@ -437,12 +442,15 @@ void pvh_start(hvm_start_info start_info)
 {
     if (start_info->magic != HVM_START_MAGIC_VALUE)
         return;
+    pvh_boot = true;
     regions->type = 0;
     hvm_memmap_entry mem_table = pointer_from_u64(start_info->memmap_paddr);
     for (int i = 0; i < start_info->memmap_entries; i++) {
         if (mem_table[i].type == HVM_MEMMAP_TYPE_RAM)
             create_region(mem_table[i].addr, mem_table[i].size, REGION_PHYSICAL);
     }
+    if (start_info->rsdp_paddr)
+        create_region(start_info->rsdp_paddr, sizeof(u64), REGION_RSDP);
     init_service(0, 0, start_info);
 }
 
@@ -528,7 +536,8 @@ void detect_devices(kernel_heaps kh, storage_attach sa)
     }
 
     /* misc / platform */
-    init_acpi(kh);
+    if (!pvh_boot)
+        init_acpi(kh);
 
     init_virtio_balloon(kh);
     init_virtio_rng(kh);
diff --git a/src/x86_64/init.s b/src/x86_64/init.s
index a76dee5d2..c298125f8 100644
--- a/src/x86_64/init.s
+++ b/src/x86_64/init.s
@@ -107,6 +107,8 @@ extern pvh_start
 
 bits 32
 pvh_start32:
+        ; ESP is undefined at PVH entry, we need a temporary stack before calls
+        mov esp, 0xa000
         PREPARE_LONG_MODE eax
         ; set up minimal mapping to be able to run in 64-bit mode, carving page
         ; tables from the top of the first 1MB of memory (which will not be
diff --git a/src/x86_64/interrupt.c b/src/x86_64/interrupt.c
index f58e289b6..0b14bc234 100644
--- a/src/x86_64/interrupt.c
+++ b/src/x86_64/interrupt.c
@@ -5,6 +5,8 @@
 #include <symtab.h>
 #include <drivers/acpi.h>
 
+extern boolean pvh_boot;
+
 //#define INT_DEBUG
 #ifdef INT_DEBUG
 #define int_debug(x, ...) do {tprintf(sym(int), 0, ss(x), ##__VA_ARGS__);} while(0)
@@ -212,7 +214,7 @@ void common_handler()
     if (handlers[i]) {
         ci->state = cpu_interrupt;
         apply(handlers[i]);
-        if (i >= INTERRUPT_VECTOR_START)
+        if (i >= INTERRUPT_VECTOR_START && !pvh_boot)
             lapic_eoi();
 
         /* enqueue interrupted user thread */
@@ -383,8 +385,9 @@ void init_interrupts(kernel_heaps kh)
     assert(v != INVALID_PHYSICAL);
     spurious_int_vector = v;
 
-    /* APIC initialization */
-    init_apic(kh);
+    /* APIC initialization, skip for PVH (Xen uses event channels) */
+    if (!pvh_boot)
+        init_apic(kh);
 }
 
 void triple_fault(void)