Softpage improvements

Cargo.toml

@@ -1,2 +1,3 @@
 [workspace]
-members = ["hbasm", "hbbytecode", "hbvm"]
+resolver = "2"
+members  = ["hbasm", "hbbytecode", "hbvm"]

hbbytecode/src/lib.rs

@@ -35,12 +35,12 @@ macro_rules! constmod {
 ///     - I: Immediate
 ///     - L: Memory load / store size (u16)
 ///     - Other types are identity-mapped
-/// 
+///
 /// # BRC special-case
 /// BRC's 3rd operand is plain byte, not a register. Encoding is the same, but for some cases it may matter.
-/// 
+///
 /// Please, if you distinguish in your API between byte and register, special case this one.
-/// 
+///
 /// Sorry for that :(
 #[macro_export]
 macro_rules! invoke_with_def {
@@ -134,34 +134,29 @@ constmod!(pub opcode(u8) {
 
 #[repr(packed)]
 pub struct ParamBBBB(pub u8, pub u8, pub u8, pub u8);
-
 #[repr(packed)]
 pub struct ParamBBB(pub u8, pub u8, pub u8);
-
 #[repr(packed)]
 pub struct ParamBBDH(pub u8, pub u8, pub u64, pub u16);
-
 #[repr(packed)]
 pub struct ParamBBD(pub u8, pub u8, pub u64);
-
 #[repr(packed)]
 pub struct ParamBBW(pub u8, pub u8, pub u32);
-
 #[repr(packed)]
 pub struct ParamBB(pub u8, pub u8);
-
 #[repr(packed)]
 pub struct ParamBD(pub u8, pub u64);
 
 /// # Safety
 /// Has to be valid to be decoded from bytecode.
-pub unsafe trait OpParam {}
+pub unsafe trait ProgramVal {}
-unsafe impl OpParam for ParamBBBB {}
+unsafe impl ProgramVal for ParamBBBB {}
-unsafe impl OpParam for ParamBBB {}
+unsafe impl ProgramVal for ParamBBB {}
-unsafe impl OpParam for ParamBBDH {}
+unsafe impl ProgramVal for ParamBBDH {}
-unsafe impl OpParam for ParamBBD {}
+unsafe impl ProgramVal for ParamBBD {}
-unsafe impl OpParam for ParamBBW {}
+unsafe impl ProgramVal for ParamBBW {}
-unsafe impl OpParam for ParamBB {}
+unsafe impl ProgramVal for ParamBB {}
-unsafe impl OpParam for ParamBD {}
+unsafe impl ProgramVal for ParamBD {}
-unsafe impl OpParam for u64 {}
+unsafe impl ProgramVal for u64 {}
-unsafe impl OpParam for () {}
+unsafe impl ProgramVal for u8 {} // Opcode
+unsafe impl ProgramVal for () {}

hbvm/fuzz/fuzz_targets/vm.rs

@@ -16,10 +16,11 @@ fuzz_target!(|data: &[u8]| {
     if validate(data).is_ok() {
         let mut vm = unsafe {
             Vm::<_, 16384>::new(
-                SoftPagedMem {
+                SoftPagedMem::<_, true> {
                     pf_handler: TestTrapHandler,
                     program:    data,
                     root_pt:    Box::into_raw(Default::default()),
+                    icache:     Default::default(),
                 },
                 0,
             )
@@ -31,6 +32,8 @@ fuzz_target!(|data: &[u8]| {
             alloc_and_map(&mut vm.memory, 4096),
         ];
 
+        unsafe { vm.memory.write() };
+
         // Run VM
         let _ = vm.run();
 
@@ -38,6 +41,8 @@ fuzz_target!(|data: &[u8]| {
         for (i, page) in pages.into_iter().enumerate() {
             unmap_and_dealloc(&mut vm.memory, page, i as u64 * 4096);
         }
+
+        let _ = unsafe { Box::from_raw(vm.memory.root_pt) };
     }
 });
 

hbvm/src/lib.rs

@@ -26,7 +26,9 @@ use {
     bmc::BlockCopier,
     core::{cmp::Ordering, mem::size_of, ops},
     derive_more::Display,
-    hbbytecode::{OpParam, ParamBB, ParamBBB, ParamBBBB, ParamBBD, ParamBBDH, ParamBBW, ParamBD},
+    hbbytecode::{
+        ParamBB, ParamBBB, ParamBBBB, ParamBBD, ParamBBDH, ParamBBW, ParamBD, ProgramVal,
+    },
     value::{Value, ValueVariant},
 };
 
@@ -366,7 +368,7 @@ where
 
     /// Decode instruction operands
     #[inline(always)]
-    unsafe fn decode<T: OpParam>(&mut self) -> T {
+    unsafe fn decode<T: ProgramVal>(&mut self) -> T {
         let pc1 = self.pc + 1;
         let data = self.memory.prog_read_unchecked::<T>(pc1 as _);
         self.pc += 1 + size_of::<T>();
@@ -515,13 +517,13 @@ pub trait Memory {
     ///
     /// # Safety
     /// - Data read have to be valid
-    unsafe fn prog_read<T>(&mut self, addr: u64) -> Option<T>;
+    unsafe fn prog_read<T: ProgramVal>(&mut self, addr: u64) -> Option<T>;
 
     /// Read from program memory to exectue
     ///
     /// # Safety
     /// - You have to be really sure that these bytes are there, understand?
-    unsafe fn prog_read_unchecked<T>(&mut self, addr: u64) -> T;
+    unsafe fn prog_read_unchecked<T: ProgramVal>(&mut self, addr: u64) -> T;
 }
 
 /// Unhandled load access trap

hbvm/src/main.rs

@@ -17,10 +17,11 @@ fn main() -> Result<(), Box<dyn std::error::Error>> {
     } else {
         unsafe {
             let mut vm = Vm::<_, 0>::new(
-                SoftPagedMem {
+                SoftPagedMem::<_, true> {
                     pf_handler: TestTrapHandler,
                     program:    &prog,
                     root_pt:    Box::into_raw(Default::default()),
+                    icache:     Default::default(),
                 },
                 4,
             );
@@ -46,12 +47,12 @@ fn main() -> Result<(), Box<dyn std::error::Error>> {
             println!("Program interrupt: {:?}", vm.run());
             println!("{:?}", vm.registers);
 
-            println!("{:?}", core::slice::from_raw_parts(data, 4096));
             std::alloc::dealloc(
                 data,
                 std::alloc::Layout::from_size_align_unchecked(4096, 4096),
             );
             vm.memory.unmap(8192).unwrap();
+            let _ = Box::from_raw(vm.memory.root_pt);
         }
     }
     Ok(())

hbvm/src/mem/softpaging/icache.rs

@@ -0,0 +1,103 @@
+//! Program instruction cache
+
+use {
+    super::{lookup::AddrPageLookuper, paging::PageTable, PageSize},
+    core::{
+        mem::{size_of, MaybeUninit},
+        ptr::{copy_nonoverlapping, NonNull},
+    },
+};
+
+/// Instruction cache
+#[derive(Clone, Debug)]
+pub struct ICache {
+    /// Current page address base
+    base: u64,
+    /// Curent page pointer
+    data: Option<NonNull<u8>>,
+    /// Current page size
+    size: PageSize,
+    /// Address mask
+    mask: u64,
+}
+
+impl Default for ICache {
+    fn default() -> Self {
+        Self {
+            base: Default::default(),
+            data: Default::default(),
+            size: PageSize::Size4K,
+            mask: Default::default(),
+        }
+    }
+}
+
+impl ICache {
+    /// Fetch instruction from cache
+    ///
+    /// # Safety
+    /// `T` should be valid to read from instruction memory
+    pub(super) unsafe fn fetch<T>(&mut self, addr: u64, root_pt: *const PageTable) -> Option<T> {
+        let mut ret = MaybeUninit::<T>::uninit();
+
+        let pbase = self
+            .data
+            .or_else(|| self.fetch_page(self.base.checked_add(self.size as _)?, root_pt))?;
+
+        // Get address base
+        let base = addr & self.mask;
+
+        // Base not matching, fetch anew
+        if base != self.base {
+            self.fetch_page(base, root_pt)?;
+        };
+
+        let offset = addr & !self.mask;
+        let requ_size = size_of::<T>();
+
+        // Page overflow
+        let rem = (offset as usize)
+            .saturating_add(requ_size)
+            .saturating_sub(self.size as _);
+        let first_copy = requ_size.saturating_sub(rem);
+
+        // Copy non-overflowing part
+        copy_nonoverlapping(pbase.as_ptr(), ret.as_mut_ptr().cast::<u8>(), first_copy);
+
+        // Copy overflow
+        if rem != 0 {
+            let pbase = self.fetch_page(self.base.checked_add(self.size as _)?, root_pt)?;
+
+            // Unlikely, unsupported scenario
+            if rem > self.size as _ {
+                return None;
+            }
+
+            copy_nonoverlapping(
+                pbase.as_ptr(),
+                ret.as_mut_ptr().cast::<u8>().add(first_copy),
+                rem,
+            );
+        }
+
+        Some(ret.assume_init())
+    }
+
+    /// Fetch a page
+    unsafe fn fetch_page(&mut self, addr: u64, pt: *const PageTable) -> Option<NonNull<u8>> {
+        let res = AddrPageLookuper::new(addr, 0, pt).next()?.ok()?;
+        if !super::perm_check::executable(res.perm) {
+            return None;
+        }
+
+        (self.size, self.mask) = match res.size {
+            4096 => (PageSize::Size4K, !((1 << 8) - 1)),
+            2097152 => (PageSize::Size2M, !((1 << (8 * 2)) - 1)),
+            1073741824 => (PageSize::Size1G, !((1 << (8 * 3)) - 1)),
+            _ => return None,
+        };
+        self.data = Some(NonNull::new(res.ptr)?);
+        self.base = addr & self.mask;
+        self.data
+    }
+}

hbvm/src/mem/softpaging/lookup.rs

@@ -111,7 +111,7 @@ impl Iterator for AddrPageLookuper {
         };
 
         // Get available byte count in the selected page with offset
-        let avail = (size as usize - offset).clamp(0, self.size);
+        let avail = (size as usize).saturating_sub(offset).clamp(0, self.size);
         self.bump(size);
 
         Some(Ok(AddrPageLookupOk {

hbvm/src/mem/softpaging/mapping.rs

@@ -10,7 +10,7 @@ use {
     derive_more::Display,
 };
 
-impl<'p, A> SoftPagedMem<'p, A> {
+impl<'p, A,  const OUT_PROG_EXEC: bool> SoftPagedMem<'p, A, OUT_PROG_EXEC> {
     /// Maps host's memory into VM's memory
     ///
     /// # Safety

hbvm/src/mem/softpaging/mod.rs

@@ -2,6 +2,9 @@
 
 use core::mem::size_of;
 
+use self::icache::ICache;
+
+pub mod icache;
 pub mod lookup;
 pub mod paging;
 
@@ -15,17 +18,25 @@ use {
 };
 
 /// HoleyBytes software paged memory
+/// 
+/// - `OUT_PROG_EXEC`: set to `false` to disable executing program
+///   not contained in initially provided program, even the pages
+///   are executable
 #[derive(Clone, Debug)]
-pub struct SoftPagedMem<'p, PfH> {
+pub struct SoftPagedMem<'p, PfH, const OUT_PROG_EXEC: bool = true> {
     /// Root page table
     pub root_pt:    *mut PageTable,
     /// Page fault handler
     pub pf_handler: PfH,
     /// Program memory segment
     pub program:    &'p [u8],
+    /// Program instruction cache
+    pub icache:     ICache,
 }
 
-impl<'p, PfH: HandlePageFault> Memory for SoftPagedMem<'p, PfH> {
+impl<'p, PfH: HandlePageFault, const OUT_PROG_EXEC: bool> Memory
+    for SoftPagedMem<'p, PfH, OUT_PROG_EXEC>
+{
     /// Load value from an address
     ///
     /// # Safety
@@ -65,6 +76,10 @@ impl<'p, PfH: HandlePageFault> Memory for SoftPagedMem<'p, PfH> {
 
     #[inline(always)]
     unsafe fn prog_read<T>(&mut self, addr: u64) -> Option<T> {
+        if OUT_PROG_EXEC && addr as usize > self.program.len() {
+            return self.icache.fetch::<T>(addr, self.root_pt);
+        }
+
         let addr = addr as usize;
         self.program
             .get(addr..addr + size_of::<T>())
@@ -73,11 +88,18 @@ impl<'p, PfH: HandlePageFault> Memory for SoftPagedMem<'p, PfH> {
 
     #[inline(always)]
     unsafe fn prog_read_unchecked<T>(&mut self, addr: u64) -> T {
+        if OUT_PROG_EXEC && addr as usize > self.program.len() {
+            return self
+                .icache
+                .fetch::<T>(addr as _, self.root_pt)
+                .unwrap_or_else(|| core::mem::zeroed());
+        }
+
         self.program.as_ptr().add(addr as _).cast::<T>().read()
     }
 }
 
-impl<'p, PfH: HandlePageFault> SoftPagedMem<'p, PfH> {
+impl<'p, PfH: HandlePageFault, const OUT_PROG_EXEC: bool> SoftPagedMem<'p, PfH, OUT_PROG_EXEC> {
     // Everyone behold, the holy function, the god of HBVM memory accesses!
 
     /// Split address to pages, check their permissions and feed pointers with offset