Optimize proc maps parsing code size

The current code size is really wastefully large. Originally, it was
1500 lines of assembly in Godbolt, now I reduced it to just under 800.
The effect of `.text` size in hello world is from 297028 to 295453 which
is small but not completely irrelevant. It's just a small fish in the
bigger pond of DWARF parsing, but it's better than nothing.

I extracted the parsing of each component into a separate function to
allow for better sharing. I replaced the string methods with manual
iteration since that results in simpler code because it has to handle
fewer cases. I also had to use unsafe because the bounds checks were
sadly not optimized out and were really large.

I also made the parser less resilient against whitespace, now it no
longer handles Unicode whitespace (an obvious simplification) but also
no longer handles any whitespace except the normal SP. I think this is
fine, it seems highly unlikely that a system would suddenly use another
type of whitespace (but I guess not impossible?).

Another simplification was simply removing the parsing of unused fields
that were not needed.

Author: Noratrieb

src/symbolize/gimli/parse_running_mmaps_unix.rs

@@ -13,20 +13,8 @@ use core::str::FromStr;
 pub(super) struct MapsEntry {
     /// start (inclusive) and limit (exclusive) of address range.
     address: (usize, usize),
-    /// The perms field are the permissions for the entry
-    ///
-    /// r = read
-    /// w = write
-    /// x = execute
-    /// s = shared
-    /// p = private (copy on write)
-    perms: [char; 4],
     /// Offset into the file (or "whatever").
     offset: u64,
-    /// device (major, minor)
-    dev: (usize, usize),
-    /// inode on the device. 0 indicates that no inode is associated with the memory region (e.g. uninitalized data aka BSS).
-    inode: usize,
     /// Usually the file backing the mapping.
     ///
     /// Note: The man page for proc includes a note about "coordination" by
@@ -56,15 +44,21 @@ pub(super) struct MapsEntry {
 }
 
 pub(super) fn parse_maps() -> Result<Vec<MapsEntry>, &'static str> {
-    let mut v = Vec::new();
     let mut proc_self_maps =
         File::open("/proc/self/maps").map_err(|_| "Couldn't open /proc/self/maps")?;
     let mut buf = String::new();
     let _bytes_read = proc_self_maps
         .read_to_string(&mut buf)
         .map_err(|_| "Couldn't read /proc/self/maps")?;
-    for line in buf.lines() {
+
+    let mut v = Vec::new();
+    let mut buf = buf.as_str();
+    while let Some(match_idx) = buf.bytes().position(|b| b == b'\n') {
+        let line = unsafe { buf.get_unchecked(..match_idx) };
+
         v.push(line.parse()?);
+
+        buf = unsafe { buf.get_unchecked((match_idx + 1)..) };
     }
 
     Ok(v)
@@ -92,70 +86,86 @@ impl FromStr for MapsEntry {
     // e.g.: "ffffffffff600000-ffffffffff601000 --xp 00000000 00:00 0                  [vsyscall]"
     // e.g.: "7f5985f46000-7f5985f48000 rw-p 00039000 103:06 76021795                  /usr/lib/x86_64-linux-gnu/ld-linux-x86-64.so.2"
     // e.g.: "35b1a21000-35b1a22000 rw-p 00000000 00:00 0"
-    //
-    // Note that paths may contain spaces, so we can't use `str::split` for parsing (until
-    // Split::remainder is stabilized #77998).
     fn from_str(s: &str) -> Result<Self, Self::Err> {
-        let (range_str, s) = s.trim_start().split_once(' ').unwrap_or((s, ""));
+        // While there are nicer standard library APIs available for this, we aim for minimal code size.
+
+        let mut state = s;
+
+        fn parse_start<'a>(state: &mut &'a str) -> &'a str {
+            let start_idx = state.bytes().position(|b| b != b' ');
+            if let Some(start_idx) = start_idx {
+                // SAFETY: It comes from position, so it's in bounds.
+                //         It must be on a UTF-8 boundary as it's the first byte that isn't ' '.
+                *state = unsafe { state.get_unchecked(start_idx..) };
+            }
+            let match_idx = state.bytes().position(|b| b == b' ');
+            match match_idx {
+                None => {
+                    let result = *state;
+                    *state = "";
+                    result
+                }
+                Some(match_idx) => {
+                    // SAFETY: match_index comes from .bytes().position() of an ASCII character,
+                    //         so it's both in bounds and a UTF-8 boundary
+                    let result = unsafe { state.get_unchecked(..match_idx) };
+                    // SAFETY: Since match_idx is the ' ', there must be at least the end after it.
+                    *state = unsafe { state.get_unchecked((match_idx + 1)..) };
+                    result
+                }
+            }
+        }
+
+        fn error(msg: &str) -> &str {
+            if cfg!(debug_assertions) {
+                msg
+            } else {
+                "invalid map entry"
+            }
+        }
+
+        let range_str = parse_start(&mut state);
         if range_str.is_empty() {
-            return Err("Couldn't find address");
+            return Err(error("Couldn't find address"));
         }
 
-        let (perms_str, s) = s.trim_start().split_once(' ').unwrap_or((s, ""));
+        let perms_str = parse_start(&mut state);
         if perms_str.is_empty() {
-            return Err("Couldn't find permissions");
+            return Err(error("Couldn't find permissions"));
         }
 
-        let (offset_str, s) = s.trim_start().split_once(' ').unwrap_or((s, ""));
+        let offset_str = parse_start(&mut state);
         if offset_str.is_empty() {
-            return Err("Couldn't find offset");
+            return Err(error("Couldn't find offset"));
         }
 
-        let (dev_str, s) = s.trim_start().split_once(' ').unwrap_or((s, ""));
+        let dev_str = parse_start(&mut state);
         if dev_str.is_empty() {
-            return Err("Couldn't find dev");
+            return Err(error("Couldn't find dev"));
         }
 
-        let (inode_str, s) = s.trim_start().split_once(' ').unwrap_or((s, ""));
+        let inode_str = parse_start(&mut state);
         if inode_str.is_empty() {
             return Err("Couldn't find inode");
         }
 
         // Pathname may be omitted in which case it will be empty
-        let pathname_str = s.trim_start();
+        let pathname_str = state.trim_ascii_start();
 
-        let hex = |s| usize::from_str_radix(s, 16).map_err(|_| "Couldn't parse hex number");
-        let hex64 = |s| u64::from_str_radix(s, 16).map_err(|_| "Couldn't parse hex number");
+        let hex = |s| usize::from_str_radix(s, 16).map_err(|_| error("Couldn't parse hex number"));
+        let hex64 = |s| u64::from_str_radix(s, 16).map_err(|_| error("Couldn't parse hex number"));
 
         let address = if let Some((start, limit)) = range_str.split_once('-') {
             (hex(start)?, hex(limit)?)
         } else {
-            return Err("Couldn't parse address range");
-        };
-        let perms: [char; 4] = {
-            let mut chars = perms_str.chars();
-            let mut c = || chars.next().ok_or("insufficient perms");
-            let perms = [c()?, c()?, c()?, c()?];
-            if chars.next().is_some() {
-                return Err("too many perms");
-            }
-            perms
+            return Err(error("Couldn't parse address range"));
         };
         let offset = hex64(offset_str)?;
-        let dev = if let Some((major, minor)) = dev_str.split_once(':') {
-            (hex(major)?, hex(minor)?)
-        } else {
-            return Err("Couldn't parse dev");
-        };
-        let inode = hex(inode_str)?;
         let pathname = pathname_str.into();
 
         Ok(MapsEntry {
             address,
-            perms,
             offset,
-            dev,
-            inode,
             pathname,
         })
     }
@@ -172,10 +182,7 @@ fn check_maps_entry_parsing_64bit() {
             .unwrap(),
         MapsEntry {
             address: (0xffffffffff600000, 0xffffffffff601000),
-            perms: ['-', '-', 'x', 'p'],
             offset: 0x00000000,
-            dev: (0x00, 0x00),
-            inode: 0x0,
             pathname: "[vsyscall]".into(),
         }
     );
@@ -187,10 +194,7 @@ fn check_maps_entry_parsing_64bit() {
             .unwrap(),
         MapsEntry {
             address: (0x7f5985f46000, 0x7f5985f48000),
-            perms: ['r', 'w', '-', 'p'],
             offset: 0x00039000,
-            dev: (0x103, 0x06),
-            inode: 0x76021795,
             pathname: "/usr/lib/x86_64-linux-gnu/ld-linux-x86-64.so.2".into(),
         }
     );
@@ -200,10 +204,7 @@ fn check_maps_entry_parsing_64bit() {
             .unwrap(),
         MapsEntry {
             address: (0x35b1a21000, 0x35b1a22000),
-            perms: ['r', 'w', '-', 'p'],
             offset: 0x00000000,
-            dev: (0x00, 0x00),
-            inode: 0x0,
             pathname: Default::default(),
         }
     );
@@ -224,10 +225,7 @@ fn check_maps_entry_parsing_32bit() {
             .unwrap(),
         MapsEntry {
             address: (0x08056000, 0x08077000),
-            perms: ['r', 'w', '-', 'p'],
             offset: 0x00000000,
-            dev: (0x00, 0x00),
-            inode: 0x0,
             pathname: "[heap]".into(),
         }
     );
@@ -239,10 +237,7 @@ fn check_maps_entry_parsing_32bit() {
             .unwrap(),
         MapsEntry {
             address: (0xb7c79000, 0xb7e02000),
-            perms: ['r', '-', '-', 'p'],
             offset: 0x00000000,
-            dev: (0x08, 0x01),
-            inode: 0x60662705,
             pathname: "/usr/lib/locale/locale-archive".into(),
         }
     );
@@ -252,10 +247,7 @@ fn check_maps_entry_parsing_32bit() {
             .unwrap(),
         MapsEntry {
             address: (0xb7e02000, 0xb7e03000),
-            perms: ['r', 'w', '-', 'p'],
             offset: 0x00000000,
-            dev: (0x00, 0x00),
-            inode: 0x0,
             pathname: Default::default(),
         }
     );
@@ -266,10 +258,7 @@ fn check_maps_entry_parsing_32bit() {
             .unwrap(),
         MapsEntry {
             address: (0xb7c79000, 0xb7e02000),
-            perms: ['r', '-', '-', 'p'],
             offset: 0x00000000,
-            dev: (0x08, 0x01),
-            inode: 0x60662705,
             pathname: "/executable/path/with some spaces".into(),
         }
     );
@@ -280,10 +269,7 @@ fn check_maps_entry_parsing_32bit() {
             .unwrap(),
         MapsEntry {
             address: (0xb7c79000, 0xb7e02000),
-            perms: ['r', '-', '-', 'p'],
             offset: 0x00000000,
-            dev: (0x08, 0x01),
-            inode: 0x60662705,
             pathname: "/executable/path/with  multiple-continuous    spaces  ".into(),
         }
     );
@@ -294,10 +280,7 @@ fn check_maps_entry_parsing_32bit() {
             .unwrap(),
         MapsEntry {
             address: (0xb7c79000, 0xb7e02000),
-            perms: ['r', '-', '-', 'p'],
             offset: 0x00000000,
-            dev: (0x08, 0x01),
-            inode: 0x60662705,
             pathname: "/executable/path/starts-with-spaces".into(),
         }
     );