Auto merge of #115594 - nnethercote:span-tweaks, r=cjgillot
Span tweaks Some minor improvements to code clarity. r? `@cjgillot`
This commit is contained in:
commit
6cc1898f5f
2 changed files with 146 additions and 121 deletions
|
@ -510,10 +510,6 @@ impl SpanData {
|
|||
pub fn is_dummy(self) -> bool {
|
||||
self.lo.0 == 0 && self.hi.0 == 0
|
||||
}
|
||||
#[inline]
|
||||
pub fn is_visible(self, sm: &SourceMap) -> bool {
|
||||
!self.is_dummy() && sm.is_span_accessible(self.span())
|
||||
}
|
||||
/// Returns `true` if `self` fully encloses `other`.
|
||||
pub fn contains(self, other: Self) -> bool {
|
||||
self.lo <= other.lo && other.hi <= self.hi
|
||||
|
@ -573,15 +569,9 @@ impl Span {
|
|||
self.data().with_parent(ctxt)
|
||||
}
|
||||
|
||||
/// Returns `true` if this is a dummy span with any hygienic context.
|
||||
#[inline]
|
||||
pub fn is_dummy(self) -> bool {
|
||||
self.data_untracked().is_dummy()
|
||||
}
|
||||
|
||||
#[inline]
|
||||
pub fn is_visible(self, sm: &SourceMap) -> bool {
|
||||
self.data_untracked().is_visible(sm)
|
||||
!self.is_dummy() && sm.is_span_accessible(self)
|
||||
}
|
||||
|
||||
/// Returns `true` if this span comes from any kind of macro, desugaring or inlining.
|
||||
|
|
|
@ -1,9 +1,3 @@
|
|||
// Spans are encoded using 1-bit tag and 2 different encoding formats (one for each tag value).
|
||||
// One format is used for keeping span data inline,
|
||||
// another contains index into an out-of-line span interner.
|
||||
// The encoding format for inline spans were obtained by optimizing over crates in rustc/libstd.
|
||||
// See https://internals.rust-lang.org/t/rfc-compiler-refactoring-spans/1357/28
|
||||
|
||||
use crate::def_id::{DefIndex, LocalDefId};
|
||||
use crate::hygiene::SyntaxContext;
|
||||
use crate::SPAN_TRACK;
|
||||
|
@ -13,59 +7,69 @@ use rustc_data_structures::fx::FxIndexSet;
|
|||
|
||||
/// A compressed span.
|
||||
///
|
||||
/// Whereas [`SpanData`] is 16 bytes, which is a bit too big to stick everywhere, `Span`
|
||||
/// is a form that only takes up 8 bytes, with less space for the length, parent and
|
||||
/// context. The vast majority (99.9%+) of `SpanData` instances will fit within
|
||||
/// those 8 bytes; any `SpanData` whose fields don't fit into a `Span` are
|
||||
/// [`SpanData`] is 16 bytes, which is too big to stick everywhere. `Span` only
|
||||
/// takes up 8 bytes, with less space for the length, parent and context. The
|
||||
/// vast majority (99.9%+) of `SpanData` instances can be made to fit within
|
||||
/// those 8 bytes. Any `SpanData` whose fields don't fit into a `Span` are
|
||||
/// stored in a separate interner table, and the `Span` will index into that
|
||||
/// table. Interning is rare enough that the cost is low, but common enough
|
||||
/// that the code is exercised regularly.
|
||||
///
|
||||
/// An earlier version of this code used only 4 bytes for `Span`, but that was
|
||||
/// slower because only 80--90% of spans could be stored inline (even less in
|
||||
/// very large crates) and so the interner was used a lot more.
|
||||
/// very large crates) and so the interner was used a lot more. That version of
|
||||
/// the code also predated the storage of parents.
|
||||
///
|
||||
/// Inline (compressed) format with no parent:
|
||||
/// - `span.base_or_index == span_data.lo`
|
||||
/// - `span.len_or_tag == len == span_data.hi - span_data.lo` (must be `<= MAX_LEN`)
|
||||
/// - `span.ctxt_or_tag == span_data.ctxt` (must be `<= MAX_CTXT`)
|
||||
/// There are four different span forms.
|
||||
///
|
||||
/// Interned format with inline `SyntaxContext`:
|
||||
/// - `span.base_or_index == index` (indexes into the interner table)
|
||||
/// - `span.len_or_tag == LEN_TAG` (high bit set, all other bits are zero)
|
||||
/// - `span.ctxt_or_tag == span_data.ctxt` (must be `<= MAX_CTXT`)
|
||||
/// Inline-context format (requires non-huge length, non-huge context, and no parent):
|
||||
/// - `span.lo_or_index == span_data.lo`
|
||||
/// - `span.len_with_tag_or_marker == len == span_data.hi - span_data.lo` (must be `<= MAX_LEN`)
|
||||
/// - `span.ctxt_or_parent_or_marker == span_data.ctxt` (must be `<= MAX_CTXT`)
|
||||
///
|
||||
/// Inline (compressed) format with root context:
|
||||
/// - `span.base_or_index == span_data.lo`
|
||||
/// - `span.len_or_tag == len == span_data.hi - span_data.lo` (must be `<= MAX_LEN`)
|
||||
/// - `span.len_or_tag` has top bit (`PARENT_MASK`) set
|
||||
/// - `span.ctxt == span_data.parent` (must be `<= MAX_CTXT`)
|
||||
/// Inline-parent format (requires non-huge length, root context, and non-huge parent):
|
||||
/// - `span.lo_or_index == span_data.lo`
|
||||
/// - `span.len_with_tag_or_marker & !PARENT_TAG == len == span_data.hi - span_data.lo`
|
||||
/// (must be `<= MAX_LEN`)
|
||||
/// - `span.len_with_tag_or_marker` has top bit (`PARENT_TAG`) set
|
||||
/// - `span.ctxt_or_parent_or_marker == span_data.parent` (must be `<= MAX_CTXT`)
|
||||
///
|
||||
/// Interned format:
|
||||
/// - `span.base_or_index == index` (indexes into the interner table)
|
||||
/// - `span.len_or_tag == LEN_TAG` (high bit set, all other bits are zero)
|
||||
/// - `span.ctxt_or_tag == CTXT_TAG`
|
||||
/// Partially-interned format (requires non-huge context):
|
||||
/// - `span.lo_or_index == index` (indexes into the interner table)
|
||||
/// - `span.len_with_tag_or_marker == BASE_LEN_INTERNED_MARKER`
|
||||
/// - `span.ctxt_or_parent_or_marker == span_data.ctxt` (must be `<= MAX_CTXT`)
|
||||
///
|
||||
/// The inline form uses 0 for the tag value (rather than 1) so that we don't
|
||||
/// need to mask out the tag bit when getting the length, and so that the
|
||||
/// dummy span can be all zeroes.
|
||||
/// Fully-interned format (all cases not covered above):
|
||||
/// - `span.lo_or_index == index` (indexes into the interner table)
|
||||
/// - `span.len_with_tag_or_marker == BASE_LEN_INTERNED_MARKER`
|
||||
/// - `span.ctxt_or_parent_or_marker == CTXT_INTERNED_MARKER`
|
||||
///
|
||||
/// The partially-interned form requires looking in the interning table for
|
||||
/// lo and length, but the context is stored inline as well as interned.
|
||||
/// This is useful because context lookups are often done in isolation, and
|
||||
/// inline lookups are quicker.
|
||||
///
|
||||
/// Notes about the choice of field sizes:
|
||||
/// - `base` is 32 bits in both `Span` and `SpanData`, which means that `base`
|
||||
/// values never cause interning. The number of bits needed for `base`
|
||||
/// - `lo` is 32 bits in both `Span` and `SpanData`, which means that `lo`
|
||||
/// values never cause interning. The number of bits needed for `lo`
|
||||
/// depends on the crate size. 32 bits allows up to 4 GiB of code in a crate.
|
||||
/// - `len` is 15 bits in `Span` (a u16, minus 1 bit for the tag) and 32 bits
|
||||
/// in `SpanData`, which means that large `len` values will cause interning.
|
||||
/// The number of bits needed for `len` does not depend on the crate size.
|
||||
/// The most common numbers of bits for `len` are from 0 to 7, with a peak usually
|
||||
/// at 3 or 4, and then it drops off quickly from 8 onwards. 15 bits is enough
|
||||
/// for 99.99%+ of cases, but larger values (sometimes 20+ bits) might occur
|
||||
/// dozens of times in a typical crate.
|
||||
/// - `ctxt_or_tag` is 16 bits in `Span` and 32 bits in `SpanData`, which means that
|
||||
/// large `ctxt` values will cause interning. The number of bits needed for
|
||||
/// `ctxt` values depend partly on the crate size and partly on the form of
|
||||
/// the code. No crates in `rustc-perf` need more than 15 bits for `ctxt_or_tag`,
|
||||
/// but larger crates might need more than 16 bits.
|
||||
/// Having no compression on this field means there is no performance cliff
|
||||
/// if a crate exceeds a particular size.
|
||||
/// - `len` is ~15 bits in `Span` (a u16, minus 1 bit for PARENT_TAG) and 32
|
||||
/// bits in `SpanData`, which means that large `len` values will cause
|
||||
/// interning. The number of bits needed for `len` does not depend on the
|
||||
/// crate size. The most common numbers of bits for `len` are from 0 to 7,
|
||||
/// with a peak usually at 3 or 4, and then it drops off quickly from 8
|
||||
/// onwards. 15 bits is enough for 99.99%+ of cases, but larger values
|
||||
/// (sometimes 20+ bits) might occur dozens of times in a typical crate.
|
||||
/// - `ctxt_or_parent_or_marker` is 16 bits in `Span` and two 32 bit fields in
|
||||
/// `SpanData`, which means intering will happen if `ctxt` is large, if
|
||||
/// `parent` is large, or if both values are non-zero. The number of bits
|
||||
/// needed for `ctxt` values depend partly on the crate size and partly on
|
||||
/// the form of the code. No crates in `rustc-perf` need more than 15 bits
|
||||
/// for `ctxt_or_parent_or_marker`, but larger crates might need more than 16
|
||||
/// bits. The number of bits needed for `parent` hasn't been measured,
|
||||
/// because `parent` isn't currently used by default.
|
||||
///
|
||||
/// In order to reliably use parented spans in incremental compilation,
|
||||
/// the dependency to the parent definition's span. This is performed
|
||||
|
@ -74,19 +78,22 @@ use rustc_data_structures::fx::FxIndexSet;
|
|||
#[derive(Clone, Copy, Eq, PartialEq, Hash)]
|
||||
#[rustc_pass_by_value]
|
||||
pub struct Span {
|
||||
base_or_index: u32,
|
||||
len_or_tag: u16,
|
||||
ctxt_or_tag: u16,
|
||||
lo_or_index: u32,
|
||||
len_with_tag_or_marker: u16,
|
||||
ctxt_or_parent_or_marker: u16,
|
||||
}
|
||||
|
||||
const LEN_TAG: u16 = 0b1111_1111_1111_1111;
|
||||
const PARENT_MASK: u16 = 0b1000_0000_0000_0000;
|
||||
const MAX_LEN: u32 = 0b0111_1111_1111_1111;
|
||||
const CTXT_TAG: u32 = 0b1111_1111_1111_1111;
|
||||
const MAX_CTXT: u32 = CTXT_TAG - 1;
|
||||
// `MAX_LEN` is chosen so that `PARENT_TAG | MAX_LEN` is distinct from
|
||||
// `BASE_LEN_INTERNED_MARKER`. (If `MAX_LEN` was 1 higher, this wouldn't be true.)
|
||||
const MAX_LEN: u32 = 0b0111_1111_1111_1110;
|
||||
const MAX_CTXT: u32 = 0b0111_1111_1111_1110;
|
||||
const PARENT_TAG: u16 = 0b1000_0000_0000_0000;
|
||||
const BASE_LEN_INTERNED_MARKER: u16 = 0b1111_1111_1111_1111;
|
||||
const CTXT_INTERNED_MARKER: u16 = 0b1111_1111_1111_1111;
|
||||
|
||||
/// Dummy span, both position and length are zero, syntax context is zero as well.
|
||||
pub const DUMMY_SP: Span = Span { base_or_index: 0, len_or_tag: 0, ctxt_or_tag: 0 };
|
||||
/// The dummy span has zero position, length, and context, and no parent.
|
||||
pub const DUMMY_SP: Span =
|
||||
Span { lo_or_index: 0, len_with_tag_or_marker: 0, ctxt_or_parent_or_marker: 0 };
|
||||
|
||||
impl Span {
|
||||
#[inline]
|
||||
|
@ -100,39 +107,43 @@ impl Span {
|
|||
std::mem::swap(&mut lo, &mut hi);
|
||||
}
|
||||
|
||||
let (base, len, ctxt2) = (lo.0, hi.0 - lo.0, ctxt.as_u32());
|
||||
let (lo2, len, ctxt2) = (lo.0, hi.0 - lo.0, ctxt.as_u32());
|
||||
|
||||
if len <= MAX_LEN && ctxt2 <= MAX_CTXT {
|
||||
let len_or_tag = len as u16;
|
||||
debug_assert_eq!(len_or_tag & PARENT_MASK, 0);
|
||||
|
||||
if let Some(parent) = parent {
|
||||
// Inline format with parent.
|
||||
let len_or_tag = len_or_tag | PARENT_MASK;
|
||||
let parent2 = parent.local_def_index.as_u32();
|
||||
if ctxt2 == SyntaxContext::root().as_u32()
|
||||
&& parent2 <= MAX_CTXT
|
||||
&& len_or_tag < LEN_TAG
|
||||
{
|
||||
debug_assert_ne!(len_or_tag, LEN_TAG);
|
||||
return Span { base_or_index: base, len_or_tag, ctxt_or_tag: parent2 as u16 };
|
||||
}
|
||||
} else {
|
||||
// Inline format with ctxt.
|
||||
debug_assert_ne!(len_or_tag, LEN_TAG);
|
||||
if len <= MAX_LEN {
|
||||
if ctxt2 <= MAX_CTXT && parent.is_none() {
|
||||
// Inline-context format.
|
||||
return Span {
|
||||
base_or_index: base,
|
||||
len_or_tag: len as u16,
|
||||
ctxt_or_tag: ctxt2 as u16,
|
||||
lo_or_index: lo2,
|
||||
len_with_tag_or_marker: len as u16,
|
||||
ctxt_or_parent_or_marker: ctxt2 as u16,
|
||||
};
|
||||
} else if ctxt2 == SyntaxContext::root().as_u32()
|
||||
&& let Some(parent) = parent
|
||||
&& let parent2 = parent.local_def_index.as_u32()
|
||||
&& parent2 <= MAX_CTXT
|
||||
{
|
||||
// Inline-parent format.
|
||||
return Span {
|
||||
lo_or_index: lo2,
|
||||
len_with_tag_or_marker: PARENT_TAG | len as u16,
|
||||
ctxt_or_parent_or_marker: parent2 as u16
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
// Interned format.
|
||||
// Partially-interned or fully-interned format.
|
||||
let index =
|
||||
with_span_interner(|interner| interner.intern(&SpanData { lo, hi, ctxt, parent }));
|
||||
let ctxt_or_tag = if ctxt2 <= MAX_CTXT { ctxt2 } else { CTXT_TAG } as u16;
|
||||
Span { base_or_index: index, len_or_tag: LEN_TAG, ctxt_or_tag }
|
||||
let ctxt_or_parent_or_marker = if ctxt2 <= MAX_CTXT {
|
||||
ctxt2 as u16 // partially-interned
|
||||
} else {
|
||||
CTXT_INTERNED_MARKER // fully-interned
|
||||
};
|
||||
Span {
|
||||
lo_or_index: index,
|
||||
len_with_tag_or_marker: BASE_LEN_INTERNED_MARKER,
|
||||
ctxt_or_parent_or_marker,
|
||||
}
|
||||
}
|
||||
|
||||
#[inline]
|
||||
|
@ -148,56 +159,80 @@ impl Span {
|
|||
/// This function must not be used outside the incremental engine.
|
||||
#[inline]
|
||||
pub fn data_untracked(self) -> SpanData {
|
||||
if self.len_or_tag != LEN_TAG {
|
||||
// Inline format.
|
||||
if self.len_or_tag & PARENT_MASK == 0 {
|
||||
debug_assert!(self.len_or_tag as u32 <= MAX_LEN);
|
||||
if self.len_with_tag_or_marker != BASE_LEN_INTERNED_MARKER {
|
||||
if self.len_with_tag_or_marker & PARENT_TAG == 0 {
|
||||
// Inline-context format.
|
||||
let len = self.len_with_tag_or_marker as u32;
|
||||
debug_assert!(len <= MAX_LEN);
|
||||
SpanData {
|
||||
lo: BytePos(self.base_or_index),
|
||||
hi: BytePos(self.base_or_index + self.len_or_tag as u32),
|
||||
ctxt: SyntaxContext::from_u32(self.ctxt_or_tag as u32),
|
||||
lo: BytePos(self.lo_or_index),
|
||||
hi: BytePos(self.lo_or_index + len),
|
||||
ctxt: SyntaxContext::from_u32(self.ctxt_or_parent_or_marker as u32),
|
||||
parent: None,
|
||||
}
|
||||
} else {
|
||||
let len = self.len_or_tag & !PARENT_MASK;
|
||||
debug_assert!(len as u32 <= MAX_LEN);
|
||||
let parent =
|
||||
LocalDefId { local_def_index: DefIndex::from_u32(self.ctxt_or_tag as u32) };
|
||||
// Inline-parent format.
|
||||
let len = (self.len_with_tag_or_marker & !PARENT_TAG) as u32;
|
||||
debug_assert!(len <= MAX_LEN);
|
||||
let parent = LocalDefId {
|
||||
local_def_index: DefIndex::from_u32(self.ctxt_or_parent_or_marker as u32),
|
||||
};
|
||||
SpanData {
|
||||
lo: BytePos(self.base_or_index),
|
||||
hi: BytePos(self.base_or_index + len as u32),
|
||||
lo: BytePos(self.lo_or_index),
|
||||
hi: BytePos(self.lo_or_index + len),
|
||||
ctxt: SyntaxContext::root(),
|
||||
parent: Some(parent),
|
||||
}
|
||||
}
|
||||
} else {
|
||||
// Interned format.
|
||||
let index = self.base_or_index;
|
||||
// Fully-interned or partially-interned format. In either case,
|
||||
// the interned value contains all the data, so we don't need to
|
||||
// distinguish them.
|
||||
let index = self.lo_or_index;
|
||||
with_span_interner(|interner| interner.spans[index as usize])
|
||||
}
|
||||
}
|
||||
|
||||
/// Returns `true` if this is a dummy span with any hygienic context.
|
||||
#[inline]
|
||||
pub fn is_dummy(self) -> bool {
|
||||
if self.len_with_tag_or_marker != BASE_LEN_INTERNED_MARKER {
|
||||
// Inline-context or inline-parent format.
|
||||
let lo = self.lo_or_index;
|
||||
let len = (self.len_with_tag_or_marker & !PARENT_TAG) as u32;
|
||||
debug_assert!(len <= MAX_LEN);
|
||||
lo == 0 && len == 0
|
||||
} else {
|
||||
// Fully-interned or partially-interned format.
|
||||
let index = self.lo_or_index;
|
||||
let data = with_span_interner(|interner| interner.spans[index as usize]);
|
||||
data.lo == BytePos(0) && data.hi == BytePos(0)
|
||||
}
|
||||
}
|
||||
|
||||
/// This function is used as a fast path when decoding the full `SpanData` is not necessary.
|
||||
/// It's a cut-down version of `data_untracked`.
|
||||
#[inline]
|
||||
pub fn ctxt(self) -> SyntaxContext {
|
||||
let ctxt_or_tag = self.ctxt_or_tag as u32;
|
||||
// Check for interned format.
|
||||
if self.len_or_tag == LEN_TAG {
|
||||
if ctxt_or_tag == CTXT_TAG {
|
||||
// Fully interned format.
|
||||
let index = self.base_or_index;
|
||||
with_span_interner(|interner| interner.spans[index as usize].ctxt)
|
||||
if self.len_with_tag_or_marker != BASE_LEN_INTERNED_MARKER {
|
||||
if self.len_with_tag_or_marker & PARENT_TAG == 0 {
|
||||
// Inline-context format.
|
||||
SyntaxContext::from_u32(self.ctxt_or_parent_or_marker as u32)
|
||||
} else {
|
||||
// Interned format with inline ctxt.
|
||||
SyntaxContext::from_u32(ctxt_or_tag)
|
||||
// Inline-parent format. We know that the SyntaxContext is root.
|
||||
SyntaxContext::root()
|
||||
}
|
||||
} else if self.len_or_tag & PARENT_MASK == 0 {
|
||||
// Inline format with inline ctxt.
|
||||
SyntaxContext::from_u32(ctxt_or_tag)
|
||||
} else {
|
||||
// Inline format with inline parent.
|
||||
// We know that the SyntaxContext is root.
|
||||
SyntaxContext::root()
|
||||
if self.ctxt_or_parent_or_marker != CTXT_INTERNED_MARKER {
|
||||
// Partially-interned format. This path avoids looking up the
|
||||
// interned value, and is the whole point of the
|
||||
// partially-interned format.
|
||||
SyntaxContext::from_u32(self.ctxt_or_parent_or_marker as u32)
|
||||
} else {
|
||||
// Fully-interned format.
|
||||
let index = self.lo_or_index;
|
||||
with_span_interner(|interner| interner.spans[index as usize].ctxt)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue