[hyperlight_guest_bin] Add page fault and undefined instruction hooks by syntactically · Pull Request #1877 · hyperlight-dev/hyperlight

syntactically · 2026-10-02T10:52:37Z

No description provided.

Copilot

Copilot review overview

🟡 Changes recommended

AMD64 hooks fall through to abort handling and enter handlers with incorrect stack alignment.

Review effort: Balanced
Findings: 2 · 5

Open (7)

Fix AMD64 hook stack alignment · New
Return after preparing redirected page-fault hook frame · New
Document safety contract for undefined-instruction hook dispatch · New
Document safety contract for page-fault hook dispatch · New
Document public exception hooks in the changelog · New
Add integration tests for public exception hooks · New
Remove dead commented-out declaration · New

What changed in this PR

Adds architecture-independent page-fault and undefined-instruction hooks for guest binaries.

Changes:

Adds public hook registration APIs.
Redirects AMD64 and AArch64 exception contexts to registered handlers.
Extends AArch64 syndrome decoding for instruction faults.

File	Description
`src/hyperlight_guest_bin/src/lib.rs`	Exposes the cross-platform exception module.
`src/hyperlight_guest_bin/src/exception.rs`	Defines and registers exception hooks.
`src/hyperlight_guest_bin/src/arch/amd64/exception/handle.rs`	Adds AMD64 hook dispatch.
`src/hyperlight_guest_bin/src/arch/aarch64/exception/handle.rs`	Adds AArch64 hook dispatch.
`src/hyperlight_common/src/arch/aarch64/exn.rs`	Decodes unknown and instruction-abort syndromes.

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

Signed-off-by: Lucy Menon <168595099+syntactically@users.noreply.github.com>

hyperlight-gh-bot · 2026-10-03T00:53:22Z

Benchmark Results

Measured commit: 08d8f5a5a8c4
Baseline commit: 66d5dd3ed585

kvm / amd (Linux) (➖ stable)

No benchmark improved or regressed.

Benchmark Results

function_call_codec

	`encode_control`	`decode_vec_bytes_copy`
`byte_chunks`	`772.92 ns` (➖ 1.03x faster)
`vec_bytes`	`593.64 ns` (➖ 1.02x slower)
		`374.08 µs` (➖ 1.00x slower)

payload_allocation

	`slot_pool_segmented`
`262144`	`538.19 ns` (➖ 1.01x slower)
`65536`	`143.10 ns` (➖ 1.02x slower)

sandboxes

	`create_initialized_and_drop`
`medium`	`77.37 ms` (➖ 1.02x slower)

slot_pool

	`alloc_dealloc_1500`	`alloc_dealloc_4096`	`alloc_dealloc_128`
	`7.75 ns` (➖ 1.01x slower)	`8.17 ns` (➖ 1.03x slower)	`7.73 ns` (➖ 1.01x faster)

snapshot_files

	`load_snapshot_unverified`
`small`	`92.38 µs` (➖ 1.00x slower)

virtq_readonly

	`slot_pool_segmented_fragmented`	`slot_pool_segmented`
`262144`	`7.37 µs` (➖ 1.00x slower)	`7.96 µs` (➖ 1.08x slower)
`65536`	`2.09 µs` (➖ 1.00x faster)	`1.95 µs` (➖ 1.06x faster)

virtq_readwrite

	`slot_pool_segmented_fragmented`	`slot_pool_segmented`
`65536`	`6.69 µs` (➖ 1.07x slower)	`6.27 µs` (➖ 1.09x faster)
`8192`	`1.05 µs` (➖ 1.03x faster)	`1.06 µs` (➖ 1.01x slower)
`262144`		`26.99 µs` (➖ 1.01x slower)

kvm / intel (Linux) (➖ stable)

No benchmark improved or regressed.

Benchmark Results

function_call_codec

	`encode_control`	`decode_vec_bytes_copy`
`byte_chunks`	`694.42 ns` (➖ 1.02x slower)
`vec_bytes`	`511.40 ns` (➖ 1.03x faster)
		`659.12 µs` (➖ 1.00x faster)

payload_allocation

	`slot_pool_segmented`
`262144`	`507.50 ns` (➖ 1.05x faster)
`65536`	`136.56 ns` (➖ 1.03x faster)

sandboxes

	`create_initialized_and_drop`
`medium`	`72.43 ms` (➖ 1.07x faster)

slot_pool

	`alloc_dealloc_1500`	`alloc_dealloc_4096`	`alloc_dealloc_128`
	`6.95 ns` (➖ 1.00x faster)	`6.92 ns` (➖ 1.00x faster)	`6.97 ns` (➖ 1.00x faster)

snapshot_files

	`load_snapshot_unverified`
`small`	`45.78 µs` (➖ 1.01x slower)

virtq_readonly

	`slot_pool_segmented_fragmented`	`slot_pool_segmented`
`262144`	`7.56 µs` (➖ 1.00x faster)	`7.64 µs` (➖ 1.00x slower)
`65536`	`2.13 µs` (➖ 1.00x slower)	`2.15 µs` (➖ 1.00x slower)

virtq_readwrite

	`slot_pool_segmented_fragmented`	`slot_pool_segmented`
`65536`	`7.13 µs` (➖ 1.02x slower)	`7.09 µs` (➖ 1.00x slower)
`8192`	`717.97 ns` (➖ 1.04x faster)	`721.39 ns` (➖ 1.00x slower)
`262144`		`30.81 µs` (➖ 1.06x slower)

mshv3 / amd (Linux) (❌ 1.65x)

Top regressions

virtq_readonly/slot_pool_segmented/262144 — ❌ 1.65x slower

Benchmark Results

function_call_codec

	`encode_control`	`decode_vec_bytes_copy`
`byte_chunks`	`952.78 ns` (➖ 1.00x faster)
`vec_bytes`	`778.99 ns` (➖ 1.10x slower)
		`370.45 µs` (➖ 1.20x slower)

payload_allocation

	`slot_pool_segmented`
`262144`	`730.67 ns` (➖ 1.00x slower)
`65536`	`193.71 ns` (➖ 1.00x slower)

sandboxes

	`create_initialized_and_drop`
`medium`	`56.32 ms` (➖ 1.02x faster)

slot_pool

	`alloc_dealloc_1500`	`alloc_dealloc_4096`	`alloc_dealloc_128`
	`9.73 ns` (➖ 1.04x faster)	`9.73 ns` (➖ 1.00x faster)	`9.69 ns` (➖ 1.01x faster)

snapshot_files

	`load_snapshot_unverified`
`small`	`86.00 µs` (➖ 1.01x slower)

virtq_readonly

	`slot_pool_segmented_fragmented`	`slot_pool_segmented`
`262144`	`9.73 µs` (➖ 1.07x slower)	`15.18 µs` (❌ 1.65x slower)
`65536`	`2.34 µs` (➖ 1.04x slower)	`2.32 µs` (➖ 1.05x faster)

virtq_readwrite

	`slot_pool_segmented_fragmented`	`slot_pool_segmented`
`65536`	`8.27 µs` (➖ 1.03x slower)	`8.35 µs` (➖ 1.02x slower)
`8192`	`1.27 µs` (➖ 1.00x faster)	`1.36 µs` (➖ 1.02x slower)
`262144`		`37.00 µs` (➖ 1.05x slower)

mshv3 / intel (Linux) (➖ stable)

No benchmark improved or regressed.

Benchmark Results

function_call_codec

	`encode_control`	`decode_vec_bytes_copy`
`byte_chunks`	`829.83 ns` (➖ 1.22x faster)
`vec_bytes`	`616.56 ns` (➖ 1.07x faster)
		`748.66 µs` (➖ 1.18x slower)

payload_allocation

	`slot_pool_segmented`
`262144`	`612.03 ns` (➖ 1.04x faster)
`65536`	`162.08 ns` (➖ 1.01x faster)

sandboxes

	`create_initialized_and_drop`
`medium`	`64.88 ms` (➖ 1.03x slower)

slot_pool

	`alloc_dealloc_1500`	`alloc_dealloc_4096`	`alloc_dealloc_128`
	`8.26 ns` (➖ 1.06x faster)	`8.25 ns` (➖ 1.06x faster)	`8.25 ns` (➖ 1.08x faster)

snapshot_files

	`load_snapshot_unverified`
`small`	`46.16 µs` (➖ 1.07x slower)

virtq_readonly

	`slot_pool_segmented_fragmented`	`slot_pool_segmented`
`262144`	`9.04 µs` (➖ 1.16x slower)	`8.97 µs` (➖ 1.16x slower)
`65536`	`2.54 µs` (➖ 1.14x slower)	`2.52 µs` (➖ 1.11x slower)

virtq_readwrite

	`slot_pool_segmented_fragmented`	`slot_pool_segmented`
`65536`	`8.46 µs` (➖ 1.12x slower)	`8.43 µs` (➖ 1.11x slower)
`8192`	`868.45 ns` (➖ 1.00x slower)	`866.30 ns` (➖ 1.05x faster)
`262144`		`34.82 µs` (➖ 1.04x faster)

hyperv-ws2025 / amd (Windows) (➖ stable)

No benchmark improved or regressed.

Benchmark Results

function_call_codec

	`encode_control`	`decode_vec_bytes_copy`
`byte_chunks`	`1.21 µs` (➖ 1.02x slower)
`vec_bytes`	`775.20 ns` (➖ 1.06x faster)
		`2.14 ms` (➖ 1.01x slower)

payload_allocation

	`slot_pool_segmented`
`262144`	`785.85 ns` (➖ 1.02x faster)
`65536`	`233.61 ns` (➖ 1.01x slower)

sandboxes

	`create_initialized_and_drop`
`medium`	`87.54 ms` (➖ 1.03x slower)

slot_pool

	`alloc_dealloc_1500`	`alloc_dealloc_4096`	`alloc_dealloc_128`
	`10.16 ns` (➖ 1.00x faster)	`11.02 ns` (➖ 1.05x slower)	`10.38 ns` (➖ 1.02x slower)

snapshot_files

	`load_snapshot_unverified`
`small`	`738.82 µs` (➖ 1.05x faster)

virtq_readonly

	`slot_pool_segmented_fragmented`	`slot_pool_segmented`
`262144`	`9.12 µs` (➖ 1.02x faster)	`9.35 µs` (➖ 1.16x faster)
`65536`	`2.38 µs` (➖ 1.02x faster)	`2.38 µs` (➖ 1.07x faster)

virtq_readwrite

	`slot_pool_segmented_fragmented`	`slot_pool_segmented`
`65536`	`8.98 µs` (➖ 1.01x faster)	`9.09 µs` (➖ 1.00x slower)
`8192`	`1.38 µs` (➖ 1.06x slower)	`1.31 µs` (➖ 1.02x slower)
`262144`		`44.17 µs` (➖ 1.03x slower)

hyperv-ws2025 / intel (Windows) (➖ stable)

No benchmark improved or regressed.

Benchmark Results

function_call_codec

	`encode_control`	`decode_vec_bytes_copy`
`byte_chunks`	`1.23 µs` (➖ 1.36x faster)
`vec_bytes`	`828.72 ns` (➖ 1.04x slower)
		`3.22 ms` (➖ 1.02x slower)

payload_allocation

	`slot_pool_segmented`
`262144`	`734.04 ns` (➖ 1.00x faster)
`65536`	`211.51 ns` (➖ 1.01x slower)

sandboxes

	`create_initialized_and_drop`
`medium`	`117.15 ms` (➖ 1.13x slower)

slot_pool

	`alloc_dealloc_1500`	`alloc_dealloc_4096`	`alloc_dealloc_128`
	`10.04 ns` (➖ 1.01x slower)	`10.16 ns` (➖ 1.01x slower)	`10.62 ns` (➖ 1.01x slower)

snapshot_files

	`load_snapshot_unverified`
`small`	`671.37 µs` (➖ 1.07x faster)

virtq_readonly

	`slot_pool_segmented_fragmented`	`slot_pool_segmented`
`262144`	`7.61 µs` (➖ 1.00x slower)	`7.73 µs` (➖ 1.01x faster)
`65536`	`2.33 µs` (➖ 1.01x slower)	`2.38 µs` (➖ 1.02x slower)

virtq_readwrite

	`slot_pool_segmented_fragmented`	`slot_pool_segmented`
`65536`	`8.67 µs` (➖ 1.02x slower)	`8.63 µs` (➖ 1.02x faster)
`8192`	`1.13 µs` (➖ 1.11x faster)	`1.22 µs` (➖ 1.10x slower)
`262144`		`59.25 µs` (➖ 1.39x slower)

_{Reported by cargo ci bench-report --candidate run:37082046581 --baseline run:37081579247 --config-file bench_report.toml.}

syntactically requested review from andreiltd, danbugs, dblnz, devigned, jprendes, jsturtevant, ludfjig, simongdavies and squillace as code owners October 2, 2026 10:52

syntactically added this pull request to stack #1875 October 2, 2026 10:52

syntactically added kind/enhancement For PRs adding features, improving functionality, docs, tests, etc. ready-for-review PR is ready for (re-)review labels Oct 2, 2026

This comment has been minimized.

Sign in to view

Copilot AI balanced review requested due to automatic review settings October 2, 2026 12:29

syntactically force-pushed the lm/exn-hooks-mini branch from a8843e2 to e50dc7c Compare October 2, 2026 12:29

Copilot started reviewing on behalf of syntactically October 2, 2026 12:33 View session

Copilot AI reviewed Oct 2, 2026

View reviewed changes

This comment has been minimized.

Sign in to view

syntactically force-pushed the lm/exn-hooks-mini branch from e50dc7c to 724e477 Compare October 2, 2026 15:49

This comment has been minimized.

Sign in to view

ludfjig previously approved these changes Oct 2, 2026

View reviewed changes

jsturtevant reviewed Oct 2, 2026

View reviewed changes

Comment thread src/hyperlight_guest_bin/src/arch/aarch64/exception/handle.rs Outdated

syntactically dismissed ludfjig’s stale review via 53f0463 October 2, 2026 20:17

syntactically force-pushed the lm/exn-hooks-mini branch 2 times, most recently from 53f0463 to 8f998bc Compare October 2, 2026 20:28

Base automatically changed from lm/extra-tlbi to main October 3, 2026 00:24

[hyperlight_guest_bin] Add page fault and undefined instruction hooks

08d8f5a

Signed-off-by: Lucy Menon <168595099+syntactically@users.noreply.github.com>

syntactically force-pushed the lm/exn-hooks-mini branch from 8f998bc to 08d8f5a Compare October 3, 2026 00:26

Conversation

syntactically commented Oct 2, 2026

Uh oh!

This comment has been minimized.

Copilot AI left a comment

Choose a reason for hiding this comment

Copilot review overview

🟡 Changes recommended

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

This comment has been minimized.

This comment has been minimized.

Uh oh!

hyperlight-gh-bot Bot commented Oct 3, 2026

Benchmark Results

Benchmark Results

function_call_codec

payload_allocation

sandboxes

slot_pool

snapshot_files

virtq_readonly

virtq_readwrite

Benchmark Results

function_call_codec

payload_allocation

sandboxes

slot_pool

snapshot_files

virtq_readonly

virtq_readwrite

Top regressions

Benchmark Results

function_call_codec

payload_allocation

sandboxes

slot_pool

snapshot_files

virtq_readonly

virtq_readwrite

Benchmark Results

function_call_codec

payload_allocation

sandboxes

slot_pool

snapshot_files

virtq_readonly

virtq_readwrite

Benchmark Results

function_call_codec

payload_allocation

sandboxes

slot_pool

snapshot_files

virtq_readonly

virtq_readwrite

Benchmark Results

function_call_codec

payload_allocation

sandboxes

slot_pool

snapshot_files

virtq_readonly

virtq_readwrite

Uh oh!

This branch has not been deployed

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants