implement MappedPageBox - #2688
Open
RajeshRk18 wants to merge 1 commit into
Open
Conversation
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
There was a problem hiding this comment.
Benchmark Results
Details
| Benchmark | Current: afb2fd0 | Previous: 2e23902 | Performance Ratio |
|---|---|---|---|
| startup_benchmark Build Time | 94.88 s |
80.34 s |
1.18 ❗ |
| startup_benchmark File Size | 0.79 MB |
0.80 MB |
0.99 ❗ |
| Startup Time - 1 core | 0.72 s (±0.01 s) |
0.75 s (±0.02 s) |
0.97 ❗ |
| Startup Time - 2 cores | 0.73 s (±0.02 s) |
0.74 s (±0.02 s) |
0.99 |
| Startup Time - 4 cores | 0.75 s (±0.02 s) |
0.74 s (±0.02 s) |
1.02 |
| multithreaded_benchmark Build Time | 97.09 s |
82.11 s |
1.18 ❗ |
| multithreaded_benchmark File Size | 0.88 MB |
0.86 MB |
1.03 ❗ |
| Multithreaded Pi Efficiency - 2 Threads | 66.38 % (±7.07 %) |
85.89 % (±6.61 %) |
0.77 ❗ |
| Multithreaded Pi Efficiency - 4 Threads | 40.77 % (±3.21 %) |
43.43 % (±2.56 %) |
0.94 |
| Multithreaded Pi Efficiency - 8 Threads | 20.25 % (±1.62 %) |
25.76 % (±1.53 %) |
0.79 ❗ |
| micro_benchmarks Build Time | 228.86 s |
80.40 s |
2.85 ❗ |
| micro_benchmarks File Size | 0.88 MB |
0.86 MB |
1.03 ❗ |
| Scheduling time - 1 thread | 181.75 ticks (±34.28 ticks) |
62.65 ticks (±4.06 ticks) |
2.90 ❗ |
| Scheduling time - 2 threads | 112.33 ticks (±19.87 ticks) |
34.08 ticks (±4.10 ticks) |
3.30 ❗ |
| Micro - Time for syscall (getpid) | 9.79 ticks (±5.47 ticks) |
3.45 ticks (±0.58 ticks) |
2.84 ❗ |
| Memcpy speed - (built_in) block size 4096 | 54954.16 MByte/s (±39455.21 MByte/s) |
82448.38 MByte/s (±56997.13 MByte/s) |
0.67 |
| Memcpy speed - (built_in) block size 1048576 | 13800.55 MByte/s (±11052.06 MByte/s) |
30585.98 MByte/s (±24707.84 MByte/s) |
0.45 |
| Memcpy speed - (built_in) block size 16777216 | 11602.18 MByte/s (±9567.56 MByte/s) |
26340.06 MByte/s (±21720.96 MByte/s) |
0.44 |
| Memset speed - (built_in) block size 4096 | 55175.27 MByte/s (±39573.39 MByte/s) |
82292.76 MByte/s (±56891.50 MByte/s) |
0.67 |
| Memset speed - (built_in) block size 1048576 | 14141.22 MByte/s (±11220.95 MByte/s) |
31323.85 MByte/s (±25145.86 MByte/s) |
0.45 |
| Memset speed - (built_in) block size 16777216 | 11914.80 MByte/s (±9749.06 MByte/s) |
27104.68 MByte/s (±22209.94 MByte/s) |
0.44 |
| Memcpy speed - (rust) block size 4096 | 52099.50 MByte/s (±37357.42 MByte/s) |
74097.96 MByte/s (±51811.44 MByte/s) |
0.70 |
| Memcpy speed - (rust) block size 1048576 | 15099.14 MByte/s (±13302.15 MByte/s) |
30361.60 MByte/s (±24602.37 MByte/s) |
0.50 |
| Memcpy speed - (rust) block size 16777216 | 12266.05 MByte/s (±10429.45 MByte/s) |
27625.34 MByte/s (±22806.88 MByte/s) |
0.44 |
| Memset speed - (rust) block size 4096 | 52678.43 MByte/s (±37705.76 MByte/s) |
74373.47 MByte/s (±51976.48 MByte/s) |
0.71 |
| Memset speed - (rust) block size 1048576 | 15352.60 MByte/s (±13395.62 MByte/s) |
31110.89 MByte/s (±25033.24 MByte/s) |
0.49 |
| Memset speed - (rust) block size 16777216 | 12627.38 MByte/s (±10644.62 MByte/s) |
28386.93 MByte/s (±23265.03 MByte/s) |
0.44 |
| alloc_benchmarks Build Time | 218.77 s |
74.76 s |
2.93 ❗ |
| alloc_benchmarks File Size | 0.87 MB |
0.87 MB |
0.99 ❗ |
| Allocations - Allocation success | 91.38 % |
91.31 % |
1.00 ❗ |
| Allocations - Deallocation success | 100.00 % |
100.00 % |
1 |
| Allocations - Pre-fail Allocations | 61.60 % |
61.44 % |
1.00 ❗ |
| Allocations - Average Allocation time | 16115.33 Ticks (±3060.92 Ticks) |
5860.58 Ticks (±98.43 Ticks) |
2.75 ❗ |
| Allocations - Average Allocation time (no fail) | 17985.55 Ticks (±3036.26 Ticks) |
6554.81 Ticks (±92.86 Ticks) |
2.74 ❗ |
| Allocations - Average Deallocation time | 7625.61 Ticks (±1503.91 Ticks) |
1805.01 Ticks (±250.35 Ticks) |
4.22 ❗ |
| mutex_benchmark Build Time | 228.32 s |
79.82 s |
2.86 ❗ |
| mutex_benchmark File Size | 0.88 MB |
0.86 MB |
1.03 ❗ |
| Mutex Stress Test Average Time per Iteration - 1 Threads | 36.20 ns (±8.62 ns) |
12.10 ns (±0.41 ns) |
2.99 ❗ |
| Mutex Stress Test Average Time per Iteration - 2 Threads | 31.36 ns (±9.11 ns) |
40.26 ns (±1.68 ns) |
0.78 |
This comment was automatically generated by workflow using github-action-benchmark.
mkroening
requested changes
Aug 30, 2026
mkroening
left a comment
mkroening
left a comment
Member
There was a problem hiding this comment.
Thanks! Did you use any AI assistance? :)
Comment on lines
+51
to
+54
| // `paging::unmap` only flushes the TLB of this CPU. Request the flush on | ||
| // all other CPUs before the frames can be reused. | ||
| #[cfg(all(target_arch = "x86_64", feature = "smp"))] | ||
| crate::arch::kernel::apic::ipi_tlb_flush(); |
Member
There was a problem hiding this comment.
This seems costly. Is this necessary? We do an IPI TLB flush on mapping after all.
Author
There was a problem hiding this comment.
will see how i can come with a better drop
Author
There was a problem hiding this comment.
@mkroening I removed the call now. But the ipi sent on mapping flushes TLB on other cpus only if the entry is present in the page table. since we delete the entry on unmap, stale TLB can still remains on other cpus.
Comment on lines
+60
to
+66
| impl Deref for MappedPageBox { | ||
| type Target = PageRange; | ||
|
|
||
| fn deref(&self) -> &Self::Target { | ||
| &self.pages | ||
| } | ||
| } |
Member
There was a problem hiding this comment.
This seems non-obvious to me, since there are two types of ranges inside. If we need something like this, I'd prefer accessor methods.
Comment on lines
+68
to
+70
| fn page_count(pages: &PageBox) -> usize { | ||
| pages.len().get() / BasePageSize::SIZE as usize | ||
| } |
Member
There was a problem hiding this comment.
Please remove this helper function.
Comment on lines
+72
to
+79
| fn map(pages: &PageBox, phys_addr: PhysAddr, flags: PageTableEntryFlags) { | ||
| paging::map::<BasePageSize>( | ||
| VirtAddr::from(pages.start()), | ||
| phys_addr, | ||
| page_count(pages), | ||
| flags, | ||
| ); | ||
| } |
Member
There was a problem hiding this comment.
Please remove this helper function.
Author
yeah i am clearing unwanted stuff it added here! |
RajeshRk18
marked this pull request as draft
August 31, 2026 08:55
RajeshRk18
force-pushed
the
feat/mapped-page-box
branch
from
September 3, 2026 14:28
d3ab508 to
afb2fd0
Compare
RajeshRk18
marked this pull request as ready for review
September 3, 2026 15:06
mkroening
requested changes
Sep 6, 2026
mkroening
left a comment
mkroening
left a comment
Member
There was a problem hiding this comment.
Thanks, this looks good to me. One more suggestion, though.
| }) | ||
| } | ||
|
|
||
| pub fn pages(&self) -> &PageBox { |
Member
There was a problem hiding this comment.
Suggested change
| pub fn pages(&self) -> &PageBox { | |
| pub fn pages(&self) -> &PageRange { |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Closes #2338
Added MappedPageBox and used it in two call sites.
Also removed
#[expect(dead_code)]in src/arch/aarch64/mm/paging.rs because new public API makes it externally reachable.