Performance optimizations

[WonderMr]

What's new

10 safe performance optimizations for STM32WB55 (Cortex-M4 @ 64MHz) + 1 Bugfix

Compiler & build:

1. -Og → -Os for release builds — enables most -O2 passes: function inlining, dead code elimination, loop optimization, aggressive register allocation, tail call optimization, and common subexpression elimination (site_scons/firmwareopts.scons)

Memory management (correctness + perf):
2. Disable heap memset on free() in release — configHEAP_CLEAR_MEMORY_ON_FREE is now conditional on FURI_DEBUG. Saves ~500+ memset calls/sec during active GUI/protocol work (FreeRTOSConfig.h)
3. Fix calloc() to explicitly zero memory — with heap-clear disabled in release, calloc() now does its own memset(0) to guarantee zero-initialized returns (memmgr.c)
4. Fix realloc() to copy min(old_size, new_size) bytes — original copied size (new) bytes, reading past old allocation when growing. Added memmgr_heap_get_block_size() that reads usable size from Heap_4 BlockLink_t header. Also added heapVALIDATE_BLOCK_POINTER to the new public memmgr_heap_get_block_size() for parity with vPortFree().

Branch prediction:
5. __builtin_expect hints on furi_check/assert/break — crash code moves to end of function, hot path becomes fall-through (0 pipeline penalty on Cortex-M4 3-stage pipeline). Affects ~2300+ call sites across the firmware (check.h)

DMA:
6. SPI TX via DMA with RX drain — furi_hal_spi_bus_tx() now delegates to DMA when scheduler is running, freeing the CPU during display updates (~1KB/frame @ 20fps) and radio TX. TX-only path sets up RX DMA channel draining into a dummy byte to prevent OVR accumulation. Polling fallback preserved for pre-scheduler context (furi_hal_spi.c)
Also fixes a pre-existing race in the cleanup path: LL_DMA_DisableIT_TC was issued after furi_semaphore_release, allowing a late ISR to crash furi_check on a double-release. Now disables TC IRQ and clears TC flag before releasing the semaphore

Hot function inlining:
7. attribute((flatten)) on furi_get_tick() — forces inlining of FreeRTOS wrappers at call sites (kernel.c)
8. attribute((flatten)) on hot thread functions — applied to furi_thread_get_current_id(), furi_thread_get_current(), furi_thread_flags_get() (thread.c)

String formatting:
9. In-place vprintf for furi_string_cat_vprintf() — formats directly into destination buffer at current offset, growing only if needed. Eliminates temporary FuriString allocation (malloc + format + memcpy + free) per call (string.c)

Power:
10. Reduce configEXPECTED_IDLE_TIME_BEFORE_SLEEP from 4 to 2 ticks — allows FreeRTOS tickless idle to enter STOP mode more aggressively (2ms threshold instead of 4ms). Reduces average power consumption (FreeRTOSConfig.h)

Bugfix:
11. Fix DMA timeout race in furi_hal_spi_bus_trx_dma() - on timeout the cleanup released spi_dma_completed while LL_DMA_DisableIT_TC was issued after. A late or pending DMA completion ISR would then call furi_semaphore_release() on an already-full binary semaphore and crash furi_check. Disabled the TC IRQ and cleared the pending TC flag before releasing the semaphore (spi_dma_isr gates its release on LL_DMA_IsEnabledIT_TC). Applied to both the TX-only path touched by #6 (b51e744) and the symmetric pre-existing TRX/RX path (f48d096) (furi_hal_spi.c).

Verification

• Build: ./fbt COMPACT=1 DEBUG=0 — compiles without warnings/errors
• Build: ./fbt DEBUG=1 — debug build still compiles and links
• Boot device, navigate Settings → About — FW version shown correctly
• Open SubGHz, NFC, IR apps — UI responsive, no hangs
• Verify formatted strings render correctly in UI (menus, popups, dialogs)
• SPI peripherals working: display renders, Sub-GHz TX/RX functional
• Leave device idle 30s — confirm no increased battery drain or wake-up issues
• Stress test: rapid app switching, menu scrolling — no crashes or visual artifacts
• Verify calloc-dependent code (e.g. allocating zero-initialized buffers) works correctly in release build

Checklist (For Reviewer)

• PR has description of feature/bug or link to Confluence/Jira task
• Description contains actions to verify feature/bugfix
• I've built this code, uploaded it to the device and verified feature/bugfix

[WillyJL]

3. Fix calloc() to explicitly zero memory — with heap-clear disabled in release, calloc() now does its own memset(0) to guarantee zero-initialized returns (memmgr.c)

this is already done in pvPortMalloc(). and before you remove that from pvPortMalloc(), keep in mind a lot of flipper code (even and especially in official firmware) already relies on this behavior from malloc().

other changes sound interesting 👀

[WonderMr]

this is already done in pvPortMalloc().

Agreed. Removed.

[Copilot]

Pull request overview

This PR targets firmware-level performance and power improvements on STM32WB55 by optimizing compiler settings, heap behavior, hot-path branching, SPI transfers, and some frequently called core helpers.

Changes:

• Adjust release build optimization level and tweak FreeRTOS idle-sleep threshold.
• Reduce heap/free overhead and fix realloc() copy sizing by reading heap block usable size (exported via API).
• Improve hot paths via __builtin_expect, function flattening, SPI TX DMA usage, and in-place vprintf string concatenation.

Reviewed changes

Copilot reviewed 11 out of 11 changed files in this pull request and generated 3 comments.

Show a summary per file

File	Description
targets/f7/inc/FreeRTOSConfig.h	Makes heap clear-on-free conditional on FURI_DEBUG; reduces idle time before tickless sleep.
targets/f7/furi_hal/furi_hal_spi.c	Uses DMA for TX when scheduler is running; adds RX-drain DMA in TX-only mode to avoid OVR.
targets/f7/api_symbols.csv	Bumps API version and exports memmgr_heap_get_block_size.
site_scons/firmwareopts.scons	Switches release CCFLAGS from -Og to -Os.
furi/core/thread.c	Applies __attribute__((flatten)) to hot thread helper functions.
furi/core/string.c	Implements in-place furi_string_cat_vprintf() using vsnprintf into the destination buffer.
furi/core/memmgr.c	Fixes realloc() to copy min(old_size, new_size) and preserve allocation on OOM.
furi/core/memmgr_heap.h	Declares the new memmgr_heap_get_block_size() API.
furi/core/memmgr_heap.c	Implements memmgr_heap_get_block_size() by reading Heap_4 block headers.
furi/core/kernel.c	Applies __attribute__((flatten)) to furi_get_tick().
furi/core/check.h	Adds __builtin_expect to check/assert/break macros to bias the hot path.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Pull request overview

Copilot reviewed 11 out of 11 changed files in this pull request and generated 3 comments.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Pull request overview

Copilot reviewed 11 out of 11 changed files in this pull request and generated 1 comment.

Comments suppressed due to low confidence (1)

furi/core/memmgr.c:35

• The PR description mentions adding a NULL-guard to preserve the original allocation on OOM in realloc(), but the implementation here still unconditionally uses the result of pvPortMalloc(size) (which furi_checks on failure) and will not preserve ptr on OOM. Please either update the PR description to match the current behavior, or adjust the implementation if standard realloc-on-OOM semantics are intended.

void* realloc(void* ptr, size_t size) {
    if(size == 0) {
        vPortFree(ptr);
        return NULL;
    }

    void* p = pvPortMalloc(size);
    if(ptr != NULL) {
        size_t old_size = memmgr_heap_get_block_size(ptr);
        size_t copy_size = old_size < size ? old_size : size;
        memcpy(p, ptr, copy_size);
        vPortFree(ptr);
    }

    return p;

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Pull request overview

Copilot reviewed 12 out of 12 changed files in this pull request and generated 4 comments.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Pull request overview

Copilot reviewed 12 out of 12 changed files in this pull request and generated no new comments.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.