From 75ac887a3033c6e4eb8e423a78490c8d4bf7d5b5 Mon Sep 17 00:00:00 2001
From: shaw young <58664393+shawbyoung@users.noreply.github.com>
Date: Mon, 24 Jun 2024 15:16:52 -0700
Subject: [BOLT][NFC] Sync CommandLineArgumentReference with options (#96563)

---
 bolt/docs/CommandLineArgumentReference.md | 84 +++++++++++++++++++++++++++----
 1 file changed, 75 insertions(+), 9 deletions(-)

diff --git a/bolt/docs/CommandLineArgumentReference.md b/bolt/docs/CommandLineArgumentReference.md
index 49e2265..d95f30a 100644
--- a/bolt/docs/CommandLineArgumentReference.md
+++ b/bolt/docs/CommandLineArgumentReference.md
@@ -56,6 +56,14 @@
 
   Allow processing of stripped binaries
 
+- `--alt-inst-feature-size=<uint>`
+
+  Size of feature field in .altinstructions
+
+- `--alt-inst-has-padlen`
+
+  Specify that .altinstructions has padlen field
+
 - `--asm-dump[=<dump folder>]`
 
   Dump function into assembly
@@ -78,6 +86,16 @@
   in the input is decoded and re-encoded. If the resulting bytes do not match
   the input, a warning message is printed.
 
+- `--comp-dir-override=<string>`
+
+  Overrides DW_AT_comp_dir, and provides an alterantive base location, which is
+  used with DW_AT_dwo_name to construct a path to *.dwo files.
+
+- `--create-debug-names-section`
+
+  Creates .debug_names section, if the input binary doesn't have it already, for
+  DWARF5 CU/TUs.
+
 - `--cu-processing-batch-size=<uint>`
 
   Specifies the size of batches for processing CUs. Higher number has better
@@ -93,7 +111,7 @@
 
 - `--debug-skeleton-cu`
 
-  Prints out offsetrs for abbrev and debu_info of Skeleton CUs that get patched.
+  Prints out offsets for abbrev and debug_info of Skeleton CUs that get patched.
 
 - `--deterministic-debuginfo`
 
@@ -104,6 +122,10 @@
 
   Add basic block instructions as tool tips on nodes
 
+- `--dump-alt-instructions`
+
+  Dump Linux alternative instructions info
+
 - `--dump-cg=<string>`
 
   Dump callgraph to the given file
@@ -117,10 +139,34 @@
   Dump function CFGs to graphviz format after each stage;enable '-print-loops'
   for color-coded blocks
 
+- `--dump-linux-exceptions`
+
+  Dump Linux kernel exception table
+
 - `--dump-orc`
 
   Dump raw ORC unwind information (sorted)
 
+- `--dump-para-sites`
+
+  Dump Linux kernel paravitual patch sites
+
+- `--dump-pci-fixups`
+
+  Dump Linux kernel PCI fixup table
+
+- `--dump-smp-locks`
+
+  Dump Linux kernel SMP locks
+
+- `--dump-static-calls`
+
+  Dump Linux kernel static calls
+
+- `--dump-static-keys`
+
+  Dump Linux kernel static keys jump table
+
 - `--dwarf-output-path=<string>`
 
   Path to where .dwo files or dwp file will be written out to.
@@ -205,6 +251,14 @@
 
   Skip processing of cold functions
 
+- `--log-file=<string>`
+
+  Redirect journaling to a file instead of stdout/stderr
+
+- `--long-jump-labels`
+
+  Always use long jumps/nops for Linux kernel static keys
+
 - `--max-data-relocations=<uint>`
 
   Maximum number of data relocations to process
@@ -274,6 +328,10 @@
 
   Number of tasks to be created per thread
 
+- `--terminal-trap`
+
+  Assume that execution stops at trap instruction
+
 - `--thread-count=<uint>`
 
   Number of threads
@@ -618,10 +676,6 @@
   threshold means fewer functions to process. E.g threshold of 90 means only top
   10 percent of functions with profile will be processed.
 
-- `--mcf-use-rarcs`
-
-  In MCF, consider the possibility of cancelling flow to balance edges
-
 - `--memcpy1-spec=<func1,func2:cs1:cs2,func3:cs1,...>`
 
   List of functions with call sites for which to specialize memcpy() for size 1
@@ -710,7 +764,7 @@
   - `none`: do not reorder functions
   - `exec-count`: order by execution count
   - `hfsort`: use hfsort algorithm
-  - `hfsort+`: use hfsort+ algorithm
+  - `hfsort+`: use cache-directed sort
   - `cdsort`: use cache-directed sort
   - `pettis-hansen`: use Pettis-Hansen algorithm
   - `random`: reorder functions randomly
@@ -804,8 +858,8 @@
 
 - `--stale-matching-min-matched-block=<uint>`
 
-  Minimum percent of exact match block for a function to be considered for
-  profile inference.
+  Percentage threshold of matched basic blocks at which stale profile inference
+  is executed.
 
 - `--stale-threshold=<uint>`
 
@@ -853,6 +907,10 @@
 
   Only apply branch boundary alignment in hot code
 
+- `--x86-strip-redundant-address-size`
+
+  Remove redundant Address-Size override prefix
+
 ### BOLT options in relocation mode:
 
 - `--align-macro-fusion=<value>`
@@ -1039,6 +1097,10 @@
 
   Print clusters
 
+- `--print-estimate-edge-counts`
+
+  Print function after edge counts are set for no-LBR profile
+
 - `--print-finalized`
 
   Print function after CFG is finalized
@@ -1071,6 +1133,10 @@
 
   Print functions after inlining optimization
 
+- `--print-large-functions`
+
+  Print functions that could not be overwritten due to excessive size
+
 - `--print-longjmp`
 
   Print functions after longjmp pass
@@ -1166,4 +1232,4 @@
 
 - `--print-options`
 
-  Print non-default options after command line parsing
+  Print non-default options after command line parsing
\ No newline at end of file
-- 
cgit v1.1