arch: use gperf to generate a perfact hash to lookup syscall names

This patch significantly improves the performance of
seccomp_syscall_resolve_name since it replaces the expensive strcmp
for each syscall in the database, with a lookup table.

The complexity for syscall_resolve_num is not changed and it
uses the linear search, that is anyway less expensive than
seccomp_syscall_resolve_name as it uses an index for comparison
instead of doing a string comparison.

On my machine, calling 1000 seccomp_syscall_resolve_name_arch and
seccomp_syscall_resolve_num_arch over the entire syscalls DB passed
from ~0.45 sec to ~0.06s.

PM: After talking with Giuseppe I made a number of additional
changes, some substantial, the highlights include:
* various style tweaks
* .gitignore fixes
* fixed subject line, tweaked the description
* dropped the arch-syscall-validate changes as they were masking
  other problems
* extracted the syscalls.csv and file deletions to other patches
  to keep this one more focused
* fixed the x86, x32, arm, all the MIPS ABIs, s390, and s390x ABIs as
  the syscall offsets were not properly incorporated into this change
* cleaned up the ABI specific headers
* cleaned up generate_syscalls_perf.sh and renamed to
  arch-gperf-generate
* fixed problems with automake's file packaging

Signed-off-by: Giuseppe Scrivano <gscrivan@redhat.com>
Reviewed-by: Tom Hromatka <tom.hromatka@oracle.com>
[PM: see notes in the "PM" section above]
Signed-off-by: Paul Moore <paul@paul-moore.com>

1 files changed, 41 insertions, 4 deletions

diff --git a/src/arch-mips64.c b/src/arch-mips64.c
index f98982c..9707d1c 100644
--- a/src/arch-mips64.c
+++ b/src/arch-mips64.c
@@ -25,13 +25,50 @@
 #include "arch.h"
 #include "arch-mips64.h"
 
+/* 64 ABI */
+#define __SCMP_NR_BASE			5000
+
+/**
+ * Resolve a syscall name to a number
+ * @param name the syscall name
+ *
+ * Resolve the given syscall name to the syscall number using the syscall table.
+ * Returns the syscall number on success, including negative pseudo syscall
+ * numbers; returns __NR_SCMP_ERROR on failure.
+ *
+ */
+int mips64_syscall_resolve_name_munge(const char *name)
+{
+	int sys;
+
+	sys = mips64_syscall_resolve_name(name);
+	if (sys == __NR_SCMP_ERROR)
+		return sys;
+
+	return sys + __SCMP_NR_BASE;
+}
+
+/**
+ * Resolve a syscall number to a name
+ * @param num the syscall number
+ *
+ * Resolve the given syscall number to the syscall name using the syscall table.
+ * Returns a pointer to the syscall name string on success, including pseudo
+ * syscall names; returns NULL on failure.
+ *
+ */
+const char *mips64_syscall_resolve_num_munge(int num)
+{
+	return mips64_syscall_resolve_num(num - __SCMP_NR_BASE);
+}
+
 const struct arch_def arch_def_mips64 = {
 	.token = SCMP_ARCH_MIPS64,
 	.token_bpf = AUDIT_ARCH_MIPS64,
 	.size = ARCH_SIZE_64,
 	.endian = ARCH_ENDIAN_BIG,
-	.syscall_resolve_name = mips64_syscall_resolve_name,
-	.syscall_resolve_num = mips64_syscall_resolve_num,
+	.syscall_resolve_name = mips64_syscall_resolve_name_munge,
+	.syscall_resolve_num = mips64_syscall_resolve_num_munge,
 	.syscall_rewrite = NULL,
 	.rule_add = NULL,
 };
@@ -41,8 +78,8 @@ const struct arch_def arch_def_mipsel64 = {
 	.token_bpf = AUDIT_ARCH_MIPSEL64,
 	.size = ARCH_SIZE_64,
 	.endian = ARCH_ENDIAN_LITTLE,
-	.syscall_resolve_name = mips64_syscall_resolve_name,
-	.syscall_resolve_num = mips64_syscall_resolve_num,
+	.syscall_resolve_name = mips64_syscall_resolve_name_munge,
+	.syscall_resolve_num = mips64_syscall_resolve_num_munge,
 	.syscall_rewrite = NULL,
 	.rule_add = NULL,
 };