1 ===================================
2 Light-weight System Calls for IA-64
3 ===================================
7 Last update: 27-Sep-2003
12 Using the "epc" instruction effectively introduces a new mode of
13 execution to the ia64 linux kernel. We call this mode the
14 "fsys-mode". To recap, the normal states of execution are:
17 Both the register stack and the memory stack have been
18 switched over to kernel memory. The user-level state is saved
19 in a pt-regs structure at the top of the kernel memory stack.
22 Both the register stack and the kernel stack are in
23 user memory. The user-level state is contained in the
26 - bank 0 interruption-handling mode:
27 This is the non-interruptible state which all
28 interruption-handlers start execution in. The user-level
29 state remains in the CPU registers and some kernel state may
30 be stored in bank 0 of registers r16-r31.
32 In contrast, fsys-mode has the following special properties:
34 - execution is at privilege level 0 (most-privileged)
36 - CPU registers may contain a mixture of user-level and kernel-level
37 state (it is the responsibility of the kernel to ensure that no
38 security-sensitive kernel-level state is leaked back to
41 - execution is interruptible and preemptible (an fsys-mode handler
42 can disable interrupts and avoid all other interruption-sources
45 - neither the memory-stack nor the register-stack can be trusted while
46 in fsys-mode (they point to the user-level stacks, which may
47 be invalid, or completely bogus addresses)
49 In summary, fsys-mode is much more similar to running in user-mode
50 than it is to running in kernel-mode. Of course, given that the
51 privilege level is at level 0, this means that fsys-mode requires some
58 Linux operates in fsys-mode when (a) the privilege level is 0 (most
59 privileged) and (b) the stacks have NOT been switched to kernel memory
60 yet. For convenience, the header file <asm-ia64/ptrace.h> provides
67 The "regs" argument is a pointer to a pt_regs structure. The "task"
68 argument is a pointer to the task structure to which the "regs"
69 pointer belongs to. user_mode() returns TRUE if the CPU state pointed
70 to by "regs" was executing in user mode (privilege level 3).
71 user_stack() returns TRUE if the state pointed to by "regs" was
72 executing on the user-level stack(s). Finally, fsys_mode() returns
73 TRUE if the CPU state pointed to by "regs" was executing in fsys-mode.
74 The fsys_mode() macro is equivalent to the expression::
76 !user_mode(regs) && user_stack(task,regs)
78 How to write an fsyscall handler
79 ================================
81 The file arch/ia64/kernel/fsys.S contains a table of fsyscall-handlers
82 (fsyscall_table). This table contains one entry for each system call.
83 By default, a system call is handled by fsys_fallback_syscall(). This
84 routine takes care of entering (full) kernel mode and calling the
85 normal Linux system call handler. For performance-critical system
86 calls, it is possible to write a hand-tuned fsyscall_handler. For
87 example, fsys.S contains fsys_getpid(), which is a hand-tuned version
88 of the getpid() system call.
90 The entry and exit-state of an fsyscall handler is as follows:
92 Machine state on entry to fsyscall handler
93 ------------------------------------------
95 ========= ===============================================================
97 r11 saved ar.pfs (a user-level value)
98 r15 system call number
99 r16 "current" task pointer (in normal kernel-mode, this is in r13)
100 r32-r39 system call arguments
101 b6 return address (a user-level value)
102 ar.pfs previous frame-state (a user-level value)
103 PSR.be cleared to zero (i.e., little-endian byte order is in effect)
104 - all other registers may contain values passed in from user-mode
105 ========= ===============================================================
107 Required machine state on exit to fsyscall handler
108 --------------------------------------------------
110 ========= ===========================================================
111 r11 saved ar.pfs (as passed into the fsyscall handler)
112 r15 system call number (as passed into the fsyscall handler)
113 r32-r39 system call arguments (as passed into the fsyscall handler)
114 b6 return address (as passed into the fsyscall handler)
115 ar.pfs previous frame-state (as passed into the fsyscall handler)
116 ========= ===========================================================
118 Fsyscall handlers can execute with very little overhead, but with that
119 speed comes a set of restrictions:
121 * Fsyscall-handlers MUST check for any pending work in the flags
122 member of the thread-info structure and if any of the
123 TIF_ALLWORK_MASK flags are set, the handler needs to fall back on
124 doing a full system call (by calling fsys_fallback_syscall).
126 * Fsyscall-handlers MUST preserve incoming arguments (r32-r39, r11,
127 r15, b6, and ar.pfs) because they will be needed in case of a
128 system call restart. Of course, all "preserved" registers also
129 must be preserved, in accordance to the normal calling conventions.
131 * Fsyscall-handlers MUST check argument registers for containing a
132 NaT value before using them in any way that could trigger a
133 NaT-consumption fault. If a system call argument is found to
134 contain a NaT value, an fsyscall-handler may return immediately
135 with r8=EINVAL, r10=-1.
137 * Fsyscall-handlers MUST NOT use the "alloc" instruction or perform
138 any other operation that would trigger mandatory RSE
139 (register-stack engine) traffic.
141 * Fsyscall-handlers MUST NOT write to any stacked registers because
142 it is not safe to assume that user-level called a handler with the
143 proper number of arguments.
145 * Fsyscall-handlers need to be careful when accessing per-CPU variables:
146 unless proper safe-guards are taken (e.g., interruptions are avoided),
147 execution may be pre-empted and resumed on another CPU at any given
150 * Fsyscall-handlers must be careful not to leak sensitive kernel'
151 information back to user-level. In particular, before returning to
152 user-level, care needs to be taken to clear any scratch registers
153 that could contain sensitive information (note that the current
154 task pointer is not considered sensitive: it's already exposed
157 * Fsyscall-handlers MUST NOT access user-memory without first
158 validating access-permission (this can be done typically via
159 probe.r.fault and/or probe.w.fault) and without guarding against
160 memory access exceptions (this can be done with the EX() macros
161 defined by asmmacro.h).
163 The above restrictions may seem draconian, but remember that it's
164 possible to trade off some of the restrictions by paying a slightly
165 higher overhead. For example, if an fsyscall-handler could benefit
166 from the shadow register bank, it could temporarily disable PSR.i and
167 PSR.ic, switch to bank 0 (bsw.0) and then use the shadow registers as
168 needed. In other words, following the above rules yields extremely
169 fast system call execution (while fully preserving system call
170 semantics), but there is also a lot of flexibility in handling more
176 The delivery of (asynchronous) signals must be delayed until fsys-mode
177 is exited. This is accomplished with the help of the lower-privilege
178 transfer trap: arch/ia64/kernel/process.c:do_notify_resume_user()
179 checks whether the interrupted task was in fsys-mode and, if so, sets
180 PSR.lp and returns immediately. When fsys-mode is exited via the
181 "br.ret" instruction that lowers the privilege level, a trap will
182 occur. The trap handler clears PSR.lp again and returns immediately.
183 The kernel exit path then checks for and delivers any pending signals.
188 The "epc" instruction doesn't change the contents of PSR at all. This
189 is in contrast to a regular interruption, which clears almost all
190 bits. Because of that, some care needs to be taken to ensure things
191 work as expected. The following discussion describes how each PSR bit
194 ======= =======================================================================
195 PSR.be Cleared when entering fsys-mode. A srlz.d instruction is used
196 to ensure the CPU is in little-endian mode before the first
197 load/store instruction is executed. PSR.be is normally NOT
198 restored upon return from an fsys-mode handler. In other
199 words, user-level code must not rely on PSR.be being preserved
200 across a system call.
203 PSR.mfl Unchanged. Note: fsys-mode handlers must not write-registers!
204 PSR.mfh Unchanged. Note: fsys-mode handlers must not write-registers!
205 PSR.ic Unchanged. Note: fsys-mode handlers can clear the bit, if needed.
206 PSR.i Unchanged. Note: fsys-mode handlers can clear the bit, if needed.
209 PSR.dfl Unchanged. Note: fsys-mode handlers must not write-registers!
210 PSR.dfh Unchanged. Note: fsys-mode handlers must not write-registers!
215 PSR.db Unchanged. The kernel prevents user-level from setting a hardware
216 breakpoint that triggers at any privilege level other than
219 PSR.tb Lazy redirect. If a taken-branch trap occurs while in
220 fsys-mode, the trap-handler modifies the saved machine state
221 such that execution resumes in the gate page at
222 syscall_via_break(), with privilege level 3. Note: the
223 taken branch would occur on the branch invoking the
224 fsyscall-handler, at which point, by definition, a syscall
225 restart is still safe. If the system call number is invalid,
226 the fsys-mode handler will return directly to user-level. This
227 return will trigger a taken-branch trap, but since the trap is
228 taken _after_ restoring the privilege level, the CPU has already
229 left fsys-mode, so no special treatment is needed.
231 PSR.cpl Cleared to 0.
232 PSR.is Unchanged (guaranteed to be 0 on entry to the gate page).
234 PSR.it Unchanged (guaranteed to be 1).
235 PSR.id Unchanged. Note: the ia64 linux kernel never sets this bit.
236 PSR.da Unchanged. Note: the ia64 linux kernel never sets this bit.
237 PSR.dd Unchanged. Note: the ia64 linux kernel never sets this bit.
238 PSR.ss Lazy redirect. If set, "epc" will cause a Single Step Trap to
239 be taken. The trap handler then modifies the saved machine
240 state such that execution resumes in the gate page at
241 syscall_via_break(), with privilege level 3.
243 PSR.ed Unchanged. Note: This bit could only have an effect if an fsys-mode
244 handler performed a speculative load that gets NaTted. If so, this
245 would be the normal & expected behavior, so no special treatment is
247 PSR.bn Unchanged. Note: fsys-mode handlers may clear the bit, if needed.
248 Doing so requires clearing PSR.i and PSR.ic as well.
249 PSR.ia Unchanged. Note: the ia64 linux kernel never sets this bit.
250 ======= =======================================================================
252 Using fast system calls
253 =======================
255 To use fast system calls, userspace applications need simply call
256 __kernel_syscall_via_epc(). For example
258 -- example fgettimeofday() call --
260 -- fgettimeofday.S --
264 #include <asm/asmmacro.h>
266 GLOBAL_ENTRY(fgettimeofday)
272 mov r2 = 0xa000000000020660;; // gate address
273 // found by inspection of System.map for the
274 // __kernel_syscall_via_epc() function. See
275 // below for how to do this for real.
278 mov r15 = 1087 // gettimeofday syscall
280 br.call.sptk.many b6 = b7
286 br.ret.sptk.many rp;; // return to caller
289 -- end fgettimeofday.S --
291 In reality, getting the gate address is accomplished by two extra
292 values passed via the ELF auxiliary vector (include/asm-ia64/elf.h)
294 * AT_SYSINFO : is the address of __kernel_syscall_via_epc()
295 * AT_SYSINFO_EHDR : is the address of the kernel gate ELF DSO
297 The ELF DSO is a pre-linked library that is mapped in by the kernel at
298 the gate page. It is a proper ELF shared object so, with a dynamic
299 loader that recognises the library, you should be able to make calls to
300 the exported functions within it as with any other shared library.
301 AT_SYSINFO points into the kernel DSO at the
302 __kernel_syscall_via_epc() function for historical reasons (it was
303 used before the kernel DSO) and as a convenience.