Merge tag 'powerpc-5.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - Optimise radix KVM guest entry/exit by 2x on Power9/Power10.

 - Allow firmware to tell us whether to disable the entry and uaccess
   flushes on Power10 or later CPUs.

 - Add BPF_PROBE_MEM support for 32 and 64-bit BPF jits.

 - Several fixes and improvements to our hard lockup watchdog.

 - Activate HAVE_DYNAMIC_FTRACE_WITH_REGS on 32-bit.

 - Allow building the 64-bit Book3S kernel without hash MMU support, ie.
   Radix only.

 - Add KUAP (SMAP) support for 40x, 44x, 8xx, Book3E (64-bit).

 - Add new encodings for perf_mem_data_src.mem_hops field, and use them
   on Power10.

 - A series of small performance improvements to 64-bit interrupt entry.

 - Several commits fixing issues when building with the clang integrated
   assembler.

 - Many other small features and fixes.

Thanks to Alan Modra, Alexey Kardashevskiy, Ammar Faizi, Anders Roxell,
Arnd Bergmann, Athira Rajeev, Cédric Le Goater, Christophe JAILLET,
Christophe Leroy, Christoph Hellwig, Daniel Axtens, David Yang, Erhard
Furtner, Fabiano Rosas, Greg Kroah-Hartman, Guo Ren, Hari Bathini, Jason
Wang, Joel Stanley, Julia Lawall, Kajol Jain, Kees Cook, Laurent Dufour,
Madhavan Srinivasan, Mark Brown, Minghao Chi, Nageswara R Sastry, Naresh
Kamboju, Nathan Chancellor, Nathan Lynch, Nicholas Piggin, Nick Child,
Oliver O'Halloran, Peiwei Hu, Randy Dunlap, Ravi Bangoria, Rob Herring,
Russell Currey, Sachin Sant, Sean Christopherson, Segher Boessenkool,
Thadeu Lima de Souza Cascardo, Tyrel Datwyler, Xiang wangx, and Yang
Guang.

* tag 'powerpc-5.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (240 commits)
  powerpc/xmon: Dump XIVE information for online-only processors.
  powerpc/opal: use default_groups in kobj_type
  powerpc/cacheinfo: use default_groups in kobj_type
  powerpc/sched: Remove unused TASK_SIZE_OF
  powerpc/xive: Add missing null check after calling kmalloc
  powerpc/floppy: Remove usage of the deprecated "pci-dma-compat.h" API
  selftests/powerpc: Add a test of sigreturning to an unaligned address
  powerpc/64s: Use EMIT_WARN_ENTRY for SRR debug warnings
  powerpc/64s: Mask NIP before checking against SRR0
  powerpc/perf: Fix spelling of "its"
  powerpc/32: Fix boot failure with GCC latent entropy plugin
  powerpc/code-patching: Replace patch_instruction() by ppc_inst_write() in selftests
  powerpc/code-patching: Move code patching selftests in its own file
  powerpc/code-patching: Move instr_is_branch_{i/b}form() in code-patching.h
  powerpc/code-patching: Move patch_exception() outside code-patching.c
  powerpc/code-patching: Use test_trampoline for prefixed patch test
  powerpc/code-patching: Fix patch_branch() return on out-of-range failure
  powerpc/code-patching: Reorganise do_patch_instruction() to ease error handling
  powerpc/code-patching: Fix unmap_patch_area() error handling
  powerpc/code-patching: Fix error handling in do_patch_instruction()
  ...

1 files changed, 91 insertions, 13 deletions

diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index ff80bbad22a5..733e6ef36758 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -492,8 +492,25 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...)
 }
 EXPORT_SYMBOL(rtas_call);
 
-/* For RTAS_BUSY (-2), delay for 1 millisecond.  For an extended busy status
- * code of 990n, perform the hinted delay of 10^n (last digit) milliseconds.
+/**
+ * rtas_busy_delay_time() - From an RTAS status value, calculate the
+ *                          suggested delay time in milliseconds.
+ *
+ * @status: a value returned from rtas_call() or similar APIs which return
+ *          the status of a RTAS function call.
+ *
+ * Context: Any context.
+ *
+ * Return:
+ * * 100000 - If @status is 9905.
+ * * 10000  - If @status is 9904.
+ * * 1000   - If @status is 9903.
+ * * 100    - If @status is 9902.
+ * * 10     - If @status is 9901.
+ * * 1      - If @status is either 9900 or -2. This is "wrong" for -2, but
+ *            some callers depend on this behavior, and the worst outcome
+ *            is that they will delay for longer than necessary.
+ * * 0      - If @status is not a busy or extended delay value.
  */
 unsigned int rtas_busy_delay_time(int status)
 {
@@ -513,17 +530,77 @@ unsigned int rtas_busy_delay_time(int status)
 }
 EXPORT_SYMBOL(rtas_busy_delay_time);
 
-/* For an RTAS busy status code, perform the hinted delay. */
-unsigned int rtas_busy_delay(int status)
+/**
+ * rtas_busy_delay() - helper for RTAS busy and extended delay statuses
+ *
+ * @status: a value returned from rtas_call() or similar APIs which return
+ *          the status of a RTAS function call.
+ *
+ * Context: Process context. May sleep or schedule.
+ *
+ * Return:
+ * * true  - @status is RTAS_BUSY or an extended delay hint. The
+ *           caller may assume that the CPU has been yielded if necessary,
+ *           and that an appropriate delay for @status has elapsed.
+ *           Generally the caller should reattempt the RTAS call which
+ *           yielded @status.
+ *
+ * * false - @status is not @RTAS_BUSY nor an extended delay hint. The
+ *           caller is responsible for handling @status.
+ */
+bool rtas_busy_delay(int status)
 {
 	unsigned int ms;
+	bool ret;
 
-	might_sleep();
-	ms = rtas_busy_delay_time(status);
-	if (ms && need_resched())
-		msleep(ms);
+	switch (status) {
+	case RTAS_EXTENDED_DELAY_MIN...RTAS_EXTENDED_DELAY_MAX:
+		ret = true;
+		ms = rtas_busy_delay_time(status);
+		/*
+		 * The extended delay hint can be as high as 100 seconds.
+		 * Surely any function returning such a status is either
+		 * buggy or isn't going to be significantly slowed by us
+		 * polling at 1HZ. Clamp the sleep time to one second.
+		 */
+		ms = clamp(ms, 1U, 1000U);
+		/*
+		 * The delay hint is an order-of-magnitude suggestion, not
+		 * a minimum. It is fine, possibly even advantageous, for
+		 * us to pause for less time than hinted. For small values,
+		 * use usleep_range() to ensure we don't sleep much longer
+		 * than actually needed.
+		 *
+		 * See Documentation/timers/timers-howto.rst for
+		 * explanation of the threshold used here. In effect we use
+		 * usleep_range() for 9900 and 9901, msleep() for
+		 * 9902-9905.
+		 */
+		if (ms <= 20)
+			usleep_range(ms * 100, ms * 1000);
+		else
+			msleep(ms);
+		break;
+	case RTAS_BUSY:
+		ret = true;
+		/*
+		 * We should call again immediately if there's no other
+		 * work to do.
+		 */
+		cond_resched();
+		break;
+	default:
+		ret = false;
+		/*
+		 * Not a busy or extended delay status; the caller should
+		 * handle @status itself. Ensure we warn on misuses in
+		 * atomic context regardless.
+		 */
+		might_sleep();
+		break;
+	}
 
-	return ms;
+	return ret;
 }
 EXPORT_SYMBOL(rtas_busy_delay);
 
@@ -809,13 +886,13 @@ void rtas_os_term(char *str)
 /**
  * rtas_activate_firmware() - Activate a new version of firmware.
  *
+ * Context: This function may sleep.
+ *
  * Activate a new version of partition firmware. The OS must call this
  * after resuming from a partition hibernation or migration in order
  * to maintain the ability to perform live firmware updates. It's not
  * catastrophic for this method to be absent or to fail; just log the
  * condition in that case.
- *
- * Context: This function may sleep.
  */
 void rtas_activate_firmware(void)
 {
@@ -890,11 +967,12 @@ int rtas_call_reentrant(int token, int nargs, int nret, int *outputs, ...)
 #endif /* CONFIG_PPC_PSERIES */
 
 /**
- * Find a specific pseries error log in an RTAS extended event log.
+ * get_pseries_errorlog() - Find a specific pseries error log in an RTAS
+ *                          extended event log.
  * @log: RTAS error/event log
  * @section_id: two character section identifier
  *
- * Returns a pointer to the specified errorlog or NULL if not found.
+ * Return: A pointer to the specified errorlog or NULL if not found.
  */
 struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log,
 					      uint16_t section_id)