summaryrefslogtreecommitdiff
path: root/arch/riscv/kernel/cpufeature.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/riscv/kernel/cpufeature.c')
-rw-r--r--arch/riscv/kernel/cpufeature.c626
1 files changed, 444 insertions, 182 deletions
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index a8f66c015229..1cfbba65d11a 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -13,18 +13,24 @@
#include <linux/memory.h>
#include <linux/module.h>
#include <linux/of.h>
-#include <linux/of_device.h>
#include <asm/acpi.h>
#include <asm/alternative.h>
#include <asm/cacheflush.h>
#include <asm/cpufeature.h>
#include <asm/hwcap.h>
+#include <asm/hwprobe.h>
#include <asm/patch.h>
#include <asm/processor.h>
#include <asm/vector.h>
+#include "copy-unaligned.h"
+
#define NUM_ALPHA_EXTS ('z' - 'a' + 1)
+#define MISALIGNED_ACCESS_JIFFIES_LG2 1
+#define MISALIGNED_BUFFER_SIZE 0x4000
+#define MISALIGNED_COPY_SIZE ((MISALIGNED_BUFFER_SIZE / 2) - 0x80)
+
unsigned long elf_hwcap __read_mostly;
/* Host ISA bitmap */
@@ -99,29 +105,252 @@ static bool riscv_isa_extension_check(int id)
return true;
}
-void __init riscv_fill_hwcap(void)
+#define __RISCV_ISA_EXT_DATA(_name, _id) { \
+ .name = #_name, \
+ .property = #_name, \
+ .id = _id, \
+}
+
+/*
+ * The canonical order of ISA extension names in the ISA string is defined in
+ * chapter 27 of the unprivileged specification.
+ *
+ * Ordinarily, for in-kernel data structures, this order is unimportant but
+ * isa_ext_arr defines the order of the ISA string in /proc/cpuinfo.
+ *
+ * The specification uses vague wording, such as should, when it comes to
+ * ordering, so for our purposes the following rules apply:
+ *
+ * 1. All multi-letter extensions must be separated from other extensions by an
+ * underscore.
+ *
+ * 2. Additional standard extensions (starting with 'Z') must be sorted after
+ * single-letter extensions and before any higher-privileged extensions.
+ *
+ * 3. The first letter following the 'Z' conventionally indicates the most
+ * closely related alphabetical extension category, IMAFDQLCBKJTPVH.
+ * If multiple 'Z' extensions are named, they must be ordered first by
+ * category, then alphabetically within a category.
+ *
+ * 3. Standard supervisor-level extensions (starting with 'S') must be listed
+ * after standard unprivileged extensions. If multiple supervisor-level
+ * extensions are listed, they must be ordered alphabetically.
+ *
+ * 4. Standard machine-level extensions (starting with 'Zxm') must be listed
+ * after any lower-privileged, standard extensions. If multiple
+ * machine-level extensions are listed, they must be ordered
+ * alphabetically.
+ *
+ * 5. Non-standard extensions (starting with 'X') must be listed after all
+ * standard extensions. If multiple non-standard extensions are listed, they
+ * must be ordered alphabetically.
+ *
+ * An example string following the order is:
+ * rv64imadc_zifoo_zigoo_zafoo_sbar_scar_zxmbaz_xqux_xrux
+ *
+ * New entries to this struct should follow the ordering rules described above.
+ */
+const struct riscv_isa_ext_data riscv_isa_ext[] = {
+ __RISCV_ISA_EXT_DATA(i, RISCV_ISA_EXT_i),
+ __RISCV_ISA_EXT_DATA(m, RISCV_ISA_EXT_m),
+ __RISCV_ISA_EXT_DATA(a, RISCV_ISA_EXT_a),
+ __RISCV_ISA_EXT_DATA(f, RISCV_ISA_EXT_f),
+ __RISCV_ISA_EXT_DATA(d, RISCV_ISA_EXT_d),
+ __RISCV_ISA_EXT_DATA(q, RISCV_ISA_EXT_q),
+ __RISCV_ISA_EXT_DATA(c, RISCV_ISA_EXT_c),
+ __RISCV_ISA_EXT_DATA(b, RISCV_ISA_EXT_b),
+ __RISCV_ISA_EXT_DATA(k, RISCV_ISA_EXT_k),
+ __RISCV_ISA_EXT_DATA(j, RISCV_ISA_EXT_j),
+ __RISCV_ISA_EXT_DATA(p, RISCV_ISA_EXT_p),
+ __RISCV_ISA_EXT_DATA(v, RISCV_ISA_EXT_v),
+ __RISCV_ISA_EXT_DATA(h, RISCV_ISA_EXT_h),
+ __RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM),
+ __RISCV_ISA_EXT_DATA(zicboz, RISCV_ISA_EXT_ZICBOZ),
+ __RISCV_ISA_EXT_DATA(zicntr, RISCV_ISA_EXT_ZICNTR),
+ __RISCV_ISA_EXT_DATA(zicsr, RISCV_ISA_EXT_ZICSR),
+ __RISCV_ISA_EXT_DATA(zifencei, RISCV_ISA_EXT_ZIFENCEI),
+ __RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE),
+ __RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM),
+ __RISCV_ISA_EXT_DATA(zba, RISCV_ISA_EXT_ZBA),
+ __RISCV_ISA_EXT_DATA(zbb, RISCV_ISA_EXT_ZBB),
+ __RISCV_ISA_EXT_DATA(zbs, RISCV_ISA_EXT_ZBS),
+ __RISCV_ISA_EXT_DATA(smaia, RISCV_ISA_EXT_SMAIA),
+ __RISCV_ISA_EXT_DATA(ssaia, RISCV_ISA_EXT_SSAIA),
+ __RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF),
+ __RISCV_ISA_EXT_DATA(sstc, RISCV_ISA_EXT_SSTC),
+ __RISCV_ISA_EXT_DATA(svinval, RISCV_ISA_EXT_SVINVAL),
+ __RISCV_ISA_EXT_DATA(svnapot, RISCV_ISA_EXT_SVNAPOT),
+ __RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT),
+};
+
+const size_t riscv_isa_ext_count = ARRAY_SIZE(riscv_isa_ext);
+
+static void __init riscv_parse_isa_string(unsigned long *this_hwcap, struct riscv_isainfo *isainfo,
+ unsigned long *isa2hwcap, const char *isa)
+{
+ /*
+ * For all possible cpus, we have already validated in
+ * the boot process that they at least contain "rv" and
+ * whichever of "32"/"64" this kernel supports, and so this
+ * section can be skipped.
+ */
+ isa += 4;
+
+ while (*isa) {
+ const char *ext = isa++;
+ const char *ext_end = isa;
+ bool ext_long = false, ext_err = false;
+
+ switch (*ext) {
+ case 's':
+ /*
+ * Workaround for invalid single-letter 's' & 'u'(QEMU).
+ * No need to set the bit in riscv_isa as 's' & 'u' are
+ * not valid ISA extensions. It works until multi-letter
+ * extension starting with "Su" appears.
+ */
+ if (ext[-1] != '_' && ext[1] == 'u') {
+ ++isa;
+ ext_err = true;
+ break;
+ }
+ fallthrough;
+ case 'S':
+ case 'x':
+ case 'X':
+ case 'z':
+ case 'Z':
+ /*
+ * Before attempting to parse the extension itself, we find its end.
+ * As multi-letter extensions must be split from other multi-letter
+ * extensions with an "_", the end of a multi-letter extension will
+ * either be the null character or the "_" at the start of the next
+ * multi-letter extension.
+ *
+ * Next, as the extensions version is currently ignored, we
+ * eliminate that portion. This is done by parsing backwards from
+ * the end of the extension, removing any numbers. This may be a
+ * major or minor number however, so the process is repeated if a
+ * minor number was found.
+ *
+ * ext_end is intended to represent the first character *after* the
+ * name portion of an extension, but will be decremented to the last
+ * character itself while eliminating the extensions version number.
+ * A simple re-increment solves this problem.
+ */
+ ext_long = true;
+ for (; *isa && *isa != '_'; ++isa)
+ if (unlikely(!isalnum(*isa)))
+ ext_err = true;
+
+ ext_end = isa;
+ if (unlikely(ext_err))
+ break;
+
+ if (!isdigit(ext_end[-1]))
+ break;
+
+ while (isdigit(*--ext_end))
+ ;
+
+ if (tolower(ext_end[0]) != 'p' || !isdigit(ext_end[-1])) {
+ ++ext_end;
+ break;
+ }
+
+ while (isdigit(*--ext_end))
+ ;
+
+ ++ext_end;
+ break;
+ default:
+ /*
+ * Things are a little easier for single-letter extensions, as they
+ * are parsed forwards.
+ *
+ * After checking that our starting position is valid, we need to
+ * ensure that, when isa was incremented at the start of the loop,
+ * that it arrived at the start of the next extension.
+ *
+ * If we are already on a non-digit, there is nothing to do. Either
+ * we have a multi-letter extension's _, or the start of an
+ * extension.
+ *
+ * Otherwise we have found the current extension's major version
+ * number. Parse past it, and a subsequent p/minor version number
+ * if present. The `p` extension must not appear immediately after
+ * a number, so there is no fear of missing it.
+ *
+ */
+ if (unlikely(!isalpha(*ext))) {
+ ext_err = true;
+ break;
+ }
+
+ if (!isdigit(*isa))
+ break;
+
+ while (isdigit(*++isa))
+ ;
+
+ if (tolower(*isa) != 'p')
+ break;
+
+ if (!isdigit(*++isa)) {
+ --isa;
+ break;
+ }
+
+ while (isdigit(*++isa))
+ ;
+
+ break;
+ }
+
+ /*
+ * The parser expects that at the start of an iteration isa points to the
+ * first character of the next extension. As we stop parsing an extension
+ * on meeting a non-alphanumeric character, an extra increment is needed
+ * where the succeeding extension is a multi-letter prefixed with an "_".
+ */
+ if (*isa == '_')
+ ++isa;
+
+#define SET_ISA_EXT_MAP(name, bit) \
+ do { \
+ if ((ext_end - ext == strlen(name)) && \
+ !strncasecmp(ext, name, strlen(name)) && \
+ riscv_isa_extension_check(bit)) \
+ set_bit(bit, isainfo->isa); \
+ } while (false) \
+
+ if (unlikely(ext_err))
+ continue;
+ if (!ext_long) {
+ int nr = tolower(*ext) - 'a';
+
+ if (riscv_isa_extension_check(nr)) {
+ *this_hwcap |= isa2hwcap[nr];
+ set_bit(nr, isainfo->isa);
+ }
+ } else {
+ for (int i = 0; i < riscv_isa_ext_count; i++)
+ SET_ISA_EXT_MAP(riscv_isa_ext[i].name,
+ riscv_isa_ext[i].id);
+ }
+#undef SET_ISA_EXT_MAP
+ }
+}
+
+static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap)
{
struct device_node *node;
const char *isa;
- char print_str[NUM_ALPHA_EXTS + 1];
- int i, j, rc;
- unsigned long isa2hwcap[26] = {0};
+ int rc;
struct acpi_table_header *rhct;
acpi_status status;
unsigned int cpu;
- isa2hwcap['i' - 'a'] = COMPAT_HWCAP_ISA_I;
- isa2hwcap['m' - 'a'] = COMPAT_HWCAP_ISA_M;
- isa2hwcap['a' - 'a'] = COMPAT_HWCAP_ISA_A;
- isa2hwcap['f' - 'a'] = COMPAT_HWCAP_ISA_F;
- isa2hwcap['d' - 'a'] = COMPAT_HWCAP_ISA_D;
- isa2hwcap['c' - 'a'] = COMPAT_HWCAP_ISA_C;
- isa2hwcap['v' - 'a'] = COMPAT_HWCAP_ISA_V;
-
- elf_hwcap = 0;
-
- bitmap_zero(riscv_isa, RISCV_ISA_EXT_MAX);
-
if (!acpi_disabled) {
status = acpi_get_table(ACPI_SIG_RHCT, 0, &rhct);
if (ACPI_FAILURE(status))
@@ -153,169 +382,7 @@ void __init riscv_fill_hwcap(void)
}
}
- /*
- * For all possible cpus, we have already validated in
- * the boot process that they at least contain "rv" and
- * whichever of "32"/"64" this kernel supports, and so this
- * section can be skipped.
- */
- isa += 4;
-
- while (*isa) {
- const char *ext = isa++;
- const char *ext_end = isa;
- bool ext_long = false, ext_err = false;
-
- switch (*ext) {
- case 's':
- /*
- * Workaround for invalid single-letter 's' & 'u'(QEMU).
- * No need to set the bit in riscv_isa as 's' & 'u' are
- * not valid ISA extensions. It works until multi-letter
- * extension starting with "Su" appears.
- */
- if (ext[-1] != '_' && ext[1] == 'u') {
- ++isa;
- ext_err = true;
- break;
- }
- fallthrough;
- case 'S':
- case 'x':
- case 'X':
- case 'z':
- case 'Z':
- /*
- * Before attempting to parse the extension itself, we find its end.
- * As multi-letter extensions must be split from other multi-letter
- * extensions with an "_", the end of a multi-letter extension will
- * either be the null character or the "_" at the start of the next
- * multi-letter extension.
- *
- * Next, as the extensions version is currently ignored, we
- * eliminate that portion. This is done by parsing backwards from
- * the end of the extension, removing any numbers. This may be a
- * major or minor number however, so the process is repeated if a
- * minor number was found.
- *
- * ext_end is intended to represent the first character *after* the
- * name portion of an extension, but will be decremented to the last
- * character itself while eliminating the extensions version number.
- * A simple re-increment solves this problem.
- */
- ext_long = true;
- for (; *isa && *isa != '_'; ++isa)
- if (unlikely(!isalnum(*isa)))
- ext_err = true;
-
- ext_end = isa;
- if (unlikely(ext_err))
- break;
-
- if (!isdigit(ext_end[-1]))
- break;
-
- while (isdigit(*--ext_end))
- ;
-
- if (tolower(ext_end[0]) != 'p' || !isdigit(ext_end[-1])) {
- ++ext_end;
- break;
- }
-
- while (isdigit(*--ext_end))
- ;
-
- ++ext_end;
- break;
- default:
- /*
- * Things are a little easier for single-letter extensions, as they
- * are parsed forwards.
- *
- * After checking that our starting position is valid, we need to
- * ensure that, when isa was incremented at the start of the loop,
- * that it arrived at the start of the next extension.
- *
- * If we are already on a non-digit, there is nothing to do. Either
- * we have a multi-letter extension's _, or the start of an
- * extension.
- *
- * Otherwise we have found the current extension's major version
- * number. Parse past it, and a subsequent p/minor version number
- * if present. The `p` extension must not appear immediately after
- * a number, so there is no fear of missing it.
- *
- */
- if (unlikely(!isalpha(*ext))) {
- ext_err = true;
- break;
- }
-
- if (!isdigit(*isa))
- break;
-
- while (isdigit(*++isa))
- ;
-
- if (tolower(*isa) != 'p')
- break;
-
- if (!isdigit(*++isa)) {
- --isa;
- break;
- }
-
- while (isdigit(*++isa))
- ;
-
- break;
- }
-
- /*
- * The parser expects that at the start of an iteration isa points to the
- * first character of the next extension. As we stop parsing an extension
- * on meeting a non-alphanumeric character, an extra increment is needed
- * where the succeeding extension is a multi-letter prefixed with an "_".
- */
- if (*isa == '_')
- ++isa;
-
-#define SET_ISA_EXT_MAP(name, bit) \
- do { \
- if ((ext_end - ext == sizeof(name) - 1) && \
- !strncasecmp(ext, name, sizeof(name) - 1) && \
- riscv_isa_extension_check(bit)) \
- set_bit(bit, isainfo->isa); \
- } while (false) \
-
- if (unlikely(ext_err))
- continue;
- if (!ext_long) {
- int nr = tolower(*ext) - 'a';
-
- if (riscv_isa_extension_check(nr)) {
- this_hwcap |= isa2hwcap[nr];
- set_bit(nr, isainfo->isa);
- }
- } else {
- /* sorted alphabetically */
- SET_ISA_EXT_MAP("smaia", RISCV_ISA_EXT_SMAIA);
- SET_ISA_EXT_MAP("ssaia", RISCV_ISA_EXT_SSAIA);
- SET_ISA_EXT_MAP("sscofpmf", RISCV_ISA_EXT_SSCOFPMF);
- SET_ISA_EXT_MAP("sstc", RISCV_ISA_EXT_SSTC);
- SET_ISA_EXT_MAP("svinval", RISCV_ISA_EXT_SVINVAL);
- SET_ISA_EXT_MAP("svnapot", RISCV_ISA_EXT_SVNAPOT);
- SET_ISA_EXT_MAP("svpbmt", RISCV_ISA_EXT_SVPBMT);
- SET_ISA_EXT_MAP("zba", RISCV_ISA_EXT_ZBA);
- SET_ISA_EXT_MAP("zbb", RISCV_ISA_EXT_ZBB);
- SET_ISA_EXT_MAP("zbs", RISCV_ISA_EXT_ZBS);
- SET_ISA_EXT_MAP("zicbom", RISCV_ISA_EXT_ZICBOM);
- SET_ISA_EXT_MAP("zicboz", RISCV_ISA_EXT_ZICBOZ);
- SET_ISA_EXT_MAP("zihintpause", RISCV_ISA_EXT_ZIHINTPAUSE);
- }
-#undef SET_ISA_EXT_MAP
- }
+ riscv_parse_isa_string(&this_hwcap, isainfo, isa2hwcap, isa);
/*
* These ones were as they were part of the base ISA when the
@@ -347,9 +414,107 @@ void __init riscv_fill_hwcap(void)
if (!acpi_disabled && rhct)
acpi_put_table((struct acpi_table_header *)rhct);
+}
+
+static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap)
+{
+ unsigned int cpu;
+
+ for_each_possible_cpu(cpu) {
+ unsigned long this_hwcap = 0;
+ struct device_node *cpu_node;
+ struct riscv_isainfo *isainfo = &hart_isa[cpu];
+
+ cpu_node = of_cpu_device_node_get(cpu);
+ if (!cpu_node) {
+ pr_warn("Unable to find cpu node\n");
+ continue;
+ }
+
+ if (!of_property_present(cpu_node, "riscv,isa-extensions")) {
+ of_node_put(cpu_node);
+ continue;
+ }
+
+ for (int i = 0; i < riscv_isa_ext_count; i++) {
+ if (of_property_match_string(cpu_node, "riscv,isa-extensions",
+ riscv_isa_ext[i].property) < 0)
+ continue;
+
+ if (!riscv_isa_extension_check(riscv_isa_ext[i].id))
+ continue;
+
+ /* Only single letter extensions get set in hwcap */
+ if (strnlen(riscv_isa_ext[i].name, 2) == 1)
+ this_hwcap |= isa2hwcap[riscv_isa_ext[i].id];
+
+ set_bit(riscv_isa_ext[i].id, isainfo->isa);
+ }
+
+ of_node_put(cpu_node);
+
+ /*
+ * All "okay" harts should have same isa. Set HWCAP based on
+ * common capabilities of every "okay" hart, in case they don't.
+ */
+ if (elf_hwcap)
+ elf_hwcap &= this_hwcap;
+ else
+ elf_hwcap = this_hwcap;
+
+ if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX))
+ bitmap_copy(riscv_isa, isainfo->isa, RISCV_ISA_EXT_MAX);
+ else
+ bitmap_and(riscv_isa, riscv_isa, isainfo->isa, RISCV_ISA_EXT_MAX);
+ }
- /* We don't support systems with F but without D, so mask those out
- * here. */
+ if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX))
+ return -ENOENT;
+
+ return 0;
+}
+
+#ifdef CONFIG_RISCV_ISA_FALLBACK
+bool __initdata riscv_isa_fallback = true;
+#else
+bool __initdata riscv_isa_fallback;
+static int __init riscv_isa_fallback_setup(char *__unused)
+{
+ riscv_isa_fallback = true;
+ return 1;
+}
+early_param("riscv_isa_fallback", riscv_isa_fallback_setup);
+#endif
+
+void __init riscv_fill_hwcap(void)
+{
+ char print_str[NUM_ALPHA_EXTS + 1];
+ unsigned long isa2hwcap[26] = {0};
+ int i, j;
+
+ isa2hwcap['i' - 'a'] = COMPAT_HWCAP_ISA_I;
+ isa2hwcap['m' - 'a'] = COMPAT_HWCAP_ISA_M;
+ isa2hwcap['a' - 'a'] = COMPAT_HWCAP_ISA_A;
+ isa2hwcap['f' - 'a'] = COMPAT_HWCAP_ISA_F;
+ isa2hwcap['d' - 'a'] = COMPAT_HWCAP_ISA_D;
+ isa2hwcap['c' - 'a'] = COMPAT_HWCAP_ISA_C;
+ isa2hwcap['v' - 'a'] = COMPAT_HWCAP_ISA_V;
+
+ if (!acpi_disabled) {
+ riscv_fill_hwcap_from_isa_string(isa2hwcap);
+ } else {
+ int ret = riscv_fill_hwcap_from_ext_list(isa2hwcap);
+
+ if (ret && riscv_isa_fallback) {
+ pr_info("Falling back to deprecated \"riscv,isa\"\n");
+ riscv_fill_hwcap_from_isa_string(isa2hwcap);
+ }
+ }
+
+ /*
+ * We don't support systems with F but without D, so mask those out
+ * here.
+ */
if ((elf_hwcap & COMPAT_HWCAP_ISA_F) && !(elf_hwcap & COMPAT_HWCAP_ISA_D)) {
pr_info("This kernel does not support systems with F but not D\n");
elf_hwcap &= ~COMPAT_HWCAP_ISA_F;
@@ -391,6 +556,103 @@ unsigned long riscv_get_elf_hwcap(void)
return hwcap;
}
+void check_unaligned_access(int cpu)
+{
+ u64 start_cycles, end_cycles;
+ u64 word_cycles;
+ u64 byte_cycles;
+ int ratio;
+ unsigned long start_jiffies, now;
+ struct page *page;
+ void *dst;
+ void *src;
+ long speed = RISCV_HWPROBE_MISALIGNED_SLOW;
+
+ page = alloc_pages(GFP_NOWAIT, get_order(MISALIGNED_BUFFER_SIZE));
+ if (!page) {
+ pr_warn("Can't alloc pages to measure memcpy performance");
+ return;
+ }
+
+ /* Make an unaligned destination buffer. */
+ dst = (void *)((unsigned long)page_address(page) | 0x1);
+ /* Unalign src as well, but differently (off by 1 + 2 = 3). */
+ src = dst + (MISALIGNED_BUFFER_SIZE / 2);
+ src += 2;
+ word_cycles = -1ULL;
+ /* Do a warmup. */
+ __riscv_copy_words_unaligned(dst, src, MISALIGNED_COPY_SIZE);
+ preempt_disable();
+ start_jiffies = jiffies;
+ while ((now = jiffies) == start_jiffies)
+ cpu_relax();
+
+ /*
+ * For a fixed amount of time, repeatedly try the function, and take
+ * the best time in cycles as the measurement.
+ */
+ while (time_before(jiffies, now + (1 << MISALIGNED_ACCESS_JIFFIES_LG2))) {
+ start_cycles = get_cycles64();
+ /* Ensure the CSR read can't reorder WRT to the copy. */
+ mb();
+ __riscv_copy_words_unaligned(dst, src, MISALIGNED_COPY_SIZE);
+ /* Ensure the copy ends before the end time is snapped. */
+ mb();
+ end_cycles = get_cycles64();
+ if ((end_cycles - start_cycles) < word_cycles)
+ word_cycles = end_cycles - start_cycles;
+ }
+
+ byte_cycles = -1ULL;
+ __riscv_copy_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE);
+ start_jiffies = jiffies;
+ while ((now = jiffies) == start_jiffies)
+ cpu_relax();
+
+ while (time_before(jiffies, now + (1 << MISALIGNED_ACCESS_JIFFIES_LG2))) {
+ start_cycles = get_cycles64();
+ mb();
+ __riscv_copy_bytes_unaligned(dst, src, MISALIGNED_COPY_SIZE);
+ mb();
+ end_cycles = get_cycles64();
+ if ((end_cycles - start_cycles) < byte_cycles)
+ byte_cycles = end_cycles - start_cycles;
+ }
+
+ preempt_enable();
+
+ /* Don't divide by zero. */
+ if (!word_cycles || !byte_cycles) {
+ pr_warn("cpu%d: rdtime lacks granularity needed to measure unaligned access speed\n",
+ cpu);
+
+ goto out;
+ }
+
+ if (word_cycles < byte_cycles)
+ speed = RISCV_HWPROBE_MISALIGNED_FAST;
+
+ ratio = div_u64((byte_cycles * 100), word_cycles);
+ pr_info("cpu%d: Ratio of byte access time to unaligned word access is %d.%02d, unaligned accesses are %s\n",
+ cpu,
+ ratio / 100,
+ ratio % 100,
+ (speed == RISCV_HWPROBE_MISALIGNED_FAST) ? "fast" : "slow");
+
+ per_cpu(misaligned_access_speed, cpu) = speed;
+
+out:
+ __free_pages(page, get_order(MISALIGNED_BUFFER_SIZE));
+}
+
+static int check_unaligned_access_boot_cpu(void)
+{
+ check_unaligned_access(0);
+ return 0;
+}
+
+arch_initcall(check_unaligned_access_boot_cpu);
+
#ifdef CONFIG_RISCV_ALTERNATIVE
/*
* Alternative patch sites consider 48 bits when determining when to patch
generated by cgit (git 2.34.1) at 2025-04-01 09:20:02 +0000