hugetlbfs: clean up command line processing

With all hugetlb page processing done in a single file clean up code.

- Make code match desired semantics
  - Update documentation with semantics
- Make all warnings and errors messages start with 'HugeTLB:'.
- Consistently name command line parsing routines.
- Warn if !hugepages_supported() and command line parameters have
  been specified.
- Add comments to code
  - Describe some of the subtle interactions
  - Describe semantics of command line arguments

This patch also fixes issues with implicitly setting the number of
gigantic huge pages to preallocate.  Previously on X86 command line,

        hugepages=2 default_hugepagesz=1G

would result in zero 1G pages being preallocated and,

        # grep HugePages_Total /proc/meminfo
        HugePages_Total:       0
        # sysctl -a | grep nr_hugepages
        vm.nr_hugepages = 2
        vm.nr_hugepages_mempolicy = 2
        # cat /proc/sys/vm/nr_hugepages
        2

After this patch 2 gigantic pages will be preallocated and all the proc,
sysfs, sysctl and meminfo files will accurately reflect this.

To address the issue with gigantic pages, a small change in behavior was
made to command line processing.  Previously the command line,

        hugepages=128 default_hugepagesz=2M hugepagesz=2M hugepages=256

would result in the allocation of 256 2M huge pages.  The value 128 would
be ignored without any warning.  After this patch, 128 2M pages will be
allocated and a warning message will be displayed indicating the value of
256 is ignored.  This change in behavior is required because allocation of
implicitly specified gigantic pages must be done when the
default_hugepagesz= is encountered for gigantic pages.  Previously the
code waited until later in the boot process (hugetlb_init), to allocate
pages of default size.  However the bootmem allocator required for
gigantic allocations is not available at this time.

Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Sandipan Das <sandipan@linux.ibm.com>
Acked-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>	[s390]
Acked-by: Will Deacon <will@kernel.org>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Christophe Leroy <christophe.leroy@c-s.fr>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Longpeng <longpeng2@huawei.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Nitesh Narayan Lal <nitesh@redhat.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Anders Roxell <anders.roxell@linaro.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Link: http://lkml.kernel.org/r/20200417185049.275845-5-mike.kravetz@oracle.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 128 insertions, 31 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 2ae0e506cfc7..786004514d10 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -59,8 +59,8 @@ __initdata LIST_HEAD(huge_boot_pages);
 /* for command line parsing */
 static struct hstate * __initdata parsed_hstate;
 static unsigned long __initdata default_hstate_max_huge_pages;
-static unsigned long __initdata default_hstate_size;
 static bool __initdata parsed_valid_hugepagesz = true;
+static bool __initdata parsed_default_hugepagesz;
 
 /*
  * Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages,
@@ -3060,7 +3060,7 @@ static void __init hugetlb_sysfs_init(void)
 		err = hugetlb_sysfs_add_hstate(h, hugepages_kobj,
 					 hstate_kobjs, &hstate_attr_group);
 		if (err)
-			pr_err("Hugetlb: Unable to add hstate %s", h->name);
+			pr_err("HugeTLB: Unable to add hstate %s", h->name);
 	}
 }
 
@@ -3164,7 +3164,7 @@ static void hugetlb_register_node(struct node *node)
 						nhs->hstate_kobjs,
 						&per_node_hstate_attr_group);
 		if (err) {
-			pr_err("Hugetlb: Unable to add hstate %s for node %d\n",
+			pr_err("HugeTLB: Unable to add hstate %s for node %d\n",
 				h->name, node->dev.id);
 			hugetlb_unregister_node(node);
 			break;
@@ -3215,19 +3215,35 @@ static int __init hugetlb_init(void)
 	if (!hugepages_supported())
 		return 0;
 
-	if (!size_to_hstate(default_hstate_size)) {
-		if (default_hstate_size != 0) {
-			pr_err("HugeTLB: unsupported default_hugepagesz %lu. Reverting to %lu\n",
-			       default_hstate_size, HPAGE_SIZE);
+	/*
+	 * Make sure HPAGE_SIZE (HUGETLB_PAGE_ORDER) hstate exists.  Some
+	 * architectures depend on setup being done here.
+	 */
+	hugetlb_add_hstate(HUGETLB_PAGE_ORDER);
+	if (!parsed_default_hugepagesz) {
+		/*
+		 * If we did not parse a default huge page size, set
+		 * default_hstate_idx to HPAGE_SIZE hstate. And, if the
+		 * number of huge pages for this default size was implicitly
+		 * specified, set that here as well.
+		 * Note that the implicit setting will overwrite an explicit
+		 * setting.  A warning will be printed in this case.
+		 */
+		default_hstate_idx = hstate_index(size_to_hstate(HPAGE_SIZE));
+		if (default_hstate_max_huge_pages) {
+			if (default_hstate.max_huge_pages) {
+				char buf[32];
+
+				string_get_size(huge_page_size(&default_hstate),
+					1, STRING_UNITS_2, buf, 32);
+				pr_warn("HugeTLB: Ignoring hugepages=%lu associated with %s page size\n",
+					default_hstate.max_huge_pages, buf);
+				pr_warn("HugeTLB: Using hugepages=%lu for number of default huge pages\n",
+					default_hstate_max_huge_pages);
+			}
+			default_hstate.max_huge_pages =
+				default_hstate_max_huge_pages;
 		}
-
-		default_hstate_size = HPAGE_SIZE;
-		hugetlb_add_hstate(HUGETLB_PAGE_ORDER);
-	}
-	default_hstate_idx = hstate_index(size_to_hstate(default_hstate_size));
-	if (default_hstate_max_huge_pages) {
-		if (!default_hstate.max_huge_pages)
-			default_hstate.max_huge_pages = default_hstate_max_huge_pages;
 	}
 
 	hugetlb_cma_check();
@@ -3287,20 +3303,34 @@ void __init hugetlb_add_hstate(unsigned int order)
 	parsed_hstate = h;
 }
 
-static int __init hugetlb_nrpages_setup(char *s)
+/*
+ * hugepages command line processing
+ * hugepages normally follows a valid hugepagsz or default_hugepagsz
+ * specification.  If not, ignore the hugepages value.  hugepages can also
+ * be the first huge page command line  option in which case it implicitly
+ * specifies the number of huge pages for the default size.
+ */
+static int __init hugepages_setup(char *s)
 {
 	unsigned long *mhp;
 	static unsigned long *last_mhp;
 
+	if (!hugepages_supported()) {
+		pr_warn("HugeTLB: huge pages not supported, ignoring hugepages = %s\n", s);
+		return 0;
+	}
+
 	if (!parsed_valid_hugepagesz) {
-		pr_warn("hugepages = %s preceded by "
-			"an unsupported hugepagesz, ignoring\n", s);
+		pr_warn("HugeTLB: hugepages=%s does not follow a valid hugepagesz, ignoring\n", s);
 		parsed_valid_hugepagesz = true;
-		return 1;
+		return 0;
 	}
+
 	/*
-	 * !hugetlb_max_hstate means we haven't parsed a hugepagesz= parameter yet,
-	 * so this hugepages= parameter goes to the "default hstate".
+	 * !hugetlb_max_hstate means we haven't parsed a hugepagesz= parameter
+	 * yet, so this hugepages= parameter goes to the "default hstate".
+	 * Otherwise, it goes with the previously parsed hugepagesz or
+	 * default_hugepagesz.
 	 */
 	else if (!hugetlb_max_hstate)
 		mhp = &default_hstate_max_huge_pages;
@@ -3308,8 +3338,8 @@ static int __init hugetlb_nrpages_setup(char *s)
 		mhp = &parsed_hstate->max_huge_pages;
 
 	if (mhp == last_mhp) {
-		pr_warn("hugepages= specified twice without interleaving hugepagesz=, ignoring\n");
-		return 1;
+		pr_warn("HugeTLB: hugepages= specified twice without interleaving hugepagesz=, ignoring hugepages=%s\n", s);
+		return 0;
 	}
 
 	if (sscanf(s, "%lu", mhp) <= 0)
@@ -3327,42 +3357,109 @@ static int __init hugetlb_nrpages_setup(char *s)
 
 	return 1;
 }
-__setup("hugepages=", hugetlb_nrpages_setup);
+__setup("hugepages=", hugepages_setup);
 
+/*
+ * hugepagesz command line processing
+ * A specific huge page size can only be specified once with hugepagesz.
+ * hugepagesz is followed by hugepages on the command line.  The global
+ * variable 'parsed_valid_hugepagesz' is used to determine if prior
+ * hugepagesz argument was valid.
+ */
 static int __init hugepagesz_setup(char *s)
 {
 	unsigned long size;
+	struct hstate *h;
+
+	parsed_valid_hugepagesz = false;
+	if (!hugepages_supported()) {
+		pr_warn("HugeTLB: huge pages not supported, ignoring hugepagesz = %s\n", s);
+		return 0;
+	}
 
 	size = (unsigned long)memparse(s, NULL);
 
 	if (!arch_hugetlb_valid_size(size)) {
-		parsed_valid_hugepagesz = false;
-		pr_err("HugeTLB: unsupported hugepagesz %s\n", s);
+		pr_err("HugeTLB: unsupported hugepagesz=%s\n", s);
 		return 0;
 	}
 
-	if (size_to_hstate(size)) {
-		pr_warn("HugeTLB: hugepagesz %s specified twice, ignoring\n", s);
-		return 0;
+	h = size_to_hstate(size);
+	if (h) {
+		/*
+		 * hstate for this size already exists.  This is normally
+		 * an error, but is allowed if the existing hstate is the
+		 * default hstate.  More specifically, it is only allowed if
+		 * the number of huge pages for the default hstate was not
+		 * previously specified.
+		 */
+		if (!parsed_default_hugepagesz ||  h != &default_hstate ||
+		    default_hstate.max_huge_pages) {
+			pr_warn("HugeTLB: hugepagesz=%s specified twice, ignoring\n", s);
+			return 0;
+		}
+
+		/*
+		 * No need to call hugetlb_add_hstate() as hstate already
+		 * exists.  But, do set parsed_hstate so that a following
+		 * hugepages= parameter will be applied to this hstate.
+		 */
+		parsed_hstate = h;
+		parsed_valid_hugepagesz = true;
+		return 1;
 	}
 
 	hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT);
+	parsed_valid_hugepagesz = true;
 	return 1;
 }
 __setup("hugepagesz=", hugepagesz_setup);
 
+/*
+ * default_hugepagesz command line input
+ * Only one instance of default_hugepagesz allowed on command line.
+ */
 static int __init default_hugepagesz_setup(char *s)
 {
 	unsigned long size;
 
+	parsed_valid_hugepagesz = false;
+	if (!hugepages_supported()) {
+		pr_warn("HugeTLB: huge pages not supported, ignoring default_hugepagesz = %s\n", s);
+		return 0;
+	}
+
+	if (parsed_default_hugepagesz) {
+		pr_err("HugeTLB: default_hugepagesz previously specified, ignoring %s\n", s);
+		return 0;
+	}
+
 	size = (unsigned long)memparse(s, NULL);
 
 	if (!arch_hugetlb_valid_size(size)) {
-		pr_err("HugeTLB: unsupported default_hugepagesz %s\n", s);
+		pr_err("HugeTLB: unsupported default_hugepagesz=%s\n", s);
 		return 0;
 	}
 
-	default_hstate_size = size;
+	hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT);
+	parsed_valid_hugepagesz = true;
+	parsed_default_hugepagesz = true;
+	default_hstate_idx = hstate_index(size_to_hstate(size));
+
+	/*
+	 * The number of default huge pages (for this size) could have been
+	 * specified as the first hugetlb parameter: hugepages=X.  If so,
+	 * then default_hstate_max_huge_pages is set.  If the default huge
+	 * page size is gigantic (>= MAX_ORDER), then the pages must be
+	 * allocated here from bootmem allocator.
+	 */
+	if (default_hstate_max_huge_pages) {
+		default_hstate.max_huge_pages = default_hstate_max_huge_pages;
+		if (hstate_is_gigantic(&default_hstate))
+			hugetlb_hstate_alloc_pages(&default_hstate);
+		default_hstate_max_huge_pages = 0;
+	}
+
 	return 1;
 }
 __setup("default_hugepagesz=", default_hugepagesz_setup);