[2/4] proc/kcore: don't walk list on every read

Commit Message

Omar Sandoval Nov. 9, 2024, 1:28 a.m. UTC

From: Omar Sandoval <[e-mail]>

We maintain a list of memory ranges for /proc/kcore, which usually has
10-20 entries. Currently, every single read from /proc/kcore walks the
entire list in order to count the number of entries and compute some
offsets. These values only change when the list of memory ranges
changes, which is very rare (only when memory is hot(un)plugged). We can
cache the values when the list is populated to avoid these redundant
walks.

In my benchmark, this reduces the time per read by another 20
nanoseconds on top of the previous change, from 215 nanoseconds per read
to 195.

Link: https://github.com/osandov/drgn/issues/106
Signed-off-by: Omar Sandoval <[e-mail]>
---
 fs/proc/kcore.c | 70 ++++++++++++++++++++++++-------------------------
 1 file changed, 35 insertions(+), 35 deletions(-)

Patch

diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 770e4e57f445..082718f5c02f 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -65,6 +65,10 @@  static inline void kc_unxlate_dev_mem_ptr(phys_addr_t phys, void *virt)
 #endif
 
 static LIST_HEAD(kclist_head);
+static int kcore_nphdr;
+static size_t kcore_phdrs_len;
+static size_t kcore_notes_len;
+static size_t kcore_data_offset;
 static DECLARE_RWSEM(kclist_lock);
 static int kcore_need_update = 1;
 
@@ -101,33 +105,32 @@  void __init kclist_add(struct kcore_list *new, void *addr, size_t size,
 	list_add_tail(&new->list, &kclist_head);
 }
 
-static size_t get_kcore_size(int *nphdr, size_t *phdrs_len, size_t *notes_len,
-			     size_t *data_offset)
+static void update_kcore_size(void)
 {
 	size_t try, size;
 	struct kcore_list *m;
 
-	*nphdr = 1; /* PT_NOTE */
+	kcore_nphdr = 1; /* PT_NOTE */
 	size = 0;
 
 	list_for_each_entry(m, &kclist_head, list) {
 		try = kc_vaddr_to_offset((size_t)m->addr + m->size);
 		if (try > size)
 			size = try;
-		*nphdr = *nphdr + 1;
+		kcore_nphdr++;
 	}
 
-	*phdrs_len = *nphdr * sizeof(struct elf_phdr);
-	*notes_len = (4 * sizeof(struct elf_note) +
-		      3 * ALIGN(sizeof(CORE_STR), 4) +
-		      VMCOREINFO_NOTE_NAME_BYTES +
-		      ALIGN(sizeof(struct elf_prstatus), 4) +
-		      ALIGN(sizeof(struct elf_prpsinfo), 4) +
-		      ALIGN(arch_task_struct_size, 4) +
-		      ALIGN(vmcoreinfo_size, 4));
-	*data_offset = PAGE_ALIGN(sizeof(struct elfhdr) + *phdrs_len +
-				  *notes_len);
-	return *data_offset + size;
+	kcore_phdrs_len = kcore_nphdr * sizeof(struct elf_phdr);
+	kcore_notes_len = (4 * sizeof(struct elf_note) +
+			   3 * ALIGN(sizeof(CORE_STR), 4) +
+			   VMCOREINFO_NOTE_NAME_BYTES +
+			   ALIGN(sizeof(struct elf_prstatus), 4) +
+			   ALIGN(sizeof(struct elf_prpsinfo), 4) +
+			   ALIGN(arch_task_struct_size, 4) +
+			   ALIGN(vmcoreinfo_size, 4));
+	kcore_data_offset = PAGE_ALIGN(sizeof(struct elfhdr) + kcore_phdrs_len +
+				       kcore_notes_len);
+	proc_root_kcore->size = kcore_data_offset + size;
 }
 
 #ifdef CONFIG_HIGHMEM
@@ -270,8 +273,6 @@  static int kcore_update_ram(void)
 {
 	LIST_HEAD(list);
 	LIST_HEAD(garbage);
-	int nphdr;
-	size_t phdrs_len, notes_len, data_offset;
 	struct kcore_list *tmp, *pos;
 	int ret = 0;
 
@@ -293,8 +294,7 @@  static int kcore_update_ram(void)
 	}
 	list_splice_tail(&list, &kclist_head);
 
-	proc_root_kcore->size = get_kcore_size(&nphdr, &phdrs_len, &notes_len,
-					       &data_offset);
+	update_kcore_size();
 
 out:
 	up_write(&kclist_lock);
@@ -326,12 +326,10 @@  static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
 	struct file *file = iocb->ki_filp;
 	char *buf = file->private_data;
 	loff_t *fpos = &iocb->ki_pos;
-	size_t phdrs_offset, notes_offset, data_offset;
+	size_t phdrs_offset, notes_offset;
 	size_t page_offline_frozen = 1;
-	size_t phdrs_len, notes_len;
 	struct kcore_list *m;
 	size_t tsz;
-	int nphdr;
 	unsigned long start;
 	size_t buflen = iov_iter_count(iter);
 	size_t orig_buflen = buflen;
@@ -344,9 +342,8 @@  static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
 	 */
 	page_offline_freeze();
 
-	get_kcore_size(&nphdr, &phdrs_len, &notes_len, &data_offset);
 	phdrs_offset = sizeof(struct elfhdr);
-	notes_offset = phdrs_offset + phdrs_len;
+	notes_offset = phdrs_offset + kcore_phdrs_len;
 
 	/* ELF file header. */
 	if (buflen && *fpos < sizeof(struct elfhdr)) {
@@ -368,7 +365,7 @@  static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
 			.e_flags = ELF_CORE_EFLAGS,
 			.e_ehsize = sizeof(struct elfhdr),
 			.e_phentsize = sizeof(struct elf_phdr),
-			.e_phnum = nphdr,
+			.e_phnum = kcore_nphdr,
 		};
 
 		tsz = min_t(size_t, buflen, sizeof(struct elfhdr) - *fpos);
@@ -382,10 +379,10 @@  static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
 	}
 
 	/* ELF program headers. */
-	if (buflen && *fpos < phdrs_offset + phdrs_len) {
+	if (buflen && *fpos < phdrs_offset + kcore_phdrs_len) {
 		struct elf_phdr *phdrs, *phdr;
 
-		phdrs = kzalloc(phdrs_len, GFP_KERNEL);
+		phdrs = kzalloc(kcore_phdrs_len, GFP_KERNEL);
 		if (!phdrs) {
 			ret = -ENOMEM;
 			goto out;
@@ -393,13 +390,14 @@  static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
 
 		phdrs[0].p_type = PT_NOTE;
 		phdrs[0].p_offset = notes_offset;
-		phdrs[0].p_filesz = notes_len;
+		phdrs[0].p_filesz = kcore_notes_len;
 
 		phdr = &phdrs[1];
 		list_for_each_entry(m, &kclist_head, list) {
 			phdr->p_type = PT_LOAD;
 			phdr->p_flags = PF_R | PF_W | PF_X;
-			phdr->p_offset = kc_vaddr_to_offset(m->addr) + data_offset;
+			phdr->p_offset = kc_vaddr_to_offset(m->addr)
+					 + kcore_data_offset;
 			phdr->p_vaddr = (size_t)m->addr;
 			if (m->type == KCORE_RAM)
 				phdr->p_paddr = __pa(m->addr);
@@ -412,7 +410,8 @@  static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
 			phdr++;
 		}
 
-		tsz = min_t(size_t, buflen, phdrs_offset + phdrs_len - *fpos);
+		tsz = min_t(size_t, buflen,
+			    phdrs_offset + kcore_phdrs_len - *fpos);
 		if (copy_to_iter((char *)phdrs + *fpos - phdrs_offset, tsz,
 				 iter) != tsz) {
 			kfree(phdrs);
@@ -426,7 +425,7 @@  static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
 	}
 
 	/* ELF note segment. */
-	if (buflen && *fpos < notes_offset + notes_len) {
+	if (buflen && *fpos < notes_offset + kcore_notes_len) {
 		struct elf_prstatus prstatus = {};
 		struct elf_prpsinfo prpsinfo = {
 			.pr_sname = 'R',
@@ -438,7 +437,7 @@  static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
 		strscpy(prpsinfo.pr_psargs, saved_command_line,
 			sizeof(prpsinfo.pr_psargs));
 
-		notes = kzalloc(notes_len, GFP_KERNEL);
+		notes = kzalloc(kcore_notes_len, GFP_KERNEL);
 		if (!notes) {
 			ret = -ENOMEM;
 			goto out;
@@ -459,9 +458,10 @@  static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
 		 */
 		append_kcore_note(notes, &i, VMCOREINFO_NOTE_NAME, 0,
 				  vmcoreinfo_data,
-				  min(vmcoreinfo_size, notes_len - i));
+				  min(vmcoreinfo_size, kcore_notes_len - i));
 
-		tsz = min_t(size_t, buflen, notes_offset + notes_len - *fpos);
+		tsz = min_t(size_t, buflen,
+			    notes_offset + kcore_notes_len - *fpos);
 		if (copy_to_iter(notes + *fpos - notes_offset, tsz, iter) != tsz) {
 			kfree(notes);
 			ret = -EFAULT;
@@ -477,7 +477,7 @@  static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
 	 * Check to see if our file offset matches with any of
 	 * the addresses in the elf_phdr on our list.
 	 */
-	start = kc_offset_to_vaddr(*fpos - data_offset);
+	start = kc_offset_to_vaddr(*fpos - kcore_data_offset);
 	if ((tsz = (PAGE_SIZE - (start & ~PAGE_MASK))) > buflen)
 		tsz = buflen;