Patch series "New page table range API", v6.
This patchset changes the API used by the MM to set up page table entries.
The four APIs are:
set_ptes(mm, addr, ptep, pte, nr)
update_mmu_cache_range(vma, addr, ptep, nr)
flush_dcache_folio(folio)
flush_icache_pages(vma, page, nr)
flush_dcache_folio() isn't technically new, but no architecture
implemented it, so I've done that for them. The old APIs remain around
but are mostly implemented by calling the new interfaces.
The new APIs are based around setting up N page table entries at once.
The N entries belong to the same PMD, the same folio and the same VMA, so
ptep++ is a legitimate operation, and locking is taken care of for you.
Some architectures can do a better job of it than just a loop, but I have
hesitated to make too deep a change to architectures I don't understand
well.
One thing I have changed in every architecture is that PG_arch_1 is now a
per-folio bit instead of a per-page bit when used for dcache clean/dirty
tracking. This was something that would have to happen eventually, and it
makes sense to do it now rather than iterate over every page involved in a
cache flush and figure out if it needs to happen.
The point of all this is better performance, and Fengwei Yin has measured
improvement on x86. I suspect you'll see improvement on your architecture
too. Try the new will-it-scale test mentioned here:
https://lore.kernel.org/linux-mm/
20230206140639.538867-5-fengwei.yin@intel.com/
You'll need to run it on an XFS filesystem and have
CONFIG_TRANSPARENT_HUGEPAGE set.
This patchset is the basis for much of the anonymous large folio work
being done by Ryan, so it's received quite a lot of testing over the last
few months.
This patch (of 38):
Determine if a value lies within a range more efficiently (subtraction +
comparison vs two comparisons and an AND). It also has useful (under some
circumstances) behaviour if the range exceeds the maximum value of the
type. Convert all the conflicting definitions of in_range() within the
kernel; some can use the generic definition while others need their own
definition.
Link: https://lkml.kernel.org/r/20230802151406.3735276-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20230802151406.3735276-2-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
return 0;
}
-static bool in_range(unsigned long start, unsigned long size,
+static bool range_in_range(unsigned long start, unsigned long size,
unsigned long range_start, unsigned long range_end)
{
return start >= range_start && start < range_end &&
if (!size)
return 0;
- if (!in_range(start, size, MODULES_VADDR, MODULES_END) &&
- !in_range(start, size, VMALLOC_START, VMALLOC_END))
+ if (!range_in_range(start, size, MODULES_VADDR, MODULES_END) &&
+ !range_in_range(start, size, VMALLOC_START, VMALLOC_END))
return -EINVAL;
return __change_memory_common(start, size, set_mask, clear_mask);
rg->end = end;
}
-static inline bool in_range(struct malidp_range *rg, u32 v)
+static inline bool malidp_in_range(struct malidp_range *rg, u32 v)
{
return (v >= rg->start) && (v <= rg->end);
}
if (komeda_fb_check_src_coords(kfb, src_x, src_y, src_w, src_h))
return -EINVAL;
- if (!in_range(&layer->hsize_in, src_w)) {
+ if (!malidp_in_range(&layer->hsize_in, src_w)) {
DRM_DEBUG_ATOMIC("invalidate src_w %d.\n", src_w);
return -EINVAL;
}
- if (!in_range(&layer->vsize_in, src_h)) {
+ if (!malidp_in_range(&layer->vsize_in, src_h)) {
DRM_DEBUG_ATOMIC("invalidate src_h %d.\n", src_h);
return -EINVAL;
}
hsize_out = dflow->out_w;
vsize_out = dflow->out_h;
- if (!in_range(&scaler->hsize, hsize_in) ||
- !in_range(&scaler->hsize, hsize_out)) {
+ if (!malidp_in_range(&scaler->hsize, hsize_in) ||
+ !malidp_in_range(&scaler->hsize, hsize_out)) {
DRM_DEBUG_ATOMIC("Invalid horizontal sizes");
return -EINVAL;
}
- if (!in_range(&scaler->vsize, vsize_in) ||
- !in_range(&scaler->vsize, vsize_out)) {
+ if (!malidp_in_range(&scaler->vsize, vsize_in) ||
+ !malidp_in_range(&scaler->vsize, vsize_out)) {
DRM_DEBUG_ATOMIC("Invalid vertical sizes");
return -EINVAL;
}
return -EINVAL;
}
- if (!in_range(&splitter->hsize, dflow->in_w)) {
+ if (!malidp_in_range(&splitter->hsize, dflow->in_w)) {
DRM_DEBUG_ATOMIC("split in_w:%d is out of the acceptable range.\n",
dflow->in_w);
return -EINVAL;
}
- if (!in_range(&splitter->vsize, dflow->in_h)) {
+ if (!malidp_in_range(&splitter->vsize, dflow->in_h)) {
DRM_DEBUG_ATOMIC("split in_h: %d exceeds the acceptable range.\n",
dflow->in_h);
return -EINVAL;
return -EINVAL;
}
- if (!in_range(&merger->hsize_merged, output->out_w)) {
+ if (!malidp_in_range(&merger->hsize_merged, output->out_w)) {
DRM_DEBUG_ATOMIC("merged_w: %d is out of the accepted range.\n",
output->out_w);
return -EINVAL;
}
- if (!in_range(&merger->vsize_merged, output->out_h)) {
+ if (!malidp_in_range(&merger->vsize_merged, output->out_h)) {
DRM_DEBUG_ATOMIC("merged_h: %d is out of the accepted range.\n",
output->out_h);
return -EINVAL;
* input/output range.
*/
if (dflow->en_scaling && scaler)
- dflow->en_split = !in_range(&scaler->hsize, dflow->in_w) ||
- !in_range(&scaler->hsize, dflow->out_w);
+ dflow->en_split = !malidp_in_range(&scaler->hsize, dflow->in_w) ||
+ !malidp_in_range(&scaler->hsize, dflow->out_w);
}
static bool merger_is_available(struct komeda_pipeline *pipe,
u32 data[];
};
-/* this should be a general kernel helper */
-static int in_range(u32 addr, u32 start, u32 size)
-{
- return addr >= start && addr < start + size;
-}
-
static bool fw_block_mem(struct a6xx_gmu_bo *bo, const struct block_header *blk)
{
if (!in_range(blk->addr, bo->iova, bo->size))
.set_link_ksettings = set_link_ksettings,
};
-static int in_range(int val, int lo, int hi)
+static int cxgb_in_range(int val, int lo, int hi)
{
return val < 0 || (val <= hi && val >= lo);
}
return -EINVAL;
if (t.qset_idx >= SGE_QSETS)
return -EINVAL;
- if (!in_range(t.intr_lat, 0, M_NEWTIMER) ||
- !in_range(t.cong_thres, 0, 255) ||
- !in_range(t.txq_size[0], MIN_TXQ_ENTRIES,
+ if (!cxgb_in_range(t.intr_lat, 0, M_NEWTIMER) ||
+ !cxgb_in_range(t.cong_thres, 0, 255) ||
+ !cxgb_in_range(t.txq_size[0], MIN_TXQ_ENTRIES,
MAX_TXQ_ENTRIES) ||
- !in_range(t.txq_size[1], MIN_TXQ_ENTRIES,
+ !cxgb_in_range(t.txq_size[1], MIN_TXQ_ENTRIES,
MAX_TXQ_ENTRIES) ||
- !in_range(t.txq_size[2], MIN_CTRL_TXQ_ENTRIES,
+ !cxgb_in_range(t.txq_size[2], MIN_CTRL_TXQ_ENTRIES,
MAX_CTRL_TXQ_ENTRIES) ||
- !in_range(t.fl_size[0], MIN_FL_ENTRIES,
+ !cxgb_in_range(t.fl_size[0], MIN_FL_ENTRIES,
MAX_RX_BUFFERS) ||
- !in_range(t.fl_size[1], MIN_FL_ENTRIES,
+ !cxgb_in_range(t.fl_size[1], MIN_FL_ENTRIES,
MAX_RX_JUMBO_BUFFERS) ||
- !in_range(t.rspq_size, MIN_RSPQ_ENTRIES,
+ !cxgb_in_range(t.rspq_size, MIN_RSPQ_ENTRIES,
MAX_RSPQ_ENTRIES))
return -EINVAL;
return is_handled;
}
-static bool in_range(struct acrn_ioreq_range *range,
+static bool acrn_in_range(struct acrn_ioreq_range *range,
struct acrn_io_request *req)
{
bool ret = false;
list_for_each_entry(client, &vm->ioreq_clients, list) {
read_lock_bh(&client->range_lock);
list_for_each_entry(range, &client->range_list, list) {
- if (in_range(range, req)) {
+ if (acrn_in_range(range, req)) {
found = client;
break;
}
#include <linux/math64.h>
#include <linux/rbtree.h>
-#define in_range(b, first, len) ((b) >= (first) && (b) < (first) + (len))
-
/*
* Enumerate bits using enum autoincrement. Define the @name as the n-th bit.
*/
*/
-#define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1)
-
struct ext2_group_desc * ext2_get_group_desc(struct super_block * sb,
unsigned int block_group,
struct buffer_head ** bh)
set_bit(BH_BITMAP_UPTODATE, &(bh)->b_state);
}
-#define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1)
-
/* For ioend & aio unwritten conversion wait queues */
#define EXT4_WQ_HASH_SZ 37
#define ext4_ioend_wq(v) (&ext4__ioend_wq[((unsigned long)(v)) %\
#include <linux/fs.h>
#include "swab.h"
-
-/*
- * some useful macros
- */
-#define in_range(b,first,len) ((b)>=(first)&&(b)<(first)+(len))
-
/*
* functions used for retyping
*/
#define _LINUX_MINMAX_H
#include <linux/const.h>
+#include <linux/types.h>
/*
* min()/max()/clamp() macros must accomplish three things:
*/
#define clamp_val(val, lo, hi) clamp_t(typeof(val), val, lo, hi)
+static inline bool in_range64(u64 val, u64 start, u64 len)
+{
+ return (val - start) < len;
+}
+
+static inline bool in_range32(u32 val, u32 start, u32 len)
+{
+ return (val - start) < len;
+}
+
+/**
+ * in_range - Determine if a value lies within a range.
+ * @val: Value to test.
+ * @start: First value in range.
+ * @len: Number of values in range.
+ *
+ * This is more efficient than "if (start <= val && val < (start + len))".
+ * It also gives a different answer if @start + @len overflows the size of
+ * the type by a sufficient amount to encompass @val. Decide for yourself
+ * which behaviour you want, or prove that start + len never overflow.
+ * Do not blindly replace one form with the other.
+ */
+#define in_range(val, start, len) \
+ ((sizeof(start) | sizeof(len) | sizeof(val)) <= sizeof(u32) ? \
+ in_range32(val, start, len) : in_range64(val, start, len))
+
/**
* swap - swap values of @a and @b
* @a: first value
static LIST_HEAD(io_range_list);
static DEFINE_MUTEX(io_range_mutex);
-/* Consider a kernel general helper for this */
-#define in_range(b, first, len) ((b) >= (first) && (b) < (first) + (len))
-
/**
* logic_pio_register_range - register logical PIO range for a host
* @new_range: pointer to the IO range to be registered.
/* If we source map this tuple so reply looks like reply_tuple, will
* that meet the constraints of range.
*/
-static int in_range(const struct nf_conntrack_tuple *tuple,
+static int nf_in_range(const struct nf_conntrack_tuple *tuple,
const struct nf_nat_range2 *range)
{
/* If we are supposed to map IPs, then we must be in the
&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
result->dst = tuple->dst;
- if (in_range(result, range))
+ if (nf_in_range(result, range))
return 1;
}
}
if (maniptype == NF_NAT_MANIP_SRC &&
!(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL)) {
/* try the original tuple first */
- if (in_range(orig_tuple, range)) {
+ if (nf_in_range(orig_tuple, range)) {
if (!nf_nat_used_tuple(orig_tuple, ct)) {
*tuple = *orig_tuple;
return;
return less_eq(left, right) && (mod(right) != mod(left));
}
-static inline int in_range(u16 val, u16 min, u16 max)
+static inline int tipc_in_range(u16 val, u16 min, u16 max)
{
return !less(val, min) && !more(val, max);
}
last_ga->bgack_cnt);
}
/* Check against the last Gap ACK block */
- if (in_range(seqno, start, end))
+ if (tipc_in_range(seqno, start, end))
continue;
/* Update/release the packet peer is acking */
bc_has_acked = true;
strncpy(if_name, data, TIPC_MAX_IF_NAME);
/* Update own tolerance if peer indicates a non-zero value */
- if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) {
+ if (tipc_in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) {
l->tolerance = peers_tol;
l->bc_rcvlink->tolerance = peers_tol;
}
/* Update own priority if peer's priority is higher */
- if (in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI))
+ if (tipc_in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI))
l->priority = peers_prio;
/* If peer is going down we want full re-establish cycle */
l->rcv_nxt_state = msg_seqno(hdr) + 1;
/* Update own tolerance if peer indicates a non-zero value */
- if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) {
+ if (tipc_in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) {
l->tolerance = peers_tol;
l->bc_rcvlink->tolerance = peers_tol;
}
/* Update own prio if peer indicates a different value */
if ((peers_prio != l->priority) &&
- in_range(peers_prio, 1, TIPC_MAX_LINK_PRI)) {
+ tipc_in_range(peers_prio, 1, TIPC_MAX_LINK_PRI)) {
l->priority = peers_prio;
rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
}
#define ENTRY_CNT 32
struct perf_branch_entry entries[ENTRY_CNT] = {};
-static inline bool in_range(__u64 val)
+static inline bool gbs_in_range(__u64 val)
{
return (val >= address_low) && (val < address_high);
}
for (i = 0; i < ENTRY_CNT; i++) {
if (i >= total_entries)
break;
- if (in_range(entries[i].from) && in_range(entries[i].to))
+ if (gbs_in_range(entries[i].from) && gbs_in_range(entries[i].to))
test1_hits++;
else if (!test1_hits)
wasted_entries++;
projects / linux-2.6-block.git / commitdiff