From: Reinette Chatre <reinette.chatre@intel.com>
To: tglx@linutronix.de, fenghua.yu@intel.com, tony.luck@intel.com
Cc: gavin.hindman@intel.com, vikas.shivappa@linux.intel.com,
dave.hansen@intel.com, mingo@redhat.com, hpa@zytor.com,
x86@kernel.org, linux-kernel@vger.kernel.org,
Reinette Chatre <reinette.chatre@intel.com>
Subject: [RFC PATCH V2 22/22] x86/intel_rdt: Support contiguous memory of all sizes
Date: Tue, 13 Feb 2018 07:47:06 -0800 [thread overview]
Message-ID: <1f495b99c766db9d7c942962bca138e695f4651c.1518443616.git.reinette.chatre@intel.com> (raw)
In-Reply-To: <cover.1518443616.git.reinette.chatre@intel.com>
In-Reply-To: <cover.1518443616.git.reinette.chatre@intel.com>
Through "mm/hugetlb: Enable large allocations through gigantic page
API" we are able to allocate contiguous memory regions larger than what
the SLAB allocators can support.
Use the alloc_gigantic_page/free_gigantic_page API to support allocation
of large contiguous memory regions in order to support pseudo-locked
regions larger than 4MB.
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
---
arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c | 89 ++++++++++++++++++++++-------
1 file changed, 68 insertions(+), 21 deletions(-)
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index 90f040166fcd..99918943a98a 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -23,6 +23,7 @@
#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/debugfs.h>
+#include <linux/hugetlb.h>
#include <linux/kernfs.h>
#include <linux/kref.h>
#include <linux/kthread.h>
@@ -136,7 +137,7 @@ struct pseudo_lock_region {
bool locked;
struct kref refcount;
bool deleted;
- void *kmem;
+ struct page *kmem;
#ifdef CONFIG_INTEL_RDT_DEBUGFS
struct dentry *debugfs_dir;
#endif
@@ -202,12 +203,69 @@ static int pseudo_lock_clos_set(struct pseudo_lock_region *plr,
return ret;
}
+/**
+ * contig_mem_alloc - Allocate contiguous memory for pseudo-locked region
+ * @plr: pseudo-locked region for which memory is requested
+ *
+ * In an effort to ensure best coverage of cache with allocated memory
+ * (fewest conflicting physical addresses) allocate contiguous memory
+ * that will be pseudo-locked. The SLAB allocators are restricted wrt
+ * the maximum memory it can allocate. If more memory is required than
+ * what can be requested from the SLAB allocators a gigantic page is
+ * requested instead.
+ */
+static int contig_mem_alloc(struct pseudo_lock_region *plr)
+{
+ void *kmem;
+
+ /*
+ * We should not be allocating from the slab cache - we need whole
+ * pages.
+ */
+ if (plr->size < KMALLOC_MAX_CACHE_SIZE) {
+ rdt_last_cmd_puts("requested region smaller than page size\n");
+ return -EINVAL;
+ }
+
+ if (plr->size > KMALLOC_MAX_SIZE) {
+ plr->kmem = alloc_gigantic_page(cpu_to_node(plr->cpu),
+ get_order(plr->size),
+ GFP_KERNEL | __GFP_ZERO);
+ if (!plr->kmem) {
+ rdt_last_cmd_puts("unable to allocate gigantic page\n");
+ return -ENOMEM;
+ }
+ } else {
+ kmem = kzalloc(plr->size, GFP_KERNEL);
+ if (!kmem) {
+ rdt_last_cmd_puts("unable to allocate memory\n");
+ return -ENOMEM;
+ }
+
+ if (!PAGE_ALIGNED(kmem)) {
+ rdt_last_cmd_puts("received unaligned memory\n");
+ kfree(kmem);
+ return -ENOMEM;
+ }
+ plr->kmem = virt_to_page(kmem);
+ }
+ return 0;
+}
+
+static void contig_mem_free(struct pseudo_lock_region *plr)
+{
+ if (plr->size > KMALLOC_MAX_SIZE)
+ free_gigantic_page(plr->kmem, get_order(plr->size));
+ else
+ kfree(page_to_virt(plr->kmem));
+}
+
static void pseudo_lock_region_clear(struct pseudo_lock_region *plr)
{
- plr->size = 0;
plr->line_size = 0;
- kfree(plr->kmem);
+ contig_mem_free(plr);
plr->kmem = NULL;
+ plr->size = 0;
plr->r = NULL;
plr->d = NULL;
}
@@ -444,7 +502,7 @@ static int measure_cycles_hist_fn(void *_plr)
* local register variable used for memory pointer.
*/
__wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
- mem_r = plr->kmem;
+ mem_r = page_to_virt(plr->kmem);
for (i = 0; i < plr->size; i += 32) {
start = rdtsc_ordered();
asm volatile("mov (%0,%1,1), %%eax\n\t"
@@ -568,7 +626,7 @@ static int measure_cycles_perf_fn(void *_plr)
pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3,
l3_miss_bits);
}
- mem_r = plr->kmem;
+ mem_r = page_to_virt(plr->kmem);
size = plr->size;
line_size = plr->line_size;
for (i = 0; i < size; i += line_size) {
@@ -912,20 +970,9 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr,
return -ENOSPC;
}
- /*
- * We do not yet support contiguous regions larger than
- * KMALLOC_MAX_SIZE
- */
- if (plr->size > KMALLOC_MAX_SIZE) {
- rdt_last_cmd_puts("requested region exceeds maximum size\n");
- return -E2BIG;
- }
-
- plr->kmem = kzalloc(plr->size, GFP_KERNEL);
- if (!plr->kmem) {
- rdt_last_cmd_puts("unable to allocate memory\n");
+ ret = contig_mem_alloc(plr);
+ if (ret < 0)
return -ENOMEM;
- }
plr->r = r;
plr->d = d;
@@ -996,7 +1043,7 @@ static int pseudo_lock_fn(void *_plr)
__wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
closid_p = this_cpu_read(pqr_state.cur_closid);
rmid_p = this_cpu_read(pqr_state.cur_rmid);
- mem_r = plr->kmem;
+ mem_r = page_to_virt(plr->kmem);
size = plr->size;
line_size = plr->line_size;
__wrmsr(IA32_PQR_ASSOC, rmid_p, plr->closid);
@@ -1630,7 +1677,7 @@ static int pseudo_lock_dev_mmap(struct file *file, struct vm_area_struct *vma)
return -EINVAL;
}
- physical = __pa(plr->kmem) >> PAGE_SHIFT;
+ physical = page_to_phys(plr->kmem) >> PAGE_SHIFT;
psize = plr->size - off;
if (off > plr->size) {
@@ -1652,7 +1699,7 @@ static int pseudo_lock_dev_mmap(struct file *file, struct vm_area_struct *vma)
return -ENOSPC;
}
- memset(plr->kmem + off, 0, vsize);
+ memset(page_to_virt(plr->kmem) + off, 0, vsize);
if (remap_pfn_range(vma, vma->vm_start, physical + vma->vm_pgoff,
vsize, vma->vm_page_prot)) {
--
2.13.6
next prev parent reply other threads:[~2018-02-13 23:50 UTC|newest]
Thread overview: 65+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-02-13 15:46 [RFC PATCH V2 00/22] Intel(R) Resource Director Technology Cache Pseudo-Locking enabling Reinette Chatre
2018-02-13 15:46 ` [RFC PATCH V2 01/22] x86/intel_rdt: Documentation for Cache Pseudo-Locking Reinette Chatre
2018-02-19 20:35 ` Thomas Gleixner
2018-02-19 22:15 ` Reinette Chatre
2018-02-19 22:19 ` Thomas Gleixner
2018-02-19 22:24 ` Reinette Chatre
2018-02-19 21:27 ` Randy Dunlap
2018-02-19 22:21 ` Reinette Chatre
2018-02-13 15:46 ` [RFC PATCH V2 02/22] x86/intel_rdt: Make useful functions available internally Reinette Chatre
2018-02-13 15:46 ` [RFC PATCH V2 03/22] x86/intel_rdt: Introduce hooks to create pseudo-locking files Reinette Chatre
2018-02-13 15:46 ` [RFC PATCH V2 04/22] x86/intel_rdt: Introduce test to determine if closid is in use Reinette Chatre
2018-02-13 15:46 ` [RFC PATCH V2 05/22] x86/intel_rdt: Print more accurate pseudo-locking availability Reinette Chatre
2018-02-13 15:46 ` [RFC PATCH V2 06/22] x86/intel_rdt: Create pseudo-locked regions Reinette Chatre
2018-02-19 20:57 ` Thomas Gleixner
2018-02-19 23:02 ` Reinette Chatre
2018-02-19 23:16 ` Thomas Gleixner
2018-02-20 3:21 ` Reinette Chatre
2018-02-13 15:46 ` [RFC PATCH V2 07/22] x86/intel_rdt: Connect pseudo-locking directory to operations Reinette Chatre
2018-02-13 15:46 ` [RFC PATCH V2 08/22] x86/intel_rdt: Introduce pseudo-locking resctrl files Reinette Chatre
2018-02-19 21:01 ` Thomas Gleixner
2018-02-13 15:46 ` [RFC PATCH V2 09/22] x86/intel_rdt: Discover supported platforms via prefetch disable bits Reinette Chatre
2018-02-13 15:46 ` [RFC PATCH V2 10/22] x86/intel_rdt: Disable pseudo-locking if CDP enabled Reinette Chatre
2018-02-13 15:46 ` [RFC PATCH V2 11/22] x86/intel_rdt: Associate pseudo-locked regions with its domain Reinette Chatre
2018-02-19 21:19 ` Thomas Gleixner
2018-02-19 23:00 ` Reinette Chatre
2018-02-19 23:19 ` Thomas Gleixner
2018-02-20 3:17 ` Reinette Chatre
2018-02-20 10:00 ` Thomas Gleixner
2018-02-20 16:02 ` Reinette Chatre
2018-02-20 17:18 ` Thomas Gleixner
2018-02-13 15:46 ` [RFC PATCH V2 12/22] x86/intel_rdt: Support CBM checking from value and character buffer Reinette Chatre
2018-02-13 15:46 ` [RFC PATCH V2 13/22] x86/intel_rdt: Support schemata write - pseudo-locking core Reinette Chatre
2018-02-20 17:15 ` Thomas Gleixner
2018-02-20 18:47 ` Reinette Chatre
2018-02-20 23:21 ` Thomas Gleixner
2018-02-21 1:58 ` Mike Kravetz
2018-02-21 6:10 ` Reinette Chatre
2018-02-21 8:34 ` Thomas Gleixner
2018-02-21 5:58 ` Reinette Chatre
2018-02-27 0:34 ` Reinette Chatre
2018-02-27 10:36 ` Thomas Gleixner
2018-02-27 15:38 ` Thomas Gleixner
2018-02-27 19:52 ` Reinette Chatre
2018-02-27 21:33 ` Reinette Chatre
2018-02-28 18:39 ` Thomas Gleixner
2018-02-28 19:17 ` Reinette Chatre
2018-02-28 19:40 ` Thomas Gleixner
2018-02-27 21:01 ` Reinette Chatre
2018-02-28 17:57 ` Thomas Gleixner
2018-02-28 17:59 ` Thomas Gleixner
2018-02-28 18:34 ` Reinette Chatre
2018-02-28 18:42 ` Thomas Gleixner
2018-02-13 15:46 ` [RFC PATCH V2 14/22] x86/intel_rdt: Enable testing for pseudo-locked region Reinette Chatre
2018-02-13 15:46 ` [RFC PATCH V2 15/22] x86/intel_rdt: Prevent new allocations from pseudo-locked regions Reinette Chatre
2018-02-13 15:47 ` [RFC PATCH V2 16/22] x86/intel_rdt: Create debugfs files for pseudo-locking testing Reinette Chatre
2018-02-13 15:47 ` [RFC PATCH V2 17/22] x86/intel_rdt: Create character device exposing pseudo-locked region Reinette Chatre
2018-02-13 15:47 ` [RFC PATCH V2 18/22] x86/intel_rdt: More precise L2 hit/miss measurements Reinette Chatre
2018-02-13 15:47 ` [RFC PATCH V2 19/22] x86/intel_rdt: Support L3 cache performance event of Broadwell Reinette Chatre
2018-02-13 15:47 ` [RFC PATCH V2 20/22] x86/intel_rdt: Limit C-states dynamically when pseudo-locking active Reinette Chatre
2018-02-13 15:47 ` [RFC PATCH V2 21/22] mm/hugetlb: Enable large allocations through gigantic page API Reinette Chatre
2018-02-13 15:47 ` Reinette Chatre [this message]
2018-02-14 18:12 ` [RFC PATCH V2 00/22] Intel(R) Resource Director Technology Cache Pseudo-Locking enabling Mike Kravetz
2018-02-14 18:31 ` Reinette Chatre
2018-02-15 20:39 ` Reinette Chatre
2018-02-15 21:10 ` Mike Kravetz
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1f495b99c766db9d7c942962bca138e695f4651c.1518443616.git.reinette.chatre@intel.com \
--to=reinette.chatre@intel.com \
--cc=dave.hansen@intel.com \
--cc=fenghua.yu@intel.com \
--cc=gavin.hindman@intel.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=tglx@linutronix.de \
--cc=tony.luck@intel.com \
--cc=vikas.shivappa@linux.intel.com \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).