Unverified Commit c9e132d6 authored by openeuler-ci-bot's avatar openeuler-ci-bot Committed by Gitee
Browse files

!3486 sync smmu patches for olk-6.6 

Merge Pull Request from: @ci-robot 
 
PR sync from: Zhang Zekun <zhangzekun11@huawei.com>
https://mailweb.openeuler.org/hyperkitty/list/kernel@openeuler.org/message/7XHUT42ODWBAXV5OJTABPVOIXB6VJE4P/ 
Make the rache depot scale better.
The origin depot size is fixed, may cause problem in
some condition.

Add another patch to fix smmu problem.

v2->v3:
- Add a smmu bugfix patch

v1->v2:
- Change the commit messge

Robin Murphy (2):
  iommu/iova: Make the rcache depot scale better
  iommu/iova: Manage the depot list size

Wenkai Lin (1):
  iommu/arm-smmu-v3: disable stall for quiet_cd


-- 
2.17.1
 
https://gitee.com/openeuler/kernel/issues/I8PSC6
https://gitee.com/openeuler/kernel/issues/I8PJ8L 
 
Link:https://gitee.com/openeuler/kernel/pulls/3486

 

Reviewed-by: default avatarWeilong Chen <chenweilong@huawei.com>
Signed-off-by: default avatarZheng Zengkai <zhengzengkai@huawei.com>
parents d64b4f93 7c950675

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c

+3 −0
Original line number Diff line number Diff line
@@ -1070,6 +1070,7 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid, 
	u64 val;

	bool cd_live;

	__le64 *cdptr;

	struct arm_smmu_device *smmu = smmu_domain->smmu;



	if (WARN_ON(ssid >= (1 << smmu_domain->s1_cfg.s1cdmax)))

		return -E2BIG;
@@ -1084,6 +1085,8 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid, 
	if (!cd) { /* (5) */

		val = 0;

	} else if (cd == &quiet_cd) { /* (4) */

		if (!(smmu->features & ARM_SMMU_FEAT_STALL_FORCE))

			val &= ~(CTXDESC_CD_0_S | CTXDESC_CD_0_R);

		val |= CTXDESC_CD_0_TCR_EPD0;

	} else if (cd_live) { /* (3) */

		val &= ~CTXDESC_CD_0_ASID;

drivers/iommu/iova.c

+65 −30
Original line number Diff line number Diff line
@@ -11,6 +11,7 @@ 
#include <linux/smp.h>

#include <linux/bitops.h>

#include <linux/cpu.h>

#include <linux/workqueue.h>



/* The anchor node sits above the top of the usable address space */

#define IOVA_ANCHOR	~0UL
@@ -622,15 +623,21 @@ EXPORT_SYMBOL_GPL(reserve_iova); 
/*

 * As kmalloc's buffer size is fixed to power of 2, 127 is chosen to

 * assure size of 'iova_magazine' to be 1024 bytes, so that no memory

 * will be wasted.

 * will be wasted. Since only full magazines are inserted into the depot,

 * we don't need to waste PFN capacity on a separate list head either.

 */

#define IOVA_MAG_SIZE 127

#define MAX_GLOBAL_MAGS 32	/* magazines per bin */



#define IOVA_DEPOT_DELAY msecs_to_jiffies(100)



struct iova_magazine {

	union {

		unsigned long size;

		struct iova_magazine *next;

	};

	unsigned long pfns[IOVA_MAG_SIZE];

};

static_assert(!(sizeof(struct iova_magazine) & (sizeof(struct iova_magazine) - 1)));



struct iova_cpu_rcache {

	spinlock_t lock;
@@ -640,9 +647,11 @@ struct iova_cpu_rcache { 


struct iova_rcache {

	spinlock_t lock;

	unsigned long depot_size;

	struct iova_magazine *depot[MAX_GLOBAL_MAGS];

	unsigned int depot_size;

	struct iova_magazine *depot;

	struct iova_cpu_rcache __percpu *cpu_rcaches;

	struct iova_domain *iovad;

	struct delayed_work work;

};



static struct iova_magazine *iova_magazine_alloc(gfp_t flags)
@@ -717,6 +726,41 @@ static void iova_magazine_push(struct iova_magazine *mag, unsigned long pfn) 
	mag->pfns[mag->size++] = pfn;

}



static struct iova_magazine *iova_depot_pop(struct iova_rcache *rcache)

{

	struct iova_magazine *mag = rcache->depot;



	rcache->depot = mag->next;

	mag->size = IOVA_MAG_SIZE;

	rcache->depot_size--;

	return mag;

}



static void iova_depot_push(struct iova_rcache *rcache, struct iova_magazine *mag)

{

	mag->next = rcache->depot;

	rcache->depot = mag;

	rcache->depot_size++;

}



static void iova_depot_work_func(struct work_struct *work)

{

	struct iova_rcache *rcache = container_of(work, typeof(*rcache), work.work);

	struct iova_magazine *mag = NULL;

	unsigned long flags;



	spin_lock_irqsave(&rcache->lock, flags);

	if (rcache->depot_size > num_online_cpus())

		mag = iova_depot_pop(rcache);

	spin_unlock_irqrestore(&rcache->lock, flags);



	if (mag) {

		iova_magazine_free_pfns(mag, rcache->iovad);

		iova_magazine_free(mag);

		schedule_delayed_work(&rcache->work, IOVA_DEPOT_DELAY);

	}

}



int iova_domain_init_rcaches(struct iova_domain *iovad)

{

	unsigned int cpu;
@@ -734,7 +778,8 @@ int iova_domain_init_rcaches(struct iova_domain *iovad) 


		rcache = &iovad->rcaches[i];

		spin_lock_init(&rcache->lock);

		rcache->depot_size = 0;

		rcache->iovad = iovad;

		INIT_DELAYED_WORK(&rcache->work, iova_depot_work_func);

		rcache->cpu_rcaches = __alloc_percpu(sizeof(*cpu_rcache),

						     cache_line_size());

		if (!rcache->cpu_rcaches) {
@@ -776,7 +821,6 @@ static bool __iova_rcache_insert(struct iova_domain *iovad, 
				 struct iova_rcache *rcache,

				 unsigned long iova_pfn)

{

	struct iova_magazine *mag_to_free = NULL;

	struct iova_cpu_rcache *cpu_rcache;

	bool can_insert = false;

	unsigned long flags;
@@ -794,13 +838,9 @@ static bool __iova_rcache_insert(struct iova_domain *iovad, 


		if (new_mag) {

			spin_lock(&rcache->lock);

			if (rcache->depot_size < MAX_GLOBAL_MAGS) {

				rcache->depot[rcache->depot_size++] =

						cpu_rcache->loaded;

			} else {

				mag_to_free = cpu_rcache->loaded;

			}

			iova_depot_push(rcache, cpu_rcache->loaded);

			spin_unlock(&rcache->lock);

			schedule_delayed_work(&rcache->work, IOVA_DEPOT_DELAY);



			cpu_rcache->loaded = new_mag;

			can_insert = true;
@@ -812,11 +852,6 @@ static bool __iova_rcache_insert(struct iova_domain *iovad, 


	spin_unlock_irqrestore(&cpu_rcache->lock, flags);



	if (mag_to_free) {

		iova_magazine_free_pfns(mag_to_free, iovad);

		iova_magazine_free(mag_to_free);

	}



	return can_insert;

}
@@ -854,9 +889,9 @@ static unsigned long __iova_rcache_get(struct iova_rcache *rcache, 
		has_pfn = true;

	} else {

		spin_lock(&rcache->lock);

		if (rcache->depot_size > 0) {

		if (rcache->depot) {

			iova_magazine_free(cpu_rcache->loaded);

			cpu_rcache->loaded = rcache->depot[--rcache->depot_size];

			cpu_rcache->loaded = iova_depot_pop(rcache);

			has_pfn = true;

		}

		spin_unlock(&rcache->lock);
@@ -895,9 +930,8 @@ static void free_iova_rcaches(struct iova_domain *iovad) 
	struct iova_rcache *rcache;

	struct iova_cpu_rcache *cpu_rcache;

	unsigned int cpu;

	int i, j;



	for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {

	for (int i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {

		rcache = &iovad->rcaches[i];

		if (!rcache->cpu_rcaches)

			break;
@@ -907,8 +941,9 @@ static void free_iova_rcaches(struct iova_domain *iovad) 
			iova_magazine_free(cpu_rcache->prev);

		}

		free_percpu(rcache->cpu_rcaches);

		for (j = 0; j < rcache->depot_size; ++j)

			iova_magazine_free(rcache->depot[j]);

		cancel_delayed_work_sync(&rcache->work);

		while (rcache->depot)

			iova_magazine_free(iova_depot_pop(rcache));

	}



	kfree(iovad->rcaches);
@@ -942,16 +977,16 @@ static void free_global_cached_iovas(struct iova_domain *iovad) 
{

	struct iova_rcache *rcache;

	unsigned long flags;

	int i, j;



	for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {

	for (int i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {

		rcache = &iovad->rcaches[i];

		spin_lock_irqsave(&rcache->lock, flags);

		for (j = 0; j < rcache->depot_size; ++j) {

			iova_magazine_free_pfns(rcache->depot[j], iovad);

			iova_magazine_free(rcache->depot[j]);

		while (rcache->depot) {

			struct iova_magazine *mag = iova_depot_pop(rcache);



			iova_magazine_free_pfns(mag, iovad);

			iova_magazine_free(mag);

		}

		rcache->depot_size = 0;

		spin_unlock_irqrestore(&rcache->lock, flags);

	}

}