!443 OLK-5.10 backport sharepool and config isolation patches

Merge Pull Request from: @zhang-zekun-zk 
 
OLK-5.10 backport sharepool and config isolation patches 
 
Link:https://gitee.com/openeuler/kernel/pulls/443 

Reviewed-by: Weilong Chen <chenweilong@huawei.com> 
Reviewed-by: Jialin Zhang <zhangjialin11@huawei.com> 
Signed-off-by: Jialin Zhang <zhangjialin11@huawei.com> 

arch/arm64/Kconfig

@@ -2081,7 +2081,7 @@ config ASCEND_CHARGE_MIGRATE_HUGEPAGES
 config ASCEND_SHARE_POOL
 	bool "Enable support for the Share Pool Memory"
 	default n
-	depends on HAVE_ARCH_HUGE_VMALLOC
+	depends on HAVE_ARCH_HUGE_VMALLOC && EXTEND_HUGEPAGE_MAPPING
 	select ARCH_USES_HIGH_VMA_FLAGS
 	help
 	  This feature allows multiple processes to share virtual memory both

arch/arm64/configs/openeuler_defconfig

@@ -721,6 +721,8 @@ CONFIG_ACPI_HMAT=y
 CONFIG_HAVE_ACPI_APEI=y
 CONFIG_ACPI_APEI=y
 CONFIG_ACPI_APEI_GHES=y
+CONFIG_ACPI_APEI_GHES_TS_CORE=y
+CONFIG_ACPI_APEI_GHES_NOTIFY_ALL_RAS_ERR=y
 CONFIG_ACPI_APEI_PCIEAER=y
 CONFIG_ACPI_APEI_SEA=y
 CONFIG_ACPI_APEI_MEMORY_FAILURE=y
@@ -1129,6 +1131,7 @@ CONFIG_PIN_MEMORY=y
 CONFIG_PID_RESERVE=y
 CONFIG_MEMORY_RELIABLE=y
 # CONFIG_CLEAR_FREELIST_PAGE is not set
+CONFIG_EXTEND_HUGEPAGE_MAPPING=y
 
 #
 # Data Access Monitoring
@@ -5927,6 +5930,7 @@ CONFIG_ARM_SMMU=y
 CONFIG_ARM_SMMU_DISABLE_BYPASS_BY_DEFAULT=y
 CONFIG_ARM_SMMU_V3=y
 CONFIG_ARM_SMMU_V3_SVA=y
+CONFIG_ARM_SMMU_V3_PM=y
 # CONFIG_AGENT_SMMU_ATOS is not set
 # CONFIG_QCOM_IOMMU is not set
 # CONFIG_VIRTIO_IOMMU is not set
@@ -6110,6 +6114,8 @@ CONFIG_THUNDERX2_PMU=m
 CONFIG_XGENE_PMU=y
 CONFIG_ARM_SPE_PMU=y
 CONFIG_HISI_PMU=m
+CONFIG_HISI_L3T_PMU=m
+CONFIG_HISI_LPDDRC_PMU=m
 CONFIG_HISI_PCIE_PMU=m
 CONFIG_HNS3_PMU=m
 # end of Performance monitor support

drivers/acpi/apei/Kconfig

@@ -33,6 +33,20 @@ config ACPI_APEI_GHES
 	  by firmware to produce more valuable hardware error
 	  information for Linux.
 
+config ACPI_APEI_GHES_TS_CORE
+	bool "Support ts core ras process for ascend"
+	depends on ARM64 && ACPI_APEI_GHES
+	default n
+	help
+	  Enable the support for ts core ras process for ascend.
+
+config ACPI_APEI_GHES_NOTIFY_ALL_RAS_ERR
+	bool "Notify all ras err to driver"
+	depends on ARM64 && ACPI_APEI_GHES
+	default n
+	help
+	  Deliver all types of error to driver.
+
 config ACPI_APEI_PCIEAER
 	bool "APEI PCIe AER logging/recovering support"
 	depends on ACPI_APEI && PCIEAER

drivers/acpi/apei/ghes.c

@@ -118,8 +118,10 @@ module_param_named(disable, ghes_disable, bool, 0);
 static LIST_HEAD(ghes_hed);
 static DEFINE_MUTEX(ghes_list_mutex);
 
+#ifdef CONFIG_ACPI_APEI_GHES_TS_CORE
 BLOCKING_NOTIFIER_HEAD(ghes_ts_err_chain);
 EXPORT_SYMBOL(ghes_ts_err_chain);
+#endif
 
 /*
  * Because the memory area used to transfer hardware error information
@@ -657,20 +659,26 @@ static bool ghes_do_proc(struct ghes *ghes,
 		}
 		else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
 			queued = ghes_handle_arm_hw_error(gdata, sev);
+#ifdef CONFIG_ACPI_APEI_GHES_TS_CORE
 		}
 		else if (guid_equal(sec_type, &CPER_SEC_TS_CORE)) {
 			blocking_notifier_call_chain(&ghes_ts_err_chain,
 					0, acpi_hest_get_payload(gdata));
+#endif
 		} else {
 			void *err = acpi_hest_get_payload(gdata);
-
+#ifndef CONFIG_ACPI_APEI_GHES_NOTIFY_ALL_RAS_ERR
+			ghes_defer_non_standard_event(gdata, sev);
+#endif
 			log_non_standard_event(sec_type, fru_id, fru_text,
 					       sec_sev, err,
 					       gdata->error_data_length);
 		}
 
+#ifdef CONFIG_ACPI_APEI_GHES_NOTIFY_ALL_RAS_ERR
 		/* Customization deliver all types error to driver. */
 		ghes_defer_non_standard_event(gdata, sev);
+#endif
 	}
 
 	return queued;

drivers/iommu/Kconfig

@@ -336,6 +336,13 @@ config AGENT_SMMU_ATOS
 	  Say Y here if your system will be used in Ascend Advanced Accelerator
 	  with HCCS bus. Or want use the ATOS of SMMU.
 
+config ARM_SMMU_V3_PM
+	bool "Add arm_smmu_v3  suspend and resume support"
+	depends on ARM_SMMU_V3 && PM_SLEEP
+	default n
+	help
+	  Add support for suspend and resume support for arm smmu v3.
+
 config S390_IOMMU
 	def_bool y if S390 && PCI
 	depends on S390 && PCI

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

@@ -4349,7 +4349,7 @@ static void arm_smmu_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg)
 	doorbell = (((u64)msg->address_hi) << 32) | msg->address_lo;
 	doorbell &= MSI_CFG0_ADDR_MASK;
 
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_SMMU_V3_PM
 	/* Saves the msg (base addr of msi irq) and restores it during resume */
 	desc->msg.address_lo = msg->address_lo;
 	desc->msg.address_hi = msg->address_hi;
@@ -4411,7 +4411,7 @@ static void arm_smmu_setup_msis(struct arm_smmu_device *smmu)
 	devm_add_action(dev, arm_smmu_free_msis, dev);
 }
 
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_SMMU_V3_PM
 static void arm_smmu_resume_msis(struct arm_smmu_device *smmu)
 {
 	struct msi_desc *desc;
@@ -5313,8 +5313,7 @@ static void __iomem *arm_smmu_ioremap(struct device *dev, resource_size_t start,
 	return devm_ioremap_resource(dev, &res);
 }
 
-#ifdef CONFIG_PM_SLEEP
-
+#ifdef CONFIG_ARM_SMMU_V3_PM
 static int arm_smmu_ecmdq_disable(struct device *dev)
 {
 	int i, j;
@@ -5521,7 +5520,7 @@ static const struct of_device_id arm_smmu_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, arm_smmu_of_match);
 
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_SMMU_V3_PM
 static const struct dev_pm_ops arm_smmu_pm_ops = {
 	.suspend = arm_smmu_suspend,
 	.resume = arm_smmu_resume,

drivers/perf/hisilicon/Kconfig

@@ -24,3 +24,22 @@ config HNS3_PMU
 	  devices.
 	  Adds the HNS3 PMU into perf events system for monitoring latency,
 	  bandwidth etc.
+
+config HISI_L3T_PMU
+	tristate "HiSilicon SoC L3T PMU drivers"
+	depends on HISI_PMU
+	default n
+	  help
+	  Support for HiSilicon SoC L3 Cache performance monitor, Hydra Home
+	  Agent performance monitor and DDR Controller performance monitor.
+	  L3T is a specialized PMU driver.
+
+config HISI_LPDDRC_PMU
+	tristate "HiSilicon SoC LDPPRC PMU drivers"
+	depends on HISI_PMU
+	default n
+	  help
+	  Support for HiSilicon SoC L3 Cache performance monitor, Hydra Home
+	  Agent performance monitor and DDR Controller performance monitor.
+	  LPDDRC is a specialize PMU driver.
+

drivers/perf/hisilicon/Makefile

 # SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_HISI_PMU) += hisi_uncore_pmu.o hisi_uncore_l3c_pmu.o \
 			  hisi_uncore_hha_pmu.o hisi_uncore_ddrc_pmu.o hisi_uncore_sllc_pmu.o \
-			  hisi_uncore_pa_pmu.o hisi_uncore_cpa_pmu.o \
-			  hisi_uncore_l3t_pmu.o \
-			  hisi_uncore_lpddrc_pmu.o
+			  hisi_uncore_pa_pmu.o hisi_uncore_cpa_pmu.o
 
 obj-$(CONFIG_HISI_PCIE_PMU) += hisi_pcie_pmu.o
 obj-$(CONFIG_HNS3_PMU) += hns3_pmu.o
+obj-$(CONFIG_HISI_L3T_PMU) += hisi_uncore_l3t_pmu.o
+obj-$(CONFIG_HISI_LPDDRC_PMU) += hisi_uncore_lpddrc_pmu.o

fs/hugetlbfs/inode.c

@@ -602,13 +602,20 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 			 * if the page is from buddy system, do not add to freed.
 			 * because freed is used for hugetlbfs reservation accounting.
 			 */
-			if (!HPageTemporary(page)) {
-				freed++;
-				if (!truncate_op) {
-					if (unlikely(hugetlb_unreserve_pages(inode,
+
+#ifdef CONFIG_ASCEND_SHARE_POOL
+			if (HPageTemporary(page) != 0) {
+				unlock_page(page);
+				if (!truncate_op)
+					mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+				continue;
+			}
+#endif
+			freed++;
+			if (!truncate_op) {
+				if (unlikely(hugetlb_unreserve_pages(inode,
 									index, index + 1, 1)))
-						hugetlb_fix_reserve_counts(inode);
-				}
+					hugetlb_fix_reserve_counts(inode);
 			}
 
 			unlock_page(page);
@@ -1061,8 +1068,12 @@ static int hugetlbfs_error_remove_page(struct address_space *mapping,
 	pgoff_t index = page->index;
 
 	remove_huge_page(page);
+#ifdef CONFIG_ASCEND_SHARE_POOL
 	if (!HPageTemporary(page) &&
 			unlikely(hugetlb_unreserve_pages(inode, index, index + 1, 1)))
+#else
+	if (unlikely(hugetlb_unreserve_pages(inode, index, index + 1, 1)))
+#endif
 		hugetlb_fix_reserve_counts(inode);
 
 	return 0;

include/acpi/ghes.h

@@ -145,6 +145,8 @@ int ghes_notify_sea(void);
 static inline int ghes_notify_sea(void) { return -ENOENT; }
 #endif
 
+#ifdef CONFIG_ACPI_APEI_GHES_TS_CORE
 extern struct blocking_notifier_head ghes_ts_err_chain;
+#endif
 
 #endif /* GHES_H */

include/linux/cper.h

@@ -197,10 +197,13 @@ enum {
 #define CPER_SEC_DMAR_IOMMU						\
 	GUID_INIT(0x036F84E1, 0x7F37, 0x428c, 0xA7, 0x9E, 0x57, 0x5F,	\
 		  0xDF, 0xAA, 0x84, 0xEC)
+
+#ifdef CONFIG_ACPI_APEI_GHES_TS_CORE
 /* HISI ts core */
 #define CPER_SEC_TS_CORE						\
 	GUID_INIT(0xeb4c71f8, 0xbc76, 0x4c46, 0xbd, 0x9, 0xd0, 0xd3,	\
 		  0x45, 0x0, 0x5a, 0x92)
+#endif
 
 #define CPER_PROC_VALID_TYPE			0x0001
 #define CPER_PROC_VALID_ISA			0x0002

include/linux/mm.h

@@ -235,11 +235,13 @@ int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *,
 /* test whether an address (unsigned long or pointer) is aligned to PAGE_SIZE */
 #define PAGE_ALIGNED(addr)	IS_ALIGNED((unsigned long)(addr), PAGE_SIZE)
 
+#ifdef CONFIG_EXTEND_HUGEPAGE_MAPPING
 /* to align the pointer to the (next) PMD hugepage boundary */
 #define PMD_ALIGN(addr) ALIGN(addr, PMD_SIZE)
 
 /* test whether an address (unsigned long or pointer) is aligned to PMD_SIZE */
 #define PMD_ALIGNED(addr)   IS_ALIGNED((unsigned long)(addr), PMD_SIZE)
+#endif
 
 #define lru_to_page(head) (list_entry((head)->prev, struct page, lru))
 

include/linux/vmalloc.h

@@ -27,7 +27,9 @@ struct notifier_block;		/* in notifier.h */
 #define VM_FLUSH_RESET_PERMS	0x00000100	/* reset direct map and flush TLB on unmap, can't be freed in atomic context */
 #define VM_MAP_PUT_PAGES	0x00000200	/* put pages and free array in vfree */
 #define VM_NO_HUGE_VMAP		0x00000400	/* force PAGE_SIZE pte mapping */
+#ifdef CONFIG_EXTEND_HUGEPAGE_MAPPING
 #define VM_HUGE_PAGES		0x00001000	/* used for vmalloc hugepages */
+#endif
 #ifdef CONFIG_ASCEND_SHARE_POOL
 #define VM_SHAREPOOL		0x00002000      /* remapped to sharepool */
 #else
@@ -142,8 +144,11 @@ extern void *__vmalloc_node_range(unsigned long size, unsigned long align,
 void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask,
 		int node, const void *caller);
 void *vmalloc_no_huge(unsigned long size);
+
+#ifdef CONFIG_EXTEND_HUGEPAGE_MAPPING
 extern void *vmalloc_hugepage(unsigned long size);
 extern void *vmalloc_hugepage_user(unsigned long size);
+#endif
 
 extern void vfree(const void *addr);
 extern void vfree_atomic(const void *addr);
@@ -160,6 +165,7 @@ extern int remap_vmalloc_range_partial(struct vm_area_struct *vma,
 extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
 							unsigned long pgoff);
 
+#ifdef CONFIG_EXTEND_HUGEPAGE_MAPPING
 extern void *vmap_hugepage(struct page **pages, unsigned int count,
 			   unsigned long flags, pgprot_t prot);
 extern int remap_vmalloc_hugepage_range_partial(struct vm_area_struct *vma,
@@ -167,6 +173,7 @@ extern int remap_vmalloc_hugepage_range_partial(struct vm_area_struct *vma,
 						unsigned long pgoff, unsigned long size);
 extern int remap_vmalloc_hugepage_range(struct vm_area_struct *vma,
 					void *addr, unsigned long pgoff);
+#endif
 
 /*
  * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values

mm/Kconfig

@@ -992,6 +992,12 @@ config CLEAR_FREELIST_PAGE
 	  To enable this feature, kernel parameter "clear_freelist" also
 	  needs to be added.
 
+config EXTEND_HUGEPAGE_MAPPING
+	bool "Extend for hugepages mapping"
+	depends on ARM64
+	default n
+	help
+	  Introduce vmalloc/vmap/remap interfaces that handle only hugepages.
 
 source "mm/damon/Kconfig"
 

mm/hugetlb.c

@@ -46,6 +46,7 @@
 #include <linux/dynamic_hugetlb.h>
 #include "internal.h"
 #include "hugetlb_vmemmap.h"
+#include "share_pool_internal.h"
 
 int hugetlb_max_hstate __read_mostly;
 unsigned int default_hstate_idx;
@@ -1625,6 +1626,7 @@ void free_huge_page(struct page *page)
 		h->resv_huge_pages++;
 
 	if (HPageTemporary(page)) {
+		sp_memcg_uncharge_hpage(page);
 		remove_hugetlb_page(h, page, false);
 		spin_unlock_irqrestore(&hugetlb_lock, flags);
 		update_and_free_page(h, page, true);

mm/share_pool_internal.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef SHARE_POOL_INTERNAL_H
+#define SHARE_POOL_INTERNAL_H
+
+#include <linux/hugetlb.h>
+#include <linux/memcontrol.h>
+
+#ifdef CONFIG_ASCEND_SHARE_POOL
+static inline void sp_memcg_uncharge_hpage(struct page *page)
+{
+	if (!sp_is_enabled())
+		return;
+
+	mem_cgroup_uncharge(page);
+}
+#else
+static inline void sp_memcg_uncharge_hpage(struct page *page)
+{
+}
+#endif
+
+#endif

mm/vmalloc.c

@@ -578,6 +578,7 @@ static int vmap_pages_range(unsigned long addr, unsigned long end,
 	return err;
 }
 
+#ifdef CONFIG_EXTEND_HUGEPAGE_MAPPING
 static int vmap_hugepages_range_noflush(unsigned long addr, unsigned long end,
 		pgprot_t prot, struct page **pages, unsigned int page_shift)
 {
@@ -609,6 +610,7 @@ static int vmap_hugepages_range(unsigned long addr, unsigned long end,
 
 	return err;
 }
+#endif
 
 /**
  * map_kernel_range_noflush - map kernel VM area with the specified pages
@@ -2792,6 +2794,7 @@ void *vmap(struct page **pages, unsigned int count,
 }
 EXPORT_SYMBOL(vmap);
 
+#ifdef CONFIG_EXTEND_HUGEPAGE_MAPPING
 /**
  *	vmap_hugepage  -  map an array of huge pages into virtually contiguous space
  *	@pages:		array of huge page pointers (only the header)
@@ -2830,6 +2833,7 @@ void *vmap_hugepage(struct page **pages, unsigned int count,
 	return area->addr;
 }
 EXPORT_SYMBOL(vmap_hugepage);
+#endif
 
 #ifdef CONFIG_VMAP_PFN
 struct vmap_pfn_data {
@@ -3015,7 +3019,11 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 		size_per_node = size;
 		if (node == NUMA_NO_NODE)
 			size_per_node /= num_online_nodes();
+#ifdef CONFIG_EXTEND_HUGEPAGE_MAPPING
 		if (size_per_node >= PMD_SIZE || vm_flags & VM_HUGE_PAGES) {
+#else
+		if (size_per_node >= PMD_SIZE) {
+#endif
 			shift = PMD_SHIFT;
 			align = max(real_align, 1UL << shift);
 			size = ALIGN(real_size, 1UL << shift);
@@ -3050,8 +3058,12 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 	return addr;
 
 fail:
+#ifdef CONFIG_EXTEND_HUGEPAGE_MAPPING
 	/* User could specify VM_HUGE_PAGES to alloc only hugepages. */
 	if (shift > PAGE_SHIFT && !(vm_flags & VM_HUGE_PAGES)) {
+#else
+	if (shift > PAGE_SHIFT) {
+#endif
 		shift = PAGE_SHIFT;
 		align = real_align;
 		size = real_size;
@@ -3261,6 +3273,7 @@ void *vmalloc_32_user(unsigned long size)
 }
 EXPORT_SYMBOL(vmalloc_32_user);
 
+#ifdef CONFIG_EXTEND_HUGEPAGE_MAPPING
 /**
  * vmalloc_hugepage - allocate virtually contiguous hugetlb memory
  *	@size:          allocation size
@@ -3298,6 +3311,7 @@ void *vmalloc_hugepage_user(unsigned long size)
 				    __builtin_return_address(0));
 }
 EXPORT_SYMBOL(vmalloc_hugepage_user);
+#endif
 
 /*
  * small helper routine , copy contents to buf from addr.
@@ -3620,6 +3634,7 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
 }
 EXPORT_SYMBOL(remap_vmalloc_range);
 
+#ifdef CONFIG_EXTEND_HUGEPAGE_MAPPING
 /**
  *	remap_vmalloc_hugepage_range_partial - map vmalloc hugepages
  *	to userspace
@@ -3706,6 +3721,7 @@ int remap_vmalloc_hugepage_range(struct vm_area_struct *vma, void *addr,
 						    vma->vm_end - vma->vm_start);
 }
 EXPORT_SYMBOL(remap_vmalloc_hugepage_range);
+#endif
 
 void free_vm_area(struct vm_struct *area)
 {