Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:

 - Support for running Linux in a protected VM under the Arm
   Confidential Compute Architecture (CCA)

 - Guarded Control Stack user-space support. Current patches follow the
   x86 ABI of implicitly creating a shadow stack on clone(). Subsequent
   patches (already on the list) will add support for clone3() allowing
   finer-grained control of the shadow stack size and placement from
   libc

 - AT_HWCAP3 support (not running out of HWCAP2 bits yet but we are
   getting close with the upcoming dpISA support)

 - Other arch features:

     - In-kernel use of the memcpy instructions, FEAT_MOPS (previously
       only exposed to user; uaccess support not merged yet)

     - MTE: hugetlbfs support and the corresponding kselftests

     - Optimise CRC32 using the PMULL instructions

     - Support for FEAT_HAFT enabling ARCH_HAS_NONLEAF_PMD_YOUNG

     - Optimise the kernel TLB flushing to use the range operations

     - POE/pkey (permission overlays): further cleanups after bringing
       the signal handler in line with the x86 behaviour for 6.12

 - arm64 perf updates:

     - Support for the NXP i.MX91 PMU in the existing IMX driver

     - Support for Ampere SoCs in the Designware PCIe PMU driver

     - Support for Marvell's 'PEM' PCIe PMU present in the 'Odyssey' SoC

     - Support for Samsung's 'Mongoose' CPU PMU

     - Support for PMUv3.9 finer-grained userspace counter access
       control

     - Switch back to platform_driver::remove() now that it returns
       'void'

     - Add some missing events for the CXL PMU driver

 - Miscellaneous arm64 fixes/cleanups:

     - Page table accessors cleanup: type updates, drop unused macros,
       reorganise arch_make_huge_pte() and clean up pte_mkcont(), sanity
       check addresses before runtime P4D/PUD folding

     - Command line override for ID_AA64MMFR0_EL1.ECV (advertising the
       FEAT_ECV for the generic timers) allowing Linux to boot with
       firmware deployments that don't set SCTLR_EL3.ECVEn

     - ACPI/arm64: tighten the check for the array of platform timer
       structures and adjust the error handling procedure in
       gtdt_parse_timer_block()

     - Optimise the cache flush for the uprobes xol slot (skip if no
       change) and other uprobes/kprobes cleanups

     - Fix the context switching of tpidrro_el0 when kpti is enabled

     - Dynamic shadow call stack fixes

     - Sysreg updates

     - Various arm64 kselftest improvements

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (168 commits)
  arm64: tls: Fix context-switching of tpidrro_el0 when kpti is enabled
  kselftest/arm64: Try harder to generate different keys during PAC tests
  kselftest/arm64: Don't leak pipe fds in pac.exec_sign_all()
  arm64/ptrace: Clarify documentation of VL configuration via ptrace
  kselftest/arm64: Corrupt P0 in the irritator when testing SSVE
  acpi/arm64: remove unnecessary cast
  arm64/mm: Change protval as 'pteval_t' in map_range()
  kselftest/arm64: Fix missing printf() argument in gcs/gcs-stress.c
  kselftest/arm64: Add FPMR coverage to fp-ptrace
  kselftest/arm64: Expand the set of ZA writes fp-ptrace does
  kselftets/arm64: Use flag bits for features in fp-ptrace assembler code
  kselftest/arm64: Enable build of PAC tests with LLVM=1
  kselftest/arm64: Check that SVCR is 0 in signal handlers
  selftests/mm: Fix unused function warning for aarch64_write_signal_pkey()
  kselftest/arm64: Fix printf() compiler warnings in the arm64 syscall-abi.c tests
  kselftest/arm64: Fix printf() warning in the arm64 MTE prctl() test
  kselftest/arm64: Fix printf() compiler warnings in the arm64 fp tests
  kselftest/arm64: Fix build with stricter assemblers
  arm64/scs: Drop unused prototype __pi_scs_patch_vmlinux()
  arm64/scs: Deal with 64-bit relative offsets in FDE frames
  ...

35 files changed, 759 insertions, 55 deletions

diff --git a/drivers/acpi/arm64/gtdt.c b/drivers/acpi/arm64/gtdt.c
index c0e77c1c8e09..3561553eff8b 100644
--- a/drivers/acpi/arm64/gtdt.c
+++ b/drivers/acpi/arm64/gtdt.c
@@ -36,19 +36,25 @@ struct acpi_gtdt_descriptor {
 
 static struct acpi_gtdt_descriptor acpi_gtdt_desc __initdata;
 
-static inline __init void *next_platform_timer(void *platform_timer)
+static __init bool platform_timer_valid(void *platform_timer)
 {
 	struct acpi_gtdt_header *gh = platform_timer;
 
-	platform_timer += gh->length;
-	if (platform_timer < acpi_gtdt_desc.gtdt_end)
-		return platform_timer;
+	return (platform_timer >= (void *)(acpi_gtdt_desc.gtdt + 1) &&
+		platform_timer < acpi_gtdt_desc.gtdt_end &&
+		gh->length != 0 &&
+		platform_timer + gh->length <= acpi_gtdt_desc.gtdt_end);
+}
+
+static __init void *next_platform_timer(void *platform_timer)
+{
+	struct acpi_gtdt_header *gh = platform_timer;
 
-	return NULL;
+	return platform_timer + gh->length;
 }
 
 #define for_each_platform_timer(_g)				\
-	for (_g = acpi_gtdt_desc.platform_timer; _g;	\
+	for (_g = acpi_gtdt_desc.platform_timer; platform_timer_valid(_g);\
 	     _g = next_platform_timer(_g))
 
 static inline bool is_timer_block(void *platform_timer)
@@ -157,6 +163,7 @@ int __init acpi_gtdt_init(struct acpi_table_header *table,
 {
 	void *platform_timer;
 	struct acpi_table_gtdt *gtdt;
+	int cnt = 0;
 
 	gtdt = container_of(table, struct acpi_table_gtdt, header);
 	acpi_gtdt_desc.gtdt = gtdt;
@@ -176,12 +183,16 @@ int __init acpi_gtdt_init(struct acpi_table_header *table,
 		return 0;
 	}
 
-	platform_timer = (void *)gtdt + gtdt->platform_timer_offset;
-	if (platform_timer < (void *)table + sizeof(struct acpi_table_gtdt)) {
+	acpi_gtdt_desc.platform_timer = (void *)gtdt + gtdt->platform_timer_offset;
+	for_each_platform_timer(platform_timer)
+		cnt++;
+
+	if (cnt != gtdt->platform_timer_count) {
+		acpi_gtdt_desc.platform_timer = NULL;
 		pr_err(FW_BUG "invalid timer data.\n");
 		return -EINVAL;
 	}
-	acpi_gtdt_desc.platform_timer = platform_timer;
+
 	if (platform_timer_count)
 		*platform_timer_count = gtdt->platform_timer_count;
 
@@ -283,7 +294,7 @@ error:
 		if (frame->virt_irq > 0)
 			acpi_unregister_gsi(gtdt_frame->virtual_timer_interrupt);
 		frame->virt_irq = 0;
-	} while (i-- >= 0 && gtdt_frame--);
+	} while (i-- > 0 && gtdt_frame--);
 
 	return -EINVAL;
 }
@@ -352,7 +363,7 @@ static int __init gtdt_import_sbsa_gwdt(struct acpi_gtdt_watchdog *wd,
 	}
 
 	irq = map_gt_gsi(wd->timer_interrupt, wd->timer_flags);
-	res[2] = (struct resource)DEFINE_RES_IRQ(irq);
+	res[2] = DEFINE_RES_IRQ(irq);
 	if (irq <= 0) {
 		pr_warn("failed to map the Watchdog interrupt.\n");
 		nr_res--;
diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
index bab8ba64162f..4e268de351c4 100644
--- a/drivers/perf/Kconfig
+++ b/drivers/perf/Kconfig
@@ -284,4 +284,11 @@ config CXL_PMU
 
 	  If unsure say 'm'.
 
+config MARVELL_PEM_PMU
+	tristate "MARVELL PEM PMU Support"
+	depends on ARCH_THUNDER || (COMPILE_TEST && 64BIT)
+	help
+	  Enable support for PCIe Interface performance monitoring
+	  on Marvell platform.
+
 endmenu
diff --git a/drivers/perf/Makefile b/drivers/perf/Makefile
index 8268f38e42c5..de71d2574857 100644
--- a/drivers/perf/Makefile
+++ b/drivers/perf/Makefile
@@ -26,6 +26,7 @@ obj-$(CONFIG_ARM_SPE_PMU) += arm_spe_pmu.o
 obj-$(CONFIG_ARM_DMC620_PMU) += arm_dmc620_pmu.o
 obj-$(CONFIG_MARVELL_CN10K_TAD_PMU) += marvell_cn10k_tad_pmu.o
 obj-$(CONFIG_MARVELL_CN10K_DDR_PMU) += marvell_cn10k_ddr_pmu.o
+obj-$(CONFIG_MARVELL_PEM_PMU) += marvell_pem_pmu.o
 obj-$(CONFIG_APPLE_M1_CPU_PMU) += apple_m1_cpu_pmu.o
 obj-$(CONFIG_ALIBABA_UNCORE_DRW_PMU) += alibaba_uncore_drw_pmu.o
 obj-$(CONFIG_DWC_PCIE_PMU) += dwc_pcie_pmu.o
diff --git a/drivers/perf/alibaba_uncore_drw_pmu.c b/drivers/perf/alibaba_uncore_drw_pmu.c
index c6ff1bc7d336..99a0ef9817e0 100644
--- a/drivers/perf/alibaba_uncore_drw_pmu.c
+++ b/drivers/perf/alibaba_uncore_drw_pmu.c
@@ -782,7 +782,7 @@ static struct platform_driver ali_drw_pmu_driver = {
 		   .acpi_match_table = ali_drw_acpi_match,
 		   },
 	.probe = ali_drw_pmu_probe,
-	.remove_new = ali_drw_pmu_remove,
+	.remove = ali_drw_pmu_remove,
 };
 
 static int __init ali_drw_pmu_init(void)
diff --git a/drivers/perf/amlogic/meson_g12_ddr_pmu.c b/drivers/perf/amlogic/meson_g12_ddr_pmu.c
index 99cc791892bc..f33e9a456e85 100644
--- a/drivers/perf/amlogic/meson_g12_ddr_pmu.c
+++ b/drivers/perf/amlogic/meson_g12_ddr_pmu.c
@@ -379,7 +379,7 @@ MODULE_DEVICE_TABLE(of, meson_ddr_pmu_dt_match);
 
 static struct platform_driver g12_ddr_pmu_driver = {
 	.probe = g12_ddr_pmu_probe,
-	.remove_new = g12_ddr_pmu_remove,
+	.remove = g12_ddr_pmu_remove,
 
 	.driver = {
 		.name = "meson-g12-ddr-pmu",
diff --git a/drivers/perf/arm-cci.c b/drivers/perf/arm-cci.c
index c76bac668dea..1cc3214d6b6d 100644
--- a/drivers/perf/arm-cci.c
+++ b/drivers/perf/arm-cci.c
@@ -1705,7 +1705,7 @@ static struct platform_driver cci_pmu_driver = {
 		   .suppress_bind_attrs = true,
 		  },
 	.probe = cci_pmu_probe,
-	.remove_new = cci_pmu_remove,
+	.remove = cci_pmu_remove,
 };
 
 module_platform_driver(cci_pmu_driver);
diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c
index 5c66b9278862..d5fcea3d4328 100644
--- a/drivers/perf/arm-ccn.c
+++ b/drivers/perf/arm-ccn.c
@@ -1529,7 +1529,7 @@ static struct platform_driver arm_ccn_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = arm_ccn_probe,
-	.remove_new = arm_ccn_remove,
+	.remove = arm_ccn_remove,
 };
 
 static int __init arm_ccn_init(void)
diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c
index 397a46410f7c..49bd811c6fd6 100644
--- a/drivers/perf/arm-cmn.c
+++ b/drivers/perf/arm-cmn.c
@@ -2662,7 +2662,7 @@ static struct platform_driver arm_cmn_driver = {
 		.acpi_match_table = ACPI_PTR(arm_cmn_acpi_match),
 	},
 	.probe = arm_cmn_probe,
-	.remove_new = arm_cmn_remove,
+	.remove = arm_cmn_remove,
 };
 
 static int __init arm_cmn_init(void)
diff --git a/drivers/perf/arm_cspmu/arm_cspmu.c b/drivers/perf/arm_cspmu/arm_cspmu.c
index 2158a5975c90..81e8b97e9353 100644
--- a/drivers/perf/arm_cspmu/arm_cspmu.c
+++ b/drivers/perf/arm_cspmu/arm_cspmu.c
@@ -1282,7 +1282,7 @@ static struct platform_driver arm_cspmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = arm_cspmu_device_probe,
-	.remove_new = arm_cspmu_device_remove,
+	.remove = arm_cspmu_device_remove,
 	.id_table = arm_cspmu_id,
 };
 
diff --git a/drivers/perf/arm_dmc620_pmu.c b/drivers/perf/arm_dmc620_pmu.c
index 7e5f1d4fca0f..619cf937602f 100644
--- a/drivers/perf/arm_dmc620_pmu.c
+++ b/drivers/perf/arm_dmc620_pmu.c
@@ -750,7 +750,7 @@ static struct platform_driver dmc620_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe	= dmc620_pmu_device_probe,
-	.remove_new = dmc620_pmu_device_remove,
+	.remove	= dmc620_pmu_device_remove,
 };
 
 static int __init dmc620_pmu_init(void)
diff --git a/drivers/perf/arm_dsu_pmu.c b/drivers/perf/arm_dsu_pmu.c
index f2bd25a3470a..cb4fb59fe04b 100644
--- a/drivers/perf/arm_dsu_pmu.c
+++ b/drivers/perf/arm_dsu_pmu.c
@@ -787,7 +787,7 @@ static struct platform_driver dsu_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = dsu_pmu_device_probe,
-	.remove_new = dsu_pmu_device_remove,
+	.remove = dsu_pmu_device_remove,
 };
 
 static int dsu_pmu_cpu_online(unsigned int cpu, struct hlist_node *node)
diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index 0afe02f879b4..b5cc11abc962 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -770,18 +770,27 @@ static void armv8pmu_enable_user_access(struct arm_pmu *cpu_pmu)
 	int i;
 	struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events);
 
-	/* Clear any unused counters to avoid leaking their contents */
-	for_each_andnot_bit(i, cpu_pmu->cntr_mask, cpuc->used_mask,
-			    ARMPMU_MAX_HWEVENTS) {
-		if (i == ARMV8_PMU_CYCLE_IDX)
-			write_pmccntr(0);
-		else if (i == ARMV8_PMU_INSTR_IDX)
-			write_pmicntr(0);
-		else
-			armv8pmu_write_evcntr(i, 0);
+	if (is_pmuv3p9(cpu_pmu->pmuver)) {
+		u64 mask = 0;
+		for_each_set_bit(i, cpuc->used_mask, ARMPMU_MAX_HWEVENTS) {
+			if (armv8pmu_event_has_user_read(cpuc->events[i]))
+				mask |= BIT(i);
+		}
+		write_pmuacr(mask);
+	} else {
+		/* Clear any unused counters to avoid leaking their contents */
+		for_each_andnot_bit(i, cpu_pmu->cntr_mask, cpuc->used_mask,
+				    ARMPMU_MAX_HWEVENTS) {
+			if (i == ARMV8_PMU_CYCLE_IDX)
+				write_pmccntr(0);
+			else if (i == ARMV8_PMU_INSTR_IDX)
+				write_pmicntr(0);
+			else
+				armv8pmu_write_evcntr(i, 0);
+		}
 	}
 
-	update_pmuserenr(ARMV8_PMU_USERENR_ER | ARMV8_PMU_USERENR_CR);
+	update_pmuserenr(ARMV8_PMU_USERENR_ER | ARMV8_PMU_USERENR_CR | ARMV8_PMU_USERENR_UEN);
 }
 
 static void armv8pmu_enable_event(struct perf_event *event)
@@ -1364,6 +1373,8 @@ PMUV3_INIT_SIMPLE(armv8_neoverse_v3ae)
 PMUV3_INIT_SIMPLE(armv8_nvidia_carmel)
 PMUV3_INIT_SIMPLE(armv8_nvidia_denver)
 
+PMUV3_INIT_SIMPLE(armv8_samsung_mongoose)
+
 PMUV3_INIT_MAP_EVENT(armv8_cortex_a35, armv8_a53_map_event)
 PMUV3_INIT_MAP_EVENT(armv8_cortex_a53, armv8_a53_map_event)
 PMUV3_INIT_MAP_EVENT(armv8_cortex_a57, armv8_a57_map_event)
@@ -1409,6 +1420,7 @@ static const struct of_device_id armv8_pmu_of_device_ids[] = {
 	{.compatible = "brcm,vulcan-pmu",	.data = armv8_brcm_vulcan_pmu_init},
 	{.compatible = "nvidia,carmel-pmu",	.data = armv8_nvidia_carmel_pmu_init},
 	{.compatible = "nvidia,denver-pmu",	.data = armv8_nvidia_denver_pmu_init},
+	{.compatible = "samsung,mongoose-pmu",	.data = armv8_samsung_mongoose_pmu_init},
 	{},
 };
 
diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c
index d5fa92ba8373..b1510f660c7a 100644
--- a/drivers/perf/arm_smmuv3_pmu.c
+++ b/drivers/perf/arm_smmuv3_pmu.c
@@ -996,7 +996,7 @@ static struct platform_driver smmu_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = smmu_pmu_probe,
-	.remove_new = smmu_pmu_remove,
+	.remove = smmu_pmu_remove,
 	.shutdown = smmu_pmu_shutdown,
 };
 
diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
index 3569050f9cf3..fd5b78732603 100644
--- a/drivers/perf/arm_spe_pmu.c
+++ b/drivers/perf/arm_spe_pmu.c
@@ -1280,7 +1280,7 @@ static struct platform_driver arm_spe_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe	= arm_spe_pmu_device_probe,
-	.remove_new = arm_spe_pmu_device_remove,
+	.remove = arm_spe_pmu_device_remove,
 };
 
 static int __init arm_spe_pmu_init(void)
diff --git a/drivers/perf/cxl_pmu.c b/drivers/perf/cxl_pmu.c
index 43d68b69e630..bee4b5b52ec6 100644
--- a/drivers/perf/cxl_pmu.c
+++ b/drivers/perf/cxl_pmu.c
@@ -354,7 +354,7 @@ static struct attribute *cxl_pmu_event_attrs[] = {
 	CXL_PMU_EVENT_CXL_ATTR(d2h_req_wowrinvf,		CXL_PMU_GID_D2H_REQ, BIT(13)),
 	CXL_PMU_EVENT_CXL_ATTR(d2h_req_wrinv,			CXL_PMU_GID_D2H_REQ, BIT(14)),
 	CXL_PMU_EVENT_CXL_ATTR(d2h_req_cacheflushed,		CXL_PMU_GID_D2H_REQ, BIT(16)),
-	/* CXL rev 3.0 Table 3-20 - D2H Repsonse Encodings */
+	/* CXL rev 3.0 Table 3-20 - D2H Response Encodings */
 	CXL_PMU_EVENT_CXL_ATTR(d2h_rsp_rspihiti,		CXL_PMU_GID_D2H_RSP, BIT(4)),
 	CXL_PMU_EVENT_CXL_ATTR(d2h_rsp_rspvhitv,		CXL_PMU_GID_D2H_RSP, BIT(6)),
 	CXL_PMU_EVENT_CXL_ATTR(d2h_rsp_rspihitse,		CXL_PMU_GID_D2H_RSP, BIT(5)),
@@ -377,12 +377,14 @@ static struct attribute *cxl_pmu_event_attrs[] = {
 	/* CXL rev 3.0 Table 13-5 directly lists these */
 	CXL_PMU_EVENT_CXL_ATTR(cachedata_d2h_data,		CXL_PMU_GID_CACHE_DATA, BIT(0)),
 	CXL_PMU_EVENT_CXL_ATTR(cachedata_h2d_data,		CXL_PMU_GID_CACHE_DATA, BIT(1)),
-	/* CXL rev 3.0 Table 3-29 M2S Req Memory Opcodes */
+	/* CXL rev 3.1 Table 3-35 M2S Req Memory Opcodes */
 	CXL_PMU_EVENT_CXL_ATTR(m2s_req_meminv,			CXL_PMU_GID_M2S_REQ, BIT(0)),
 	CXL_PMU_EVENT_CXL_ATTR(m2s_req_memrd,			CXL_PMU_GID_M2S_REQ, BIT(1)),
 	CXL_PMU_EVENT_CXL_ATTR(m2s_req_memrddata,		CXL_PMU_GID_M2S_REQ, BIT(2)),
 	CXL_PMU_EVENT_CXL_ATTR(m2s_req_memrdfwd,		CXL_PMU_GID_M2S_REQ, BIT(3)),
 	CXL_PMU_EVENT_CXL_ATTR(m2s_req_memwrfwd,		CXL_PMU_GID_M2S_REQ, BIT(4)),
+	CXL_PMU_EVENT_CXL_ATTR(m2s_req_memrdtee,		CXL_PMU_GID_M2S_REQ, BIT(5)),
+	CXL_PMU_EVENT_CXL_ATTR(m2s_req_memrddatatee,		CXL_PMU_GID_M2S_REQ, BIT(6)),
 	CXL_PMU_EVENT_CXL_ATTR(m2s_req_memspecrd,		CXL_PMU_GID_M2S_REQ, BIT(8)),
 	CXL_PMU_EVENT_CXL_ATTR(m2s_req_meminvnt,		CXL_PMU_GID_M2S_REQ, BIT(9)),
 	CXL_PMU_EVENT_CXL_ATTR(m2s_req_memcleanevict,		CXL_PMU_GID_M2S_REQ, BIT(10)),
@@ -404,10 +406,11 @@ static struct attribute *cxl_pmu_event_attrs[] = {
 	CXL_PMU_EVENT_CXL_ATTR(s2m_bisnp_curblk,		CXL_PMU_GID_S2M_BISNP, BIT(4)),
 	CXL_PMU_EVENT_CXL_ATTR(s2m_bisnp_datblk,		CXL_PMU_GID_S2M_BISNP, BIT(5)),
 	CXL_PMU_EVENT_CXL_ATTR(s2m_bisnp_invblk,		CXL_PMU_GID_S2M_BISNP, BIT(6)),
-	/* CXL rev 3.0 Table 3-43 S2M NDR Opcopdes */
+	/* CXL rev 3.1 Table 3-50 S2M NDR Opcopdes */
 	CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_cmp,			CXL_PMU_GID_S2M_NDR, BIT(0)),
 	CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_cmps,			CXL_PMU_GID_S2M_NDR, BIT(1)),
 	CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_cmpe,			CXL_PMU_GID_S2M_NDR, BIT(2)),
+	CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_cmpm,			CXL_PMU_GID_S2M_NDR, BIT(3)),
 	CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_biconflictack,		CXL_PMU_GID_S2M_NDR, BIT(4)),
 	/* CXL rev 3.0 Table 3-46 S2M DRS opcodes */
 	CXL_PMU_EVENT_CXL_ATTR(s2m_drs_memdata,			CXL_PMU_GID_S2M_DRS, BIT(0)),
diff --git a/drivers/perf/dwc_pcie_pmu.c b/drivers/perf/dwc_pcie_pmu.c
index 4ca50f9b6dfe..9cbea9675e21 100644
--- a/drivers/perf/dwc_pcie_pmu.c
+++ b/drivers/perf/dwc_pcie_pmu.c
@@ -82,7 +82,6 @@ struct dwc_pcie_pmu {
 	u16			ras_des_offset;
 	u32			nr_lanes;
 
-	struct list_head	pmu_node;
 	struct hlist_node	cpuhp_node;
 	struct perf_event	*event[DWC_PCIE_EVENT_TYPE_MAX];
 	int			on_cpu;
@@ -107,6 +106,7 @@ struct dwc_pcie_vendor_id {
 
 static const struct dwc_pcie_vendor_id dwc_pcie_vendor_ids[] = {
 	{.vendor_id = PCI_VENDOR_ID_ALIBABA },
+	{.vendor_id = PCI_VENDOR_ID_AMPERE },
 	{.vendor_id = PCI_VENDOR_ID_QCOM },
 	{} /* terminator */
 };
@@ -203,10 +203,10 @@ static struct attribute *dwc_pcie_pmu_time_event_attrs[] = {
 	DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(L1_AUX, 0x09),
 
 	/* Group #1 */
-	DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(Tx_PCIe_TLP_Data_Payload, 0x20),
-	DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(Rx_PCIe_TLP_Data_Payload, 0x21),
-	DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(Tx_CCIX_TLP_Data_Payload, 0x22),
-	DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(Rx_CCIX_TLP_Data_Payload, 0x23),
+	DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(tx_pcie_tlp_data_payload, 0x20),
+	DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(rx_pcie_tlp_data_payload, 0x21),
+	DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(tx_ccix_tlp_data_payload, 0x22),
+	DWC_PCIE_PMU_TIME_BASE_EVENT_ATTR(rx_ccix_tlp_data_payload, 0x23),
 
 	/*
 	 * Leave it to the user to specify the lane ID to avoid generating
@@ -216,9 +216,9 @@ static struct attribute *dwc_pcie_pmu_time_event_attrs[] = {
 	DWC_PCIE_PMU_LANE_EVENT_ATTR(tx_update_fc_dllp, 0x601),
 	DWC_PCIE_PMU_LANE_EVENT_ATTR(rx_ack_dllp, 0x602),
 	DWC_PCIE_PMU_LANE_EVENT_ATTR(rx_update_fc_dllp, 0x603),
-	DWC_PCIE_PMU_LANE_EVENT_ATTR(rx_nulified_tlp, 0x604),
-	DWC_PCIE_PMU_LANE_EVENT_ATTR(tx_nulified_tlp, 0x605),
-	DWC_PCIE_PMU_LANE_EVENT_ATTR(rx_duplicate_tl, 0x606),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(rx_nullified_tlp, 0x604),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(tx_nullified_tlp, 0x605),
+	DWC_PCIE_PMU_LANE_EVENT_ATTR(rx_duplicate_tlp, 0x606),
 	DWC_PCIE_PMU_LANE_EVENT_ATTR(tx_memory_write, 0x700),
 	DWC_PCIE_PMU_LANE_EVENT_ATTR(tx_memory_read, 0x701),
 	DWC_PCIE_PMU_LANE_EVENT_ATTR(tx_configuration_write, 0x702),
diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c
index 746b92330ca7..b989ffa95d69 100644
--- a/drivers/perf/fsl_imx8_ddr_perf.c
+++ b/drivers/perf/fsl_imx8_ddr_perf.c
@@ -846,7 +846,7 @@ static struct platform_driver imx_ddr_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe          = ddr_perf_probe,
-	.remove_new     = ddr_perf_remove,
+	.remove         = ddr_perf_remove,
 };
 
 module_platform_driver(imx_ddr_pmu_driver);
diff --git a/drivers/perf/fsl_imx9_ddr_perf.c b/drivers/perf/fsl_imx9_ddr_perf.c
index 69f920b1caf2..3c856d9a4e97 100644
--- a/drivers/perf/fsl_imx9_ddr_perf.c
+++ b/drivers/perf/fsl_imx9_ddr_perf.c
@@ -81,6 +81,10 @@ struct ddr_pmu {
 	int id;
 };
 
+static const struct imx_ddr_devtype_data imx91_devtype_data = {
+	.identifier = "imx91",
+};
+
 static const struct imx_ddr_devtype_data imx93_devtype_data = {
 	.identifier = "imx93",
 };
@@ -100,6 +104,7 @@ static inline bool is_imx95(struct ddr_pmu *pmu)
 }
 
 static const struct of_device_id imx_ddr_pmu_dt_ids[] = {
+	{ .compatible = "fsl,imx91-ddr-pmu", .data = &imx91_devtype_data },
 	{ .compatible = "fsl,imx93-ddr-pmu", .data = &imx93_devtype_data },
 	{ .compatible = "fsl,imx95-ddr-pmu", .data = &imx95_devtype_data },
 	{ /* sentinel */ }
@@ -848,7 +853,7 @@ static struct platform_driver imx_ddr_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe          = ddr_perf_probe,
-	.remove_new     = ddr_perf_remove,
+	.remove         = ddr_perf_remove,
 };
 module_platform_driver(imx_ddr_pmu_driver);
 
diff --git a/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c b/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c
index 0e923f94fa5b..3f3fb1de11f5 100644
--- a/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c
@@ -358,7 +358,7 @@ static struct platform_driver hisi_cpa_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = hisi_cpa_pmu_probe,
-	.remove_new = hisi_cpa_pmu_remove,
+	.remove = hisi_cpa_pmu_remove,
 };
 
 static int __init hisi_cpa_pmu_module_init(void)
diff --git a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
index b804e3738113..a6ebf2ec99d3 100644
--- a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
@@ -547,7 +547,7 @@ static struct platform_driver hisi_ddrc_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = hisi_ddrc_pmu_probe,
-	.remove_new = hisi_ddrc_pmu_remove,
+	.remove = hisi_ddrc_pmu_remove,
 };
 
 static int __init hisi_ddrc_pmu_module_init(void)
diff --git a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
index 21e69b1cdd4d..32624872596f 100644
--- a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c
@@ -550,7 +550,7 @@ static struct platform_driver hisi_hha_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = hisi_hha_pmu_probe,
-	.remove_new = hisi_hha_pmu_remove,
+	.remove = hisi_hha_pmu_remove,
 };
 
 static int __init hisi_hha_pmu_module_init(void)
diff --git a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
index 51ba76871097..c235b46ce873 100644
--- a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c
@@ -584,7 +584,7 @@ static struct platform_driver hisi_l3c_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = hisi_l3c_pmu_probe,
-	.remove_new = hisi_l3c_pmu_remove,
+	.remove = hisi_l3c_pmu_remove,
 };
 
 static int __init hisi_l3c_pmu_module_init(void)
diff --git a/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c
index 3cdb35c741f9..c0f5d7c73e06 100644
--- a/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c
@@ -538,7 +538,7 @@ static struct platform_driver hisi_pa_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = hisi_pa_pmu_probe,
-	.remove_new = hisi_pa_pmu_remove,
+	.remove = hisi_pa_pmu_remove,
 };
 
 static int __init hisi_pa_pmu_module_init(void)
diff --git a/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c
index 765bbd61db26..c5f4764ee888 100644
--- a/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c
@@ -476,7 +476,7 @@ static struct platform_driver hisi_sllc_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = hisi_sllc_pmu_probe,
-	.remove_new = hisi_sllc_pmu_remove,
+	.remove = hisi_sllc_pmu_remove,
 };
 
 static int __init hisi_sllc_pmu_module_init(void)
diff --git a/drivers/perf/marvell_cn10k_ddr_pmu.c b/drivers/perf/marvell_cn10k_ddr_pmu.c
index 94f1ebcd2a27..8860d9f687ae 100644
--- a/drivers/perf/marvell_cn10k_ddr_pmu.c
+++ b/drivers/perf/marvell_cn10k_ddr_pmu.c
@@ -732,7 +732,7 @@ static struct platform_driver cn10k_ddr_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe		= cn10k_ddr_perf_probe,
-	.remove_new	= cn10k_ddr_perf_remove,
+	.remove		= cn10k_ddr_perf_remove,
 };
 
 static int __init cn10k_ddr_pmu_init(void)
diff --git a/drivers/perf/marvell_cn10k_tad_pmu.c b/drivers/perf/marvell_cn10k_tad_pmu.c
index 9e635f355470..cda55ee35eee 100644
--- a/drivers/perf/marvell_cn10k_tad_pmu.c
+++ b/drivers/perf/marvell_cn10k_tad_pmu.c
@@ -383,7 +383,7 @@ static struct platform_driver tad_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe          = tad_pmu_probe,
-	.remove_new     = tad_pmu_remove,
+	.remove         = tad_pmu_remove,
 };
 
 static int tad_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
diff --git a/drivers/perf/marvell_pem_pmu.c b/drivers/perf/marvell_pem_pmu.c
new file mode 100644
index 000000000000..29fbcd1848e4
--- /dev/null
+++ b/drivers/perf/marvell_pem_pmu.c
@@ -0,0 +1,425 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Marvell PEM(PCIe RC) Performance Monitor Driver
+ *
+ * Copyright (C) 2024 Marvell.
+ */
+
+#include <linux/acpi.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/perf_event.h>
+#include <linux/platform_device.h>
+
+/*
+ * Each of these events maps to a free running 64 bit counter
+ * with no event control, but can be reset.
+ */
+enum pem_events {
+	IB_TLP_NPR,
+	IB_TLP_PR,
+	IB_TLP_CPL,
+	IB_TLP_DWORDS_NPR,
+	IB_TLP_DWORDS_PR,
+	IB_TLP_DWORDS_CPL,
+	IB_INFLIGHT,
+	IB_READS,
+	IB_REQ_NO_RO_NCB,
+	IB_REQ_NO_RO_EBUS,
+	OB_TLP_NPR,
+	OB_TLP_PR,
+	OB_TLP_CPL,
+	OB_TLP_DWORDS_NPR,
+	OB_TLP_DWORDS_PR,
+	OB_TLP_DWORDS_CPL,
+	OB_INFLIGHT,
+	OB_READS,
+	OB_MERGES_NPR,
+	OB_MERGES_PR,
+	OB_MERGES_CPL,
+	ATS_TRANS,
+	ATS_TRANS_LATENCY,
+	ATS_PRI,
+	ATS_PRI_LATENCY,
+	ATS_INV,
+	ATS_INV_LATENCY,
+	PEM_EVENTIDS_MAX
+};
+
+static u64 eventid_to_offset_table[] = {
+	[IB_TLP_NPR]	     = 0x0,
+	[IB_TLP_PR]	     = 0x8,
+	[IB_TLP_CPL]	     = 0x10,
+	[IB_TLP_DWORDS_NPR]  = 0x100,
+	[IB_TLP_DWORDS_PR]   = 0x108,
+	[IB_TLP_DWORDS_CPL]  = 0x110,
+	[IB_INFLIGHT]	     = 0x200,
+	[IB_READS]	     = 0x300,
+	[IB_REQ_NO_RO_NCB]   = 0x400,
+	[IB_REQ_NO_RO_EBUS]  = 0x408,
+	[OB_TLP_NPR]         = 0x500,
+	[OB_TLP_PR]          = 0x508,
+	[OB_TLP_CPL]         = 0x510,
+	[OB_TLP_DWORDS_NPR]  = 0x600,
+	[OB_TLP_DWORDS_PR]   = 0x608,
+	[OB_TLP_DWORDS_CPL]  = 0x610,
+	[OB_INFLIGHT]        = 0x700,
+	[OB_READS]	     = 0x800,
+	[OB_MERGES_NPR]      = 0x900,
+	[OB_MERGES_PR]       = 0x908,
+	[OB_MERGES_CPL]      = 0x910,
+	[ATS_TRANS]          = 0x2D18,
+	[ATS_TRANS_LATENCY]  = 0x2D20,
+	[ATS_PRI]            = 0x2D28,
+	[ATS_PRI_LATENCY]    = 0x2D30,
+	[ATS_INV]            = 0x2D38,
+	[ATS_INV_LATENCY]    = 0x2D40,
+};
+
+struct pem_pmu {
+	struct pmu pmu;
+	void __iomem *base;
+	unsigned int cpu;
+	struct	device *dev;
+	struct hlist_node node;
+};
+
+#define to_pem_pmu(p)	container_of(p, struct pem_pmu, pmu)
+
+static int eventid_to_offset(int eventid)
+{
+	return eventid_to_offset_table[eventid];
+}
+
+/* Events */
+static ssize_t pem_pmu_event_show(struct device *dev,
+				  struct device_attribute *attr,
+				  char *page)
+{
+	struct perf_pmu_events_attr *pmu_attr;
+
+	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
+	return sysfs_emit(page, "event=0x%02llx\n", pmu_attr->id);
+}
+
+#define PEM_EVENT_ATTR(_name, _id)					\
+	(&((struct perf_pmu_events_attr[]) {				\
+	{ .attr = __ATTR(_name, 0444, pem_pmu_event_show, NULL),	\
+		.id = _id, }						\
+	})[0].attr.attr)
+
+static struct attribute *pem_perf_events_attrs[] = {
+	PEM_EVENT_ATTR(ib_tlp_npr, IB_TLP_NPR),
+	PEM_EVENT_ATTR(ib_tlp_pr, IB_TLP_PR),
+	PEM_EVENT_ATTR(ib_tlp_cpl_partid, IB_TLP_CPL),
+	PEM_EVENT_ATTR(ib_tlp_dwords_npr, IB_TLP_DWORDS_NPR),
+	PEM_EVENT_ATTR(ib_tlp_dwords_pr, IB_TLP_DWORDS_PR),
+	PEM_EVENT_ATTR(ib_tlp_dwords_cpl_partid, IB_TLP_DWORDS_CPL),
+	PEM_EVENT_ATTR(ib_inflight, IB_INFLIGHT),
+	PEM_EVENT_ATTR(ib_reads, IB_READS),
+	PEM_EVENT_ATTR(ib_req_no_ro_ncb, IB_REQ_NO_RO_NCB),
+	PEM_EVENT_ATTR(ib_req_no_ro_ebus, IB_REQ_NO_RO_EBUS),
+	PEM_EVENT_ATTR(ob_tlp_npr_partid, OB_TLP_NPR),
+	PEM_EVENT_ATTR(ob_tlp_pr_partid, OB_TLP_PR),
+	PEM_EVENT_ATTR(ob_tlp_cpl_partid, OB_TLP_CPL),
+	PEM_EVENT_ATTR(ob_tlp_dwords_npr_partid, OB_TLP_DWORDS_NPR),
+	PEM_EVENT_ATTR(ob_tlp_dwords_pr_partid, OB_TLP_DWORDS_PR),
+	PEM_EVENT_ATTR(ob_tlp_dwords_cpl_partid, OB_TLP_DWORDS_CPL),
+	PEM_EVENT_ATTR(ob_inflight_partid, OB_INFLIGHT),
+	PEM_EVENT_ATTR(ob_reads_partid, OB_READS),
+	PEM_EVENT_ATTR(ob_merges_npr_partid, OB_MERGES_NPR),
+	PEM_EVENT_ATTR(ob_merges_pr_partid, OB_MERGES_PR),
+	PEM_EVENT_ATTR(ob_merges_cpl_partid, OB_MERGES_CPL),
+	PEM_EVENT_ATTR(ats_trans, ATS_TRANS),
+	PEM_EVENT_ATTR(ats_trans_latency, ATS_TRANS_LATENCY),
+	PEM_EVENT_ATTR(ats_pri, ATS_PRI),
+	PEM_EVENT_ATTR(ats_pri_latency, ATS_PRI_LATENCY),
+	PEM_EVENT_ATTR(ats_inv, ATS_INV),
+	PEM_EVENT_ATTR(ats_inv_latency, ATS_INV_LATENCY),
+	NULL
+};
+
+static struct attribute_group pem_perf_events_attr_group = {
+	.name = "events",
+	.attrs = pem_perf_events_attrs,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-5");
+
+static struct attribute *pem_perf_format_attrs[] = {
+	&format_attr_event.attr,
+	NULL
+};
+
+static struct attribute_group pem_perf_format_attr_group = {
+	.name = "format",
+	.attrs = pem_perf_format_attrs,
+};
+
+/* cpumask */
+static ssize_t pem_perf_cpumask_show(struct device *dev,
+				     struct device_attribute *attr,
+				     char *buf)
+{
+	struct pem_pmu *pmu = dev_get_drvdata(dev);
+
+	return cpumap_print_to_pagebuf(true, buf, cpumask_of(pmu->cpu));
+}
+
+static struct device_attribute pem_perf_cpumask_attr =
+	__ATTR(cpumask, 0444, pem_perf_cpumask_show, NULL);
+
+static struct attribute *pem_perf_cpumask_attrs[] = {
+	&pem_perf_cpumask_attr.attr,
+	NULL
+};
+
+static struct attribute_group pem_perf_cpumask_attr_group = {
+	.attrs = pem_perf_cpumask_attrs,
+};
+
+static const struct attribute_group *pem_perf_attr_groups[] = {
+	&pem_perf_events_attr_group,
+	&pem_perf_cpumask_attr_group,
+	&pem_perf_format_attr_group,
+	NULL
+};
+
+static int pem_perf_event_init(struct perf_event *event)
+{
+	struct pem_pmu *pmu = to_pem_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	struct perf_event *sibling;
+
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	if (event->attr.config >= PEM_EVENTIDS_MAX)
+		return -EINVAL;
+
+	if (is_sampling_event(event) ||
+	    event->attach_state & PERF_ATTACH_TASK) {
+		return -EOPNOTSUPP;
+	}
+
+	if (event->cpu < 0)
+		return -EOPNOTSUPP;
+
+	/*  We must NOT create groups containing mixed PMUs */
+	if (event->group_leader->pmu != event->pmu &&
+	    !is_software_event(event->group_leader))
+		return -EINVAL;
+
+	for_each_sibling_event(sibling, event->group_leader) {
+		if (sibling->pmu != event->pmu &&
+		    !is_software_event(sibling))
+			return -EINVAL;
+	}
+	/*
+	 * Set ownership of event to one CPU, same event can not be observed
+	 * on multiple cpus at same time.
+	 */
+	event->cpu = pmu->cpu;
+	hwc->idx = -1;
+	return 0;
+}
+
+static u64 pem_perf_read_counter(struct pem_pmu *pmu,
+				 struct perf_event *event, int eventid)
+{
+	return readq_relaxed(pmu->base + eventid_to_offset(eventid));
+}
+
+static void pem_perf_event_update(struct perf_event *event)
+{
+	struct pem_pmu *pmu = to_pem_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	u64 prev_count, new_count;
+
+	do {
+		prev_count = local64_read(&hwc->prev_count);
+		new_count = pem_perf_read_counter(pmu, event, hwc->idx);
+	} while (local64_xchg(&hwc->prev_count, new_count) != prev_count);
+
+	local64_add((new_count - prev_count), &event->count);
+}
+
+static void pem_perf_event_start(struct perf_event *event, int flags)
+{
+	struct pem_pmu *pmu = to_pem_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	int eventid = hwc->idx;
+
+	/*
+	 * All counters are free-running and associated with
+	 * a fixed event to track in Hardware
+	 */
+	local64_set(&hwc->prev_count,
+		    pem_perf_read_counter(pmu, event, eventid));
+
+	hwc->state = 0;
+}
+
+static int pem_perf_event_add(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	hwc->idx = event->attr.config;
+	if (WARN_ON_ONCE(hwc->idx >= PEM_EVENTIDS_MAX))
+		return -EINVAL;
+	hwc->state |= PERF_HES_STOPPED;
+
+	if (flags & PERF_EF_START)
+		pem_perf_event_start(event, flags);
+
+	return 0;
+}
+
+static void pem_perf_event_stop(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (flags & PERF_EF_UPDATE)
+		pem_perf_event_update(event);
+
+	hwc->state |= PERF_HES_STOPPED;
+}
+
+static void pem_perf_event_del(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	pem_perf_event_stop(event, PERF_EF_UPDATE);
+	hwc->idx = -1;
+}
+
+static int pem_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
+{
+	struct pem_pmu *pmu = hlist_entry_safe(node, struct pem_pmu, node);
+	unsigned int target;
+
+	if (cpu != pmu->cpu)
+		return 0;
+
+	target = cpumask_any_but(cpu_online_mask, cpu);
+	if (target >= nr_cpu_ids)
+		return 0;
+
+	perf_pmu_migrate_context(&pmu->pmu, cpu, target);
+	pmu->cpu = target;
+	return 0;
+}
+
+static int pem_perf_probe(struct platform_device *pdev)
+{
+	struct pem_pmu *pem_pmu;
+	struct resource *res;
+	void __iomem *base;
+	char *name;
+	int ret;
+
+	pem_pmu = devm_kzalloc(&pdev->dev, sizeof(*pem_pmu), GFP_KERNEL);
+	if (!pem_pmu)
+		return -ENOMEM;
+
+	pem_pmu->dev = &pdev->dev;
+	platform_set_drvdata(pdev, pem_pmu);
+
+	base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	pem_pmu->base = base;
+
+	pem_pmu->pmu = (struct pmu) {
+		.module	      = THIS_MODULE,
+		.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
+		.task_ctx_nr = perf_invalid_context,
+		.attr_groups = pem_perf_attr_groups,
+		.event_init  = pem_perf_event_init,
+		.add	     = pem_perf_event_add,
+		.del	     = pem_perf_event_del,
+		.start	     = pem_perf_event_start,
+		.stop	     = pem_perf_event_stop,
+		.read	     = pem_perf_event_update,
+	};
+
+	/* Choose this cpu to collect perf data */
+	pem_pmu->cpu = raw_smp_processor_id();
+
+	name = devm_kasprintf(pem_pmu->dev, GFP_KERNEL, "mrvl_pcie_rc_pmu_%llx",
+			      res->start);
+	if (!name)
+		return -ENOMEM;
+
+	cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_MRVL_PEM_ONLINE,
+					 &pem_pmu->node);
+
+	ret = perf_pmu_register(&pem_pmu->pmu, name, -1);
+	if (ret)
+		goto error;
+
+	return 0;
+error:
+	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_MRVL_PEM_ONLINE,
+					    &pem_pmu->node);
+	return ret;
+}
+
+static void pem_perf_remove(struct platform_device *pdev)
+{
+	struct pem_pmu *pem_pmu = platform_get_drvdata(pdev);
+
+	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_MRVL_PEM_ONLINE,
+					    &pem_pmu->node);
+
+	perf_pmu_unregister(&pem_pmu->pmu);
+}
+
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id pem_pmu_acpi_match[] = {
+	{"MRVL000E", 0},
+	{}
+};
+MODULE_DEVICE_TABLE(acpi, pem_pmu_acpi_match);
+#endif
+
+static struct platform_driver pem_pmu_driver = {
+	.driver	= {
+		.name   = "pem-pmu",
+		.acpi_match_table = ACPI_PTR(pem_pmu_acpi_match),
+		.suppress_bind_attrs = true,
+	},
+	.probe		= pem_perf_probe,
+	.remove		= pem_perf_remove,
+};
+
+static int __init pem_pmu_init(void)
+{
+	int ret;
+
+	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_MRVL_PEM_ONLINE,
+				      "perf/marvell/pem:online", NULL,
+				       pem_pmu_offline_cpu);
+	if (ret)
+		return ret;
+
+	ret = platform_driver_register(&pem_pmu_driver);
+	if (ret)
+		cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_MRVL_PEM_ONLINE);
+	return ret;
+}
+
+static void __exit pem_pmu_exit(void)
+{
+	platform_driver_unregister(&pem_pmu_driver);
+	cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_MRVL_PEM_ONLINE);
+}
+
+module_init(pem_pmu_init);
+module_exit(pem_pmu_exit);
+
+MODULE_DESCRIPTION("Marvell PEM Perf driver");
+MODULE_AUTHOR("Gowthami Thiagarajan <gthiagarajan@marvell.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/perf/qcom_l2_pmu.c b/drivers/perf/qcom_l2_pmu.c
index 980e3051edd7..ea8c85729937 100644
--- a/drivers/perf/qcom_l2_pmu.c
+++ b/drivers/perf/qcom_l2_pmu.c
@@ -981,7 +981,7 @@ static struct platform_driver l2_cache_pmu_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = l2_cache_pmu_probe,
-	.remove_new = l2_cache_pmu_remove,
+	.remove = l2_cache_pmu_remove,
 };
 
 static int __init register_l2_cache_pmu_driver(void)
diff --git a/drivers/perf/thunderx2_pmu.c b/drivers/perf/thunderx2_pmu.c
index faf763d2c95c..cadd60221b8f 100644
--- a/drivers/perf/thunderx2_pmu.c
+++ b/drivers/perf/thunderx2_pmu.c
@@ -1010,7 +1010,7 @@ static struct platform_driver tx2_uncore_driver = {
 		.suppress_bind_attrs = true,
 	},
 	.probe = tx2_uncore_probe,
-	.remove_new = tx2_uncore_remove,
+	.remove = tx2_uncore_remove,
 };
 
 static int __init tx2_uncore_driver_init(void)
diff --git a/drivers/perf/xgene_pmu.c b/drivers/perf/xgene_pmu.c
index c01466ae1e3d..33b5497bdc06 100644
--- a/drivers/perf/xgene_pmu.c
+++ b/drivers/perf/xgene_pmu.c
@@ -1943,7 +1943,7 @@ static void xgene_pmu_remove(struct platform_device *pdev)
 
 static struct platform_driver xgene_pmu_driver = {
 	.probe = xgene_pmu_probe,
-	.remove_new = xgene_pmu_remove,
+	.remove = xgene_pmu_remove,
 	.driver = {
 		.name		= "xgene-pmu",
 		.of_match_table = xgene_pmu_of_match,
diff --git a/drivers/virt/coco/Kconfig b/drivers/virt/coco/Kconfig
index d9ff676bf48d..ff869d883d95 100644
--- a/drivers/virt/coco/Kconfig
+++ b/drivers/virt/coco/Kconfig
@@ -14,3 +14,5 @@ source "drivers/virt/coco/pkvm-guest/Kconfig"
 source "drivers/virt/coco/sev-guest/Kconfig"
 
 source "drivers/virt/coco/tdx-guest/Kconfig"
+
+source "drivers/virt/coco/arm-cca-guest/Kconfig"
diff --git a/drivers/virt/coco/Makefile b/drivers/virt/coco/Makefile
index b69c30c1c720..c3d07cfc087e 100644
--- a/drivers/virt/coco/Makefile
+++ b/drivers/virt/coco/Makefile
@@ -7,3 +7,4 @@ obj-$(CONFIG_EFI_SECRET)	+= efi_secret/
 obj-$(CONFIG_ARM_PKVM_GUEST)	+= pkvm-guest/
 obj-$(CONFIG_SEV_GUEST)		+= sev-guest/
 obj-$(CONFIG_INTEL_TDX_GUEST)	+= tdx-guest/
+obj-$(CONFIG_ARM_CCA_GUEST)	+= arm-cca-guest/
diff --git a/drivers/virt/coco/arm-cca-guest/Kconfig b/drivers/virt/coco/arm-cca-guest/Kconfig
new file mode 100644
index 000000000000..9dd27c3ee215
--- /dev/null
+++ b/drivers/virt/coco/arm-cca-guest/Kconfig
@@ -0,0 +1,11 @@
+config ARM_CCA_GUEST
+	tristate "Arm CCA Guest driver"
+	depends on ARM64
+	default m
+	select TSM_REPORTS
+	help
+	  The driver provides userspace interface to request and
+	  attestation report from the Realm Management Monitor(RMM).
+
+	  If you choose 'M' here, this module will be called
+	  arm-cca-guest.
diff --git a/drivers/virt/coco/arm-cca-guest/Makefile b/drivers/virt/coco/arm-cca-guest/Makefile
new file mode 100644
index 000000000000..69eeba08e98a
--- /dev/null
+++ b/drivers/virt/coco/arm-cca-guest/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_ARM_CCA_GUEST) += arm-cca-guest.o
diff --git a/drivers/virt/coco/arm-cca-guest/arm-cca-guest.c b/drivers/virt/coco/arm-cca-guest/arm-cca-guest.c
new file mode 100644
index 000000000000..488153879ec9
--- /dev/null
+++ b/drivers/virt/coco/arm-cca-guest/arm-cca-guest.c
@@ -0,0 +1,224 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2023 ARM Ltd.
+ */
+
+#include <linux/arm-smccc.h>
+#include <linux/cc_platform.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/smp.h>
+#include <linux/tsm.h>
+#include <linux/types.h>
+
+#include <asm/rsi.h>
+
+/**
+ * struct arm_cca_token_info - a descriptor for the token buffer.
+ * @challenge:		Pointer to the challenge data
+ * @challenge_size:	Size of the challenge data
+ * @granule:		PA of the granule to which the token will be written
+ * @offset:		Offset within granule to start of buffer in bytes
+ * @result:		result of rsi_attestation_token_continue operation
+ */
+struct arm_cca_token_info {
+	void           *challenge;
+	unsigned long   challenge_size;
+	phys_addr_t     granule;
+	unsigned long   offset;
+	unsigned long   result;
+};
+
+static void arm_cca_attestation_init(void *param)
+{
+	struct arm_cca_token_info *info;
+
+	info = (struct arm_cca_token_info *)param;
+
+	info->result = rsi_attestation_token_init(info->challenge,
+						  info->challenge_size);
+}
+
+/**
+ * arm_cca_attestation_continue - Retrieve the attestation token data.
+ *
+ * @param: pointer to the arm_cca_token_info
+ *
+ * Attestation token generation is a long running operation and therefore
+ * the token data may not be retrieved in a single call. Moreover, the
+ * token retrieval operation must be requested on the same CPU on which the
+ * attestation token generation was initialised.
+ * This helper function is therefore scheduled on the same CPU multiple
+ * times until the entire token data is retrieved.
+ */
+static void arm_cca_attestation_continue(void *param)
+{
+	unsigned long len;
+	unsigned long size;
+	struct arm_cca_token_info *info;
+
+	info = (struct arm_cca_token_info *)param;
+
+	size = RSI_GRANULE_SIZE - info->offset;
+	info->result = rsi_attestation_token_continue(info->granule,
+						      info->offset, size, &len);
+	info->offset += len;
+}
+
+/**
+ * arm_cca_report_new - Generate a new attestation token.
+ *
+ * @report: pointer to the TSM report context information.
+ * @data:  pointer to the context specific data for this module.
+ *
+ * Initialise the attestation token generation using the challenge data
+ * passed in the TSM descriptor. Allocate memory for the attestation token
+ * and schedule calls to retrieve the attestation token on the same CPU
+ * on which the attestation token generation was initialised.
+ *
+ * The challenge data must be at least 32 bytes and no more than 64 bytes. If
+ * less than 64 bytes are provided it will be zero padded to 64 bytes.
+ *
+ * Return:
+ * * %0        - Attestation token generated successfully.
+ * * %-EINVAL  - A parameter was not valid.
+ * * %-ENOMEM  - Out of memory.
+ * * %-EFAULT  - Failed to get IPA for memory page(s).
+ * * A negative status code as returned by smp_call_function_single().
+ */
+static int arm_cca_report_new(struct tsm_report *report, void *data)
+{
+	int ret;
+	int cpu;
+	long max_size;
+	unsigned long token_size = 0;
+	struct arm_cca_token_info info;
+	void *buf;
+	u8 *token __free(kvfree) = NULL;
+	struct tsm_desc *desc = &report->desc;
+
+	if (desc->inblob_len < 32 || desc->inblob_len > 64)
+		return -EINVAL;
+
+	/*
+	 * The attestation token 'init' and 'continue' calls must be
+	 * performed on the same CPU. smp_call_function_single() is used
+	 * instead of simply calling get_cpu() because of the need to
+	 * allocate outblob based on the returned value from the 'init'
+	 * call and that cannot be done in an atomic context.
+	 */
+	cpu = smp_processor_id();
+
+	info.challenge = desc->inblob;
+	info.challenge_size = desc->inblob_len;
+
+	ret = smp_call_function_single(cpu, arm_cca_attestation_init,
+				       &info, true);
+	if (ret)
+		return ret;
+	max_size = info.result;
+
+	if (max_size <= 0)
+		return -EINVAL;
+
+	/* Allocate outblob */
+	token = kvzalloc(max_size, GFP_KERNEL);
+	if (!token)
+		return -ENOMEM;
+
+	/*
+	 * Since the outblob may not be physically contiguous, use a page
+	 * to bounce the buffer from RMM.
+	 */
+	buf = alloc_pages_exact(RSI_GRANULE_SIZE, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	/* Get the PA of the memory page(s) that were allocated */
+	info.granule = (unsigned long)virt_to_phys(buf);
+
+	/* Loop until the token is ready or there is an error */
+	do {
+		/* Retrieve one RSI_GRANULE_SIZE data per loop iteration */
+		info.offset = 0;
+		do {
+			/*
+			 * Schedule a call to retrieve a sub-granule chunk
+			 * of data per loop iteration.
+			 */
+			ret = smp_call_function_single(cpu,
+						       arm_cca_attestation_continue,
+						       (void *)&info, true);
+			if (ret != 0) {
+				token_size = 0;
+				goto exit_free_granule_page;
+			}
+		} while (info.result == RSI_INCOMPLETE &&
+			 info.offset < RSI_GRANULE_SIZE);
+
+		if (info.result != RSI_SUCCESS) {
+			ret = -ENXIO;
+			token_size = 0;
+			goto exit_free_granule_page;
+		}
+
+		/*
+		 * Copy the retrieved token data from the granule
+		 * to the token buffer, ensuring that the RMM doesn't
+		 * overflow the buffer.
+		 */
+		if (WARN_ON(token_size + info.offset > max_size))
+			break;
+		memcpy(&token[token_size], buf, info.offset);
+		token_size += info.offset;
+	} while (info.result == RSI_INCOMPLETE);
+
+	report->outblob = no_free_ptr(token);
+exit_free_granule_page:
+	report->outblob_len = token_size;
+	free_pages_exact(buf, RSI_GRANULE_SIZE);
+	return ret;
+}
+
+static const struct tsm_ops arm_cca_tsm_ops = {
+	.name = KBUILD_MODNAME,
+	.report_new = arm_cca_report_new,
+};
+
+/**
+ * arm_cca_guest_init - Register with the Trusted Security Module (TSM)
+ * interface.
+ *
+ * Return:
+ * * %0        - Registered successfully with the TSM interface.
+ * * %-ENODEV  - The execution context is not an Arm Realm.
+ * * %-EBUSY   - Already registered.
+ */
+static int __init arm_cca_guest_init(void)
+{
+	int ret;
+
+	if (!is_realm_world())
+		return -ENODEV;
+
+	ret = tsm_register(&arm_cca_tsm_ops, NULL);
+	if (ret < 0)
+		pr_err("Error %d registering with TSM\n", ret);
+
+	return ret;
+}
+module_init(arm_cca_guest_init);
+
+/**
+ * arm_cca_guest_exit - unregister with the Trusted Security Module (TSM)
+ * interface.
+ */
+static void __exit arm_cca_guest_exit(void)
+{
+	tsm_unregister(&arm_cca_tsm_ops);
+}
+module_exit(arm_cca_guest_exit);
+
+MODULE_AUTHOR("Sami Mujawar <sami.mujawar@arm.com>");
+MODULE_DESCRIPTION("Arm CCA Guest TSM Driver");
+MODULE_LICENSE("GPL");