Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR.

No conflicts.

Adjacent changes:

net/core/page_pool_user.c
  0b11b1c5c320 ("netdev: let netlink core handle -EMSGSIZE errors")
  429679dcf7d9 ("page_pool: fix netlink dump stop/resume")

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

7 files changed, 180 insertions, 107 deletions

diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c
index 96e6c51515f5..cf1b78cb2d04 100644
--- a/arch/x86/hyperv/hv_vtl.c
+++ b/arch/x86/hyperv/hv_vtl.c
@@ -16,6 +16,11 @@
 extern struct boot_params boot_params;
 static struct real_mode_header hv_vtl_real_mode_header;
 
+static bool __init hv_vtl_msi_ext_dest_id(void)
+{
+	return true;
+}
+
 void __init hv_vtl_init_platform(void)
 {
 	pr_info("Linux runs in Hyper-V Virtual Trust Level\n");
@@ -38,6 +43,8 @@ void __init hv_vtl_init_platform(void)
 	x86_platform.legacy.warm_reset = 0;
 	x86_platform.legacy.reserve_bios_regions = 0;
 	x86_platform.legacy.devices.pnpbios = 0;
+
+	x86_init.hyper.msi_ext_dest_id = hv_vtl_msi_ext_dest_id;
 }
 
 static inline u64 hv_vtl_system_desc_base(struct ldttss_desc *desc)
diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
index 7dcbf153ad72..768d73de0d09 100644
--- a/arch/x86/hyperv/ivm.c
+++ b/arch/x86/hyperv/ivm.c
@@ -15,6 +15,7 @@
 #include <asm/io.h>
 #include <asm/coco.h>
 #include <asm/mem_encrypt.h>
+#include <asm/set_memory.h>
 #include <asm/mshyperv.h>
 #include <asm/hypervisor.h>
 #include <asm/mtrr.h>
@@ -503,6 +504,31 @@ static int hv_mark_gpa_visibility(u16 count, const u64 pfn[],
 }
 
 /*
+ * When transitioning memory between encrypted and decrypted, the caller
+ * of set_memory_encrypted() or set_memory_decrypted() is responsible for
+ * ensuring that the memory isn't in use and isn't referenced while the
+ * transition is in progress.  The transition has multiple steps, and the
+ * memory is in an inconsistent state until all steps are complete. A
+ * reference while the state is inconsistent could result in an exception
+ * that can't be cleanly fixed up.
+ *
+ * But the Linux kernel load_unaligned_zeropad() mechanism could cause a
+ * stray reference that can't be prevented by the caller, so Linux has
+ * specific code to handle this case. But when the #VC and #VE exceptions
+ * routed to a paravisor, the specific code doesn't work. To avoid this
+ * problem, mark the pages as "not present" while the transition is in
+ * progress. If load_unaligned_zeropad() causes a stray reference, a normal
+ * page fault is generated instead of #VC or #VE, and the page-fault-based
+ * handlers for load_unaligned_zeropad() resolve the reference.  When the
+ * transition is complete, hv_vtom_set_host_visibility() marks the pages
+ * as "present" again.
+ */
+static bool hv_vtom_clear_present(unsigned long kbuffer, int pagecount, bool enc)
+{
+	return !set_memory_np(kbuffer, pagecount);
+}
+
+/*
  * hv_vtom_set_host_visibility - Set specified memory visible to host.
  *
  * In Isolation VM, all guest memory is encrypted from host and guest
@@ -515,16 +541,28 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo
 	enum hv_mem_host_visibility visibility = enc ?
 			VMBUS_PAGE_NOT_VISIBLE : VMBUS_PAGE_VISIBLE_READ_WRITE;
 	u64 *pfn_array;
+	phys_addr_t paddr;
+	void *vaddr;
 	int ret = 0;
 	bool result = true;
 	int i, pfn;
 
 	pfn_array = kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL);
-	if (!pfn_array)
-		return false;
+	if (!pfn_array) {
+		result = false;
+		goto err_set_memory_p;
+	}
 
 	for (i = 0, pfn = 0; i < pagecount; i++) {
-		pfn_array[pfn] = virt_to_hvpfn((void *)kbuffer + i * HV_HYP_PAGE_SIZE);
+		/*
+		 * Use slow_virt_to_phys() because the PRESENT bit has been
+		 * temporarily cleared in the PTEs.  slow_virt_to_phys() works
+		 * without the PRESENT bit while virt_to_hvpfn() or similar
+		 * does not.
+		 */
+		vaddr = (void *)kbuffer + (i * HV_HYP_PAGE_SIZE);
+		paddr = slow_virt_to_phys(vaddr);
+		pfn_array[pfn] = paddr >> HV_HYP_PAGE_SHIFT;
 		pfn++;
 
 		if (pfn == HV_MAX_MODIFY_GPA_REP_COUNT || i == pagecount - 1) {
@@ -538,14 +576,30 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo
 		}
 	}
 
- err_free_pfn_array:
+err_free_pfn_array:
 	kfree(pfn_array);
+
+err_set_memory_p:
+	/*
+	 * Set the PTE PRESENT bits again to revert what hv_vtom_clear_present()
+	 * did. Do this even if there is an error earlier in this function in
+	 * order to avoid leaving the memory range in a "broken" state. Setting
+	 * the PRESENT bits shouldn't fail, but return an error if it does.
+	 */
+	if (set_memory_p(kbuffer, pagecount))
+		result = false;
+
 	return result;
 }
 
 static bool hv_vtom_tlb_flush_required(bool private)
 {
-	return true;
+	/*
+	 * Since hv_vtom_clear_present() marks the PTEs as "not present"
+	 * and flushes the TLB, they can't be in the TLB. That makes the
+	 * flush controlled by this function redundant, so return "false".
+	 */
+	return false;
 }
 
 static bool hv_vtom_cache_flush_required(void)
@@ -608,6 +662,7 @@ void __init hv_vtom_init(void)
 	x86_platform.hyper.is_private_mmio = hv_is_private_mmio;
 	x86_platform.guest.enc_cache_flush_required = hv_vtom_cache_flush_required;
 	x86_platform.guest.enc_tlb_flush_required = hv_vtom_tlb_flush_required;
+	x86_platform.guest.enc_status_change_prepare = hv_vtom_clear_present;
 	x86_platform.guest.enc_status_change_finish = hv_vtom_set_host_visibility;
 
 	/* Set WB as the default cache mode. */
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index a5e89641bd2d..9aee31862b4a 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -47,6 +47,7 @@ int set_memory_uc(unsigned long addr, int numpages);
 int set_memory_wc(unsigned long addr, int numpages);
 int set_memory_wb(unsigned long addr, int numpages);
 int set_memory_np(unsigned long addr, int numpages);
+int set_memory_p(unsigned long addr, int numpages);
 int set_memory_4k(unsigned long addr, int numpages);
 int set_memory_encrypted(unsigned long addr, int numpages);
 int set_memory_decrypted(unsigned long addr, int numpages);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 0b97bcde70c6..fbc4e60d027c 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1589,6 +1589,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 		get_cpu_vendor(c);
 		get_cpu_cap(c);
 		setup_force_cpu_cap(X86_FEATURE_CPUID);
+		get_cpu_address_sizes(c);
 		cpu_parse_early_param();
 
 		if (this_cpu->c_early_init)
@@ -1601,10 +1602,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 			this_cpu->c_bsp_init(c);
 	} else {
 		setup_clear_cpu_cap(X86_FEATURE_CPUID);
+		get_cpu_address_sizes(c);
 	}
 
-	get_cpu_address_sizes(c);
-
 	setup_force_cpu_cap(X86_FEATURE_ALWAYS);
 
 	cpu_set_bug_bits(c);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index a927a8fc9624..40dec9b56f87 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -184,6 +184,90 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c)
 	return false;
 }
 
+#define MSR_IA32_TME_ACTIVATE		0x982
+
+/* Helpers to access TME_ACTIVATE MSR */
+#define TME_ACTIVATE_LOCKED(x)		(x & 0x1)
+#define TME_ACTIVATE_ENABLED(x)		(x & 0x2)
+
+#define TME_ACTIVATE_POLICY(x)		((x >> 4) & 0xf)	/* Bits 7:4 */
+#define TME_ACTIVATE_POLICY_AES_XTS_128	0
+
+#define TME_ACTIVATE_KEYID_BITS(x)	((x >> 32) & 0xf)	/* Bits 35:32 */
+
+#define TME_ACTIVATE_CRYPTO_ALGS(x)	((x >> 48) & 0xffff)	/* Bits 63:48 */
+#define TME_ACTIVATE_CRYPTO_AES_XTS_128	1
+
+/* Values for mktme_status (SW only construct) */
+#define MKTME_ENABLED			0
+#define MKTME_DISABLED			1
+#define MKTME_UNINITIALIZED		2
+static int mktme_status = MKTME_UNINITIALIZED;
+
+static void detect_tme_early(struct cpuinfo_x86 *c)
+{
+	u64 tme_activate, tme_policy, tme_crypto_algs;
+	int keyid_bits = 0, nr_keyids = 0;
+	static u64 tme_activate_cpu0 = 0;
+
+	rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate);
+
+	if (mktme_status != MKTME_UNINITIALIZED) {
+		if (tme_activate != tme_activate_cpu0) {
+			/* Broken BIOS? */
+			pr_err_once("x86/tme: configuration is inconsistent between CPUs\n");
+			pr_err_once("x86/tme: MKTME is not usable\n");
+			mktme_status = MKTME_DISABLED;
+
+			/* Proceed. We may need to exclude bits from x86_phys_bits. */
+		}
+	} else {
+		tme_activate_cpu0 = tme_activate;
+	}
+
+	if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) {
+		pr_info_once("x86/tme: not enabled by BIOS\n");
+		mktme_status = MKTME_DISABLED;
+		return;
+	}
+
+	if (mktme_status != MKTME_UNINITIALIZED)
+		goto detect_keyid_bits;
+
+	pr_info("x86/tme: enabled by BIOS\n");
+
+	tme_policy = TME_ACTIVATE_POLICY(tme_activate);
+	if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128)
+		pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy);
+
+	tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate);
+	if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) {
+		pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n",
+				tme_crypto_algs);
+		mktme_status = MKTME_DISABLED;
+	}
+detect_keyid_bits:
+	keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate);
+	nr_keyids = (1UL << keyid_bits) - 1;
+	if (nr_keyids) {
+		pr_info_once("x86/mktme: enabled by BIOS\n");
+		pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids);
+	} else {
+		pr_info_once("x86/mktme: disabled by BIOS\n");
+	}
+
+	if (mktme_status == MKTME_UNINITIALIZED) {
+		/* MKTME is usable */
+		mktme_status = MKTME_ENABLED;
+	}
+
+	/*
+	 * KeyID bits effectively lower the number of physical address
+	 * bits.  Update cpuinfo_x86::x86_phys_bits accordingly.
+	 */
+	c->x86_phys_bits -= keyid_bits;
+}
+
 static void early_init_intel(struct cpuinfo_x86 *c)
 {
 	u64 misc_enable;
@@ -322,6 +406,13 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	 */
 	if (detect_extended_topology_early(c) < 0)
 		detect_ht_early(c);
+
+	/*
+	 * Adjust the number of physical bits early because it affects the
+	 * valid bits of the MTRR mask registers.
+	 */
+	if (cpu_has(c, X86_FEATURE_TME))
+		detect_tme_early(c);
 }
 
 static void bsp_init_intel(struct cpuinfo_x86 *c)
@@ -482,90 +573,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
 #endif
 }
 
-#define MSR_IA32_TME_ACTIVATE		0x982
-
-/* Helpers to access TME_ACTIVATE MSR */
-#define TME_ACTIVATE_LOCKED(x)		(x & 0x1)
-#define TME_ACTIVATE_ENABLED(x)		(x & 0x2)
-
-#define TME_ACTIVATE_POLICY(x)		((x >> 4) & 0xf)	/* Bits 7:4 */
-#define TME_ACTIVATE_POLICY_AES_XTS_128	0
-
-#define TME_ACTIVATE_KEYID_BITS(x)	((x >> 32) & 0xf)	/* Bits 35:32 */
-
-#define TME_ACTIVATE_CRYPTO_ALGS(x)	((x >> 48) & 0xffff)	/* Bits 63:48 */
-#define TME_ACTIVATE_CRYPTO_AES_XTS_128	1
-
-/* Values for mktme_status (SW only construct) */
-#define MKTME_ENABLED			0
-#define MKTME_DISABLED			1
-#define MKTME_UNINITIALIZED		2
-static int mktme_status = MKTME_UNINITIALIZED;
-
-static void detect_tme(struct cpuinfo_x86 *c)
-{
-	u64 tme_activate, tme_policy, tme_crypto_algs;
-	int keyid_bits = 0, nr_keyids = 0;
-	static u64 tme_activate_cpu0 = 0;
-
-	rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate);
-
-	if (mktme_status != MKTME_UNINITIALIZED) {
-		if (tme_activate != tme_activate_cpu0) {
-			/* Broken BIOS? */
-			pr_err_once("x86/tme: configuration is inconsistent between CPUs\n");
-			pr_err_once("x86/tme: MKTME is not usable\n");
-			mktme_status = MKTME_DISABLED;
-
-			/* Proceed. We may need to exclude bits from x86_phys_bits. */
-		}
-	} else {
-		tme_activate_cpu0 = tme_activate;
-	}
-
-	if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) {
-		pr_info_once("x86/tme: not enabled by BIOS\n");
-		mktme_status = MKTME_DISABLED;
-		return;
-	}
-
-	if (mktme_status != MKTME_UNINITIALIZED)
-		goto detect_keyid_bits;
-
-	pr_info("x86/tme: enabled by BIOS\n");
-
-	tme_policy = TME_ACTIVATE_POLICY(tme_activate);
-	if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128)
-		pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy);
-
-	tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate);
-	if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) {
-		pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n",
-				tme_crypto_algs);
-		mktme_status = MKTME_DISABLED;
-	}
-detect_keyid_bits:
-	keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate);
-	nr_keyids = (1UL << keyid_bits) - 1;
-	if (nr_keyids) {
-		pr_info_once("x86/mktme: enabled by BIOS\n");
-		pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids);
-	} else {
-		pr_info_once("x86/mktme: disabled by BIOS\n");
-	}
-
-	if (mktme_status == MKTME_UNINITIALIZED) {
-		/* MKTME is usable */
-		mktme_status = MKTME_ENABLED;
-	}
-
-	/*
-	 * KeyID bits effectively lower the number of physical address
-	 * bits.  Update cpuinfo_x86::x86_phys_bits accordingly.
-	 */
-	c->x86_phys_bits -= keyid_bits;
-}
-
 static void init_cpuid_fault(struct cpuinfo_x86 *c)
 {
 	u64 msr;
@@ -702,9 +709,6 @@ static void init_intel(struct cpuinfo_x86 *c)
 
 	init_ia32_feat_ctl(c);
 
-	if (cpu_has(c, X86_FEATURE_TME))
-		detect_tme(c);
-
 	init_intel_misc_features(c);
 
 	split_lock_init();
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index fb8cf953380d..b66f540de054 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1017,10 +1017,12 @@ void __init e820__reserve_setup_data(void)
 		e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
 
 		/*
-		 * SETUP_EFI and SETUP_IMA are supplied by kexec and do not need
-		 * to be reserved.
+		 * SETUP_EFI, SETUP_IMA and SETUP_RNG_SEED are supplied by
+		 * kexec and do not need to be reserved.
 		 */
-		if (data->type != SETUP_EFI && data->type != SETUP_IMA)
+		if (data->type != SETUP_EFI &&
+		    data->type != SETUP_IMA &&
+		    data->type != SETUP_RNG_SEED)
 			e820__range_update_kexec(pa_data,
 						 sizeof(*data) + data->len,
 						 E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index e9b448d1b1b7..102880404046 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -755,10 +755,14 @@ pmd_t *lookup_pmd_address(unsigned long address)
  * areas on 32-bit NUMA systems.  The percpu areas can
  * end up in this kind of memory, for instance.
  *
- * This could be optimized, but it is only intended to be
- * used at initialization time, and keeping it
- * unoptimized should increase the testing coverage for
- * the more obscure platforms.
+ * Note that as long as the PTEs are well-formed with correct PFNs, this
+ * works without checking the PRESENT bit in the leaf PTE.  This is unlike
+ * the similar vmalloc_to_page() and derivatives.  Callers may depend on
+ * this behavior.
+ *
+ * This could be optimized, but it is only used in paths that are not perf
+ * sensitive, and keeping it unoptimized should increase the testing coverage
+ * for the more obscure platforms.
  */
 phys_addr_t slow_virt_to_phys(void *__virt_addr)
 {
@@ -2041,17 +2045,12 @@ int set_mce_nospec(unsigned long pfn)
 	return rc;
 }
 
-static int set_memory_p(unsigned long *addr, int numpages)
-{
-	return change_page_attr_set(addr, numpages, __pgprot(_PAGE_PRESENT), 0);
-}
-
 /* Restore full speculative operation to the pfn. */
 int clear_mce_nospec(unsigned long pfn)
 {
 	unsigned long addr = (unsigned long) pfn_to_kaddr(pfn);
 
-	return set_memory_p(&addr, 1);
+	return set_memory_p(addr, 1);
 }
 EXPORT_SYMBOL_GPL(clear_mce_nospec);
 #endif /* CONFIG_X86_64 */
@@ -2104,6 +2103,11 @@ int set_memory_np_noalias(unsigned long addr, int numpages)
 					CPA_NO_CHECK_ALIAS, NULL);
 }
 
+int set_memory_p(unsigned long addr, int numpages)
+{
+	return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_PRESENT), 0);
+}
+
 int set_memory_4k(unsigned long addr, int numpages)
 {
 	return change_page_attr_set_clr(&addr, numpages, __pgprot(0),