RISC-V: Fix IPI/RFENCE hmask on non-monotonic hartid ordering

If the boot CPU does not have the lowest hartid, "hartid - hbase" can
become negative, leading to an incorrect hmask, causing userspace to
crash with SEGV. This is observed on e.g. Starlight Beta, where cpuid 1
maps to hartid 0, and cpuid 0 maps to hartid 1.

Fix this by detecting this case, and shifting the accumulated mask and
updating hbase, if possible.

Fixes: 26fb751ca37846c9 ("RISC-V: Do not use cpumask data structure for hartid bitmap")
Signed-off-by: Geert Uytterhoeven <[e-mail]>
Reviewed-by: Atish Patra <[e-mail]>
Tested-by: Atish Patra <[e-mail]>
Signed-off-by: Palmer Dabbelt <[e-mail]>

arch/riscv/kernel/sbi.c

···
 
 static int __sbi_send_ipi_v02(const struct cpumask *cpu_mask)
 {
-	unsigned long hartid, cpuid, hmask = 0, hbase = 0;
+	unsigned long hartid, cpuid, hmask = 0, hbase = 0, htop = 0;
 	struct sbiret ret = {0};
 	int result;
 
···
 
 	for_each_cpu(cpuid, cpu_mask) {
 		hartid = cpuid_to_hartid_map(cpuid);
-		if (hmask && ((hbase + BITS_PER_LONG) <= hartid)) {
-			ret = sbi_ecall(SBI_EXT_IPI, SBI_EXT_IPI_SEND_IPI,
-					hmask, hbase, 0, 0, 0, 0);
-			if (ret.error)
-				goto ecall_failed;
-			hmask = 0;
-			hbase = 0;
+		if (hmask) {
+			if (hartid + BITS_PER_LONG <= htop ||
+			    hbase + BITS_PER_LONG <= hartid) {
+				ret = sbi_ecall(SBI_EXT_IPI,
+						SBI_EXT_IPI_SEND_IPI, hmask,
+						hbase, 0, 0, 0, 0);
+				if (ret.error)
+					goto ecall_failed;
+				hmask = 0;
+			} else if (hartid < hbase) {
+				/* shift the mask to fit lower hartid */
+				hmask <<= hbase - hartid;
+				hbase = hartid;
+			}
 		}
-		if (!hmask)
+		if (!hmask) {
 			hbase = hartid;
+			htop = hartid;
+		} else if (hartid > htop) {
+			htop = hartid;
+		}
 		hmask |= BIT(hartid - hbase);
 	}
 
···
 			    unsigned long start, unsigned long size,
 			    unsigned long arg4, unsigned long arg5)
 {
-	unsigned long hartid, cpuid, hmask = 0, hbase = 0;
+	unsigned long hartid, cpuid, hmask = 0, hbase = 0, htop = 0;
 	int result;
 
 	if (!cpu_mask || cpumask_empty(cpu_mask))
···
 
 	for_each_cpu(cpuid, cpu_mask) {
 		hartid = cpuid_to_hartid_map(cpuid);
-		if (hmask && ((hbase + BITS_PER_LONG) <= hartid)) {
-			result = __sbi_rfence_v02_call(fid, hmask, hbase,
-						       start, size, arg4, arg5);
-			if (result)
-				return result;
-			hmask = 0;
-			hbase = 0;
+		if (hmask) {
+			if (hartid + BITS_PER_LONG <= htop ||
+			    hbase + BITS_PER_LONG <= hartid) {
+				result = __sbi_rfence_v02_call(fid, hmask,
+						hbase, start, size, arg4, arg5);
+				if (result)
+					return result;
+				hmask = 0;
+			} else if (hartid < hbase) {
+				/* shift the mask to fit lower hartid */
+				hmask <<= hbase - hartid;
+				hbase = hartid;
+			}
 		}
-		if (!hmask)
+		if (!hmask) {
 			hbase = hartid;
+			htop = hartid;
+		} else if (hartid > htop) {
+			htop = hartid;
+		}
 		hmask |= BIT(hartid - hbase);
 	}